第一篇：外文翻譯--使用語音識別技術(shù)控制的焊接機器人工作單元-精品

Use of Voice Recognition for Control of a Robotic

Welding Workcell

ABSTRACT: This paper describes work underway to evaluate the effectiveness of voice recognition systems as an element in the control of a robotic welding workcell.Factors being considered for control include program editor access security,Preoperation checklist requirements, welding process variable control,and robot manipulator motion overrides.In the latter two categories, manual vocal control is being compared against manual tactile control and fully automatic control in terms of speed of response, accuracy, stability, reliability.And safety.Introduction

Voice recognition technology is now recognized as a potential means for easing the workload of operators of complex systems.Numerous applications have already been implemented, are in various stages of development, or are under consideration.These include data entry,control of aircraft systems, and voice identification and verification for security purposes.Voice control has also been proposed for use aboard the space station.One prime area for application would be control of some functions of robots used for intraand extravehicular inspection, assembly, repair,satellite retrieval, and satellite maintenance when a crewmember is serving in a supervisory capacity or the system is operating in a teleoperation mode.Voice control of sensors and process variables would free the crewmember’s hands for other tasks, such as direct control or override of the manipulator motion.Similarly, the workload associated with control of many onboard experiments could be eased through the use of this technology.This paper describes the application of voice recognition for control of a robotic welding workcell.This is a complex system involving inputs from multiple sensors and control of a wide variety of robot manipulator motions and process variables.While many functions are automated, a human operator serves in a supervisory capacity, ready to override functions when necessary.In the present investigation, a commercially available voice recognition system is being integrated with a robotic welding workcell at NASA Marshall Space Flight Center, which is used as a test bed for evaluation and development of advanced technologies for use in fabrication of the Space Shuttle Main Engine.In the system under development, some functions do not yet have automatic closedloop control, thus requiring continuous monitoring and real-time adjustment by the human operator.Presently, these ovemdes are input to the system through tactile commands(;.e..pushing buttons.turning knobs for potentiometers, or adjusting mechanical devices).Since the operator monitors the process primarily visually, he must either look away from the process to find the proper button or knob or rely on“muscular memory”much as a touch-typist does.In the first case, the time of response to a deviant condition may be excessive.In the second case, there is an increased probability of a secondary error being introduced by the operator.A voice recognition system could reduce the response time required from the operator.The probability of pushing the wrong button should similarly be reduced.Also, operator fatigue should be minimized.Since the operator can continuously monitor the process during override input, the effect of the change can be observed more quickly.Thus, if the desired value is exceeded and reverse correction is required, it should be accomplished more quickly, allowing less overshoot.This reduction in oscillation about the desired value makes the system more stable.Another factor that can be improved is operator safety.In a safety-critical situation,the robot’s operation can be halted immediately by use of the “emergency stop,’’ or E-stop, mode, which is initiated, conventionally, by depressing a large button.If an operator inadvertently finds himself in a hazardous situation, it may be necessary for him to initiate the E-stop sequence.Should the operator not be within reach of the button,however, he may be unable to take the necessary action, and, as a result, could suffer serious injury.Having the capability of stopping the robot by issuing a voice command could significantly improve the operator’s safety by enabling him to stop the robot even when not within reach of the E-stop button.Manual corrections are occasionally required to adjust the location at which the weld filler wire enters the weld pool.Proper entry location is absolutely critical to sound weld quality.Adjustments are made either by manually adjusting mechanisms that hold the wirefeed guide tube or by issuing tactile commands to a servomechanism.Use of a voice recognition system could eliminate the need for the operator to place his hand within the working envelope of the robot end effector or, if servomechanisms are employed,could improve speed of response and stability.Another aspect of robot operation in an industrial environment that is very important is the security of a program editing capability of the system.Under no circumstances should any unauthorized person be able to enter this programming mode and alter the robot’s program.A voice recognition system can provide the necessary security by allowing access only for individuals who are authorized and whose voices can be identified by the system.Background

Robotic welding is under development by NASA and Rocketdyne for the automation of welds on the Space Shuttle Main Engine that are presently made manually.The programmability of a robot can reduce the percentage of welding defects through a combination of consistency and repeatability unattainable by its human counterparts.To do this, the robot is programmed to a nominal weld path and level of weld process parameters(i.e., current, travel speed.voltage,wire addition rate).Some adjustment of these values is often necessary due to conditions changing during the weld.A human making a manual weld accomplishes this adjustment readily, while a robot must rely on the limited talents of sensors and the ability of the operator to override functions when necessary.System Integration

The basic elements of the workcell system are shown diagrammatically in the illustration.The ultimate goal of the system development work in progress is to generate robot manipulator programs and weld process programs off line, download them to the workcell supervisory computer, then use sensor subsystems to make closed-loop corrections to the robot path and process variables.Offline programming is being done with an Intergraph modified VAX 780/785-205 computer system with Interact color graphics workstations.Deviations between the programmed robot path and the actual required path are observed and corrected by a sophisticated vision-based sensor developed for this application by Ohio State University.This sensor system is also designed to permit measurement of the molten weld pool surface dimensions and correct welding current level to maintain the weld pool dimensions within desired limits.Presently, a number of functions are still controlled manually, and manual overrides capability is required for all functions.As stated in the Introduction, use of voice recognition may improve the accuracy and speed of response of these manual overrides.To explore this technology, a Votan VRT 6050 stand-alone voice recognition terminal has been integrated into the workcell.This system provides continuous speech recognition of up to 10 sets of words with 75-150 words per set.The integration of the voice recognition system is broken into analog and discrete signals for control.The voice recognition system connects to the control computer through a standard RS232-C communications link.Discrete Control Signals

In this project, most of the control circuitry is based on discrete digital signals.This is due to the on/off state nature of the circuits to be controlled in the robot controller.The circuits of the system to be controlled by the voice recognition control computer(VRCC)by discrete signals are the emergency stop circuit and the positive jog and negative jog circuits for motion control.Since the safety of the operator is paramount in any automated workcell, the voice recognition system should be incorporated as a safety feature.To accomplish this, the VRCC has been interfaced into the workcell emergency stop circuit.The emergency stop circuit in the robotic workcell will shut down the welding process and the mechanical motion of the manipulators.Through the use of a digital signal from the VRCC, a relay is energized that interrupts the necessary circuits in the weld power supply and robot controller.With the use of the voice recognition system as a safety control for this workcell, we have added a third level of redundancy into the emergency stopping ability of the operator(in addition to the present emergency stop buttons).Manipulator motions are controlled through an axis select button in conjunction with a positive or negative jog button that is depressed by the operator.Once the operator has selected an axis, he depresses one of the jog buttons for the desired travel distance.This function was selected to be controlled by the VRCC because of its utilization during automatic operation of the manipulator to correct trajectory errors.The circuitry necessary to control this operation draws the signal to ground through the activation of relays for the positive or negative jog motion.Because motion is achieved only as long as these signals are active low.they can be controlled by discrete digital signals from the VRCC.Analog Control Signals

There are many variables that affect the quality of weld during the welding process.but the welding current has the greatest effect over a small range of values.It was for this reason, that the welding current was chosen to be controlled by the voice recognition system.The welding power supply controls the current level through a voltage circuit that uses a range of 0-10 V DC.These voltage values are converted to current levels from 0 to 300 A for welding.A digital-to-analog converter is used in conjunction with a multiplying circuit.The converter allows the VRCC to control a voltage level that is used by the weld power supply to achieve the proper welding current.The multiplier circuit is necessary to allow the weld power supply to be controlled by the other subcontroller used in the workcell.Experimental Investigation

The accuracy and speed of response of corrections to robot manipulator motion and welding process variables made with the VRCC are being compared with those made with the original control system.Step input errors to robot motion and welding current are introduced randomly into the robot program.By graphically recording relevant system output signals,the time required for the operator to detect the change and initiate corrective action may be measured.Response accuracy and stability may also be gaged through similar analysis of the relevant recorded system output signals.Conclusions

Future work will investigate voice control of welding filler wirefeed speed and location of wire entry into the weld pool.Also to be investigated is voice control of welding arc voltage override.Later, restriction of access to the robot program editor by voice recognition may be implemented.The use of voice recognition technology for manual supervisory control of industrial robot systems is very promising.This technology has application for aerospace welding due to the need to have constant human supervision over a multitude of process parameters in real time.Future development of this technology will permit rapid expansion of its application to both robotic and nonrobotic processes.Acknowledgment

Special thanks to Mr.Jeff Hudson of Martin Marietta Corporation for assistance in the preparation of the illustration presented in this article.References

[1] C.A.Simpson.hl.E.McCauley.E.F.Rolland.J.C.Ruth.and B.H.Williges.“System Design for Speech Recognition and Generation.” Hutnnn Factors.vol.27.no.2.pp.115-1-11.1985.[2] National Research Council.Committee on Computerized Speech Recognition Technologies.Automatic Speech Rerop1irior1 in severe Environments National Research Council.1984.[3] E.J.Lerner.“Talking to Your Aircraft.” Aerospace America.vol.24.no.2.pp.85-88.1986.[4] J.T.Memlield.“Bosing Explores Voice Recognition for Future Transpon Flight Deck.” Ariarinn Week and Space Techno/-og!.vol.124.no.16.pp.85-91.1986.[5] A.Cohen and J.D.Erickson,..Future Uses of Machine Intelligence and Robotics for the Space Station and Implications for the U.S.Economy.'' IEEE J.Robotics and Automarion.vol.SMC-16.pp.1 11-12 I.Jan.iFeb.1986 [6] “Automation and Robotics for the National Space Program,” California Space Institute Automation and Robotics Panel.Cal Space Repon CS1185-01, Feb.25, 1985.[7] “Advancing Automation and Robotics Technology for the Space Station and for the U.S.Economy.” Advanced Technology AdvisoryCommittee.NASA TM 87566.Mar.1985.使用語音識別技術(shù)控制的焊接機器人工作單元

摘要：本文論述了使用聲音識別技術(shù)的焊接機器人工作單元在工作過程中的效果、程序編輯者接近機器人的安全﹑試行運轉(zhuǎn)的必要性﹑焊接過程的控制變量﹑機器人操作者的動作規(guī)范等因素給與考慮。在焊接過程控制和操作動作兩個方面，按照反應(yīng)速度﹑定位精確性﹑焊接穩(wěn)定性﹑焊接可靠性和安全性把人工聲音控制與手工觸覺控制和完全自動化控制進行了比較。

緒論

聲音識別技術(shù)已經(jīng)成為可能緩解操作者工作負擔的一種有潛力的復雜系統(tǒng)。許多應(yīng)用已經(jīng)落實,或正陸續(xù)開發(fā),或正在研究之中。這些措施包括數(shù)據(jù)的輸入﹑飛機的控制﹑和以安全為目的的語音識別。

許多應(yīng)用語音控制技術(shù)還建議用于太空站.一個主要的應(yīng)用領(lǐng)域?qū)C器人控制功能用于太空艙內(nèi)檢查、裝配、維修、衛(wèi)星回收、維修衛(wèi)星,是在船上服務(wù)的監(jiān)督能力和系統(tǒng)運作模式的反饋.聲音感應(yīng)器和過程控制的變數(shù)將使船員影響他手上的其它工作,例如直接控制或推翻的操縱議案。同樣,利用工作量控制機載實驗這種技術(shù)可以緩解許多工作負擔。

這份文件描述應(yīng)用語音識別控制的焊接機器人工作單元。這是一個復雜的系統(tǒng),涉及多個傳感器及控制投入各種機械操作件和變化多樣的工藝參數(shù)。雖然許多功能是自動化，且為人類監(jiān)督管理能力所控制,但在必要時隨時準備超越這些功能。在當前的調(diào)查中，在美國航天局的馬歇爾空間飛行中心可供商業(yè)使用語音識別系統(tǒng)結(jié)合了焊接機器人工作單元的技術(shù)，這一技術(shù)作為試點的評價和開發(fā)先進技術(shù)并用于制造航天飛機主發(fā)動機。在系統(tǒng)開發(fā)中，有些功能尚不具備自動跟蹤控制,因此需要不斷地人力監(jiān)測和實時調(diào)整操作。目前,該系統(tǒng)投入方案是通過觸覺指令(即： 推動按鈕.旋轉(zhuǎn)電位計、或者調(diào)整機械裝置)。由于操作過程中,主要監(jiān)測者必須考慮在遠離的過程中尋找適當?shù)陌粹o或把手或靠像打字員一樣那種打字時的肌肉記憶。第二種情況，可能由于操作者的的二次反應(yīng)而增加了錯誤發(fā)生的可能性。

一個語音識別系統(tǒng)可減少操作者的反應(yīng)時間。操作者按錯按鈕的可能性了同樣的也會減少。并且,操作者勞累也會大大減小。

由于在方案運行的過程中操作者不斷監(jiān)測，可以更快地觀察到運行狀況改變所帶來的影響。因此,如果超過了預期值,應(yīng)該更快糾正,，但不能太過度。這對減少振蕩,使系統(tǒng)更加穩(wěn)定的實現(xiàn)了預期的價值。

另一個因素是可以改善操作者的安全.。在一個安全的緊急情況下，機器人的操作者可以采取緊急停止來停止其運行，這種緊急停止模式一般來說是設(shè)置一個大按鈕，按慣例是一種經(jīng)常用的方式。如果操作者無意中發(fā)現(xiàn)自己在危險的情況下，這時也許他有必要采取緊急停止這種模式。如果操作者不能夠按到的按鈕，可他也沒有能力采取必要的行動時，這樣下去，他可能會受重傷。如果操作者者能通過發(fā)出聲音指令來停止機器人的運行那將會大大的改善操作者的安全，即使操作者在不能按到緊急停止按鈕無法停止機器的情況下也將很安全。

手工調(diào)整有時候需要適應(yīng)焊絲填充到焊接溶池中的位置。填充到正確合適的位置是焊接質(zhì)量的關(guān)鍵。既可通過手工調(diào)節(jié)機制來控制送絲導管也可給自動控制裝置發(fā)出移動指令來進行調(diào)整。使用語音識別系統(tǒng)可以讓操作者者不必再把機器人控制效應(yīng)得指令文件拿在手中，如自動控制裝置被使用，可以改善操作的反應(yīng)速度和運行穩(wěn)定性。

另一方面，編輯系統(tǒng)程序權(quán)限的安全是工業(yè)機器人在作業(yè)環(huán)境中很重要的一個安全。在任何情況下，任何未經(jīng)授權(quán)的人能進入程序編輯模式，并且可以改變機器人的控制程序。一個語音識別系統(tǒng)，可提供必要的安全，使他們那些久久是獲得授權(quán)的人的聲音，才能被機器人系統(tǒng)識別。

背景

美國航天局正在開發(fā)焊接機器人并且焊接自動化設(shè)備來代替目前正在用手工焊接的航天飛機的主發(fā)動機。使用該機器人的程序，可以通過用手工來難以做到的焊接一致性和重復操作來達到減少焊接缺陷的比例。為此，焊接機可以編成控制額定的焊接通路和所需要的焊接過程參數(shù)，(即焊接電流、焊接速度、焊接電壓、送絲速度等)。當焊接條件改變的時候做一些有價值調(diào)整是很有必要的。一個人用手工來操作焊接時作出調(diào)整是很容易的，但是機器人的調(diào)節(jié)靠傳感器的智能和必要的人工操作者的方案調(diào)節(jié)。

系統(tǒng)綜述

機器人工作系統(tǒng)的基本情況如圖表所示，最終的系統(tǒng)開發(fā)工作是編輯操作的程序和焊接過程生產(chǎn)線的控制程序，下載這些程序到控制工作單元的電腦，然后使用子系統(tǒng)傳感器修正機器人的運行路徑和過程，使其可變。利用VAX 780/785-205電腦連接到彩色圖形處理工作站來進行圖表處理實現(xiàn)脫機設(shè)計。機器人由于程序編輯和實際需要之間的偏差是通過俄亥俄州大學研究的精密的視覺傳感器來發(fā)現(xiàn)和糾正的。這種傳感系統(tǒng)也設(shè)計成允許測量焊接溶池表面尺寸和改變電流大小來調(diào)節(jié)焊接溶池保持理想的形狀。目前，仍有許多功能人工控制，而且各個方面的功能都需要人工的操作。如前緒論中所述，引進聲音識別技術(shù)可以改進人工操作的準確性和反應(yīng)速度。為研究這項技術(shù)，Votan VRT 6050聲音識別單機終端被引入到機器人的工作單元中。這個連續(xù)的語音識別系統(tǒng)可以提供多達10套，每套有75—150句話。

把語音識別系統(tǒng)的模擬和離散信號輸入控制。語音識別系統(tǒng)通過RS232-C的通信連接到控制主機。

圖1焊接機器人系統(tǒng)設(shè)計

離散控制信號

在這個項目中，大多數(shù)控制電路是基于不同的數(shù)字信號。這主要是用在一些國產(chǎn)性質(zhì)的機器人控制器上的。通過語音識別技術(shù)控制的計算機來控制的電路系統(tǒng)是通過一種離散信號來控制，這種信號有緊急停止電路和積極響應(yīng)和消極響應(yīng)電路的功能。

因為任何自動化工作單元中操作者的安全是必須保障的,所以應(yīng)把語音識別系統(tǒng)的安全也考慮在內(nèi)。為達到這一目標，貞技術(shù)已引入緊急停止電路的工作單元。機器人工作單元中的緊急停止電路將會停止焊接過程的終止操作者的操作。通過使用數(shù)字貞信號，需要中斷焊接動力供電線路和機器人控制器的繼電器被廣泛使用。由于在這一工作單元中使用的語音識別技術(shù)這一安全系統(tǒng)，我們又增加了第三種供選擇的緊急停車的方案（除了現(xiàn)在已經(jīng)有的緊急停車按鈕）。

方案是通過操作者在軸配合正按鈕或負按鈕之間選擇來實現(xiàn)控制的。一旦操作者選擇了軸，它可以在理想的距離之內(nèi)控制負按鈕。這種功能的選用是通過控貞信號來控制的，因為貞信號的使用在自動操作中可以糾正運行的錯誤。在這一操作中有必要通過繼電器的正負極的地面信號來達到目的。只因為這些信號很微弱才能達到目的。他們可以通過貞信號遠距離控制。

模擬控制信號

有很多因素影響焊接過程的質(zhì)量，但是焊接電流對焊接質(zhì)量的影響絕不是一個小的因素。正因為如此，所以焊接電流被選擇為聲音識別系統(tǒng)控制的對象。

使用0—10V直流電壓來控制焊接電源從而控制電流大小，這種電壓可以使電流在焊接過程中從0—300A之間變化。數(shù)子—模擬轉(zhuǎn)化器配合的電路在廣泛的使用。這種轉(zhuǎn)換器允許貞信號控制電壓的大小從而使電源能提供合適的焊接電流。這種電路必須允許焊接電源通過工作單元中的其它輔助設(shè)備來控制。

實驗研究

在準確性和反應(yīng)速度方面通過貞信號控制的各種焊接過程與原始的控制系統(tǒng)進行了比較。目前焊接機器人操作的的輸入誤差提和焊接電流已經(jīng)被引入到機器人程序中。通過圖表記錄了系統(tǒng)相關(guān)的信號，可以通過操作者發(fā)覺錯誤和糾正這一錯誤所需要的時間來衡量。反應(yīng)的準確性和穩(wěn)定性也可以通過類似的記錄儀器來分析系統(tǒng)信號的輸入。

結(jié)論

今后的工作將會把語音控制技術(shù)應(yīng)用到焊絲填充速度焊絲填入溶池位置的控制，也會將該技術(shù)用在弧焊電壓控制上。以后，那些現(xiàn)在在機器人編程受到限制的的方案在采用語音識別技術(shù)之后有可能實現(xiàn)。

利用語音識別技術(shù)控制工業(yè)機器人系統(tǒng)非常有前景的。由于航空焊接需要大量人力監(jiān)管過程實時參數(shù)控制所以這項技術(shù)已申請用于航空焊接。這一技術(shù)的未來發(fā)展將可迅速擴展為機器人的應(yīng)用和非機器人的處理過程。

致謝

在此特別感謝Martin Marietta 公司的Mr.Jeff Hudson協(xié)助編作本篇論文。

參考文獻

[1] C.A.Simpson.hl.E.McCauley.E.F.Rolland.J.C.Ruth.and B.H.Williges.“System Design for Speech Recognition and Generation.” Hutnnn Factors.vol.27.no.2.pp.115-1-11.1985.[2] National Research Council.Committee on Computerized Speech Recognition Technologies.Automatic Speech Rerop1irior1 in severe Environments National Research Council.1984.[3] E.J.Lerner.“Talking to Your Aircraft.” Aerospace America.vol.24.no.2.pp.85-88.1986.[4] J.T.Memlield.“Bosing Explores Voice Recognition for Future Transpon Flight Deck.” Ariarinn Week and Space Techno/-og!.vol.124.no.16.pp.85-91.1986.[5] A.Cohen and J.D.Erickson,..Future Uses of Machine Intelligence and Robotics for the Space Station and Implications for the U.S.Economy.'' IEEE J.Robotics and Automarion.vol.SMC-16.pp.1 11-12 I.Jan.iFeb.1986 [6] “Automation and Robotics for the National Space Program,” California Space Institute Automation and Robotics Panel.Cal Space Repon CS1185-01, Feb.25, 1985.[7] “Advancing Automation and Robotics Technology for the Space Station and for the U.S.Economy.” Advanced Technology AdvisoryCommittee.NASA TM 87566.Mar.1985.

第二篇：智能語音識別機器人文獻翻譯

改進型智能機器人的語音識別方法

2、語音識別概述

最近，由于其重大的理論意義和實用價值，語音識別已經(jīng)受到越來越多的關(guān)注。到現(xiàn)在為止，多數(shù)的語音識別是基于傳統(tǒng)的線性系統(tǒng)理論，例如隱馬爾可夫模型和動態(tài)時間規(guī)整技術(shù)。隨著語音識別的深度研究，研究者發(fā)現(xiàn)，語音信號是一個復雜的非線性過程，如果語音識別研究想要獲得突破，那么就必須引進非線性系統(tǒng)理論方法。最近，隨著非線性系統(tǒng)理論的發(fā)展，如人工神經(jīng)網(wǎng)絡(luò)，混沌與分形，可能應(yīng)用這些理論到語音識別中。因此，本文的研究是在神經(jīng)網(wǎng)絡(luò)和混沌與分形理論的基礎(chǔ)上介紹了語音識別的過程。

語音識別可以劃分為獨立發(fā)聲式和非獨立發(fā)聲式兩種。非獨立發(fā)聲式是指發(fā)音模式是由單個人來進行訓練，其對訓練人命令的識別速度很快，但它對與其他人的指令識別速度很慢，或者不能識別。獨立發(fā)聲式是指其發(fā)音模式是由不同年齡，不同性別，不同地域的人來進行訓練，它能識別一個群體的指令。一般地，由于用戶不需要操作訓練，獨立發(fā)聲式系統(tǒng)得到了更廣泛的應(yīng)用。所以，在獨立發(fā)聲式系統(tǒng)中，從語音信號中提取語音特征是語音識別系統(tǒng)的一個基本問題。

語音識別包括訓練和識別，我們可以把它看做一種模式化的識別任務(wù)。通常地，語音信號可以看作為一段通過隱馬爾可夫模型來表征的時間序列。通過這些特征提取，語音信號被轉(zhuǎn)化為特征向量并把它作為一種意見，在訓練程序中，這些意見將反饋到HMM的模型參數(shù)估計中。這些參數(shù)包括意見和他們響應(yīng)狀態(tài)所對應(yīng)的概率密度函數(shù)，狀態(tài)間的轉(zhuǎn)移概率，等等。經(jīng)過參數(shù)估計以后，這個已訓練模式就可以應(yīng)用到識別任務(wù)當中。輸入信號將會被確認為造成詞，其精確度是可以評估的。整個過程如圖一所示。

圖1 語音識別系統(tǒng)的模塊圖

3、理論與方法

從語音信號中進行獨立揚聲器的特征提取是語音識別系統(tǒng)中的一個基本問題。解決這個問題的最流行方法是應(yīng)用線性預測倒譜系數(shù)和Mel頻率倒譜系數(shù)。這兩種方法都是基于一種假設(shè)的線形程序，該假設(shè)認為說話者所擁有的語音特性是由于聲道共振造成的。這些信號特征構(gòu)成了語音信號最基本的光譜結(jié)構(gòu)。然而，在語音信號中，這些非線形信息不容易被當前的特征提取邏輯方法所提取，所以我們使用分型維數(shù)來測量非線形語音擾動。

本文利用傳統(tǒng)的LPCC和非線性多尺度分形維數(shù)特征提取研究并實現(xiàn)語音識別系統(tǒng)。

3.1線性預測倒譜系數(shù)

線性預測系數(shù)是一個我們在做語音的線形預分析時得到的參數(shù)，它是關(guān)于毗鄰語音樣本間特征聯(lián)系的參數(shù)。線形預分析正式基于以下幾個概念建立起來的，即一個語音樣本可以通過一些以前的樣本的線形組合來快速地估計，根據(jù)真實語音樣本在確切的分析框架（短時間內(nèi)的）和預測樣本之間的差別的最小平方原則，最后會確認出唯一的一組預測系數(shù)。

LPC可以用來估計語音信號的倒譜。在語音信號的短時倒譜分析中，這是一種特殊的處理方法。信道模型的系統(tǒng)函數(shù)可以通過如下的線形預分析來得到：

其中p代表線形預測命令，（k=1，2，? ?，p）代表預測參數(shù)，脈沖響應(yīng)用

。那么（1）式可以擴展為（2）式： h(n)來表示，假設(shè)h（n）的倒譜是

將（1）帶入（2），兩邊同時，（2）變成（3）。

就獲得了方程（4）：

那么 可以通過

來獲得。

（5）中計算的倒譜系數(shù)叫做LPCC，n代表LPCC命令。

在我們采集LPCC參數(shù)以前，我們應(yīng)該對語音信號進行預加重，幀處理，加工和終端窗口檢測等，所以，中文命令字“前進”的端點檢測如圖2所示，接下來，斷點檢測后的中文命令字“前進”語音波形和LPCC的參數(shù)波形如圖3所示。

圖2 中文命令字“前進”的端點檢測

圖3 斷點檢測后的中文命令字“前進”語音波形和LPCC的參數(shù)波形

3.2 語音分形維數(shù)計算

分形維數(shù)是一個與分形的規(guī)模與數(shù)量相關(guān)的定值，也是對自我的結(jié)構(gòu)相似性的測量。分形分維測量是[6-7]。從測量的角度來看，分形維數(shù)從整數(shù)擴展到了分數(shù)，打破了一般集拓撲學方面被整數(shù)分形維數(shù)的限制，分數(shù)大多是在歐幾里得幾何尺寸的延伸。

有許多關(guān)于分形維數(shù)的定義，例如相似維度，豪斯多夫維度，信息維度，相關(guān)維度，容積維度，計盒維度等等，其中，豪斯多夫維度是最古老同時也是最重要的，它的定義如【3】所示：

其中，表示需要多少個單位來覆蓋子集F.端點檢測后，中文命令詞“向前”的語音波形和分形維數(shù)波形如圖4所示。

圖4 端點檢測后，中文命令詞“向前”的語音波形和分形維數(shù)波形

3.3 改進的特征提取方法

考慮到LPCC語音信號和分形維數(shù)在表達上各自的優(yōu)點，我們把它們二者混合到信號的特取中，即分形維數(shù)表表征語音時間波形圖的自相似性，周期性，隨機性，同時，LPCC特性在高語音質(zhì)量和高識別速度上做得很好。

由于人工神經(jīng)網(wǎng)絡(luò)的非線性，自適應(yīng)性，強大的自學能力這些明顯的優(yōu)點，它的優(yōu)良分類和輸入輸出響應(yīng)能力都使它非常適合解決語音識別問題。

由于人工神經(jīng)網(wǎng)絡(luò)的輸入碼的數(shù)量是固定的，因此，現(xiàn)在是進行正規(guī)化的特征參數(shù)輸入到前神經(jīng)網(wǎng)絡(luò)[9]，在我們的實驗中，LPCC和每個樣本的分形維數(shù)需要分別地通過時間規(guī)整化的網(wǎng)絡(luò)，LPCC是一個4幀數(shù)據(jù)（LPCC1,LPCC2,LPCC3,LPCC4，每個參數(shù)都是14維的），分形維數(shù)被模范化為12維數(shù)據(jù)，（FD1,FD2,?FD12，每一個參數(shù)都是一維），以便于每個樣本的特征向量有4*14+12*1=68-D維，該命令就是前56個維數(shù)是LPCC，剩下的12個維數(shù)是分形維數(shù)。因而，這樣的一個特征向量可以表征語音信號的線形和非線性特征。

自動語音識別的結(jié)構(gòu)和特征

自動語音識別是一項尖端技術(shù)，它允許一臺計算機，甚至是一臺手持掌上電腦（邁爾斯，2000）來識別那些需要朗讀或者任何錄音設(shè)備發(fā)音的詞匯。自動語音識別技術(shù)的最終目的是讓那些不論詞匯量，背景噪音，說話者變音的人直白地說出的單詞能夠達到100%的準確率（CSLU，2002）。然而，大多數(shù)的自動語音識別工程師都承認這樣一個現(xiàn)狀，即對于一個大的語音詞匯單位，當前的準確度水平仍然低于90%。舉一個例子，Dragon's Naturally Speaking或者IBM公司，闡述了取決于口音，背景噪音，說話方式的基線識別的準確性僅僅為60%至80%(Ehsani & Knodt, 1998)。更多的能超越以上兩個的昂貴的系統(tǒng)有Subarashii(Bernstein, et al., 1999), EduSpeak(Franco, etal., 2001), Phonepass(Hinks, 2001), ISLE Project(Menzel, et al., 2001)and RAD(CSLU, 2003)。語音識別的準確性將有望改善。

在自動語音識別產(chǎn)品中的幾種語音識別方式中，隱馬爾可夫模型（HMM）被認為是最主要的算法，并且被證明在處理大詞匯語音時是最高效的(Ehsani & Knodt, 1998)。詳細說明隱馬爾可夫模型如何工作超出了本文的范圍，但可以在任何關(guān)于語言處理的文章中找到。其中最好的是Jurafsky & Martin(2000)and Hosom, Cole, and Fanty(2003)。簡而言之，隱馬爾可夫模型計算輸入接收信號和包含于一個擁有數(shù)以百計的本土音素錄音的數(shù)據(jù)庫的匹配可能性(Hinks, 2003, p.5)。也就是說，一臺基于隱馬爾可夫模型的語音識別器可以計算輸入一個發(fā)音的音素可以和一個基于概率論相應(yīng)的模型達到的達到的接近度。高性能就意味著優(yōu)良的發(fā)音，低性能就意味著劣質(zhì)的發(fā)音(Larocca, et al., 1991)。

雖然語音識別已被普遍用于商業(yè)聽寫和獲取特殊需要等目的，近年來，語言學習的市場占有率急劇增加(Aist, 1999;Eskenazi, 1999;Hinks, 2003)。早期的基于自動語音識別的軟件程序采用基于模板的識別系統(tǒng)，其使用動態(tài)規(guī)劃執(zhí)行模式匹配或其他時間規(guī)范化技術(shù)(Dalby & Kewley-Port,1999).這些程序包括Talk to Me(Auralog, 1995), the Tell Me More Series(Auralog, 2000), Triple-Play Plus(Mackey & Choi, 1998), New Dynamic English(DynEd, 1997), English Discoveries(Edusoft, 1998), and See it, Hear It, SAY IT!(CPI, 1997)。這些程序的大多數(shù)都不會提供任何反饋給超出簡單說明的發(fā)音準確率，這個基于最接近模式匹配說明是由用戶提出書面對話選擇的。學習者不會被告之他們發(fā)音的準確率。特別是內(nèi)里，（2002年）評論例如Talk to Me和Tell Me More等作品中的波形圖，因為他們期待浮華的買家，而不會提供有意義的反饋給用戶。Talk to Me 2002年的版本已經(jīng)包含了更多Hinks(2003)的特性，比如，信任對于學習者來說是非常有用的: ★ 一個視覺信號可以讓學習者把他們的語調(diào)同模型揚聲器發(fā)出的語調(diào)進行對比。★ 學習者發(fā)音的準確度通常以數(shù)字7來度量（越高越好）★ 那些發(fā)音失真的詞語會被識別出來并被明顯地標注。

Improved speech recognition method

for intelligent robot

2、Overview of speech recognition Speech recognition has received more and more attention recently due to the important theoretical meaning and practical value [5 ].Up to now, most speech recognition is based on conventional linear system theory, such as Hidden Markov Model(HMM)and Dynamic Time Warping(DTW).With the deep study of speech recognition, it is found that speech signal is a complex nonlinear process.If the study of speech recognition wants to break through, nonlinear-system theory method must be introduced to it.Recently, with the developmentof nonlinea-system theories such as artificial neural networks(ANN), chaos and fractal, it is possible to apply these theories to speech recognition.Therefore, the study of this paper is based on ANN and chaos and fractal theories are introduced to process speech recognition.Speech recognition is divided into two ways that are speaker dependent and speaker independent.Speaker dependent refers to the pronunciation model trained by a single person, the identification rate of the training person?sorders is high, while others’orders is in low identification rate or can’t be recognized.Speaker independent refers to the pronunciation model trained by persons of different age, sex and region, it can identify a group of persons’orders.Generally, speaker independent system ismorewidely used, since the user is not required to conduct the training.So extraction of speaker independent features from the speech signal is the fundamental problem of speaker recognition system.Speech recognition can be viewed as a pattern recognition task, which includes training and recognition.Generally, speech signal can be viewed as a time sequence and characterized by the powerful hidden Markov model(HMM).Through the feature extraction, the speech signal is transferred into feature vectors and act asobservations.In the training procedure, these observationswill feed to estimate the model parameters of HMM.These parameters include probability density function for the observations and their corresponding states, transition probability between the states, etc.After the parameter estimation, the trained models can be used for recognition task.The input observations will be recognized as the resulted words and the accuracy can be evaluated.Thewhole process is illustrated in Fig.1.Fig.1 Block diagram of speech recognition system Theory andmethod Extraction of speaker independent features from the speech signal is the fundamental problem of speaker recognition system.The standard methodology for solving this problem uses Linear Predictive Cepstral Coefficients(LPCC)and Mel-Frequency Cepstral Co-efficient(MFCC).Both these methods are linear procedures based on the assumption that speaker features have properties caused by the vocal tract resonances.These features form the basic spectral structure of the speech signal.However, the non-linear information in speech signals is not easily extracted by the present feature extraction methodologies.So we use fractal dimension to measure non2linear speech turbulence.This paper investigates and implements speaker identification system using both traditional LPCC and non-linear multiscaled fractal dimension feature extraction.3.1 L inear Predictive Cepstral Coefficients

Linear prediction coefficient(LPC)is a parameter setwhich is obtained when we do linear prediction analysis of speech.It is about some correlation characteristics between adjacent speech samples.Linear prediction analysis is based on the following basic concepts.That is, a speech sample can be estimated approximately by the linear combination of some past speech samples.According to the minimal square sum principle of difference between real speech sample in certain analysis frame short-time and predictive sample, the only group ofprediction coefficients can be determined.LPC coefficient can be used to estimate speech signal cepstrum.This is a special processing method in analysis of speech signal short-time cepstrum.System function of channelmodel is obtained by linear prediction analysis as follow.Where p represents linear prediction order, ak,(k=1,2,…,p)represent sprediction coefficient, Impulse response is represented by h(n).Suppose cepstrum of h(n)is represented by ,then(1)can be expanded as(2).The cepstrum coefficient calculated in the way of(5)is called LPCC, n represents LPCC order.When we extract LPCC parameter before, we should carry on speech signal pre-emphasis, framing processing, windowingprocessing and endpoints detection etc., so the endpoint detection of Chinese command word“Forward”is shown in Fig.2, next, the speech waveform ofChinese command word“Forward”and LPCC parameter waveform after Endpoint detection is shown in Fig.3.3.2 Speech Fractal Dimension Computation

Fractal dimension is a quantitative value from the scale relation on the meaning of fractal, and also a measuring on self-similarity of its structure.The fractal measuring is fractal dimension[6-7].From the viewpoint of measuring, fractal dimension is extended from integer to fraction, breaking the limitof the general to pology set dimension being integer Fractal dimension,fraction mostly, is dimension extension in Euclidean geometry.There are many definitions on fractal dimension, eg.,similar dimension, Hausdoff dimension, inforation dimension, correlation dimension, capability imension, box-counting dimension etc., where,Hausdoff dimension is oldest and also most important, for any sets, it is defined as[3].Where, M￡(F)denotes how many unit ￡ needed to cover subset F.In thispaper, the Box-Counting dimension(DB)of ,F, is obtained by partitioning the plane with squares grids of side ￡, and the numberof squares that intersect the plane(N(￡))and is defined as[8].The speech waveform of Chinese command word“Forward”and fractal dimension waveform after Endpoint detection is shown in Fig.4.3.3 Improved feature extractions method Considering the respective advantages on expressing speech signal of LPCC and fractal dimension,we mix both to be the feature signal, that is, fractal dimension denotes the self2similarity, periodicity and randomness of speech time wave shape, meanwhile LPCC feature is good for speech quality and high on identification rate.Due to ANN′s nonlinearity, self-adaptability, robust and self-learning such obvious advantages, its good classification and input2output reflection ability are suitable to resolve speech recognition problem.Due to the number of ANN input nodes being fixed, therefore time regularization is carried out to the feature parameter before inputted to the neural network[9].In our experiments, LPCC and fractal dimension of each sample are need to get through the network of time regularization separately, LPCC is 4-frame data(LPCC1,LPCC2,LPCC3,LPCC4, each frame parameter is 14-D), fractal dimension is regularized to be12-frame data(FD1,FD2,…,FD12, each frame parameter is 1-D), so that the feature vector of each sample has 4*14+1*12=68-D, the order is, the first 56 dimensions are LPCC, the rest 12 dimensions are fractal dimensions.Thus, such mixed feature parameter can show speech linear and nonlinear characteristics as well.Architectures and Features of ASR ASR is a cutting edge technology that allows a computer or even a hand-held PDA(Myers, 2000)to identify words that are read aloud or spoken into any sound-recording device.The ultimate purpose of ASR technology is to allow 100% accuracy with all words that are intelligibly spoken by any person regardless of vocabulary size, background noise, or speaker variables(CSLU, 2002).However, most ASR engineers admit that the current accuracy level for a large vocabulary unit of speech(e.g., the sentence)remains less than 90%.Dragon's Naturally Speaking or IBM's ViaVoice, for example, show a baseline recognition accuracy of only 60% to 80%, depending upon accent, background noise, type of utterance, etc.(Ehsani & Knodt, 1998).More expensive systems that are reported to outperform these two are Subarashii(Bernstein, et al., 1999), EduSpeak(Franco, et al., 2001), Phonepass(Hinks, 2001), ISLE Project(Menzel, et al., 2001)and RAD(CSLU, 2003).ASR accuracy is expected to improve.Among several types of speech recognizers used in ASR products, both implemented and proposed, the Hidden Markov Model(HMM)is one of the most dominant algorithms and has proven to be an effective method of dealing with large units of speech(Ehsani & Knodt, 1998).Detailed descriptions of how the HHM model works go beyond the scope of this paper and can be found in any text concerned with language processing;among the best are Jurafsky & Martin(2000)and Hosom, Cole, and Fanty(2003).Put simply, HMM computes the probable match between the input it receives and phonemes contained in a database of hundreds of native speaker recordings(Hinks, 2003, p.5).That is, a speech recognizer based on HMM computes how close the phonemes of a spoken input are to a corresponding model, based on probability theory.High likelihood represents good pronunciation;low likelihood represents poor pronunciation(Larocca, et al., 1991).While ASR has been commonly used for such purposes as business dictation and special needs accessibility, its market presence for language learning has increased dramatically in recent years(Aist, 1999;Eskenazi, 1999;Hinks, 2003).Early ASR-based software programs adopted template-based recognition systems which perform pattern matching using dynamic programming or other time normalization techniques(Dalby & Kewley-Port, 1999).These programs include Talk to Me(Auralog, 1995), the Tell Me More Series(Auralog, 2000), Triple-Play Plus(Mackey & Choi, 1998), New Dynamic English(DynEd, 1997), English Discoveries(Edusoft, 1998), and See it, Hear It, SAY IT!(CPI, 1997).Most of these programs do not provide any feedback on pronunciation accuracy beyond simply indicating which written dialogue choice the user has made, based on the closest pattern match.Learners are not told the accuracy of their pronunciation.In particular, Neri, et al.(2002)criticizes the graphical wave forms presented in products such as Talk to Me and Tell Me More because they look flashy to buyers, but do not give meaningful feedback to users.The 2000 version of Talk to Me has incorporated more of the features that Hinks(2003), for example, believes are useful to learners: ★ A visual signal allows learners to compare their intonation to that of the model speaker.★ The learners' pronunciation accuracy is scored on a scale of seven(the higher the better).Words whose pronunciation fails to be recognized are highlighted

第三篇：機器人及機器人傳感技術(shù)(畢業(yè)論文外文翻譯).

機器人和機器人傳感器 介紹

工業(yè)機器人以及它的運行是本文的主題。工業(yè)機器人是應(yīng)用于制造環(huán)境下 以提高生產(chǎn)率的一種工具。它可用于承擔常規(guī)的、冗長乏味的裝配線工作, 或執(zhí) 行那些對工人也許有危害的工作。例如, 在第一代工業(yè)機器人中, 曾有一臺被用 于更換核電廠的核燃料棒。從事這項工作的工人可能會暴露在有害量的放射線 下。工業(yè)機器人也能夠在裝配線上操作——安裝小型元件, 例如將電子元件安裝 在線路板上。為此, 工人可以從這種冗長乏味任務(wù)的常規(guī)操作中解放出來。通過 編程的機器人還能去掉炸彈的雷管、為殘疾者服務(wù)以及在我們社會的眾多應(yīng)用中 發(fā)揮作用。

機器人可被看作將臂端執(zhí)行工具、傳感器以及 /或夾爪移動到某個預定位 置的一臺機器。當機器人到達該位置,它將執(zhí)行某個任務(wù)。該任務(wù)可能是焊接、密封、機械裝載、機械卸載,或許多裝配工作。除了編程以及打開和關(guān)閉系統(tǒng)之 外,一般情況下,均不需要人們的參與就能完成這類工作。

機器人專業(yè)術(shù)語

機器人是一臺可再編程的多功能機械手,它可通過可編程運動移動零件、物料、工具或特殊裝置以執(zhí)行某種不同任務(wù)。由這項定義可導致下面段落中被闡 述的其他定義,它們?yōu)闄C器人系統(tǒng)提供了完整的寫照。

預編程位置是機器人為了完成工作必須遵循和通過的途徑。在這些位置 的某點,機器人會停下來并執(zhí)行某種操作,例如裝配零件,噴漆或焊接。這些預 編程位置被存儲在機器人的記憶裝置中供以后繼續(xù)操作時使用。此外, 當工作的 要求發(fā)生變化時, 不僅其他編程數(shù)據(jù)而且這些預編程位置均可作修改。因此, 正 由于這種編程的特點, 一臺工業(yè)機器人與一臺可存儲數(shù)據(jù)、以及可回憶及編輯的 計算機十分相似。

機械手是機器人的手臂, 它允許機器人俯仰、伸縮和轉(zhuǎn)動。這種動作是由 機械手的軸所提供的, 機械手的軸又稱為機器人的自由度。一臺機器人可以具有 3至 16根軸。在本人的后面部分,自由度這個術(shù)語總與一臺機器人軸的數(shù)目相

關(guān)聯(lián)。

工具及夾爪并非屬于機器人系統(tǒng)的本身, 它們是裝在機器人手臂端部的附 件。有了與機器人手臂端部相連接的這些附件,機器人就可以提起零件、點焊、噴漆、弧焊、鉆孔、去毛刺,還可以根據(jù)所提要求指向各種類型的任務(wù)。

機器人系統(tǒng)還可以控制操作機器人的工作單元。機器人工作單元是一種總 體環(huán)境, 在該環(huán)境下機器人必須執(zhí)行賦予它的任務(wù)。該單元可包容控制器、機器 人的機械手、工作臺、安全裝置,或輸送機。機器人開展工作所需要的所有設(shè)備 均被包括在這個工作單元中。此外, 來自外界裝置的信號能夠與機器人進行交流, 這樣就可以告訴機器人什么時候它該裝配零件、撿起零件或?qū)⒘慵兜捷斔蜋C?；静考?/p>

機器人系統(tǒng)具有 3個基本部件:機械手、控制器及動力源。在某些機器人 系統(tǒng)中可以看到第 4個部件,端部執(zhí)行件,有關(guān)這些部件將在下面小節(jié)描述。機械手

機械手承擔機器人系統(tǒng)的體力工作,它由兩部分組成:機械部分及被連接 的附屬物。機械手還有一個與附屬物相連的底座。

機械手的底座通常被固定在工作領(lǐng)域的地面。有時, 底座也可以移動。在 該情況下, 底座被安裝到導軌上, 這樣該機械手就可以從一處移動到另一處。例 如,一臺機器人可以為幾臺機床工作,為每臺機床裝載和卸載。

正如前面所述,附屬物從機器人的底座伸出。該附屬物是機器人的手臂。它既可以是一個直線型的可動臂,也可以是一個鉸接臂。鉸接臂也稱關(guān)節(jié)臂。機器人機械手的附屬物可為機械手提供各種運動軸。這些軸與固定底座相 連接, 而該底座又被緊固到機架上。這個機架能確保該機械手被維持在某個位置 上。

在手臂的端部連接著一個手腕。該手腕由附加軸及手腕法蘭組成, 有了該 手腕法蘭,機器人用戶就可以根據(jù)不同的工作在手腕上安裝不同的工具。

機械手的軸允許機械手在一定區(qū)域內(nèi)執(zhí)行工作。如前所述, 該區(qū)域被稱為 機器人的工作單元, 它的尺度與機械手的尺寸相對應(yīng)。當機器人的物理尺寸增大

時,工作單元的尺寸必然也隨之增加。

機械手的運動由驅(qū)動器, 或驅(qū)動系統(tǒng)所控制。驅(qū)動器或驅(qū)動系統(tǒng)允許各根 軸在工作單元內(nèi)運動, 驅(qū)動系統(tǒng)可利用電力的、液壓的或氣壓動力。驅(qū)動系統(tǒng)發(fā) 出的能量由各種機械驅(qū)動裝置轉(zhuǎn)換成機械動力。這些驅(qū)動裝置通過機械聯(lián)動機構(gòu) 接合在一起。這些聯(lián)動機構(gòu)依次驅(qū)動機器人的不同軸。機械聯(lián)動機構(gòu)由鏈輪機構(gòu), 齒輪機構(gòu)及滾珠絲杠所組成。

控制器

機器人系統(tǒng)的控制器是運行的心臟。控制器存儲著為以后回憶所用的預編 程信息,控制著外圍設(shè)備,它還與廠內(nèi)計算機進行交流以使生產(chǎn)不斷更新?？刂破饔糜诳刂茩C器人機械手運動以及工作單元中的外圍部件。工作人員 可以利用手遞示教盒將機械手的動作編程進入控制器。這種信息可被存儲在控制 器的記憶裝置中以便以后回憶使用。控制器存儲著機器人系統(tǒng)的所有程序數(shù)據(jù)。它可以存儲幾種不同的程序,并且它們中任一程序均可被編輯。

也可要求控制器與工作單元中外圍設(shè)備進行交流。例如, 控制器具有一根 輸入線, 該輸入線可識別某項機械加工什么時候完成。當該機械循環(huán)完成時, 輸 入線被接通,它會吩咐控制器讓機械手到位以便機械手能夾起以加工完的零件。接著, 該機械手再撿起一根新的零件并將它安放到機床上, 然后, 控制器向該機 床發(fā)出信號讓它開始運轉(zhuǎn)。

控制器可由機械操縱的磁鼓構(gòu)成, 這些鼓按工作發(fā)生的先后次序操作。這 類控制器用于非常簡單的機器人系統(tǒng)。在大多數(shù)機器人系統(tǒng)中見到的控制器是很 復雜的裝置, 它們體現(xiàn)了現(xiàn)代化的電子科學。換言之, 它們由微信息處理器操縱。這些

微信息處理器不是 8位、16位就是 32位的信息處理器。這種功能使控制器 的運行具有非常好的柔性。

控制器可通過通訊線路發(fā)出電子信號, 發(fā)出能與機械手各軸線進行溝通的 電信號, 機器人機械手與控制器之間這種雙向交流可使系統(tǒng)的位置及運行維持在 不斷修正及更新得狀態(tài)下,控制器還可以控制安裝在機器人手腕端部的任意工 具。

控制器還有與工廠中不同計算機開展交流的任務(wù), 這個通訊網(wǎng)絡(luò)可使機器 人成為計算機輔助制造(CAM 系統(tǒng)的一部分。

根據(jù)上述基本定義, 機器人是一臺可再編程序的多功能機械手。所以, 控 制器必須包含某種形式的記憶存儲器, 以微信息處理器為基礎(chǔ)的系統(tǒng)常與固態(tài)記 憶裝置連同運行。這些記憶裝置可以是磁泡、隨機存取記憶裝置、軟塑料磁盤或 磁帶。每種記憶存儲裝置均可存儲編程信息以便以后回憶使用。

動力源

動力源是向控制器及機械手供給動力得裝置,有兩類動力供給機器人系 統(tǒng)。一類動力是供控制器運行的交流點動力, 另一類被用于驅(qū)動機械手各軸。例 如, 若機器人的機械手由液壓或氣壓裝置控制, 則控制信號被發(fā)送到這些裝置才 能使機器人運動。

每個機器人系統(tǒng)均需要動力來驅(qū)動機械手,這種動力既可由液壓動力源、氣壓動力源, 也可以由電力動力源提供, 這些動力源是機器人工作單元總的部件 及設(shè)備中的一部分。

當液壓動力源與及機器人機械手底座相連接, 液壓源產(chǎn)生液壓流體, 這些 流體輸送到機械手各控制元件,于是,使軸繞機器人底座旋轉(zhuǎn)。

壓力空氣被輸送到機械手, 使軸沿軌道作直線運動, 也可將這種氣動源連 接到鉆床, 它可為鉆頭的旋轉(zhuǎn)提供動力。一般情況下, 可從工廠得供給站獲取氣 動源并做調(diào)整,然后將它輸入機器人機械手的軸。

電動機可以是交流式的, 也可以是直流式的?？刂破靼l(fā)出的脈沖信號被發(fā) 送到機械手得電機。這些脈沖為電機提供必要的指令信息以使機械手在機器人底 座上旋轉(zhuǎn)。

用于機械手軸的三種動力系統(tǒng)任一種均需要使用反饋監(jiān)督系統(tǒng), 這種系統(tǒng) 會不斷地將每個軸位置數(shù)據(jù)反饋給控制器。

每種機器人系統(tǒng)不僅需要動力來開動機械手的軸, 還需要動力來驅(qū)動控制 器,這種動力可由制造環(huán)境的動力源提供。

端部執(zhí)行件

在大部分機器人應(yīng)用的場合見到的端部執(zhí)行件均是機械手手腕法蘭相連 接的一個裝置, 端部執(zhí)行件可應(yīng)用于生產(chǎn)領(lǐng)域中許多不同場合, 例如, 它可用于 撿起零件, 用于焊接, 或用于噴漆, 端部執(zhí)行件為機器人系統(tǒng)提供了機器人運行 時必須的柔性。

通常所設(shè)計得端部執(zhí)行件可滿足機器人用戶的需要。這些部件可由機器人 制造商或機器人系統(tǒng)的物主制造。

端部執(zhí)行件事機器人系統(tǒng)中唯一可將一種工作變成另一種工作的部件, 例 如, 即日起可與噴水割機相連, 它在汽車生產(chǎn)線上被用于切割板邊。也可要求機 器人將零件安放到磁盤中, 在這簡單的過程中, 改變了機器人端部執(zhí)行件, 該機 器人就可以用于其它應(yīng)用場合, 端部執(zhí)行件得變更以及機器人的再編程序可使該 系統(tǒng)具有很高的柔性。

機器人傳感器

盡管機器人有巨大的能力,但很多時候卻比不過沒有經(jīng)過一點訓練的工 人。例如, 工人們能夠發(fā)現(xiàn)零件掉在地上或發(fā)現(xiàn)進料機上沒有零件, 但沒有了傳 感器, 機器人就得不到這些信息, 及時使用最尖端的傳感器, 機器人也比不上一 個經(jīng)驗豐富的

工人, 因此, 一個好的機器人系統(tǒng)的設(shè)計需要使用許多傳感器與機 器人控制器相接,使其盡可能接近操作工人得感知能力。

機器人技術(shù)最經(jīng)常使用的傳感器分為接觸式的與非接觸式的。接觸式傳感 器可以進一步分為觸覺傳感器、力和扭矩傳感器。觸覺或接觸傳感器可以測出受 動器端與其他物體間的實際接觸, 微型開關(guān)就是一個簡單的觸覺傳感器, 當機器 人得受動氣端與其他物體接觸時, 傳感器是機器人停止工作, 避免物體間的碰撞, 告訴機器人已到達目標;或者在檢測時用來測量物體尺寸。力和扭矩傳感器位于 機器人得抓手與手腕的最后一個關(guān)節(jié)之間, 或者放在機械手得承載部件上, 測量 反力與力矩。力和扭矩傳感器有壓電傳感器和裝在柔性部件上的應(yīng)變儀等。非接觸傳感器包括接近傳感器、視覺傳感器、聲敏元件及范圍探測器等。接近傳感器和標示傳感器附近的物體。例如, 可以用渦流傳感器精確地保持與鋼 板之間的固定的距離。最簡單的機器人接近傳感器包括一個發(fā)光二極管發(fā)射機和

一個光敏二極管接收器, 接收反射面移近時的反射光線, 這種傳感器的主要缺點 是移近物對光線的反射率會影響接收信號。其他得接近傳感器使用的是與電容和 電感相關(guān)的原理。

視覺傳感系統(tǒng)十分復雜, 基于電視攝像或激光掃描的工作原理。攝像信號 經(jīng)過硬件預處理, 以 30幀至 60幀每秒的速度輸入計算機。計算機分析數(shù)據(jù)并提 取所需的信息,例如,物體是否存在以及物體的特征、位置、操作方向,或者檢 測元件的組裝及產(chǎn)品是否完成。

聲敏元件用來感應(yīng)并解釋聲波, 從基本的聲波探測到人們連續(xù)講話的逐字 識別, 各種聲敏元件的復雜程序不等, 除了人機語音交流外, 機器人還可以使用 聲敏元件控制弧焊, 聽到碰撞或倒塌的聲音時阻止機器人的運動, 預測將要發(fā)生 的機械破損及檢測物體內(nèi)部缺陷。

還有一種非接觸系統(tǒng)使用投影儀和成像設(shè)備獲取物體的表面形狀信息或 距離信息。

傳感器有靜態(tài)探測與閉環(huán)探測兩種使用方法。當機器人系統(tǒng)的探測和操作 動作交替進行時, 通常就要使用傳感器, 也就是說探測時機器人不操作, 操作時 與傳感器無關(guān), 這種方法被稱為靜態(tài)探測, 使用這種方法, 視覺傳感器先尋找被 捕捉物體的位置與方向,然后機器人徑直朝那個地點移動。

相反, 閉式探測的機器人在操作運動中, 始終受傳感器的控制, 多數(shù)視覺傳感器 都采用閉環(huán)模式, 它們隨時監(jiān)測機器人的實際位置與理想位置間的偏差, 并驅(qū)動 機器人修正這一偏差。在閉環(huán)探測中,即使物體在運動,例如在傳送帶上,機器 人也能抓住它并把它送到預定位置。

Robots and robot sensor Introduction Industrial robot and its operation is the subject of this article.Industrial robots are used in manufacturing environment as a tool to increase productivity.It can be used to undertake routine, tedious assembly line work, or the implementation of those workers may be hazardous work.For example, in the first generation of industrial robots, there were a nuclear power plant is for the replacement of fuel rods.Workers engaged in this work may be exposed to harmful amounts of radiation in the next.Industrial robots can operate in the assembly line-to install small-scale components, such as electronic components mounted on circuit board.To this end, workers from the tedious task of this routine operation freed.The robot can be programmed to remove the bomb detonators for the disabled in our community services and play a role in many applications.Robot arm can be seen as the end of the implementation of tools, sensors, and / or jaws to move to a predetermined position of a machine.When the robot reaches the position, it will perform a task.The task may be welded, sealed, mechanical loading, mechanical unloading, or many assembly work.In addition to programming, and open

and close the system, the general, not require the participation of people will be able to complete such work.Robotics Glossary Robot is a reprogrammable multifunctional manipulator that can be programmable motion moving parts, materials, tools or special devices to perform a different task.By the following paragraphs of this definition may lead to other definitions were described, which provides a complete system for the robot itself.Location is pre-programmed robot must follow in order to complete the work and the way through.A point in these locations, the robot will stop and perform some operations, such as assembling parts, painting or welding.These pre-programmed robot position is stored in the memory device to continue operation for later use.In addition, when job requirements change, the only other programming data and these can be modified pre-programmed locations.Therefore, precisely because of the characteristics of this program, an industrial robot and one can store data, and can recall and edit the computer is very similar.Robot is a robot arm, which allows the robot pitch, stretching and rotating.This action is provided by the robot axis, mechanical axis, also known as robot hand of freedom.A robot can have 3-16 axis.In my later, the term degrees of freedom and a total number of robot axes associated.Tools and not within the robot gripper itself, which is mounted on the robot arm end attachment.With the end of the robot arm connected to these attachments, the robot can lift parts, spot welding, painting, welding, drilling, deburring, the request can also point to various types of tasks.Robot system can also control the operation of the robot's work unit.Robotic work cell is a general environment in the environment, the robot must perform the tasks entrusted to it.The unit can accommodate the controller, the robot manipulator, working platforms, safety devices, or conveyor.Robot to carry out all the equipment needed for the work are included in this unit of work.In addition, the signal from the external device to communicate with the robot, so that you can tell the robot when it is part of the assembly, pick up the parts or the parts to the unloading conveyor.Basic components Robotic system has three basic components: the robot, controller and power source.In some robot system can be seen in the first four components, end of the implementation of parts, these parts will be described in the following sections.Manipulator Robot bear robot system manual work, which consists of two parts: the mechanical parts and is connected to appendages.There is also a robot appendage connected to the base.The base of the robot work area is usually fixed in the ground.Sometimes, the base can be moved.In that case, the base is installed to the rail so that the robot can move from one place to another.For example, a robot can work for a few machine tools, loading and unloading for each machine.As mentioned earlier, the appendage extending from the base of the robot.The attachment is a robot arm.It can be a linear movable arm, it can be a hinged arm.Articulated arm, also known as articulated arm.Adjunct manipulator can provide a variety of sports-axis robot.The shaft is connected with the fixed base, which base has been tightened to the rack.This rack can ensure that the robot is in a position to maintain.Ends of the arm connected to a wrist.The axis of the wrist and wrist flange by additional components, with the flange of the wrist, the robot according to the different users can work in different tools installed on the wrist.Axis allows the robot manipulator in a certain area implementation.As mentioned earlier, the region known as the robot work unit, and its scale and size of the corresponding robot.When the robot's physical size increases, the size of the unit of work must also increase.Mechanical hand movements by the driver, or drive system control.Drive or shaft drive system allows the movement in the work unit, drive system using electric, hydraulic or pneumatic power.Drive the energy emitted from a variety of mechanical drive into mechanical power.These drives are joined together by a mechanical linkage.The linkage in turn drive the various robot axes.Mechanical linkage from the sprocket body, composed of gears and ball screws.Controller Robot controller is running in the heart.After the memory controller stores used for the pre-programmed information, control peripherals, to communicate it with the factory computer to make the production of constantly updated.Controller used to control the manipulator motion and the outer parts of the work unit.Staff can use the box to teach hand-delivery actions programmed into the robot controller.This information can be stored in the controller's memory for later recall using the device.Robot controller stores all program data.It can store several different programs, and they can be in any program to be edited.May also request the work unit controller and peripheral devices to communicate.For example, the controller has an input line, the input line can be identified when a mechanical process to complete.When the mechanical cycle is complete, the input line is connected, it will place orders for the controller to the robot manipulator to pick up the processing of finished parts.Then, the robot then picked up a new part and it is placed into the machine, then, the controller send a signal to the machine to get it started operation.Mechanical manipulation of the drum controller can be constituted, the work place by order of the drum operation.The controller for a very simple robot system.Seen in most of the robot system controller is a very complex device, which reflects the modern electronic science.In other words, they are manipulated by the micro-information processor.These micro-information processors instead of 8 bits, 16 bits of information that is 32-bit processors.This feature allows the controller to run with very good flexibility.Controller can send electronic signals through the communication line to issue with the mechanical hand signals to communicate with the axis of the robot manipulator and controller, this two-way communication between the location and operation makes the system constantly revised and updated to maintain the state may The controller can also control the robot wrist in the end installed any tools.There are different controller computers and factory to carry out the task of communication, the communication network will enable the robot to become computer-aided manufacturing(CAM part of the system.According to the basic definition, the robot is a multi-function can be re-programmed robot.Therefore, the controller must include some form of memory storage, to micro-processor-based information systems are often associated with solid-state

memory device with the operation.These memory devices can be magnetic bubbles, random access memory device, soft plastic disk or tape.Each memory storage device programming information can be stored for later recall using the.Power source Source of power to the controller and the robot was powered device, there are two types of robot power supply system.Controller for a class of power is power to run the exchange point, and the other is used to drive the robot axes.For example, if the robot manipulator controlled by a hydraulic or pneumatic device, the control signal is sent to these devices to make the robot movement.Each robot systems require power to drive the robot, this source of power either by hydraulic power, pneumatic power source, power source can also be provided by electricity, the power source is a unit of work the robot parts and equipment in the total part.When the hydraulic power source with and connected to the base manipulator, hydraulic pressure source to produce the hydraulic fluid, the fluid transport of the control components to the robot, so the robot base rotated around the axis.Pressure air is fed to the robot, the axis along the track in a straight line, the source can also be connected to such a pneumatic drill, it can provide power for the drill rotation.Under normal circumstances, can be obtained from the factory air supply station for the source and make adjustments, and then enter it in the axis manipulator.AC motor type can also be a DC-style.Controller sends out pulses of the signal was sent to the robot motors.These pulses provide the necessary instructions for the motor information to enable the robot in the robot base rotation.The three-axis robot for power systems either require the use of feedback control systems, this system will continue to position data for each axis of feedback to the controller.Each robot system not only need power to start the robot axis, also need power to drive the controller, this dynamic manufacturing environment, the power source can provide.Implementation of end pieces In most applications where the robot to see implementation of end pieces are connected to the robot wrist flange of a device, end pieces can be used in the production areas of the

implementation of many different occasions, for example, it can be used to pick up parts, used for welding, or for painting, the implementation of parts for the robot end system provides the flexibility of the robot must run.Usually designed to meet the end of the implementation of pieces of the robot users.These components can robot manufacturer or owner of manufacturing robot system.The implementation of the system end the only thing the robot can be a work into another working parts, for example, are available from the cutting machine is connected with the water, which is used in the automotive production line cutting edge.May also request the robot placed the parts to disk, in this simple process, change the end of the implementation of parts of the robot, the robot can be used for other applications, the implementation of end pieces may change, and then the robot programmed allows the system to have high flexibility.Robot Sensor Although the robot has great ability, but often than not with a little practice, but the workers.For example, workers can find parts that fall to the ground or no parts feeder, but not the sensor, the robot will not get this information in a timely manner using the most sophisticated sensors, the robot is smaller than an experienced worker Therefore, a good robot system design requires many sensor and robot controller using the phase, it was as close as possible operative awareness.The most frequently used robotics sensors into contact with the non-contact.Contact sensors can be further divided into tactile sensors, force and torque sensors.Tactile or contact sensors can be measured by the drive-side and the actual contact between other objects, micro-switch is a simple tactile sensor, the robot may be angry when the client contact with other objects, the sensor is the robot to stop work and avoid objects between collisions, tell the robot has reached the goal;or when used to measure the size of objects detected.Force and torque sensors in the robot gripper and wrist was the last joint, or between the parts on the robot to carry a measured reaction force and torque.Force and torque sensors are mounted on the flexible piezoelectric sensors and strain gauges on the parts.Non-contact sensors include proximity sensors, vision sensors, sound detectors, sensitive components and scope.Proximity sensors and labeling of objects near the

sensor.For example, eddy current sensor can be used to accurately maintain a fixed distance between the plates.The most simple robot proximity sensors including a light-emitting diode and a photodiode receiver transmitter, receiver reflector closer to the reflection of light, the main disadvantage of this sensor is closer to the object reflectance of light will affect the received signal.The other was close to the sensor using a capacitance and inductance associated with the principle.Visual sensing system is very complex, based on the TV camera or laser scanner works.Video signal through the hardware pretreatment to 30-60 per second input into the computer.Computer analysis of the data and extract the required information, for example, the existence of objects and object features, location, operating direction, or components of the assembly and product testing is complete.Sound sensitive devices used to sense and interpret sound waves, sound waves detected from the basic people recognize continuous speech, word for word, all kinds of sound ranging from sensitive components of the complex procedures, in addition to human-computer voice communication, the robot can also use the sound sensitive devices control of arc welding, I heard the sound of collision or collapse of the movement to stop the robot to predict the mechanical damage will occur and the detection of objects within the defects.There is also a non-contact systems for projector and imaging the surface of the object shape information or distance information.Static detection and closed-loop sensor probe used in two ways.When the detection and operation of the robot system moves alternately, it is usually necessary to use sensors that detect when the robot is not operating, the operation has nothing to do with the sensors, this method is called static detection, using this method, visual Find the sensor captured the first position and orientation of objects, and then the robot moves straight to the site.In contrast, closed manipulation and motion detection robot, always under the control of sensors, vision sensors are used the majority of closed-loop mode, which monitor the robot's actual position at any time and the deviation between the ideal position, and drive the robot fix this error.In the closed-loop detection, even if the object

in motion, for example, the conveyor belt, the robot can grasp it and send it to the desired location.

第四篇：外文翻譯——使用遠程網(wǎng)絡(luò)控制系統(tǒng)的三軸機器人

使用遠程網(wǎng)絡(luò)控制系統(tǒng)的三軸機器人

Min-Chie Chiu, Tian-Syung Lan, Ho-Chih Cheng 自動控制工程系，中州技術(shù)學院，彰化，臺灣，中國 宇達商業(yè)科技大學資訊管理系，苗栗縣，臺灣，中國

摘要 對于石油行業(yè)，在有發(fā)生瓦斯爆炸危險的工作區(qū)使用防爆設(shè)備以降低風險，如空氣驅(qū)動裝置，這對于避免爆炸是必不可少的。此外，使用一個可視化的監(jiān)測系統(tǒng)和網(wǎng)絡(luò)的遠程操作的機器人，以達到節(jié)省人力的目的。然而，要克服昂貴的人力成本的缺點和提高防爆區(qū)域的安全，提出了使用遠程網(wǎng)絡(luò)控制一個三軸機器人的系統(tǒng)控制。在本文中，三軸的機器人可以經(jīng)由USB協(xié)議被在線監(jiān)視。此外，它也可以通過點擊客戶端PC上的VB接口的命令，利用TCP/ IP協(xié)議遠程操作。因此，遠程控制三軸機器人不僅能在嚴重和危險的情況下為人們工作，而且還可以降低人力成本。

關(guān)鍵詞：三軸機器人，遠程網(wǎng)絡(luò)監(jiān)控

1.簡介

在現(xiàn)代世界發(fā)展的新趨勢，機器人開始感覺到他們的存在。為了提高這個過程，并減少不必要的人力，各種工業(yè)機器人已被廣泛開發(fā)[1]。傳統(tǒng)的機器人已被禁止在爆炸危險區(qū)使用電機驅(qū)動。為了克服這個缺點，需要一個新的設(shè)計要求的防爆電機[2]。但是，它是非常昂貴的。因此，在石油工業(yè)中為避免引起爆炸的火花，空氣驅(qū)動裝置對于防止爆炸是必要的[3,4]。目前，各種機器人已被提出，但是他們?nèi)狈h程機器人和用戶之間的交互性。為了在危險的工作區(qū)手動操作機器人執(zhí)行特定的工作，一個空氣系統(tǒng)驅(qū)動的遠程控制機器人是非常重要的。在本文中，三軸機器人配備一個網(wǎng)絡(luò)攝像頭，它可以通過USB協(xié)議進行在線監(jiān)視。顯然，遠程控制三軸機器人不僅可以為人們在動蕩和危險的情況下工作，還可以降低人力成本。因此，一個基于PC的控制系統(tǒng)使用VB在一個服務(wù)器電腦和客戶端PC通過RS232/RS485協(xié)議建立接口。2.基于PC的遠程控制系統(tǒng)

用于減少人力的工業(yè)加工的自動化系統(tǒng)是隨處可見。正如圖1中，使用兩個VB經(jīng)由網(wǎng)絡(luò)接口（一個服務(wù)器中的PC和另一個在客戶端中的PC）和Web攝像頭已建立的遠程三軸機器人系統(tǒng)。正如在圖2中所示，施加兩種系統(tǒng)模量（7060D和7520）中的遠程監(jiān)視/控制系統(tǒng)。由于RS232協(xié)議傳送的距離超過十五米時信號會產(chǎn)生嚴重的衰減，一個新建議的協(xié)議（RS485）在長距離傳輸時信號衰減的影響是微不足道的[5,6]。在這里，7520是一個從RS232—RS485協(xié)議的轉(zhuǎn)換設(shè)備[7,8]。通過RS232/RS485轉(zhuǎn)換器從服務(wù)器PC發(fā)出的命令將被發(fā)送到其他模量。電磁控制閥的硬件如圖3所示用于操縱的活塞運動（即機器人臂的運動）使用一個7060D模塊的DI/O（數(shù)字輸入和輸出），被發(fā)射的信號從一個服務(wù)器PC通過一個7520A模塊（從RS232，RS285協(xié)議轉(zhuǎn)換器）。正如圖4所示，電磁控制閥7060模塊通過使用一個VB接口的服務(wù)器PC上一個RS232/RS485協(xié)議觸發(fā)數(shù)字信號輸出?？刂崎y的位置狀態(tài)會從控制閥(a0, a1, b0, b1, c0, and c1)傳送的磁信號被7060模塊的數(shù)字輸入信號檢測到。

圖1 遠程三軸機器人系統(tǒng)

圖2 兩種模塊

圖3 三個電磁控制閥相對于活塞的圖表

圖4 導線連接的模塊

正如在圖5和圖6中所示，用戶可以通過點擊的移動按鈕通過VB 服務(wù)器PC和客戶端PC上的對話相關(guān)的電磁控制閥操縱機器人的手臂。此外，當前位置活塞A，B和C監(jiān)測的燈光A +，A-，B+，B-，C+，和C-可以在服務(wù)器和客戶端PC的VB對話框中控制。

氣動機械臂在被執(zhí)行之前，系統(tǒng)在系統(tǒng)的測試圖的基礎(chǔ)上進行確認。正如在圖7中所示，三個電磁控制閥的信號的操縱過程中將被重新檢查。此外，也可以通過單擊命令按鈕，在PC界面上VB的對話框中觸發(fā)相關(guān)的活塞將燈光A +，A-，B+，B-，C+，和C-作出回應(yīng)。

圖5 VB對話框（PC服務(wù)器）手動移動機器人的手臂 要監(jiān)視在線的真實運動的機器人手臂，需要安裝一個網(wǎng)絡(luò)攝像頭。機器人手臂的圖像將被捕獲，并通過一個USB協(xié)議發(fā)送回至服務(wù)器電腦。此外，圖像將通過TCP / IP協(xié)議被傳輸?shù)娇蛻舳穗娔X。

圖6 VB對話框（PC客戶端）手動移動機器人的手臂

3.結(jié)果與討論 3.1 結(jié)果

正如在圖5和圖6上所示，使用兩個VB的接口（一個中的服務(wù)器的PC和客戶端中的pc），通過網(wǎng)絡(luò)與Web攝像頭的一個三軸機器人的遠程控制已經(jīng)成功建立。在客戶端電腦可以被操縱，TCP/ IP協(xié)議的基礎(chǔ)上，應(yīng)先連接電腦的服務(wù)器和在客戶端的電腦對話中輸入IP地址和運輸端口號。要保持的機器人臂的特定移動，6個按鈕（x軸正向，x軸向后，y軸轉(zhuǎn)發(fā)，y軸向后，z軸的正向，和z軸向后，）對應(yīng)于服務(wù)器電腦VB對話框的上選擇機器人的動作。

3.2 討論

用戶可以通過服務(wù)器PC和客戶端PC操縱機器人手臂。VB界面所示的機器人手臂（活塞的位置的電磁信號）的狀態(tài)將通過TCP / IP協(xié)議被發(fā)送到PC客戶端。點擊在客戶端PC的命令，也將被發(fā)送到服務(wù)器的PC導致的電磁控制閥的動作，從而通過切換空氣路徑控制所述活塞的活塞運動。同時，活塞的位置信號將被轉(zhuǎn)換成的燈光A +，A-，B+，B-，C+，和C-顯示在兩個VB在PC服務(wù)器和客戶端的對話框上。此外，機器人手臂的圖像通過USB協(xié)議將被捕獲并發(fā)送到服務(wù)器PC。通過TCP / IP協(xié)議圖像將從PC服務(wù)器傳輸?shù)絇C客戶端。4.結(jié)論

這證明該遠程控制系統(tǒng)控制的空氣驅(qū)動三軸機器人手臂節(jié)省了人力，避免了爆炸，并提高了工業(yè)生產(chǎn)過程。傳統(tǒng)的機器人已被禁止在危險爆炸區(qū)使用電機驅(qū)動。此外，另一種用電氣馬達防爆的設(shè)計是昂貴的。因此，為了節(jié)省人力，避免發(fā)生爆炸的危險，同時，降低成本費用，使用空氣驅(qū)動的機器人手臂是必要的?？諝怛?qū)動的機器人在無火花化學過程中，并使用VB對話可以安全地和遠程操縱，它通過RS232/RS485協(xié)議，利用電磁控制閥，以觸發(fā)一個空氣驅(qū)動的活塞。此外，通過經(jīng)由USB協(xié)議的監(jiān)控機器人臂運動的圖像發(fā)送到服務(wù)器電腦。此外，機器人運動的圖像將通過TCP / IP協(xié)議被轉(zhuǎn)發(fā)到客戶端電腦機。在客戶端PC的用戶也可以在客戶端PC使用VB界面通過TCP / IP協(xié)議操縱機器人運動。

因此，應(yīng)當指出，如果在危險的工作環(huán)境中進行操作時，使用遠程網(wǎng)絡(luò)監(jiān)視/控制系統(tǒng)控制空氣驅(qū)動的機械臂，工人/植物和工業(yè)過程的安全和效率將得到改善。

5.致謝

作者感謝財政支持這個項目（CCUT-AI-96-AC02）。筆者感謝匿名審稿人友情提供的建議和意見，以改進這項工作。

6.參考文獻

[1] M.C.Chiu, L.J.Yeh and Y.C.Lin, “The Design and Application of a Robot ic Vacuum Cleaner,”Journal of Information & Optimization Sciences, Vol.30, No.1, 2009, pp.39-62.[2] H.A.Akeel and A.J.Malarz, “Electric Robot for Use in a Hazardous Location,” United States Patent 4984745, 2002.[3] Users’ Guidebook for Explosion Protection Electric Facility, Guildline, RIIS-TR-94-2, National Institute of Industrial Safety, 1994.[4] M.-R.Lin and C.-Y.Chen, “Applications of Inherently Safer Design on Industrial Processes,” Chemical Engineering, Vol.47, No.1, 2000, pp.41-51.[5] M.C.Chiu, “An Automatic Thermal Control on Green-house Using Network Remote Controlling System,” Journal of Applied Sciences , Vol.10, No.17, 2010, pp.1944-1950.[6] M.C.Chiu,“A Multi-Function Aquarium Equipped with Automatic Thermal Control/Fodder-Feeding/Water Treat-ment Using Network Remote Controlling System,” Information Technology Journal , Vol.9, No.7, 2010, pp.1458-1466.[7] M.C.Chiu, “The Study of Remote Network Monitoring and Controlling System on Thermal Procedure,” in: Y.-L.Chang-Hwa and C.-H.Chai-Ialley, Eds., The Proceedings of 2008 Academic Joint Venture, 2008.[8] M.C.Chiu, H.C.Cheng and M.J.Hsu, “The Study of Remote Network Monitoring and Controlling System on Gas-Driven Robotic,” The Proceedings of Mechanics, Light, and Electricity, San-Johns Technical University, Taipei, 2008.A Three-Axis Robot Using a Remote Network Control System

Min-Chie Chiu, Tian-Syung Lan, Ho-Chih Cheng Department of Automatic Control Engineering, Chungchou Institute of Technology，Changhua, Taiwan, China

Department of Information Management, Yu Da University, Miaoli, Taiwan, China

E-mail : tslan888@yahoo.com.tw

Received August 7 , 2010;revised October 8 , 2010;accepted October 18 , 2010

Abstract For the petroleum industry, to reduce the risk of a gas explosion in dangerous working areas, the use of explosion-proof equipment such as air-driven devices which are free from explosions becomes essential.Moreover, for the purpose of saving manpower, a remote operation using a robot via a visual monitoring system and a network is used.However, to overcome the drawback of costly manpower and to improve safety in explosion-prone zones, a three-axis robot using a remote network control system is proposed.In this paper, the three-axis robot can be monitored on line via the USB protocol.Furthermore, it also can be remotely manipulated via the TCP/IP protocol by clicking the command of the VB interface on the client pc.Consequently, the remote-control three-axis robot can not only work for people in severe and dangerous circumstances but also can reduce the cost of manpower.Keywords: Three-Axis Robot, Remote Network Monitoring

1.Introduction

As new trends in the modern world evolve, robots begin to make their presence felt.In order to improve the process and reduce unnecessary manpower, various industrial robots have been widely developed [1].Traditional robot driven by electrical motor used in a dangerous explosion zone has been prohibited.To overcome the drawback, a new design of explosion proof for an electrical motor is required [2].However, it is extremely expensive.Therefore, to avoid explosions caused by sparks in the petroleum industry, an air-driven device which is explosion free is necessary [3,4].Currently, various robots have been presented;however, they lack remote interactivity between the robot and the user.In order to manually operate a robot to execute a specific job in a dangerous working area, a remote-control robot system driven by air is vital.In this paper, the three-axis robot equipped with a web camera, which can be monitored online via the USB protocol, is established.Obviously, the remote-control three-axis robot not only can work for people in volatile and dangerous circumstances but also can lower the cost of manpower.Consequently, a PC-based control system is constructed using a VB interface in both a sever pc and a client pc via the RS232/RS485 protocol.2.A PC-Based Remote Controlling System

Automation systems used in industrial processing to reduce manpower are seen everywhere.As indicated in Figure 1, a remote three-axis robot system using two VB interfaces(one in the sever pc and the other in the client pc)via a network and a web camera has been established.As indicated in Figure 2, two kinds of system modulus(7060D and 7520)are applied in the remote monitoring/control system.Because of the serious decay of the signal for a RS232 protocol traveling over a distance of fifteen meters, a new protocol(RS485)in which the effect of signal decay is trivial for long-distance transportation is recommended [5,6].Here, the 7520 module is a protocol transfer device from RS232 to RS485 [7,8].A command emitted from the sever pc will be sent to other modulus via the RS232/RS485 converter.The hardware of the electromagnetic control valve shown in Figure 3 is used to manipulate the piston motion(i.e., the motion of the robotic arm)using a 7060D module’s DI/O(digital input and output)that is emitted from a sever pc via a 7520A module(a protocol translator from RS232 to RS285).As indicated in Figure 4 , the electromagnetic control valve will be triggered by the digital output signal of the 7060 module via a RS232/RS485 protocol using a VB interface on the sever pc.The status of the piston positions will be also detected by the digital input signal of the 7060 module transmitted from the magnetic signals(a0, a1, b0, b1, c0, and c1)of the pistons.Figure 1.A remote three-axis robot system.Figure 2.Two kinds of modulus.Figure 3.The diagram of the pistons with respect to three electromagnetic control valves.As indicated in Figures 5 and 6 , the user can manipulate the robot’s arm by clicking the movement button to actuate the related electromagnetic control valve via the VB dialogue on both the pc sever and the pc client.Moreover, the current position of pistons A, B, and C will be monitored by the lights of A+, A–, B+, B–, C+, and C– in the VB dialogues in pc server and client.Before the gas robotic arm is performed, the system confirmation is carried based on a system testing diagram.As indicated in Figure 7 , the signals of three electromagnetic control valves will be rechecked during the manipulating process.Besides, the related piston triggered by clicking the command button in the VB dialogue will also be responded to the lights of A+, A–, B+, B–, C+, and C– in pc’s interface.To monitor the real motion of robotic arm online, a web camera is installed.The image of the robotic arm will be caught and sent back to the sever pc via a USB protocol.Moreover, the image will be transmitted to the client pc via the TCP/IP protocol.Figure 4.The wire connections of the modulus.3.Results and Discussion

3.1.Results

As indicated in Figures 5 and 6 , the remote control of a three-axis robot using two VB interfaces(one in the sever pc and the other in the client pc)via a network and a web camera has been established successfully.Before the client pc can be manipulated, based on the TCP/IP protocol, the sever pc shall be connected first by inputting the IP address and transp ort number in the client’s pc dialogue.To keep the

Figure 5.The manual movement of the robot’s arm on the VB dialogue(pc sever).Figure 6.The manual movement of the robot’s arm on the VB dialogue(pc client).Figure 7.A system testing diagram for a remote-controlled three-axis robotic arm.robotic arm in a specific motion, six buttons(x-axis forward, x-axis backward, y-axis forwarding, y-axis backward, z-axis forward, and z-axis backward,)of the robot’s motion will be selected on the VB dialogue of the sever pc.3.2.Discussion

The user can manipulate the robotic arm in both the pc sever and the pc client.The status of the robotic arm(the electromagnetic signal of the piston’s location)shown in the VB interface will be transmitted to the pc client via a TCP/IP protocol.The command clicked in the pc client will be also transmitted to the pc sever to actuate the electromagnetic control valve so as to control the piston motion of the piston by switching the air path.Meanwhile, the signals of pistons’position will be translated as the lights of A+, A–, B+, B–, C+, and C– shown in two VB dialogues in pc server and client.Moreover, the image of the robotic arm will be caught and sent to the pc sever using the USB protocol.The image will be then transmitted from the pc sever to the pc client via the TCP/IP.4.Conclusions

It has been shown that a remote control system dealing with an air-driven three-axis robotic arm reduces manpower, avoids the explosion, and improves the industrial process.Traditional robot driven by electrical motor used in a dangerous explosion zone has been prohibited.Moreover, an alternative design of explosion proof for an electrical motor is expensive.Therefore, in order to save manpower, avoid the danger for explosion simultaneously, and to cost down the f ee of machine, an air-driven robotic arm is compulsory.The air-driven robot provides no spark in the chemical process and can be safely and remotely manipulated using a VB dialogue to trigger an air-driven piston, which is actuated by an electromagnetic control valve via the RS232/RS485.Additionally, a visual monitoring of the robotic arm is performed by transmitting the image of the robotic motion to the sever pc via the USB protocol.Moreover, the image of the robotic motion will be forwarded to the client pc via the TCP/IP protocol.The user at the client pc can also manipulate the robotic motion using a VB interface at the client pc via the TCP/IP protocol.Consequently, it is noted that both the safety of workers/plant and the efficiency of the industrial process will be improved if an air-driven robotic arm in conjunction with a remote network monitoring/control system is applied when operating in a dangerous work environment.5.Acknowledgements

The authors acknowledge the financial support of the Project(CCUT-AI-96-AC02).The author would like to thank the anonymous referees who kindly provided the suggestions and comments to improve this work.6.References

[1] M.C.Chiu, L.J.Yeh and Y.C.Lin, “The Design and Application of a Robot ic Vacuum Cleaner,” Journal of Information & Optimization Sciences, Vol.30, No.1, 2009, pp.39-62.[2] H.A.Akeel and A.J.Malarz, “Electric Robot for Use in a Hazardous Location,” United States Patent 4984745, 2002.[3] Users’ Guidebook for Explosion Protection Electric Facility, Guildline, RIIS-TR-94-2, National Institute of Industrial Safety, 1994.[4] M.-R.Lin and C.-Y.Chen, “Applications of Inherently Safer Design on Industrial Processes,” Chemical Engineering, Vol.47, No.1, 2000, pp.41-51.[5] M.C.Chiu, “An Automatic Thermal Control on Green-house Using Network Remote Controlling System,” Journal of Applied Sciences , Vol.10, No.17, 2010, pp.1944-1950.[6] M.C.Chiu,“A Multi-Function Aquarium Equipped with Automatic Thermal Control/Fodder-Feeding/Water Treat-ment Using Network Remote Controlling System,” Information Technology Journal , Vol.9, No.7, 2010, pp.1458-1466.[7] M.C.Chiu, “The Study of Remote Network Monitoring and Controlling System on Thermal Procedure,” in: Y.-L.Chang-Hwa and C.-H.Chai-Ialley, Eds., The Proceedings of 2008 Academic Joint Venture, 2008.[8] M.C.Chiu, H.C.Cheng and M.J.Hsu, “The Study of Remote Network Monitoring and Controlling System on Gas-Driven Robotic,” The Proceedings of Mechanics, Light, and Electricity, San-Johns Technical University, Taipei, 2008.

第五篇：高性能的PLC控制步進電機在機器人機械手外文翻譯

高性能的PLC控制步進電機在機器人機械手

摘要：在最近幾年，一個完整的多軸數(shù)字控制系統(tǒng)已經(jīng)研制成功。本文

介紹了一個用工業(yè)可編程邏輯控制(PLC）來控制五軸轉(zhuǎn)子位置，方向和速度，從而減少電路元件的數(shù)量，降低成本和提高可靠性。一些實驗結(jié)果表明是由控制器的高性能和功能得來的。關(guān)鍵詞：

PLC，機器人和步進電機。

1、簡介

運動控制的主要目的是設(shè)計控制系統(tǒng)能實現(xiàn)真正的自動運動機器。這種性能必須達到優(yōu)化機械，即生產(chǎn)力實現(xiàn)更高的工作速度，盡量減少能源要求，減少了使機械磨損的因素（1）。一個完全數(shù)字化的體系來說通過對基于總線控制系統(tǒng)的最大的靈活性應(yīng)用系統(tǒng)提供高性能的伺服控制是必需的。在大多數(shù)情況下，PLC是一種固態(tài)裝置，設(shè)計工作在嘈雜的工業(yè)環(huán)境并執(zhí)行所有的邏輯功能，早先就實現(xiàn)了對鼓機電繼電器開關(guān)，機械定時器和計數(shù)器的使用（2）。步進電機，通常用于微型電子計算機，現(xiàn)已廣泛應(yīng)用于機器人（3）。在本文中，我提出了各軸包含一個由plc控制的步進電機的五檔速度控制軸機器人。(SLC 150)

2、可編程控制器

PLC，像一臺電腦，采用了微處理器芯片進行處理和存儲芯片來存儲方案。PLC的基本結(jié)構(gòu)如圖1所示，輸入設(shè)備是監(jiān)控機器或被控制的過程的傳感器。這些傳感器的狀態(tài)（ON或OFF）被輸送到PLC控制器。取決于這些傳感器輸入狀態(tài)的PLC的輸出可能切換到活力馬達，繼電器，閥門等....,來控制機器或過程。SLC150的PLC[2]有10個輸入，編號從1到10的，然后再從10數(shù)到1的IO當作 IO1的輸入。SLCI50有12個輸出編號從11至16，和111至116。

3、機器人的描述、圖2顯示了一個典型的機器人（4）。它由一英寸上有8-32螺紋孔的12英寸至14英寸大小的底板和炮塔——一個周圍配備了傳送帶的旋轉(zhuǎn)平臺（它的每一英寸的中心有8-32螺紋孔）。這些孔配合安裝在機器人的手臂和手腕馬達的相對于其中心的不同地；，炮塔鉗，可連接炮塔和炮塔軸；炮塔裝載，可連接底板唇，覆蓋炮塔馬達，和支撐炮塔軸和炮塔。炮塔軸是用來保留炮塔和炮塔內(nèi)的炮架集合，炮塔軸承（有兩個）的

呈遞擔保裝入舉行炮塔軸，推力 軸承安裝在炮塔的軸上，以適應(yīng) 機器人的重量，提供平穩(wěn)和旋轉(zhuǎn) 炮塔，推力墊圈安裝在炮塔軸接口的推力軸承的安裝和炮塔鉗總成（他們是在任的推力軸承一面放置），炮塔齒輪（有二分之一254?0tha屆一，步進電機（五電機），數(shù)字編碼器，40齒）臂環(huán)節(jié)，是一個機器人手爪手，提供下巴 位置和動態(tài)壓縮力信息到控制器。