《堆垛机英文资料翻译.docx》由会员分享，可在线阅读，更多相关《堆垛机英文资料翻译.docx（15页珍藏版）》请在三一文库上搜索。
1、翻译 英文原文 Realization of Neural Network Inverse System with PLC in Variable Frequency Speed-Regulating SystemAbstract. The variable frequency speed-regulating system which consists of an induction motor and a general inverter, and controlled by PLCis widely used in industrial field. .However, for the
2、multivariable, nonlinear and strongly coupled induction motor, the control performance is not good enough to meet the needs of speed-regulating. The mathematic model of the variable frequency speed-regulating system in vector control modeis presented and its reversibility has been proved. By constru
3、cting a neural network inverse system and combining it with the variable frequency speed-regulating system, a pseudo-linear system is completed, and then a linear close-loop adjustor is designed to get high performance. Using PLC, a neural network inverse system can be realized in actural system. Th
4、e results of experiments have shown that the performances of variable frequency speed-regulating system can be improved greatly and the practicability of neural network inverse control was testified.1.IntroductionIn recent years, with power electronic technology, microelectronic technology and moder
5、n control theory infiltrating into AC electric driving system, inverters have been widely used in speed-regulating of AC motor. The variable frequency speed-regulating system which consists of an induction motor and a general inverter is used to take the place of DCspeed-regulating system. Because o
6、f terrible environment and severe disturbance in industrial field, the choice of controller is an important problem. In reference 123, Neural network inverse control was realized by using industrial control computer and several data acquisition cards. The advantages of industrial control computer ar
7、e high computation speed, great memory capacity and good compatibility with other software etc. But industrial control computer also has some disadvantages in industrial application such as instability and fallibility and worse communication ability. PLC control system is special designed for indust
8、rial environment application, and its stability and reliability are good. PLC control system can be easily integrated into field bus control system with the high ability of communication configuration, so it is wildly used in recent years, and deeply welcomed. Since the system composed of normal inv
9、erter and induction motor is a complicated nonlinear system, traditional PID control strategy could not meet the requirement for further control. Therefore, how to enhance control performance of this system is very urgent.The neural network inverse system 45 is a novel control method in recent years
10、. The basic idea is that: for a given system, an inverse system of the original system is created by a dynamic neural network, and the combination system of inverse and object is transformed into a kind of decoupling standardized system with linear relationship. Subsequently, a linear close-loop reg
11、ulator can be designed to achieve high control performance. The advantage of this method is easily to be realized in engineering. The linearization and decoupling control of normal nonlinear system can realize using this method.Combining the neural network inverse into PLC can easily makeup the insu
12、fficiency of solving the problems of nonlinear and coupling in PLC control system. This combination can promote the application of neural network inverse into practice to achieve its full economic and social benefits.In this paper, firstly the neural network inverse system method is introduced, and
13、mathematic model of the variable frequency speed-regulating system in vector control mode is presented. Then a reversible analysis of the system is performed, and the methods and steps are given in constructing NN-inverse system with PLC control system.Finally, the method is verified in experiments,
14、 and compared with traditional PI control and NN-inverse control.2. Neural Network Inverse System Control MethodThe basic idea of inverse control method 6 is that: for a given system, an a -th integral inverse system of the original system is created by feedback method, and combining the inverse sys
15、tem with original system, a kind of decoupling standardized system with linear relationship is obtained, which is named as a pseudo linear system as shown in Fig.1. Subsequently, a linear close-loop regulator will be designed to achieve high control performance.Inverse system control method with the
16、 features of direct, simple and easy to understand does not like differential geometry method 7, which is discusses the problems in geometry domain. The main problem is the acquisition of the inverse model in the applications. Since non-linear system is a complex system, and desired strict analytica
17、l inverse is very difficult to obtain, even impossible. The engineering application of inverse system control doesn t meet the expectations. As neural network has non-linear approximate ability, especially for nonlinear complexity system, it becomesthe powerful tool to solve the problem.a - th NNinv
18、erse system integrated inverse system with non-linear ability of the neural network can avoid the troubles of inverse system method. Then it is possible to apply inverse control method to a complicated non-linear system. a - th NNinverse system method needs less system information such as the relati
19、ve order of system, and it is easy to obtain the inverse model by neural network training. Cascading the NN inverse system with the original system, a pseudo-linear system is completed. Subsequently, a linear close-loop regulator will be designed.3. Mathematic Model of Induction Motor Variable Frequ
20、ency Speed-Regulating System and Its ReversibilityInduction motor variable frequency speed-regulating system supplied by the inverter of tracking current SPWM can be expressed by 5-th order nonlinear model in d-q two-phase rotating coordinate. The model was simplified as a 3-order nonlinear model. I
21、f the delay of inverter is neglected,the model is expressed as follows:where denotes synchronous angle frequency, and 吗 is rotate speed.J叫 are stator s current, and甲曰押气 are rotor s flux linkage in(d,q)axis. is number of poles.4 is mutual inductance, and L is,T ,rotor s inductance. J is momentof iner
22、tia. is rotor s time constant, andis load torque.In vector mode, thenLn十一fS叱乙Substituted it into formula (1), thennn工也十囹明亍W；-TJ-1L憾.% =7% +7小r Taking reversibility analyses of forum (2), theny - h(r) - yr f 二七mJ二八眄(4)The state variables are chosen as follows.r = 0工J =吗yjInput variables are口 二=囱Takin
23、g the derivative on output in formula(4), then二号i 一工后一J(5)ji 1 L.=X. +-If(6)Then the Jacobi matrix is Realization of Neural Network Inverse Systemwith PLCAsso(8)Dei(A(x,u.) =0, and system isa = (1J), and += 2 = rt .reversible. Relative-order of system isWhenthe inverter is running in vector mode, th
24、e variability of flux linkage can be neglected (considering the flux linkage to be invariableness and equal to the rating). The original system was simplified as an input and an output system concluded by forum (2).According to implicit function ontology theorem, inverse system of formula (3)can be
25、expressed asy = S 叭SWhenthe inverse system is connected to the original system in series, the pseudo linear compound system can be built as the type of4. Realization Steps of Neural Network Inverse System4.1 Acquisition of the Input and Output Training SamplesTraining samples are extremely important
26、 in the reconstruction of neural network inverse system. It is not only need to obtain the dynamic data of the original system, but also need to obtain the static date.Reference signal should include all the work region of original system, which can be ensure the approximate ability. Firstly the ste
27、p of actuating signal is given corresponding every 10 HZ form 0HZ to 50HZ, and the responses of open loop are obtain. Secondly a random tangle signal is input, which is a random signal cascading on the step of actuating signal every 10 seconds, and the close loop responses is obtained. Basedon these
28、 inputs, 1600 groups training samples are gotten.4.2 The Construction of Neural NetworkA static neural network and a dynamic neural network composed of integral is used to construct the inverse system. The structure of static neural network is 2 neurons in input layer, 3 neurons in output layer, and
29、 12 neurons in hidden layer. The excitation function of hidden neuron is monotonic smooth hyperbolic tangent function. The output layer is composed of neuron with linear threshold excitation function. The training datum are the corresponding speed of open-loop, close-loop, first order derivative of
30、these speed, and setting reference speed. After 50 timestraining, the training error of neural network achieves to 0.001. The weight and threshold of the neural network are saved. The inverse model of original system is obtained.5. .Experiments and Results5.1 Hardware of the SystemThe hardware of th
31、e experiment system is shown in Fig 5. The hardware system includes upper computer installed with Supervisory & Control configuration software WinCC6.08, and S7-300 PLCof SIEMENS,inverter, induction motor and photoelectric coder.PLCcontroller chooses S7-315-2DP, which has a PROFIBUS-Dinterface and a
32、 MPI interface. Speed acquisition module is FM350-1. WinCC is connected with S7-300 by CP5611 using MPI protocol.The type of inverter is MMWf SIEMENS.It can communicate with SIEMENS PLC by USS protocol. ACB15 module is added on the inverter in this system.5.2 Software Program5.2.1 Communication Intr
33、oductionMPI (MultiPoint Interface) is a simple and inexpensive communication strategy using in slowly and non-large data transforming field. The data transforming between WinCC and PLC is not large, so the MPI protocol is chosen.The MMV inverter is connected to the PROFIBUS network as a slave statio
34、n, which is mounted with CB15 PROFIBUS module. PPO1 or PPO3 data type can be chosen. It permits to send the control data directly to the inverter addresses, or to use the system function blocks of STEP7V5.2 SFC14/15.OPC can efficiently provide data integral and intercommunication.Different type serv
35、ers and clients can access data sources of each other. Comparing with the traditional modeof software and hardware development, equipment manufacturers only need to develop one driver. This can short the development cycle, save manpower resources, and simplify the structure of the entire control sys
36、tem.Variety data of the system is needed in the neural network training of Matlab, which can not obtain by reading from PLC or WinCC directly. So OPC technology can be used l to obtain the needed data between WinCC and Exce. Setting WinCC as OPC DA server, an OPC client is constructed in Excel by VB
37、A. System real time data is readed and writen to Excel by WinCC, and then the data in Excel is transform toMatlab for offlinetraining to get the inverse system of original system.5.2.2 Control ProgramUsed STLto program the communication and data acquisition and control algorithm subroutine in STEP7
38、V5.2, velocity sample subroutine and storage subroutine are programmed in regularly interrupt A, and the interrupt cycle chooses 100ms. In order to minimum the cycle time of A to prevent the run time of A exceeding 100msand system error, the control procedure and neural network algorithm are program
39、med in main procedure B. In neural network algorithm normalized the training samples is need to speed up the rate of convergence by multiplying a magnification factor in input and output data before the final training.5.3 Experiment ResultsWhen speed reference is square wave signal with 100 seconds
40、cycle, where the inverter is running in vector mode. The results show that the tracking performance of neural network control is better than traditional PI control.When speed reference keeps in constant, and the load is reduced to no load at 80 seconds, and increased to full load at 120 seconds, the
41、 response curves of speed with traditional PI control and neural network inverse control are shown in Fig. 11 and 12 respectively. It is clearly that the performance of resisting the load disturbing with neural network inversecontrol is better than the traditional PI control.-a101mBjdd中口 (Speed resp
42、onse in PI control)(Speed response in neural network inverse control)6. ConclusionIn order to improve the control performance of PLCVariable Frequency Speed-regulating System, neural network inverse system is used. A mathematic model of variable frequency speed-regulating system was given, and its r
43、eversibility was testified. The inverse system and original system is compound to construct the pseudo linear system and linear control method is design to control. With experiment, neural network inverse system with PLC has its effectiveness and its feasibility in industry application.中文译文PLC变频调速的网
44、络反馈系统的实现摘要。变频调速系统，包括一个异步电动机和通用逆变器、且PLC控制被广泛 地应用于工业领域。然而，对多变量、非线性和强耦合的异步电机的控制性能却 不足，不能很好地满足客户的调速要求。该数学模型的变频调速系统提出了矢量 控制方式，其可逆转性得到证实。通过构建一种基于神经网络的逆系统，并结合变 频调速系统,pseudo-linear系统被完成了 ,并且为了得到性能优良的系统采用 了一个线性闭环调节器。采用 PLC神经网络逆系统在实际系统可以实现。实验 结果表明变频调速系统的性能得到了很大的提高，并且神经网络反馈控制的可行 性得到了验证。1 .导论近年来，随着电力电子技术、微电子技术和
45、现代控制理论，逐渐涉及到交流电 机系统，这些技术已经广泛应用于变频器调速的 AC马达。变频调速系统，包括一 个异步电动机和通用逆变器，用来代替直流调速系统。由于在工业领域中的糟糕 的环境和严重的干扰，选择控制器是一个十分重要的问题。在文献123, 介 绍了利用工业控制计算机和数据采集卡实现了神经网络反馈控制。工业控制计算机的优势有较高的计算速度，庞大的记忆能力以及与其他软件良好的兼容性等。 但是工业控制计算机在工业应用上也有一些不足，比如运行不稳定，不可靠及更恶劣的通信能力。可编程序控制器（PLC）控制系统是专为工业环境中的应用而设 计的，它的稳定性和可靠性好。PLC控制系统，可以很容易地集成
46、到现场总线控制 系统并得到高性能的通信结构，所以它在近年来被广泛地使用，并且深受欢迎。该 系统由普通的逆变器和异步电机组成，是一种复杂的非线性系统，传统的PID控制策略，并不能满足要求和进一步控制。因此，如何加强系统的控制性能是非常迫 切的事情。神经网络逆系统45,在未来几年里将是一种新型的控制方法。其基本的想法是：对于一个给定的系统，原系统的逆系统是由一个动态神经网络引起的，对 象信号和反馈信号的组合系统被转化成一种线性关系的解耦标准系统。随后 ，一 个线性闭环调节器设计可以达到较高的控制性能。该方法的优点是在工程上很容易实现。在线性化及其解耦控制正常的非线性系统能实现采用这种方法。把神经网
47、络反馈结合到可编程序控制器（PLC）上就可以很容易地弥补不足的 问题，解决在PLC控制系统上的非线性耦合。这个组合可以促进神经网络反馈付诸实践，来实现其全部的经济效益和社会效益,并且描述了采用矢量在这篇文章中，首先对神经网络反馈方法进行了介绍控制的变频调速系统的数学模型。然后是对反馈系统进行分析的的介绍，并给出了关于PLC控制系统中构造NN-K馈系统的方法和步骤。最后,该方法在实验中 被验证，并将传统的PI控制和NN-K馈控制进行了对比。2 .神经反馈网络控制方法基本的反馈控制方法6就是：对于一个给定的系统、一种a -th由反馈方法 建立的完整的反馈系统，并结合反馈系统与原系统的特点，提出了一
48、种解耦的线 性关系，以标准化体系，并命名为伪线性系统。随后，一个线性闭环调节器运行并 将达到较高的控制性能。当在“几何领域”讨论这些问题时，反馈系统控制方法并不像微分几何方法， 其特点是直接，简单，易于理解。主要的问题是怎样在应用软件中获得反馈模型。 由于非线性系统是一个复杂的系统，所以很难要求严格解析反馈信号，这甚至是 不可能的。反馈系统控制在工程应用中不能达到期望值。作为神经网络非线性逼 近能力，尤其是对于非线性的复杂系统，它会是来解决问题的强大工具。反馈系统 集成了具有非线性逼近能力的反馈系统，其中具有非线性逼近能力的反馈系统能 够避免使用反馈方法带来的麻烦。这样就可能，运用反馈控制方法去控制一个复 杂的非线性系统。a - th NN反馈系统的控制方法只需要较少的系统信息，比如 与系统相关的命令，并且容易获得运行网络的反馈模型。原系统的层叠式的NN反馈系统，会形成一个伪线性系统。然后，一个线性闭环调节校准器将工作。3 .异步电机变频调速系统的数学模型和它的反馈性能异步电机变频调速系统提供的跟踪电流正弦脉宽调制逆变器可以表示为非线性模型在两相循环的协调。该模型简化为一个3-order非线性模型。如果忽略逆变器的延迟，该模型表述如下:*t 口 1a处=丁(旷一口叩心)7。 ujF J .diJ（