Application of Neural Network Inverse System in Motor Variable Frequency Speed ​​Control System

The traditional control system design is based on the known mathematical model of the system. Therefore, the quality of the control system has a lot to do with the accuracy of the mathematical model. However, the actual system is very different and complex, so it is difficult to find a suitable description model. It is even more difficult for nonlinear systems, and sometimes it can't even be done. The neural network is different for the control system design. Instead of the mathematical model of the controlled object, it can train the neural network online or offline, and then use the training results to design. Because neural networks have strong adaptability, parallel processing capability and intrinsic nonlinearity, controllers using neural network design will have stronger adaptability, better real-time performance and robustness for nonlinear and uncertain systems. Sex. There are many design methods for control systems based on neural networks, but no perfect theoretical system and systematic design methods have been formed yet. The proposed neural network controllers mainly include neural network PID control, neural network predictive control, and neural network. Mode control, neural network fuzzy control, etc.
Induction motors are typical multivariable, nonlinear systems, and with the addition of frequency converters, the entire system is more complex. In this paper, the induction motor variable frequency speed control system is selected as the control object, and its mathematical model is reversible. The neural network is used to construct the inverse controller to control the induction motor variable frequency speed control system. The neural network inverse controller combines the inverse system method with the neural network. Liu Guohai, born in 1964, Ph.D., professor and associate dean of the School of Electrical and Information Engineering of Jiangsu University, whose research direction is motor control and complex system control.
The BP network is used to approximate the a-order inverse system of the object, and then connected with the object to form a composite pseudo-linear system, and then the design method of the existing linear system is used to design the control system. The paper uses the neural network inverse system method to carry out the no-load/full load start test, sudden/decrement load test and tracking test verification of the actual induction motor variable frequency speed control system. The first system is formed into a first-order pseudo-linear system before the inverse system is connected in series with the original system, so that the entire composite system is converted into a type 1 pseudo-linear single-input single-output system.
The simulation results of the simulation curve of the unit under variable working conditions show that the control system effectively solves the impact of boiler nonlinearity, large time lag and load disturbance on the unit operation. Not only under normal load stability, the main steam pressure can be kept quite stable, and in the case of peaking of the unit and large change of combustion rate, the control unit can quickly track the load, effectively improving the control quality of the system and satisfying the actual situation. The control requirements have important practical significance for improving the peak shaving performance of the unit.
4 Conclusions The prominent features of cluster adaptive fuzzy control based on neural network prediction model designed in this paper are as follows: () The neural network is used to predict the system, which provides guarantee for the precise control of nonlinear large time-delay systems.
(2) While using fuzzy control to implement fuzzy rules based on expert control strategies and experience, cluster adaptive control is used to compensate for the incompatibility and incompleteness of fuzzy rules. The control method is concise, flexible and fast.
The simulation shows that the control has strong robustness, real-time and anti-interference ability, and even the peak-shaving unit can maintain good control performance and operation effect under variable working conditions (large range of variable load).