A Fault Detection Method of Networked Control System Based on Neural Network Prediction

Abstract

The invention discloses a networked control system fault detection method based on neural network prediction, which comprises four steps of RBF neural network system building, system fault detection function building, system stability judgment and operation and system fault judgment and operation function building. The system building and operation process is simple, the operation efficiency and the operation precision are relatively high, an improved RBF neural network prediction controller is adopted to effectively predict system output data information, and thus, bad influences on the system by packet loss can be effectively cancelled, errors are smaller and training times are reduced through adjusting learning efficiency on the basis of adopting feedback correction on the obtained predicted output value for correction, and better convergence and quicker prediction speed can be obtained. Meanwhile, when fault happens to the system, happening of the fault can be quickly detected according to a designed fault observer and a judgment criterion.

Description

technical field [0001] The invention relates to a networked control system fault detection method based on neural network prediction, which belongs to the technical field of power system and industrial process control. Background technique [0002] The networked control system has the advantages of low cost, strong reliability, and flexible structure. It is widely used in telemedicine, robotics, aerospace and other fields. However, the introduction of the network is prone to problems such as time delay and packet loss. These phenomena will not only make the system Performance drops and even makes it run unstable [1,2]. With the gradual expansion of the network scale, the stability and security requirements of the system are gradually increasing. Therefore, the fault detection problem of the networked control system has been widely concerned and studied by experts and scholars. Aiming at the problems existing in the operation of the current networked control system, the curre...

AI Technical Summary

Problems solved by technology

[0002] The networked control system has the advantages of low cost, strong reliability, and flexible structure. It is widely used in telemedicine, robotics, aerospace and other fields. However, the introduction of the network is prone to problems such as time delay and packet loss. These phenomena will not only make the system performance degradation and even make it run unstable[1,2]

With the gradual expansion of the network scale, the stability and security requirements of the system are gradually increasing. Therefore, the fault detection problem of the networked control system has been widely concerned and studied by experts and scholars. Aiming at the problems existing in the operation of the current networked control system, the current For short-delay networked control systems, the sufficient conditions for system stability are given by constructing the Lyapunov function and using the linear matrix inequality (LMI) method; considering the filter design problem of the network system with time delay and random packet loss, the LMI method is used to The method obtained the sufficient condition for the stability of the mean square index of the system; although these two methods can solve the problem of networked control system operation to a certain extent, they do not deal with the nonlinear terms appearing in the theorem, and their inequality constraints are a The non-strict LMI cannot directly obtain the observer parameters. To solve this problem, the traditional RBF neural network is currently developed to predict the networked control system with time delay, which can achieve fast convergence speed and unique best approximation. advantages, but the selection of the center vector is arbitrary, resulting in unsatisfactory system performance. Therefore, it is not difficult to see that there is still a lack of an effective solution and judgment method for the problems existing in the operation of the networked control system. In order to improve the networked control system The operation stability and reliability of the control system urgently need to develop a new networked control system fault detection method

Images