The Fault Diagnosis Research Of Actuator And Sensor In Process Control System

With development of technology, control system is more and more complicated, so diagnosing fault becomes more and more important, diagnosing accurately fault in time and ensuring that system runs reliably. The paper introducing the tasks of fault diagnosis, discuss the fault in the control system and their mathematical representing methods. The Actuator and sensor, as the performance terminating parts of the control system, usually work under the formidable circumstance with high temperature, high pressure, and having corrosion etc, is easier to make faults. The actuator and sensor's faults always make direct effect in the control performance; even make oscillation in the process, ultimately lead to the serious consequence as sub-quality products etc. So the demands of ensuring the control process operate stably and economically, is raising the performer itself reliability, finding the fault in the operation process in time.Summarizes the achievements up to the minute in the sensor fault diagnoses field in recent years, and makes deeply study on the two basic diagnose methods. Realizing the sensor fault and actor diagnoses of control system by using observer principle.In the control system of neural network, the fault diagnosis consists two parts: one is the collection of fault sample data, the other is fault diagnosis. So during the collection of fault sample datas and checking datas,the paper sets up the mathematics model of control system first. We cause all kinds of fault in the control system, and then collect a variety of fault datas. After unitarily dealing, the fault datas server as the sample datas of training neural network. At the same time, according to the collection of checking datas, which are used to examine whether the trained neural network have the function of fault diagnosis.In this paper, the author combines an artificial neural network with the genetic algorithms and forms a new algorithm, GA-BP algorithm, and establishes a GA-ANN model for the intelligent fault diagnosis of the process control system, which is used the features and virtues of ANN and GA. The model takes the advantages of traditional neural network and genetic algorithms, and gets rid of their defects. In order to demonstrate the feasibility of the model, a case of the electro-hydraulic servo valve's faults are selected for discussion. In the case, the simulation results are in good agreement with the measured data. This shows that the method presented in this paper is feasible in simulating the faults of process control system.