• CN: 11-2187/TH
  • ISSN: 0577-6686

Journal of Mechanical Engineering ›› 2020, Vol. 56 ›› Issue (22): 131-141.doi: 10.3901/JME.2020.22.131

Previous Articles     Next Articles

Research on Self-healing Control Method of Reciprocating Compressor Capacity Control Instability

JIANG Zhinong1,2, ZHOU Chao1, ZHANG Jinjie1,3, LIU Wenhua1, WANG Yao1,3, SUN Xu1   

  1. 1. Compressor Health and Intelligent Monitoring Center of National Key Laboratory of Compressor Technology, Beijing University of Chemical Technology, Beijing 100029;
    2. Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery, Beijing University of Chemical Technology, Beijing 100029;
    3. State Key Laboratory of Compressor Technology(Anhui Provincial Laboratory of Compressor Technology), Hefei 230031
  • Received:2019-11-04 Revised:2020-07-30 Online:2020-11-20 Published:2020-12-31

Abstract: For the common regulation instability fault of reciprocating compressor stepless capacity regulation system, a multi-system coupling control model of stepless capacity regulation system which includes compressor, pipeline, buffer tank, actuator and so on, is built to simulate the dynamic characteristics of reciprocating compressor stepless capacity regulation system. By using the pulse width modulation control signal from the control system as input and the compressor exhaust pressure of every stage as output. The law of the dynamic response of the actuator and the influence of the control parameters in control system on the capacity regulation results are studied. Further, for the problem of capacity control instability caused by the change of actuators' performance parameters, a multi-parameter load dynamic feedback model is built by using BP neural network to realize the regulation instability fault diagnosis and fault type identification. Based on the results of abnormal fault type recognition, a self-healing control method based on adaptive optimal compensation of control parameters is proposed. The experimental results indicated that the proposed self-healing control method can automatically apply the compensation of control parameters after the instability fault, so that the capacity regulation system returned to the normal state, and the fault self-healing can be realized on-line.

Key words: reciprocating compressor, regulatory instability failure, self-healing control, BP neural network

CLC Number: