Premium
Neuron PID Control for a BPMSM Based on RBF Neural Network On‐Line Identification
Author(s) -
Sun Xiaodong,
Zhu Huangqiu
Publication year - 2013
Publication title -
asian journal of control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.769
H-Index - 53
eISSN - 1934-6093
pISSN - 1561-8625
DOI - 10.1002/asjc.547
Subject(s) - pid controller , control theory (sociology) , nonlinear system , artificial neural network , controller (irrigation) , computer science , system identification , identification (biology) , line (geometry) , control engineering , engineering , control (management) , artificial intelligence , mathematics , temperature control , data modeling , agronomy , physics , botany , geometry , quantum mechanics , database , biology
The ability to improve the dynamic performance and control accuracy of the bearingless permanent magnet synchronous motor ( BPMSM ) is critical to developing and maintaining a high application. BPMSM , however, is a nonlinear system with unavoidable and unmeasured disturbances, in addition to having parameter variations. Traditional control strategies cannot attain good performance. Thus, it is important to propose a new design procedure in order to construct a robust controller with good closed‐loop capability. This paper presents a neuron proportional‐integral‐derivative ( PID ) controller based on radial basis function neural network ( RBFNN ) on‐line identification to regulate optimal parameters using the approximated ability of RBFNN . Through the RBFNN algorithm, the current model of the system is automatically extracted for updating the PID controller parameters. This scheme can adjust the PID parameters in an on‐line manner even if the system has nonlinear properties. Simulations and experiments demonstrate that the new method has better control system performance than conventional PID controllers.