Artificial neural network based robust speed control of permanent magnet synchronous motors

Abstract

PurposeThe aim of the paper is to find a simple structure of speed controller robust against drive parameters variations. Application of artificial neural network (ANN) in the controller of PI type creates proper non‐linear characteristics, which ensures controller robustness.Design/methodology/approachThe robustness of the controller is based on its non‐linear characteristic introduced by ANN. The paper proposes a novel approach to neural controller synthesis to be performed in two stages. The first stage consists in training the ANN to form the proper shape of the control surface, which represents the non‐linear characteristic of the controller. At the second stage, the PI controller settings are adjusted by means of the random weight change (RWC) procedure, which optimises the control quality index formulated in the paper. The synthesis is performed using simulation techniques and subsequently the behaviour of a laboratory speed control system is validated in the experimental set‐up. The control algorithms of the system are performed by a microprocessor floating point DSP control system.FindingsThe proposed controller structure with proper control surface created by ANN guarantees expected robustness.Originality/valueThe original method of robust controller synthesis was proposed and validated by simulation and experimental investigations.

Adaptive speed controller for servodrive based on artificial neural network trained online

“…Due to it a dynamic drop of speed, involved by this change, is compensated. As a result of such controller operation a steady state speed control error is kept at value near zero with accuracy, which depends on width of assumed tolerant band in training procedure (5). Influence of tolerant bandwidth on speed control error, involved by step change of load torque, is shown in Fig.…”

“…Simulation investigations of proposed control system were provided on the computer model of the system in MATLAB -Simulink language, described in [5]. The results of simulation investigations were verified by experiment, which was provided on laboratory stand.…”

Application of artificial neural network for adaptive speed control of PMSM drive with variable parameters

“…Simulation investigations of proposed control system were provided on the computer model of the system in MATLAB – Simulink language, described in Pajchrowski et al (2006, 2007). During simulation tests the responses on step change of reference speed and step change of motor load were analysed for drive with constant and variable moment of inertia.…”

Application of neuro‐fuzzy techniques to robust speed control of PMSM

“…Robustness is achieved by creating a proper nonlinear characteristic of the controller by the fuzzy or neuro‐fuzzy module. The paper builds on earlier results given by the authors in Pajchrowski and Zawirski (2004) and Pajchrowski et al (2006). The previously described neural robust speed controller has been replaced by a neuro‐fuzzy network whose synthesis combines advantages of both control methods.…”