In this paper, an adaptive neural network sensorless control scheme is introduced for permanent magnet synchronous machines (PMSMs). The control strategy consists of an adaptive speed controller that capitalizes on the machine's inverse model to achieve accurate tracking, two artificial neural networks (ANNs) for currents control, and an ANN-based observer for speed estimation to overcome the drawback associated with the use of mechanical sensors while the rotor position is obtained by the estimated rotor speed direct integration to reduce the effect of the system noise. A Lyapunov stability-based ANN learning technique is also proposed to insure the ANNs' convergence and stability. Unlike other sensorless control strategies, no a priori offline training, weights initialization, voltage transducer, or mechanical parameters knowledge is required. Results for different situations highlight the performance of the proposed controller in transient, steady-state, and standstill conditions.

Additional Metadata
Keywords Intelligent control, Neural networks, Sensorless control, Uncertain systems
Persistent URL dx.doi.org/10.1007/s00521-010-0412-6
Journal Neural Computing and Applications
Citation
Chaoui, H, & Sicard, P. (Pierre). (2011). Adaptive Lyapunov-based neural network sensorless control of permanent magnet synchronous machines. Neural Computing and Applications, 20(5), 717–727. doi:10.1007/s00521-010-0412-6