For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
In comparison to classical control approaches in the domain of electrical drives like the field-oriented control (FOC), model predictive control (MPC) approaches are able to provide a higher control performance. This refers to shorter settling times, lower overshoots, and a better decoupling of control variables in case of multi-variable controls. However, this can only be achieved if the used prediction model covers the actual behaviour of the plant sufficiently well. In case of model deviations, the performance utilising MPC remains below its potential. Among other effects, this results in increased current ripple or steady state setpoint deviations. In particular, the strong (cross-)saturation or temperature dependencies of permanent magnet synchronous motors (PMSM) lead to considerable deviations between model and motor. To address this important issue, measurement data can be used to obtain accurate models in the entire operation range. Against this background, three data-driven modelling approaches are compared: an online capable least squares system identification, an offline created least squares model and an offline trained artificial neural network (ANN). An experimental evaluation verifies the high prediction accuracy of all considered data-driven modelling techniques. While all approaches deliver bias-free prediction, a trade off problem between computational complexity and the variance of the residuals is revealed.
Inspec keywords: multivariable control systems; predictive control; machine vector control; neurocontrollers; synchronous motor drives; least squares approximations; permanent magnet motors; computational complexity
Subjects: Other topics in statistics; Neural nets; Synchronous machines; Optimal control; Drives; Multivariable control systems; Control of electric power systems; Other topics in statistics; Neurocontrol