Learning-based model predictive current control for synchronous machines: An LSTM approach

In this work, a data-driven model predictive control (MPC) approach for the current control of syn-chronous machines is presented. The model of the motor is represented via a long-short term mem-ory (LSTM) neural network (NN). The model is obtained purely from collected data and doesn't include any physical knowledge. As an online optimization using the obtained data-driven model is not easily implementable in the available sampling time, the neural model is used to solve an MPC problem of-fline. Finally, the control policy is learned via another computationally implementable NN that runs in real-time as a current controller. The proposed data-driven MPC controller is tested experimentally, and is bench-marked against MPC schemes that incorporate the well-known physically-based first-principles linear and nonlinear model1 of the machine.(c) 2022 European Control Association. Published by Elsevier Ltd. All rights reserved.

Automated summary

This paper presents a data-driven model predictive control (MPC) approach for the current control of synchronous machines. The motor model is represented using a long-short term memory (LSTM) neural network (NN), which is obtained purely from collected data without any physical knowledge. As online optimization using the obtained data-driven model is not easily implementable in the available sampling time, the neural model is used to solve an MPC problem offline. Finally, the control policy is learned through another computationally implementable neural network that runs in real-time as a current controller. The proposed data-driven MPC controller is experimentally tested and benchmarked against MPC schemes incorporating physically-based models.