A neural network-based model predictive controller for displacement tracking of piezoelectric actuator with feedback delays

Abstract

Piezoelectric actuators are widely used in micro/nanoscale robotic manipulators. Due to its hysteresis and dynamic-related nonlinearity, accurate displacement tracking control of piezoelectric actuator is challenging. Besides, in some low-cost practical systems with low sampling rate, transmission delay causes mismatches between feedback and real displacement, further increasing the challenge in tracking control. In this article, a neural network-based model predictive controller (MPC) is proposed for precise tracking control of piezoelectric actuator’s displacement in situation where feedback is slow and delayed. The prediction model is based on a nonlinear-autoregressive-moving-average-with-exogenous-inputs framework, which outputs entire prediction horizon of future displacement in a single time, and is fulfilled by a multilayer feedforward neural network. An extended Kalman filter-based estimation for displacement is introduced to relieve the influence of feedback delays so as to improve dynamic performance of the controller. Another neural network is trained to provide initial values for MPC to reduce computation costs and improve performance in dynamic tracking. In a series of tracking experiments, the effectiveness of proposed controller is verified.

Ultraprecise Controller for Piezoelectric Actuators Based on Deep Learning and Model Predictive Control

“…In addition, the tracking performance of this control scheme is comparable to our approach in percentage but not in range. Actually, authors in [ 40 ] report a tracking error below 4nm for a displacement of 3 µm (tracking error of 0.13 %), whereas in our approach the tracking error is below 50 nm for a much longer displacement, 38 µm (tracking error of 0.13%).…”

“…Other articles such as [ 37 , 40 ] show a control scheme similar to the one presented in this work but with significant differences. Both papers model the hysteresis of the PEA using a neural network and then make the feedback control using a MPC scheme.…”

“…In fact, some research works show the strong dependency between the hystereis behavior of the PEAs against the input rate [ 39 ]. Moreover, the first two ways for modeling PEAs typically use complex structures, which require high computing costs, and require the incorporation of additional creep and dynamic models [ 40 ].The second class of hysteresis models, the so-called rate-dependent models, have been used to investigate this type of behavior. The output of these models depends on the frequency and amplitude of the input signal.…”

“…The authors of [ 40 ] made use of a neural network to model the hysteresis of the PEA. However, their approach employed a second neural network for implementing an ANN based feed forward control aimed at improving the performance of the MPC.…”

Aircraft Actuator Performance Analysis Based on Dynamic Neural Network

“…However, the vibration signal will be feeble at low speeds and may connect to other motor mechanical components. Te current signal has been added as another problem indicator together with the vibration signal to improve diagnostic accuracy [8]. To avoid high dimensionality, both the principle component analysis (PCA) and linear discriminant analysis (LDA) were used [7].…”