Event‐triggered model reference adaptive control system design for SISO plants using meta‐learning‐based physics‐informed neural networks without labeled data and transfer learning
- 28 January 2024
- journal article
- research article
- Published by Wiley in International Journal of Adaptive Control and Signal Processing
- Vol. 38 (4) , 1442-1456
Abstract
Summary: This paper examines the controllability of a novel Lyapunov‐based model reference adaptive control (MRAC) system designed with a meta‐learning‐based physics‐informed neural network (MLPINN) for linear and nonlinear single‐input and single‐output (SISO) plants without labeled data (MLPINN‐MRAC system). It is devised with the benefits of several techniques: the integration of the identification process in a training mode into an online control mode (straightforward design); no labeled data generation for online identification by a physics‐informed neural network; the prevention of degradation in tracking performance by meta‐learning, as the system triggers a meta‐learning process only when an error threshold detects the deterioration (high efficiency and the reduction of computation cost); quick adaptation to new inputs and an updated control input for each sub‐time span by transfer learning. It is worth noting that the frequency of the meta‐learning event detection significantly affects the step response stability of the nonlinear plant. To achieve a better quality of the stabilization, more frequent event detection is necessary for both beginning and end intervals in control. Sixteen triggering events are enough to shape the acceptable step response of the nonlinear plant, and 44 triggering events achieve the plant's desired step response with its minor modeling error. While, as for the linear plant, a single triggering event is sufficient to attain its tolerable step response and modeling error, implying that intensive event detection is not critical in the identification. It is obvious that the MLPINN‐MRAC system functions well and is more beneficial and efficient for the nonlinear plant.Keywords
Funding Information
- KMIT Ladkrabang (2566‐02‐01‐007)
This publication has 50 references indexed in Scilit:
- Identification of dynamic models in complex networks with prediction error methods—Basic methods for consistent module estimatesAutomatica, 2013
- Prediction error estimation methodsCircuits, Systems, and Signal Processing, 2002
- Neural network-based model reference adaptive control systemIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2000
- Multichannel blind identification: from subspace to maximum likelihood methodsProceedings of the IEEE, 1998
- Nonlinear adaptive control for flexible-link manipulatorsIEEE Transactions on Robotics and Automation, 1997
- Adaptive-critic-based neural networks for aircraft optimal controlJournal of Guidance, Control, and Dynamics, 1996
- Adaptive control of nonlinear systems via approximate linearizationIEEE Transactions on Automatic Control, 1996
- Laboratory implementation of a neural network trajectory controller for a DC motorIEEE Transactions on Energy Conversion, 1993
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Adaptive feedback linearization of non-linear systems with significant actuator dynamicsModeling, Identification and Control: A Norwegian Research Bulletin, 1990