A Machine Learning-Based Reference Governor for Nonlinear Systems With Application to Automotive Fuel Cells
- 24 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 33 (6) , 2271-2287
Abstract
The prediction-based nonlinear reference governor (PRG) is an add-on algorithm to enforce constraints on prestabilized nonlinear systems by modifying, whenever necessary, the reference signal. The implementation of PRG carries a heavy computational burden, as it may require multiple numerical simulations of the plant model at each sample time. To this end, this article proposes an alternative approach based on machine learning, where we first use a regression neural network (NN) to approximate the input-output map of the PRG from a set of training data. During the real-time operation, at each sample time, we use the trained NN to compute a nominal reference command, which may not be constraint admissible due to training errors and limited data. We adopt a novel sensitivity-based approach to minimally adjust the nominal reference while ensuring constraint enforcement. We thus refer to the resulting control strategy as the modified NN reference governor (MNN-RG), which is computationally more efficient than the PRG. The computational and theoretical properties of the MNN-RG are presented. Finally, the effectiveness and limitations of the proposed method are studied by applying it as a load governor for constraint management in automotive fuel cell (FC) systems through simulation-based case studies.Keywords
All Related Versions
Funding Information
- Ford Motor Company through URP (002092-URP)
This publication has 30 references indexed in Scilit:
- Simultaneous constraint management of hydration and oxygen excess ratio for PEM fuel cells: A parallel cascaded reference governor approachEnergy Conversion and Management, 2023
- A novel Reference Governor approach for constraint management of nonlinear systemsAutomatica, 2022
- Safe Learning for Control using Control Lyapunov Functions and Control Barrier Functions: A ReviewProcedia Computer Science, 2021
- Degradation-conscious control for enhanced lifetime of automotive polymer electrolyte membrane fuel cellsJournal of Power Sources, 2020
- Robust MPC for tracking constrained unicycle robots with additive disturbancesAutomatica, 2018
- Reference and command governors for systems with constraints: A survey on theory and applicationsAutomatica, 2017
- Stability regions for constrained nonlinear systems and their functional characterization via support-vector-machine learningAutomatica, 2004
- Control of Fuel Cell Power Systems2004
- Fuel Cell Systems Explained2003
- Discrete‐time reference governors and the nonlinear control of systems with state and control constraintsInternational Journal of Robust and Nonlinear Control, 1995