Neural Network-Based Identification of State-Space Switching Nonlinear Systems

• 成果类型: Article
• 署名作者: Zhang, Yanxin; Yu, Chengpu; Ferrer, Gonzalo; Fabiani, Filippo
• 署名单位: Beijing Institute of Technology; IMT School for Advanced Studies Lucca
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2026.3669446
• 发表日期: 2026
• 关键词: piecewise; models

摘要

We design specific neural networks (NNs) for the identification of switching nonlinear systems in the state-space form, which explicitly model the switching behavior and address the inherent coupling between system parameters and switching modes. Such coupling is specifically addressed by leveraging the expectation-maximization framework. In particular, our technique will combine a moving window approach in the expectation-step to efficiently estimate the switching sequence, together with an extended Kalman filter in the maximization-step to train the NNs with a local quadratic convergence rate. Extensive numerical simulations, involving both academic examples and a battery charge management system case study, illustrate that our technique outperforms available ones in terms of parameter estimation accuracy, model fitting, and switching sequence identification.