AUT Journal of Modeling and Simulation

AUT Journal of Modeling and Simulation

Complete Automated Structure Discovery and Parameter Estimation for Piecewise Affine Models with Guaranteed Convergence

Document Type : Research Article

Authors
Mohammad Lotfi 1
Mohammad Bagher Menhaj 1
Mehdi Karrari 1
Mohammad Haeri 2
1 Department of Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
2 Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran.
10.22060/miscj.2026.25021.5447
Abstract
This paper presents a novel, fully automated framework for the complete structure discovery and parameter estimation of Piecewise Affine (PWA) models. To the best of our knowledge, this is the first approach that simultaneously determines the number of submodels, their orders, parameter vectors, and polyhedral partitions from data, without any prior structural knowledge or the need for tuning parameters. The methodology integrates three key innovations: (1) Automated submodel order selection via Orthogonal Least Squares with an Error-to-Signal Ratio test; (2) A clustering-based algorithm for determining the number of submodels and generating a robust initial labeled dataset; and (3) An iterative algorithm that integrates a novel self-labeling support vector machine (SL-SVM) for estimating polyhedral partitions with a recursive least squares (RLS) scheme for refining submodel parameters, both with guaranteed convergence. Theoretical analysis demonstrates both computational efficiency and convergence properties, with the SL-SVM algorithm significantly reducing complexity compared to standard SVM. Extensive simulations validate the framework's performance across multiple benchmark systems, achieving Best Fit Rates exceeding 98% in scenarios of complete structural uncertainty. The approach consistently outperforms existing methods in accuracy while maintaining computational efficiency. Furthermore, we demonstrate the method's applicability to nonlinear system identification through PWARX approximation, showcasing its versatility for practical engineering applications. The proposed framework represents a significant advancement in automated system identification, providing a comprehensive solution for black-box modeling of hybrid and nonlinear systems.
Keywords
Piecewise Affine Models
Structure Discovery
Parameter Estimation
Hyperspherical Partitioning
Self-Labeling SVM
Convergence Analysis
Subjects
[1] Y. Huo, Z. Chen, Q. Li, Q. Li, and M. Yin, "Machine Learning Based Model Predictive Control with Piecewise-Affine Approximation Structure for Maximizing Wind Energy Capture," Journal of Modern Power Systems and Clean Energy, 2025.
[2] J. Tian, S. Wang, X. Zhao, Y. Li, Z. Zheng, and H. Zhang, "Integrated Control Strategy of Active Front-Wheel Steering and Active Suspension Based on 3D Piecewise Affine Tire Model," IEEE Transactions on Transportation Electrification, 2025.
[3] J. Guo and Z. Ren, "On Prediction of Air Pollution Using Piecewise Affine Models," Polish Journal of Environmental Studies, vol. 34, no. 1, 2025.
[4] Z. Ren, J. Zhang, Y. Zhou, and X. Ji, "Prediction of PM2. 5 with a piecewise affine model considering spatial-temporal correlation," Journal of Intelligent & Fuzzy Systems, vol. 46, no. 4, pp. 9525–9542, 2024.
[5] L. Zeineb and A. Kamel, "Extension of a clustering identification approach to multivariable piecewise affine systems: Application to an industrial dryer," Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 238, no. 6, pp. 1037–1049, 2024.
[6] X. Li, T. Zhao, and Y. Weng, "Research of PWA Modeling and Predictive Control for the MCR-BWPT Systems," IEEE Transactions on Transportation Electrification, 2025.
[7] M. Lotfi, M. B. Menhaj, S. A. Hosseini, and A. S. Shirani, "A design of switching supervisory control based on fuzzy-PID controllers for VVER-1000 pressurizer system with RELAP5 and MATLAB coupling," Annals of Nuclear Energy, vol. 147, p. 107625, 2020.
[8] S. A. Hosseini, A. S. Shirani, M. Lotfi, and M. B. Menhaj, "Design and application of supervisory control based on neural network PID controllers for pressurizer system," Progress in Nuclear Energy, vol. 130, p. 103570, 2020.
[9] N. Moustakis, B. Zhou, T. Le Quang, and S. Baldi, "Fault detection and identification for a class of continuous piecewise affine systems with unknown subsystems and partitions," International Journal of Adaptive Control and Signal Processing, vol. 32, no. 7, pp. 980–993, 2018.
[10]         X. Sun, P. Wu, Y. Cai, S. Wang, and L. Chen, "Piecewise affine modeling and hybrid optimal control of intelligent vehicle longitudinal dynamics for velocity regulation," Mechanical Systems and Signal Processing, vol. 162, p. 108089, 2022.
[11]         P. Bacher and H. Madsen, "Identifying suitable models for the heat dynamics of buildings," Energy and buildings, vol. 43, no. 7, pp. 1511–1522, 2011.
[12]         M. Mejari, V. V. Naik, D. Piga, and A. Bemporad, "Identification of hybrid and linear parameter‐varying models via piecewise affine regression using mixed integer programming," International Journal of Robust and Nonlinear Control, vol. 30, no. 15, pp. 5802–5819, 2020.
[13]         X. Wang, G. Chen, Z. Wang, and J. Xia, "Stability Analysis of Piecewise Affine Networked Control Systems under Aperiodic Sampling," IEEE Control Systems Letters, 2025.
[14]         A. Ma, D. Li, and Y. Xi, "Event‐triggered distributed model predictive control for PWA systems," International Journal of Robust and Nonlinear Control, vol. 35, no. 2, pp. 435–451, 2025.
[15]         C. Zhang, Q. Gao, Y. Deng, and J. Qiu, "An integral sliding‐mode parallel control approach for general nonlinear systems via piecewise affine linear models," International Journal of Robust and Nonlinear Control, vol. 33, no. 8, pp. 4438–4458, 2023.
[16]         S. Xiao, G. Yan, X. Huang, and R. Li, "Adaptive Fault‐Tolerant Tracking Control of Piecewise Affine Systems With Performance Constraint," International Journal of Robust and Nonlinear Control, 2025.
[17]         A. Bemporad, A. Garulli, S. Paoletti, and A. Vicino, "A bounded-error approach to piecewise affine system identification," IEEE Transactions on Automatic Control, vol. 50, no. 10, pp. 1567–1580, 2005.
[18]         W. Bai, F. Guo, L. Chen, K. Hao, and B. Huang, "Variational Bayesian inference for robust identification of PWARX systems with time-varying time-delays," IEEE Transactions on Cybernetics, vol. 53, no. 6, pp. 3613–3623, 2021.
[19]         R. Vidal, S. Soatto, Y. Ma, and S. Sastry, "An algebraic geometric approach to the identification of a class of linear hybrid systems," in 42nd IEEE International Conference on Decision and Control (IEEE Cat. No. 03CH37475), 2003, vol. 1: IEEE, pp. 167–172.
[20]         Y. Du, F. Liu, J. Qiu, and M. Buss, "A semi-supervised learning approach for identification of piecewise affine systems," IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 67, no. 10, pp. 3521–3532, 2020.
[21]         M. Lotfi and M. B. Menhaj, "An overview of intelligent systems (neural networks) from the perspective of classical theory and their application in modeling and control of complex systems," Journal of Control, vol. 17, no. 2, pp. 47–79, 2023.
[22]         G. Ferrari-Trecate, M. Muselli, D. Liberati, and M. Morari, "A clustering technique for the identification of piecewise affine systems," Automatica, vol. 39, no. 2, pp. 205–217, 2003.
[23]         H. Nakada, K. Takaba, and T. Katayama, "Identification of piecewise affine systems based on statistical clustering technique," Automatica, vol. 41, no. 5, pp. 905–913, 2005.
[24]         M. Lotfi, M. Habibi, B. Vahidi, S. H. Hosseinian, and M. B. Menhaj, "Physics-aware neural networks for integrated energy systems management," in Physics-Aware Machine Learning for Integrated Energy Systems Management: Elsevier, 2025, pp. 381–420.
[25]         L. Zeineb and A. Kamel, "A Modified DBSCAN clustering algorithm for the identification of PWA systems," in 2023 20th International Multi-Conference on Systems, Signals & Devices (SSD), 2023: IEEE, pp. 306–311.
[26]         V. Breschi and M. Mejari, "Shrinkage strategies for structure selection and identification of piecewise affine models," in 2020 59th IEEE Conference on Decision and Control (CDC), 2020: IEEE, pp. 1626–1631.
[27]         S. Billings, S. Chen, and M. Korenberg, "Identification of MIMO non-linear systems using a forward-regression orthogonal estimator," International journal of control, vol. 49, no. 6, pp. 2157–2189, 1989.
[28]         L. Bottou and C.-J. Lin, "Support vector machine solvers," 2007.
[29]         L. Wang and H. Garnier, System identification, environmental modelling, and control system design. Springer, 2011.
[30]         A. Bemporad, A. Garulli, S. Paoletti, and A. Vicino, "A greedy approach to identification of piecewise affine models," in Hybrid Systems: Computation and Control: 6th International Workshop, HSCC 2003 Prague, Czech Republic, April 3–5, 2003 Proceedings 6, 2003: Springer, pp. 97–112.
[31]         A. K. Shah and D. M. Adhyaru, "Parameter identification of PWARX models using fuzzy distance weighted least squares method," Applied Soft Computing, vol. 25, pp. 174–183, 2014.
[32]         L. C. YIN, "Identification and control of nonlinear systems using multiple models," 2011.
[33]         F.-C. Chen and H. K. Khalil, "Adaptive control of a class of nonlinear discrete-time systems using neural networks," IEEE Transactions on Automatic Control, vol. 40, no. 5, pp. 791–801, 1995.
[34]         K. S. Narendra and J. Balakrishnan, "Adaptive control using multiple models," IEEE transactions on automatic control, vol. 42, no. 2, pp. 171–187, 1997.
[35]         H. Ahmadian, M. Lotfi, M. B. Menhaj, H. A. Talebi, and I. Sharifi, "A novel L1 adaptive-hybrid control with guaranteed stability for a class of uncertain nonlinear systems: A case study on SA330 Puma," Journal of the Franklin Institute, vol. 359, no. 17, pp. 9860–9885, 2022.
AUT Journal of Modeling and Simulation
Volume 57, Issue 2
December 2025
Pages 191-214