Thanh bên bài viết

Số xuất bản: Số 87 (2026): Số 87 (07/2026)
Chuyên mục: KỸ THUẬT VÀ CÔNG NGHỆ HÀNG HẢI
DOI: 10.65154/jmst.1133
Lượt xem 9
Trích dẫn bài báo
Nguyen, T. A., Tran, T. T. H., Nguyen, T. T., Nguyen, M. L., & Tran, Q. V. (2026). ADAPTIVE NEURAL NETWORK-ASSISTED LINEAR QUADRATIC REGULATOR CONTROL WITH FULL-ORDER EXTENDED STATE OBSERVER FOR ACTIVE SUSPENSION SYSTEMS. Tạp chí Khoa học Công nghệ Hàng hải, 87. https://doi.org/10.65154/jmst.1133
Crossref
Scopus
Google Scholar
Europe PMC

ADAPTIVE NEURAL NETWORK-ASSISTED LINEAR QUADRATIC REGULATOR CONTROL WITH FULL-ORDER EXTENDED STATE OBSERVER FOR ACTIVE SUSPENSION SYSTEMS

Nguyen Tuan Anh1, , Tran Thi Thu Huong2, Nguyen The Truc2, Nguyen Manh Long3, Tran Quang Vinh3
1 Faculty of Mechanical Engineering, Thuyloi University; School of Mechanical Engineering, Hanoi University of Science and Technology
2 School of Mechanical Engineering, Hanoi University of Science and Technology
3 Phenikaa school of Engineering, Phenikaa University

Nội dung chính của bài viết

Tóm tắt

This paper proposes integrating a Linear Quadratic Regulator (LQR) control scheme with an adaptive Neural Network (NN) updating law to improve ride comfort performance. The dynamic states of the suspension system are effectively estimated using a Full-Order Extended State Observer (FOESO) rather than through direct sensor measurements, thereby reducing implementation costs and minimizing the influence of sensor noise. Numerical simulations are conducted under two different road profile scenarios based on ISO standards, while accounting for lumped uncertainties in the system dynamic modeling. The results show that the Root Mean Square (RMS) body displacement is reduced to 4.854 mm in the first case with ISO C-class road disturbance, and the RMS body acceleration decreases to 0.220 m/s² in the second case with ISO D-class road disturbance; both are significantly lower than those achieved by conventional controllers. Furthermore, the dynamic states are estimated with high accuracy, confirming the effectiveness of the proposed control strategy in suspension system regulation.

Từ khóa

Active suspension, Linear quadratic regulator, Neural network, Extended state observer

Chi tiết bài viết

Tài liệu tham khảo

[1] M. H. A. Talib, et al. (2023), Experimental evaluation of ride comfort performance for suspension system using PID and fuzzy logic controllers by advanced firefly algorithm, Journal of the Brazilian Society of Mechanical Sciences and Engineering, vol. 45.
[2] Le Van Duong, et al. (2023), Comparison of controllers for nonlinear active suspension system, Journal of Science and Technology – Hanoi University of Industry, vol. 59, no. 2A, pp. 131–136.
[3] Tran Thi Thu Huong, Nguyen Tuan Anh, and Nguyen Manh Long (2022), Simulation oscillation of active suspension system considering the effect of the hydraulic actuator, Journal of Science and Technology – Danang University, vol. 20, no. 5, pp. 23–26.
[4] Hoang Thang Binh, et al. (2024), Research a hybrid PID controller for an active suspension system, Journal of Science and Technology – Hanoi University of Industry, vol. 60, no. 6, pp. 112–118.
[5] Vu Hai Quan and Le Huu Chuc (2020), Simulation and control of active suspension for a full car model, Journal of Science and Technology – Hanoi University of Industry, vol. 56, no. 2, pp. 84–89.
[6] Nguyen Trong Duc, et al. (2021), Modeling and analysis of active supply system for models vehicles using some different control methods, Journal of Science and Technology – Hanoi University of Industry, Special Issue, vol. 11, 2021.
[7] Tran Van Da and Bui Duc Tien (2021), Controlling an active suspension system for four wheels car by combining LQR method and particle swarm optimization, Journal of Science and Technology – Hanoi University of Industry, vol. 57, no. 4, pp. 85–88.
[8] Vu Hai Quan, Nguyen Anh Ngoc, and Nguyen Huy Truong (2021), Dynamic analysis of active suspension system for1/4 model vehicle using PID and LQR controller, Journal of Marine Science and Technology, Special Issue, pp. 229–233.