.png){kind=icon}
.png){kind=icon}
Return
A Performance-Controllable Neural Network-Guided Backstepping Predictive Control for Interconnected Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TASE.2025.3645774.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the inherent structural complexity, dynamic behavior, and strong nonlinearities of interconnected systems, conventional control and existing data-driven methods such as T–S fuzzy models and SINDy often struggle to simultaneously ensure modeling accuracy, structural interpretability, and real-time adaptability under dynamic operation modes. To address these limitations, this paper proposes an affine-structured performance-controllable neural network guided backstepping predictive control framework. Unlike conventional black-box data-driven models, the proposed approach embeds the affine nonlinear system structure into the neural network and adopts a Lyapunov-based training strategy, enabling both accurate dynamic approximation and explicit control law design. Meanwhile, a backstepping predictive control scheme is developed to effectively handle interconnection-induced coupling and multivariable constraints with reduced computational burden. Furthermore, a performance-controllable integrated neural network adaptive update method is introduced by reformulating model adaptation as a control problem, allowing near-real-time model updating using only finite data and guaranteeing stable and rapid convergence of prediction errors. Rigorous theoretical analysis and extensive experimental results demonstrate that the proposed method achieves superior control performance under dynamic operation modes. Note to Practitioners—This paper addresses high-performance control of interconnected industrial systems with complex nonlinearities and dynamic operation modes. The proposed method integrates neural networks with backstepping predictive control, enabling near-real-time adaptation to system variations. Practitioners can implement the affine-structured neural networks to accurately model subsystem dynamics, while the backstepping framework ensures stability despite complex interconnections. The performance-controllable adaptive mechanism allows the prediction model to rapidly adjust to mode changes using minimal data. Experimental results demonstrate effective control under both known and drifted operation modes, making this approach suitable for process industries, aerospace, and power systems.
Keywords:
Neural network
backstepping predictive control
interconnected systems
dynamic mode control
Journal
IF:
6.4
Papers:
4.9K
Citations:
1.6W