Performance-Enhanced Intelligent Fault-Tolerant Control for Unknown Nonlinear Systems With Multiple Faults

This article investigates the practical problem of the fault-tolerant tracking control for nonlinear systems subjected to dynamic uncertainties, unknown disturbances, and simultaneous actuator and sensor faults. A novel performance-enhanced intelligent fault-tolerant control (IFTC) framework is developed by integrating the predefined-time stability theory with the optimal control principle. A 1-dimensional convolutional neural network is proposed as a restorer to efficiently detect and isolate sensor faults, upon whose outputs a single radial basis function neural network is constructed to approximate two distinct components of the unknown system dynamics in real time. The proposed fault-tolerant controller ensures the boundedness of all signals within the closed-loop system and guarantees that the tracking errors converge within a user-specified time. Moreover, by incorporating a cost function related to the control effort, the developed controller avoids the excessive control input, achieving an enhanced control performance alongside the predefined-time convergence. Comprehensive simulation results validate the effectiveness and practicality of the proposed performance-enhanced IFTC scheme, highlighting its potential for real-world applications. Note to Practitioners—General input-affine nonlinear systems are capable of modeling a wide range of physical systems, such as motors, robotic arms, and aircraft. Due to the inherent complexity of these systems, which involve numerous parameters and are often subject to harsh operating conditions, multiple uncertainties like faults and disturbances frequently arise and may coexist. To address these challenges, this paper develops a performance-enhanced intelligent fault-tolerant controller for unknown input-affine nonlinear systems. The proposed IFTC framework utilizes offline system data, collected under both normal and faulty conditions, to detect and isolate sensor faults. Additionally, online adaptive control laws are designed to compensate for dynamic uncertainties, actuator faults, and disturbances, ensuring the system convergence within a user-specified time with reduced control effort. These improvements in the control performance have significant practical implications, demonstrating substantial potential for real-world engineering applications.