Data-Driven Human-in-the-Loop Iterative Learning Fault Estimation Method

Abstract

For control systems with unknown model parameters, this paper proposes a data-driven iterative learning method for fault estimation. First, input and output data from the system under fault-free conditions are collected. By applying orthogonal triangular decomposition and singular value decomposition, a data-driven realization of the system's kernel representation is derived, based on this representation, a residual generator is constructed. Then, the actuator fault signal is estimated online by analyzing the system's dynamic residual, and an iterative learning algorithm is introduced to continuously optimize the residual-based performance function, thereby enhancing estimation accuracy. The proposed method achieves actuator fault estimation without requiring knowledge of model parameters, eliminating the time-consuming system modeling process, and allowing operators to focus on system optimization and decision-making. Compared with existing fault estimation methods, the proposed method demonstrates superior transient performance, steady-state performance, and real-time capability, reduces the need for manual intervention and lowers operational complexity. Finally, experimental results on a mobile robot verify the effectiveness and advantages of the method.