Aiming at the problems of complex fault propagation paths, insufficient diagnostic robustness and low accuracy of fault-tolerant control in electromechanical systems, this paper proposes a fault detection and compensatory control method integrating ISM model and adaptive filtering algorithm. Based on the ISM, we analyze the fault hierarchy and identify the key propagation paths, and propose the DDAF-FD algorithm to realize the online identification of faults. The state feedback fault-tolerant controller is designed to utilize the real-time diagnosis results to dynamically compensate the performance degradation caused by faults. Experiments show that DDAF-FD achieves optimal results in the diagnosis of four different migration tasks with an average accuracy as high as 98.98% compared with six comparison algorithms. The average control accuracy of the fault-tolerant control system based on fault compensation reaches 95.2%, and the research results verify the effectiveness of the method in fault diagnosis and fault-tolerant control of complex electromechanical systems.
