To address the difficulty of conventional tuning methods in adapting to time-varying degradation and the limited capability of existing degradation detection approaches to directly support control compensation, this paper proposes a data-driven degradation-aware parameter self-tuning method for industrial robot joint servo systems. First, a set of degradation-sensitive features is constructed from closed-loop operational data by incorporating error-related, response-related, and control-related characteristics, and a health indicator is further established to describe the evolution of the performance state of the joint servo system. Second, a tuning trigger mechanism is designed according to the state stratification and variation trend of the health indicator, and the key parameters in the position and speed loops are updated in a data-driven manner using a composite control performance index, so as to achieve performance recovery under degraded conditions. Finally, comparative experiments under multiple operating conditions are carried out on an industrial robot joint servo platform to validate the effectiveness of the proposed method in degradation detection, self-tuning control, and overall performance improvement. The results show that the proposed method can effectively identify servo performance degradation and adaptively adjust controller parameters under different degradation levels, thereby improving trajectory tracking capability, dynamic behavior, and operational adaptability. This study provides a useful reference for intelligent monitoring and adaptive optimal control of industrial robot joint servo systems.

industrial robot, joint servo system, performance degradation detection, parameter self-tuning, data-driven