The safe and stable supply of electricity and energy is a prerequisite for ensuring the construction of a new type of power system, addressing the issues of poor detection accuracy and low efficiency in existing insulation state detection methods for power capacitors, based on the analysis of the online monitoring system for power capacitors, propose an improved adaptive neural fuzzy inference system for detecting the insulation status of power capacitors, by optimizing the parameters of the adaptive network-based fuzzy inference system through improved particle swarm optimization algorithm, improved model detection accuracy and reduced model training time. Analyze the performance of the proposed method through numerical examples, verify its effectiveness and superiority. The results indicate that, compared with conventional detection methods, the detection results of the proposed detection method are basically the same as the actual insulation state level, and can accurately detect the insulation state, the detection speed can meet the needs of real-time detection, higher detection accuracy. It can provide support for the construction of new power systems.