Wind turbine fault diagnosis based on a mivar expert system

This research proposes a rule-driven expert system based on the mivar architecture for intelligent fault diagnosis and maintenance decision-making of wind turbines. Targeting high-risk components, the system constructs a three-layer structured rule base with 20 interpretable IF-THEN-ELSE rules. By integrating real-time SCADA/CMS data and domain expertise, it enables rapid reasoning of critical faults and generates priority-driven maintenance actions. Implemented under the mivar framework, the system decouples knowledge representation from reasoning logic, supporting dynamic rule expansion and uncertainty handling. The study demonstrates that this method provides an explainable, low-data-dependent decision support framework for intelligent wind turbine operation and maintenance, significantly reducing manual diagnosis costs and offering a paradigm for industrial expert system deployment.