Study on the Condition Monitoring Technology of Electric Valve Based on Principal Component Analysis

Valves are the most diverse and widely used general purpose mechanical equipment in nuclear power plants. During its use, due to the prolonged exposure to vapors, oils and radioactive liquids, the valve inevitably ages and fails. Furthermore, the safety and reliable operation of nuclear power plants are adversely affected. Therefore, it is of great significance to monitor the running state of valves in real time and find the hidden danger in time to ensure the safe operation of nuclear power plants. Based on this, this study built an experimental bench that can simulate the valve leakage fault, and used acoustic emission sensor to measure the operation data of the valve under normal and leakage conditions. And the intelligent condition monitoring technology of the valve is preliminarily discussed with artificial intelligence algorithm PCA as the monitoring means. So as to provide the technical basis for the follow-up valve maintenance and fault diagnosis. It is found that the PCA algorithm can be used to monitor the running state of the valve, and the leakage state of the valve can be found in time. Therefore, it has certain reference significance for the follow-up maintenance treatment.