A method and system for predicting the remaining service life of an electric gate valve

Abstract

The invention relates to a method and a system for predicting the remaining service life of an electric gate valve. The method includes: establishing a particle filter state equation according to the typical fault and aging mechanism of the electric gate valve; obtaining the first degradation data of the electric gate valve at the current moment; The network corrects the first degradation data to obtain the corrected first degradation data; the trained neural network includes a convolution kernel and an LSTM network; according to the particle filter state equation and the corrected first degradation data The second degradation data at a moment; the second degradation data is the remaining service life of the electric gate valve. The above method and system of the present invention can predict the remaining service life of the electric gate valve, and improve the accuracy of the remaining service life prediction.

Description

technical field [0001] The invention relates to the technical field of electric gate valve maintenance prediction, in particular to a method and system for predicting the remaining service life of an electric gate valve. Background technique [0002] At present, corrective or preventive maintenance is generally adopted in China's nuclear power plants, which leads to the need to carry a large number of spare parts when nuclear power plants go to sea, which not only affects the layout space of other resources, but also has a huge annual maintenance volume. According to statistics, unnecessary or improper maintenance accounts for more than 1 / 3 of the total maintenance cost, wasting a lot of human and material resources. The American Electric Power Association statistics show that by implementing predictive maintenance in fields such as aerospace, operating costs can be reduced by more than 20%. Therefore, it is necessary to carry out health management technology research on th...

AI Technical Summary

Problems solved by technology

However, this method still has obvious shortcomings: first, for some complex equipment, it is difficult to understand the degradation mechanism, which limits the application of these methods; second, even if the physical model is established, some parameters in the model are not related to material properties Depends on the stress level and must still be determined by specific experiments or analyses.

Images