Abstract
In order to ensure safe operation, the risks associated with Nuclear Power Plants (NPP) needs to be precisely assessed. For that very reason, Prognostics and Health Management (PHM) is so crucial as it determines the best time for each equipment maintenance. At present, the bottleneck of predictive maintenance is the prediction of equipment’s remaining useful life (RUL). With the development of artificial intelligent techniques, deep learning algorithms are becoming more and more popular for RUL prediction. Upon this, this paper studied RUL prediction techniques for nuclear electric gate valves with temporal convolutional network (TCN). The main advantage of using TCN is its ability to avoid loss of information due short-term changes. More importantly, we enhanced the effectiveness of traditional TCN by incorporating an additional auto-encoder in its structure along with improving its residual convolution mode. The technique was successfully applied and then verified on simulated crack data obtained from electric gate valve platform (estabilshed by authors). Comparison of results with typical methods shows that the proposed method can predict electric valves’ RUL with higher accuracy. Furthermore, this paper tested the generalization ability and universality of the proposed method through aero-engine standard datasets. Aforesaid in view, it is envisaged that PHM systems for NPPs can be further developed through application of proposed methodology.
Highlights
Concerns over energy security and global warming have risen during the past decade and those concerns have increased the NPPs share in the global energy mix due to its zero-carbon and sulfur compound emission
We propose an improved Temporal Convolution Network (TCN) for remaining useful life prediction (RUL) prediction
(3) recurrent neural network (RNN) retain the information at each step, which will occupy a large amount of computer memory
Summary
Concerns over energy security and global warming have risen during the past decade and those concerns have increased the NPPs share in the global energy mix due to its zero-carbon and sulfur compound emission. It is difficult to directly obtain operating data for various working conditions, different failure modes, aging and degradation modes Without such historical data, it is difficult to develop deep learning models and accurately estimate the RUL of components. The need to make plant data available for researchers and to optimize sensor layout can be significantly justified by demonstrating the benefits of effective RUL prediction This manuscript focuses on the development of an enhanced, accurate, and generalized RUL predictive model. Compared with RNN and other networks, a convolution neural network (CNN) has a natural advantage in large-scale parallel processing of data, especially in dealing with time series problems On this basis, we propose an improved Temporal Convolution Network (TCN) for RUL prediction.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
