Development of a Plug-and-Play Anti-Noise Module for Fault Diagnosis of Rotating Machines in Nuclear Power Plants

The health of rotating machines is critical to the stable operation and safety of nuclear power plants. However, research on machine learning-based rotating machine fault diagnosis is still in its infancy in the nuclear industry. The signal noise generated in the plant may negatively affect the effectiveness of the analysis. We propose a plug-and-play anti-noise machine learning module to fill the knowledge and capability gap. The modules are loaded into a convolutional neural network called deep residual network (ResNet) to obtain a new model with noise reduction ability. The basic idea is that the module is able to identify noise features and include them in subsequent analyses, effectively filtering noise at the feature level of the network. Nine variants of the new model are compared with the original ResNet and four classical machine learning models to test the effectiveness of the module and to check the impact of the loading pattern of the module on the performance of the new model. The study helps facilitate the application of machine learning in the noise environment of nuclear power plants