Data-Driven Incipient Fault Prediction for Non-Stationary and Non-Linear Rotating Systems: Methodology, Model Construction and Application

Abstract

Many researches have been carried out on incipient fault prediction technology for key machine components (such as bearings) based on historical and real-time condition monitoring data. However, there is still lack of well-understood systematic methodologies for detecting incipient fault for rotating machines. Based on machine learning technology, this paper studies an incipient fault prediction model applying with wavelet packet decomposition and dynamic kernel principal component analysis (WPD-DKPCA) to meet the needs of engineering applications. The incipient fault prediction WPD-DKPCA model, which does not require knowledge on equipment structure and failure mechanisms, only requires normal state data of the machine, and incipient fault prediction can be achieved through self-learning. Run-to-failure experimental data and engineering case data have been used to verify the constructed model, and the verification results show that the constructed model can reliably and accurately detect an incipient bearing fault. Comparisons of fault prediction effects prove that using T2 statistic monitoring can detect upcoming faults of machines much earlier than Kurtosis and Root Mean Square (RMS).

Keywords

• Data-driven
• incipient fault prediction
• systematic methodology
• WPD-DKPCA model
• fault prediction effect