A novel HI construction method based on healthy-state data training for rotating machinery components

In predictive maintenance for rotating machinery components, constructing health indicators is crucial for improving operational efficiency and extending the equipment lifespan. However, traditional processes of building health indicators face two significant challenges: the high cost of collecting full lifecycle data and the requirement for the operating conditions of the equipment to remain consistent with those under which the indicators were developed. These limitations make health indicators expensive and time-consuming to construct and use. This article proposed a health indicator developed based on the Joint Principal Component Cumulative Empirical Distribution Model (JPCCED-HI) to overcome these challenges. This innovative method utilizes only healthy state data, combining principal component analysis with the empirical cumulative distribution function to construct a health indicator that ranges from 0 to 1, thereby eliminating the reliance on complete lifecycle data and relaxing the requirements for specific operating conditions. The effectiveness and practical benefits of JPCCED-HI are illustrated through two detailed case studies. In the first case study, we explore the impact of different parameter settings on model performance and evaluate its anti-interference capabilities in high-noise environments based on a gearbox dataset. This study demonstrates the model’s robustness in maintaining accurate health assessments despite external noise. The second case study employs a publicly available bearing dataset to compare the JPCCED-HI method against other models trained on health-stage data. This analysis reveals the superior performance of JPCCED-HI in trendability and scale similarity, affirming its effectiveness in various operational conditions. These case studies not only prove the adaptability and robustness of JPCCED-HI but also highlight its potential as a scalable solution for real-time health monitoring and predictive maintenance in industrial applications.