Health Indicators for Monitoring, Diagnostics and Prognostics: Methods, Evaluation and Applications
Year: 2026
Type: article
Abstract: Health indicators (HIs) provide compact representations of machinery degradation and are central to condition monitoring, fault diagnosis, and remaining useful life (RUL) prediction. However, the rapidly expanding literature spans mechanism-based signal features, data-driven representation learning, and approaches that integrate data with explicit state, probabilistic, or physical models, making method selection and fair comparison increasingly difficult. This review develops a construction-evaluation-application framework for HIs in rotating machinery. A structured narrative search of the Web of Science Core Collection covering January 2010 to August 2026, supplemented by backward and forward citation tracking, is used to identify and classify representative studies. HI construction methods are organized into mechanism-modeling, data-driven, and data-model-integration paradigms and compared in terms of assumptions, applicable conditions, limitations, robustness, interpretability, data requirements, computational cost, and industrial deployability. The review then relates tendency, monotonicity, robustness, and scale similarity to downstream task requirements and discusses the trade-offs that prevent a single indicator from being universally optimal. Applications in condition monitoring, fault diagnosis, RUL prediction, and comprehensive health assessment are synthesized, including a public-dataset comparison of representative RUL results. Finally, the review identifies research priorities in physically interpretable HIs, adaptive and transferable construction, open benchmarks, multisource fusion, and digital-twin-enabled prognostics. The resulting framework supports method selection by linking construction principles to evaluation evidence, failure modes, and deployment constraints.
Institution: Southwest Jiaotong University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid:
Awards: G110512609, G9001368503
OpenAlex ID: W7226013741
