Health Indicators for Monitoring, Diagnostics and Prognostics: Methods, Evaluation and Applications

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.

Authors

Institutions

Publication Details

Journal
Journal of Reliability Science and Engineering
Published
2026-11-13
DOI
https://doi.org/10.1088/3050-2454/aec1e6
Primary Topic
Machine Fault Diagnosis Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Health Indicators for Monitoring, Diagnostics and Prognostics: Methods, Evaluation and Applications

Wenchang Song, Yifan Xu, Liang Guo, Yuan Xiao et al.
1 links
Journal of Reliability Science and Engineering
Machine Fault Diagnosis Techniques
article

Health Indicators for Monitoring, Diagnostics and Prognostics: Methods, Evaluation and Applications

Wenchang Song, Yifan Xu, Liang Guo, Yuan Xiao, Hongli Gao
article en

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.

Journal of Reliability Science and Engineering
Southwest Jiaotong University (CN)
National Natural Science Foundation of China, Key Programme
Good health and well-being
Machine Fault Diagnosis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon