Contents lists available at ScienceDirect
Journal of Manufacturing Systems
journal homepage: www.elsevier.com/locate/jmansys
Review
Comprehensive evaluations of condition monitoring-based technologies in
industrial maintenance: A systematic review
Mehdi Dadfarnia
a,b ,
∗
, Michael E. Sharp
a
, Jeffrey W. Herrmann
c
a
National Institute of Standards and Technology, Communications Technology Laboratory, 100 Bureau Dr, Gaithersburg, MD 20899, USA
b
University of Maryland, College Park, Department of Mechanical Engineering, 4298 Campus Dr, College Park, MD 20742, USA
c
Catholic University of America, Department of Mechanical Engineering, 620 Michigan Ave NE, Washington DC 20064, USA
A R T I C L E I N F O
Keywords:
Condition monitoring
Condition-based maintenance
Evaluation methods
Prognostics and health management
Systematic review
A B S T R A C T
Condition monitoring involves detecting, diagnosing, or predicting faults or failures in industrial equipment.
Given advances in the underlying artificial intelligence solutions and internet of things-based technologies,
condition monitoring has the potential to improve industrial maintenance processes rapidly. Adopting condition
monitoring-based technologies requires evaluating their engineering and financial benefits to determine
whether the investment is justified. An increasing number of studies describe procedures to evaluate condition
monitoring-based maintenance, but the literature lacks a review of these evaluation studies to identify research
opportunities and best practices. This systematic review aims to report and analyze the evaluation methods for
using condition monitoring-based technologies in industrial maintenance. This review identified 465 relevant
peer-reviewed studies between 2001 and 2023, from which 42 articles met the eligibility criteria. For each
article, this paper analyzed facets of the evaluation process related to the study’s characterizations of the
industrial application, condition monitoring, maintenance deployment, evaluation techniques, performance
measures, and economic analysis. Collectively, these results yield several insights. Few condition monitoring
evaluation studies exist for manufacturing systems, unlike the domains of energy systems and transportation
modes. Also, many studies lack details about condition monitoring and maintenance models. Additionally,
the evaluation techniques across most studies can improve with combinations of analytical frameworks,
simulation, and expanded sensitivity analysis. Lastly, the reviewed studies are difficult to directly compare
due to heterogeneity in economic analysis, performance measures, and uncertainty analysis — indicating
an opportunity for future research to structure comprehensive reporting items to enhance the comparability
of domain-specific condition monitoring-based maintenance evaluations. Based on the literature review and
analyses, this review suggests specific recommendations for future condition monitoring evaluation and
opportunities for further research.
1. Introduction
Emerging advancements in artificial intelligence (AI) and the inter-
net of things (IoT) create new opportunities for improving operations
and maintenance in manufacturing as well as broader industrial set-
tings, where enterprises use IoT to sense measurands and exploit data
with analytics and AI methods [1]. These AI and IoT advancements
have been rapidly embedded into condition monitoring-based technolo-
gies, providing users with potential improvements to the maintenance
of industrial equipment by way of more options for better-performing
anomaly detection, fault diagnosis, and failure prediction [2,3]. How-
∗
Corresponding author at: National Institute of Standards and Technology, Communications Technology Laboratory, 100 Bureau Dr, Gaithersburg, MD 20899,
USA.
E-mail addresses: mehdi.dadfarnia@nist.gov (M. Dadfarnia), michael.sharp@nist.gov (M.E. Sharp), herrmannj@cua.edu (J.W. Herrmann).
ever, the impact of AI and IoT technologies on productivity growth has
been low [4,5], and their adoption has especially been scant for small-
and medium-sized manufacturing enterprises [6].
Maintenance-related uses of condition monitoring face a unique
challenge to harness the power of AI and IoT technologies, as main-
tenance is typically under-prioritized by industrial firms, and novel
technological interventions for maintenance are often hindered by
factors such as the lack of technological expertise [6] and managerial
commitment [7]. Crucially, many manufacturing enterprises perceive
the value of maintenance to be invisible, and facilitating the approval
of maintenance-related investments requires proof of profits, financial
https://doi.org/10.1016/j.jmsy.2025.06.015
Received 5 April 2025; Received in revised form 23 May 2025; Accepted 10 June 2025
Journal of Manufacturing Systems 82 (2025) 449–477
0278-6125/Published by Elsevier Ltd on behalf of The Society of Manufacturing Engineers.
