A review on condition-based maintenance optimization models for stochastically deteriorating system Suzan Alaswad a,n , Yisha Xiang b a College of Business, Zayed University, Abu Dhabi, UAE b Department of Industrial Engineering, Lamar University, Beaumont, TX 77710, USA article info Article history: Received 30 September 2015 Received in revised form 4 August 2016 Accepted 15 August 2016 Available online 20 August 2016 Keywords: Condition-based maintenance Preventive maintenance Stochastic deterioration Maintenance optimization Inspection abstract Condition-based maintenance (CBM) is a maintenance strategy that collects and assesses real-time in- formation, and recommends maintenance decisions based on the current condition of the system. In recent decades, research on CBM has been rapidly growing due to the rapid development of computer- based monitoring technologies. Research studies have proven that CBM, if planned properly, can be ef- fective in improving equipment reliability at reduced costs. This paper presents a review of CBM lit- erature with emphasis on mathematical modeling and optimization approaches. We focus this review on important aspects of the CBM, such as optimization criteria, inspection frequency, maintenance degree, solution methodology, etc. Since the modeling choice for the stochastic deterioration process greatly influences CBM strategy decisions, this review classifies the literature on CBM models based on the underlying deterioration processes, namely discrete- and continuous-state deterioration, and propor- tional hazard model. CBM models for multi-unit systems are also reviewed in this paper. This paper provides useful references for CBM management professionals and researchers working on CBM mod- eling and optimization. & 2016 Elsevier Ltd. All rights reserved. 1. Introduction Industrial organizations are continuously seeking new strate- gies to improve the effectiveness of their operations. Maintenance optimization and the selection of maintenance strategies play an important role in the effectiveness of any industrial system's op- eration. Maintenance actions can be generally classified into two categories: corrective maintenance and preventive maintenance (PM). Traditionally, PM takes the form of system overhaul or unit replacement based on elapsed time, which is often referred to as time-based maintenance (TBM). TBM schedules are typically de- termined based on a probabilistic model of system failure. In re- cent years, condition-based maintenance (CBM) has received much attention in the maintenance research community. Unlike TBM policies that are developed based on historical failure data, CBM is a maintenance approach that emphasizes on combining data-driven reliability models with sensor data collected from monitored operating systems to develop strategies for condition monitoring and maintenance. The goal of CBM is to reduce unnecessary maintenance actions and eliminate the risks asso- ciated with preventive maintenance actions. Rapid development of computer based monitoring technologies (e.g., advanced sensors) has further facilitated CBM practices. The literature on the use of mathematical modeling for the purpose of analyzing, planning, and optimizing TBM is abundant. Reviews on TBM can be found in [1–7]. In contrast, CBM has only received increasing attention recently, and only a few survey papers have considered CBM models extensively. The majority of existing CBM survey papers limits the scope within the diag- nostic and prognostic methods and algorithms. For example, Jardine et al. [8] review recent studies and developments in CBM with emphasis on models, algorithms, and technologies for data acquisition and data processing. Peng et al. [9] divide the prog- nostic models into four categories: physical model, knowledge- based model, data-driven model, and combination model, and review various techniques and algorithms by this category. Ah- mad and Kamaruddin [10] present an overview of time-based and condition-based maintenance in industrial applications, and summarize the most recent condition monitoring techniques. Shin and Jun [11] review CBM approach and address several as- pects of CBM, such as definition, advantages and disadvantages, related international standards, procedures and techniques. De- spite the recent rapid development of sensor technology that Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/ress Reliability Engineering and System Safety http://dx.doi.org/10.1016/j.ress.2016.08.009 0951-8320/& 2016 Elsevier Ltd. All rights reserved. n Corresponding author. E-mail addresses: suzan.alaswad@zu.ac.ae (S. Alaswad), yxiang@lamar.edu (Y. Xiang). Reliability Engineering and System Safety 157 (2017) 54–63