Condition-based Maintenance Decision Research Articles

Multiple-failure mode division and condition-based maintenance decision making for systems with multi-indicator performance degradation

In prognostics and health management research, it is typically assumed that the health status of a system can be reflected by a single performance indicator. However, modern industrial systems are complex and often require multiple indicators to represent different aspects of system health. Furthermore, these indicators may be associated with multiple fault types, leading to multiple failure modes. This study focuses on systems with multi-indicator performance degradation. We construct a division model of multiple failure modes, and investigate the optimal condition-based maintenance decision under multiple failure modes. By constructing division models for systems with two-indicator performance degradation and systems with three-indicator performance degradation, a common multiple-failure mode division model for systems with multi-indicator performance degradation is to distinguish different fault types that may occur in such systems. Taking the systems with two-indicator performance degradation as an example, a condition-based maintenance strategy is developed that considers the differences in maintenance types and effectiveness corresponding to different faults types. A joint probability recursive model under the influence of strategies is derived, and a cost-rate model in a finite time horizon is established to determine the optimal inspection cycle and maintenance threshold for each indicator. Taking the steel rolling system as an application case, the correctness and effectiveness of the proposed strategy and model are verified. The results indicate that the division model can represent the complex relationships among multiple indicators and fault types and that the strategy considering multiple maintenance types and effects can reduce the cost rate of the system.

Condition-Based Production for Stochastically Deteriorating Systems: Optimal Policies and Learning

Problem definition: Production systems deteriorate stochastically due to use and may eventually break down, resulting in high maintenance costs at scheduled maintenance moments. This deterioration behavior is affected by the system’s production rate. Although producing at a higher rate generates more revenue, the system may also deteriorate faster. Production should thus be controlled dynamically to tradeoff deterioration and revenue accumulation in between maintenance moments. We study systems for which the relation between production and deterioration is known and the same for each system and systems for which this relation differs from system to system and needs to be learned on-the-fly. The decision problem is to find the optimal production policy given planned maintenance moments (operational) and the optimal interval length between such maintenance moments (tactical). Methodology/results: For systems with a known production-deterioration relation, we cast the operational decision problem as a continuous time Markov decision process and prove that the optimal policy has intuitive monotonic properties. We also present sufficient conditions for the optimality of bang-bang policies, and we partially characterize the structure of the optimal interval length, thereby enabling efficient joint optimization of the operational and tactical decision problem. For systems that exhibit variability in their production-deterioration relations, we propose a Bayesian procedure to learn the unknown deterioration rate under any production policy. Numerical studies indicate that on average across a wide range of settings (i) condition-based production increases profits by 50% compared with static production, (ii) integrating condition-based production and maintenance decisions increases profits by 21% compared with the state-of-the-art sequential approach, and (iii) our Bayesian approach performs close, especially in the bang-bang regime, to an Oracle policy that knows each system’s production-deterioration relation. Managerial implications: Production should be adjusted dynamically based on real-time condition monitoring and the tactical maintenance planning should anticipate and integrate these operational decisions. Our proposed framework assists managers to do so optimally. Funding: This work was supported by the Nederlandse Organisatie voor Wetenschappelijk Onderzoek [Grant 439.17.708]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0473 .

Joint optimization of inspection and condition-based maintenance for a deteriorating product under extended warranty

Condition-based maintenance (CBM) has been widely applied in engineering practice, but it has been rarely integrated into extended warranty policies. When the inspection cost is high, it becomes important to schedule the inspection plan when making CBM decisions. This paper jointly optimizes inspection and CBM for a deteriorating product under extended warranty. The deterioration of the product is characterized as a non-stationary gamma process. At each inspection epoch, the decision maker needs to determine whether to repair the product and when to perform the next inspection. The objective is to simultaneously optimize the inspection policy and the maintenance policy that minimize the warranty servicing cost. The joint optimization problem is formulated by stochastic dynamic programming. The optimal policy is proven to be of a control-limit form. A backward induction algorithm integrating the obtained structural properties is proposed to find the optimization results. A numerical example is conducted to illustrate the effectiveness of the proposed approach. A graphical representation of the obtained policy is provided to support practical maintenance implementation. The comparison with a popular CBM policy confirms the superiority of the proposed policy.

Condition-based maintenance optimisation for multi-component systems using mean residual life

This paper aims to propose a Novel Condition-based maintenance (CBM) decision aid model for optimising the maintenance of complex multi-component systems. As the degradation level of each component is assumed to be independent and stochastic, it follows a specific probability distribution determined from historical data of experimental observations and inspection. The main objective is to optimise the total cost for providing maintenance actions and reducing the excess of spare parts usage. The decision support model consists of determining measurements on components with the aim of estimating the instant of time of removing predictively one or a group of components before they fail. The measurement model includes the mean residual lifetime (MRL) and some extensions developed for this purpose. For demonstrating the pertinency of the proposed model, we use a preventive maintenance strategy for one-component systems and a grouping/opportunistic maintenance for multi-component systems. Besides, a numerical comparative study performing these measurements is carried out using several examples and a case study from Electric energy distribution systems. The solution is illustrated as a decision-making optimal model for optimising the maintenance operations’ costs and the total number of spare parts. The numerical results and the comparison show the efficiency of the proposed approach.

Optimal condition-based maintenance policy for leased equipment considering hybrid preventive maintenance and periodic inspection

Innovations in technology have made the structure of leased equipment more complex, which poses a challenge for lessors to develop maintenance policies. In view of the situation that the single periodic preventive maintenance (PM) policy during leasing activities may cause excessive or insufficient maintenance on the leased equipment, a condition-based maintenance (CBM) policy considering hybrid preventive maintenance (HPM) and periodic inspections is proposed. This policy contains imperfect preventive maintenance (IPM), preventive replacement (PR) and corrective maintenance (CM). The lessor can decide to take maintenance actions depending on whether the state of the equipment reaches the corresponding maintenance threshold. The warranty period of the leased equipment is also considered. To seal the deal, the lessor will give a discount on the rental to cover the CM costs and penalties out of the warranty period. To minimize the lessor's costs, we propose a CBM decision model to determine the optimal inspection period, PM threshold and PR period. The results show that the HPM policy can reduce leasing costs by about 5 –15 % for the lessor compared to that of the single PM policy.

Optimal switching and condition-based maintenance of cold standby systems subject to competitive failure and imperfect switchover

Cold standby redundant structures can improve system reliability and availability but are subjected to internal degradation and external shocks during operation. Thus, the switching process in a standby system is prone to failures. This study investigates the optimal switching and condition-based maintenance (CBM) decision of a two-unit cold standby system subject to mutually dependent competitive failure processes with an imperfect switchover. First, periodic switching and offline CBM policies under imperfect switchover are proposed; second, the reliability models of competitive failure—between soft failure caused by system degradation subject to nonfatal shock and hard failure caused by fatal shock—are established. An iterative model of the system state probability distribution is subsequently derived by analysing the characteristics of state transitions in alternate use and maintenance of the active and standby units. An analytical decision model is also established to minimise the average cost rate in a finite horizon to obtain the optimal switching period and maintenance threshold. Finally, a case study of a coal mine main ventilator system validates the proposed model.

Condition-based multi-component maintenance decision support under degradation uncertainties

Multi-component maintenance optimization is a well-studied area for age-based failure models but in contrast, incorporation of condition-based maintenance (CBM) is still an open area of research. Taking advantage of condition monitoring information for updating components’ health conditions demands a dynamic short-term approach when grouping multiple activities subject to CBM policy. Degradation models are commonly utilized in CBM for predicting the future condition of a given component to decide appropriate maintenance actions where inherent uncertainties exist in the degradation processes. There are a limited number of works in literature that account for degradation uncertainties where maintenance cost is a function of such uncertainty. This paper aims to develop a maintenance decision support for a multi-component system by incorporating CBM while considering the degradation uncertainties. In this paper, a two-stage stochastic programming is proposed to address such an issue and the problem is formulated for situations where maintenance opportunities are limited due to practical constraints (e.g., remote offshore maintenance operations of wind farms, unmanned platforms in oil and gas industries, etc.). The concept of marginal cost is used in developing the equation of optimality. This is a combinatorial problem and becomes intractable when the number of components is large therefore a heuristic is proposed to reduce the problem size which reduces the required computational time substantially. It is shown that significant cost savings are possible, especially, when the downtime cost and common setup cost are significant. A numerical example is provided with a system of six components achieving above 10%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$10\\%$$\\end{document} cost reduction when the degradation uncertainties are taken into account.

Condition-based maintenance and production speed optimization under limited maintenance capacity

Many industrial facilities consist of multiple units working in parallel to reach a production target or to maximize production revenues. These units deteriorate due to stress that is often dependent on the production speed, and thus maintenance needs to be performed to ensure that the system remains functional. Maintenance generally requires a considerable amount of time and maintenance capacity is often limited. Therefore, during maintenance of a specific unit, a failure of another unit may lead to additional downtime until maintenance capacity becomes available again. In this study we examine the value of condition-based production in such a system, and jointly optimize production and maintenance decisions. The problem is formulated as a Markov decision process, and the results are compared with a benchmark policy without an adjustable production speed. A numerical analysis shows that adjustable production speeds are used to actively desynchronize the deterioration levels of units for systems with a production target. For systems that aim to maximize total production output, considerable profit increases are obtained by lowering the production speed (i) at high deterioration levels to reduce the risk of failure, and (ii) when the maintenance station is busy to reduce the risk that multiple units require maintenance simultaneously. A sensitivity analysis is used to illustrate under what circumstances joint condition-based production and maintenance decisions are most beneficial.

Operation reliability monitoring towards fault diagnosis of airplane hydraulic system using Quick Access Recorder flight data

Hydraulic system operation reliability (HSOR) can evaluate time series state reliability for hydraulic system fault diagnosis and provide condition based maintenance decisions. The quick access recorder (QAR) flight data and normal values of the hydraulic system are utilized to analyze time series HSOR by calculating the operation reliability index. Considering the relationship of the hydraulic subsystem among the components, hydraulic components Bayesian Network is constructed to analyze time series HSOR. Furthermore, the sensitivity of HSOR features to fault location is assessed using categorical boosting (CatBoost) and Shapley Additive ex-Planations values. Through the analysis of two flights hydraulic system QAR datasets, it is revealed that (a) HSOR can accurately monitor the time series operating states of the hydraulic system; and (b) with demonstrating two illustrative case, the HSOR values and features sensitivity analysis can be a useful reference for the fault diagnosis and location of the airplane hydraulic system. The study intends to develop a practical reference approach for hydraulic system fault diagnosis and location using QAR data.

Diagnosis of Multiple Faults in Rotating Machinery Using Ensemble Learning.

Fault diagnosis of rotating machines is an important task to prevent machinery downtime, and provide verifiable support for condition-based maintenance (CBM) decision-making. Deep learning-enabled fault diagnosis operations have become increasingly popular because features are extracted and selected automatically. However, it is challenging for these models to give superior results with rotating machine components of different scales, single and multiple faults across different rotating components, diverse operating speeds, and diverse load conditions. To address these challenges, this paper proposes a comprehensive learning approach with optimized signal processing transforms for single as well as multiple faults diagnosis across dissimilar rotating machine components: gearbox, bearing, and shaft. The optimized bicoherence, spectral kurtosis and cyclic spectral coherence feature spaces, and deep blending ensemble learning are explored for multiple faults diagnosis of these components. The performance analysis of the proposed approach has been demonstrated through a single joint training of the entire framework on a compound dataset containing multiple faults derived from three public repositories. A comparison with the state-of-the-art approaches that used these datasets, shows that our method gives improved results with different components and faults with nominal retraining.

A Stochastic Programming Model for Jointly Optimizing Maintenance and Spare Parts Inventory for IoT Applications

Service supply chain models typically use conservative maintenance and spare part management policies that result in significant losses due to redundancies. Conservatism without an improved understanding of risks, however, does not cushion against unexpected consequences. Risk scenarios associated with asset failure and inventory shortage are frequently observed in practice. Advances in Internet of Things (IoT) technology is unlocking new methods that attain significant prediction accuracy for these risk factors. IoT-enabled predictions on asset state of health can drive dynamic decision models that conduct maintenance and replenishment actions more efficiently while reducing risk. In this study, we propose a unified framework that utilizes IoT data to jointly optimize condition-based maintenance and inventory decisions. We formulate our problem as a stochastic mixed integer program that accounts for the interplay between maintenance, spare parts inventory, and asset reliability. We introduce a new reformulation that’s efficient for solving large-scale instances of the proposed model. The framework presented herein is applied to real world degradation data to demonstrate the benefits of our methodology in terms of cost and reliability.

A neural-network-based proportional hazard model for IoT signal fusion and failure prediction

Accurate prediction of Remaining Useful Life (RUL) plays a critical role in optimizing condition-based maintenance decisions. In this article, a novel joint prognostic modeling framework that simultaneously combines both time-to-event data and multi-sensor degradation signals is proposed. With the increasing use of IoT devices, unprecedented amounts of diverse signals associated with the underlying health condition of in-situ units have become easily accessible. To take full advantage of the modern IoT-enabled engineering systems, we propose a specialized framework for RUL prediction at the level of individual units. Specifically, a Bayesian linear regression model is developed for the multi-sensor degradation signals and a functional neural network is proposed to allow the proportional hazard model to characterize the complex nonlinearity between the hazard function and degradation signals. Based on the proposed model, an online model updating procedure is established to accurately predict RUL in real time. The advantageous features of the proposed method are demonstrated through simulation studies and the application to a high-fidelity gas turbine engine dataset.

A Deep Adversarial Learning Prognostics Model for Remaining Useful Life Prediction of Rolling Bearing

Remaining useful life (RUL) prediction for condition-based maintenance decision making plays a key role in prognostics and health management (PHM). Accurately predicting RUL of the rotating components of complex machines becomes a challenging task for PHM. For many existing methods, the current prediction error of RUL prediction may be accumulated into the future predictions, and thus can lead to a prediction error superposition problem. In this article, the formation mechanism of prediction error superposition is analyzed, and for the first time a deep adversarial long short-term memory (LSTM) prognostic framework is proposed to overcome the major issue related to prediction error superposition. In the proposed framework, a generative adversarial network (GAN) architecture combining the LSTM network and autoencoder (AE) is investigated for bearing RUL monitoring. In the proposed deep adversarial learning prediction framework, due to the potential involvement of long-term and complex tasks, the LSTM network (generator) is used to predict the degradation process of rolling bearings based on available historical data, and a simple but useful AE (discriminator) is used to determine and refine the accuracy of the prediction. Therefore, the AE plays the adversarial role of the LSTM network, and the prediction accuracy of the LSTM network can be significantly improved. For illustration purpose, two practical case studies, which use a series of bearing degradation data and the IEEE PHM 2012 PRONOSTIA datasets, respectively, are presented to show the prediction performance of the proposed method. Experimental results show that the proposed method works very well for vibration monitoring and performs better in comparison with the reference machine learning and deep learning approaches. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement</i>—The damage of rolling bearing usually leads to a significant consequence to industrial production process. However, the existing remaining useful life (RUL) prediction methods for rolling bearing have a prediction error superposition problem that can affect the multistep prediction performance. The new adversarial learning prognostics model proposed in this article can overcome the problem. The proposed method uses LSTM network as a generator to predict RUL life for rolling bearing, and uses AE as a discriminator to estimate the prediction accuracy. The method can significantly improve the multistep prediction accuracy of RUL for rolling bearing, and provides reliable and scientific strategy in PHM of mechatronics equipment.

Optimal State Risk Scheduling Based on Selective Maintenance Strategy

Because stochastic fault cases (i.e., opportunistic maintenance strategy) of the equipment are not considered in the condition-based maintenance decision of the system, which will deviate from the actual situation, a system condition-based maintenance scheduling model considering opportunistic maintenance strategy is proposed in this paper. To implement the system maintenance strategies, the correlation set is formulated by considering the relationship among different equipment. According to renewal process theory, the availability of the correlation set considering planned maintenance and opportunity maintenance is deduced and the maintenance strategy of the system is realized. Then, to reflect the relationship between equipment maintenance and system operation, a system state scheduling model aiming at minimizing the sum of maintenance risk and failure risk as well as considering system resource constraints is proposed, thus obtaining the optimal maintenance schedule based on system state. Finally, a simple test system and IEEE-RTS79 node system are employed to demonstrate the feasibility and effectiveness of the proposed maintenance model, and it also verified that the proposed model can be integrated into the power system condition-based maintenance theory.

Communication Equipment Condition Based Maintenance Decision

In order to develop a scientific and cost reasonable maintenance strategy to solve the current high cost problem of running and maintenance management for communication equipment, introduce the same type set which has the similar running condition with the object set as the reference set and propose a life prediction method for communication equipment. The method solves the similarity factor of life evaluation parameters (running time, times of starting and stopping) in actual and benchmark running condition by using experience running data. In order to accurately calculate the running life of the object set under the actual running conditions and overcome the shortcomings of the traditional artificial statistics, the calculation method of real time and historical life is presented. Then based on the product of the maintenance factor and service factor of running time and the times of starting and stopping, the concept of the key parameters of the decision of condition-based maintenanceequivalent service factor is put forward; According to the relationship between the equivalent service factor in running time and to predict period, four kinds of decision models of condition-based maintenance are established. The historical data of communication equipment running were perioded to predict when given equivalent service factor.

Condition-based maintenance strategy optimization of meta-action unit considering imperfect preventive maintenance based on Wiener process

With the popularization and application of technologies such as monitoring and sensing, the application of condition-based maintenance has become increasingly widespread. However, most traditional condition-based maintenance strategies focus on a component or system, which is too large for fault diagnosis and location. Moreover, imperfect maintenance is seldom considered and most of them only optimize the single variable in condition-based maintenance decision. In this paper, the meta-action unit is taken as the research object, and the Wiener process is used to describe the performance degradation of the meta-action unit. Considering that the maintenance quality deteriorates with the increase of the number of maintenance, and has randomness, the beta distribution is used to establish an imperfect preventive maintenance quality model. A new maintenance optimization strategy is proposed, with the long-term maintenance cost rate as the goal, to obtain the best preventive maintenance threshold, inspection cycle and the optimal number of maintenance. Finally, a Monte Carlo simulation was used to solve numerically and analyze the influence of each parameter on the optimal decision. It can provide a reference for the decision-making when developing maintenance policies.

Prognostics and Health Management System for Electric Vehicles with a Hierarchy Fusion Framework: Concepts, Architectures, and Methods

The prognostics and health management (PHM) of electric vehicles is an important guarantee for their safety and long-term development. At present, there are few studies researching about life cycle PHM system of electric vehicles. In this paper, we first summarize the research progress and key methods of PHM. Then, we propose a three-level PHM system with a hierarchy fusion architecture for electric vehicles based on the structure, data source of them. In the PHM system, we introduce a database consisting of the factory data, real-time data, and detection data. The electric vehicle's factory parameters are used for determining the life curve of the electric vehicle and its components, the real-time data are used for predicting the remaining useful lifetime (RUL) of the electric vehicle and its components, and the detection data are used for fault diagnosis. This health management database is established to help make condition-based maintenance decisions for electric vehicles. In this way, a complete electric vehicle PHM system is formed, which can realize the whole-life-cycle life prediction and fault diagnosis of electric vehicles.

Condition-Based Multiobjective Maintenance Decision Making for Highway Bridges Considering Risk Perceptions

This paper proposes a novel optimal condition-based life-cycle highway bridge maintenance framework incorporating decision makers’ risk perceptions. The inspection and repair planning are formulated as a multiobjective optimization problem, i.e., simultaneously minimizing the expected maintenance cost and expected failure cost. Monte Carlo simulation is employed to calculate the distribution of maintenance and failure costs. To be consistent with bridge maintenance practices, both preventative and essential maintenance are considered, where the maintenance action is dependent on the load rating factor of individual bridge components. Utility theory and cumulative prospect theory are used to model decision makers’ risk preference among the Pareto front solutions. The cost-benefit implications of the Pareto front in terms of maintenance and failure costs, in conjunction with the preference solutions provided by utility theory and cumulative prospect theory, assist in the selection of the optimal bridge maintenance solution. The developed framework is illustrated on an in-service highway bridge.

Optimal condition-based maintenance with general repair and two dependent failure modes

This paper proposes a condition-based maintenance (CBM) policy for a system subject to dependent soft and hard failures. When the deterioration exceeds a predetermined level, the system experiences a soft failure that can be rectified by corrective general repair or corrective replacement. Three possible actions, namely no maintenance, preventive general repair, and preventive replacement, are considered at each inspection epoch. The hard failure rate depending on both age and deterioration is described by a proportional hazards model with the covariate characterized by a gamma process. The hard failure can be corrected by minimal repair, general repair, or by replacement. Different from previous CBM policies, no thresholds are used to define maintenance actions. The objective is to determine the optimal maintenance policy that minimizes the long-run expected average cost per unit time. The optimization problem is formulated in the semi-Markov decision process (SMDP) framework and solved by the policy iteration algorithm. Two practical numerical examples are provided to illustrate the proposed policy. The comparison with other CBM policies shows an outstanding performance of the proposed policy, as well as the significance of minimal repair and general repair in CBM decision making.

Condition-based maintenance decision based on inverse gaussian deterioration process under the condition of regular detection and maintenance

Condition-based maintenance decision based on inverse gaussian deterioration process under the condition of regular detection and maintenance