Preventive Maintenance Decisions Research Articles

Preventive maintenance decision model of electric vehicle charging pile based on mutation operator and life cycle optimization

AbstractThis paper proposes a preventive maintenance decision model for electric vehicle charging stations based on mutation operators and lifecycle optimization to address the impact of potential faults on maintenance effectiveness. By introducing the particle swarm optimization algorithm with mutation operator, a comprehensive analysis of opportunity service age factor and safety failure probability factor was conducted to establish an indicator system for the operation status of charging piles, and a potential fault identification model was constructed. By optimizing the life cycle, the balance problem between optimal maintenance life and optimal opportunity maintenance life has been solved, thus completing preventive maintenance decisions. The experimental results show that the accuracy of this method in preventive maintenance decision‐making for electric vehicle charging piles can reach 98%, with an average preventive maintenance decision‐making time of 1.6 s for load piles. At the same time, the risk probability value and load loss value are effectively controlled. This study has good application prospects in improving the preventive maintenance effect of electric vehicle charging piles.

Analysis of remaining useful life of slope based on nonlinear wiener process

A remaining useful life (RUL) prediction model based on the nonlinear Wiener process is proposed to better tackle the life evaluation problem in the slope degradation process. Taking the displacement of the slope as its performance degradation index, and the nonlinear Wiener process is used to establish the RUL prediction model of the slope. For this model, the least squares method (LSM) is used to estimate the drift coefficients, the maximum likelihood estimation method (MLEM) is used to estimate the diffusion parameters, and then the probability density function (PDF) of the RUL of the slope is deduced and the RUL is predicted. The proposed model is verified by slope engineering examples. The results demonstrated that the RUL of the degradation model based on the nonlinear Wiener process has a greater prediction accuracy than the linear Wiener process. Because the various nonlinear functions have varying slope adaptations, and it can predict the RUL of a slope more accurately, which can provide more reliable preventive maintenance decisions.

Group Maintenance for Numerical Control Machine Tools: A Case Study

The high-reliability requirement of numerical control (NC) machine tools emphasizes the effectiveness of preventive maintenance (PM). However, most existing PM decisions are made by treating them as single-component systems, resulting in the problems of “excessive maintenance” or “insufficient maintenance.” Moreover, real failure data has rarely been utilized for maintenance decision-making, which leads to idealized policies far from practice. This article presents a framework to derive the optimal group maintenance (GM) policy from real failure histories for an NC machine tool comprised of heterogeneous components. Criticality analysis is first conducted to identify high-risk and low-risk components. The lifetime of each high-risk component is characterized by a two-parameter Weibull model or by a Weibull competing-risk model according to whether its failures are independent of the other components. High-risk components with strictly increasing or bathtub-shaped failure rates are selected for PM decision-making. This article introduces a multilevel PM decision-making approach: 1) a repair-replacement model is developed at the component level to derive the optimal PM interval and the maximum number of PM actions; and 2) at the system level, a GM procedure is presented to obtain the optimal PM interval of the system. The failure histories of an NC machine tool with 13 components are used to illustrate the effectiveness of the proposed approach. A maintenance plan is finally made based on optimization results to guide maintenance implementation.

Research on imperfect condition-based maintenance strategy based on accelerated degradation process

To address the situation that the degraded system cannot be repaired as new and the degradation is accelerated after repair in engineering practice, an imperfect condition-based maintenance model is proposed based on the Gamma process by introducing the maintenance improvement factor and the accelerated degradation factor. The maintenance improvement factor describes the recovery degree of the degradation amount after imperfect maintenance, then gives a quantitative representation method of the system maintenance improvement effect and the determination method of the maximum number of imperfect maintenance. The accelerated degradation factor is combined with the geometric process to describe the accelerated degradation process of the system after imperfect maintenance. The Monte Carlo method is used to determine the optimal number of imperfect preventive maintenance decisions. Through the demonstration of calculation examples, the influence of accelerated degradation factor and maintenance improvement factor on the long-term operation maintenance rate and the optimal number of imperfect maintenance is analyzed. The results show that the model can more comprehensively describe the degradation and maintenance process of degraded systems, and it can effectively reduce maintenance cost ratio under long-term operation. It provides a certain theoretical support for formulating an economical and reasonable maintenance strategy that is more in line with the actual degradation and maintenance process in engineering practice.

Multi-phase preventive maintenance strategy for leased equipment considering usage rate variation

Lessors are responsible for equipment maintenance during the lease period. The usage rate of these equipment affects their failures, reliability and decision-making on maintenance strategy. For some leased equipment, such as those producing seasonal products, the usage rate varies. However, conventional approaches usually set usage rate as a constant. Different from the existing literature, this work considers the variation of usage rate, and proposes a multi-phase preventive maintenance (PM) decision model to determine the PM times and degrees at different phases. The goal is to minimize lessors’ lease service cost by balancing corrective maintenance (CM) cost, PM cost and penalty cost during the lease period. In this model, an age correspondence framework is applied to characterize the variation of usage rate at different phases. An accelerated failure time model and an age reduction model are adopted to capture the effect of variable usage rate and imperfect PM on the equipment’s reliability. To verify the effectiveness of the proposed model, it is contrasted with a PM decision model with average usage rate. The impact of unit PM cost, CM cost, and penalty cost on maintenance strategy is discussed by numerical examples. Managerial insights for maintenance strategy are provided for lessors. The results indicate that the proposed approach considering varied usage rate can change the optimal PM times and degrees, and consequently lead to a lower lease service cost than conventional approaches using average usage rate; lessors need to enhance PM capability and reduce PM cost.

Refined evaluation methods for preventive maintenance of project-level asphalt pavement based on confusion-regression model

Accurate evaluation of the performance of airport pavement can help managers make scientific and systematic preventive maintenance (PM) decisions, ensuring pavement safety and extending service life. To this end, firstly, this paper sorted out the pavement performance evaluation index system, based on which a multi-dimensional evaluation system for PM was proposed, including control indexes, macroscopic indexes, and microscopic indexes. Then, the pavement decay model based on the pavement condition index (PCI) was developed, and the regression model between PCI and International roughness index (IRI) and friction coefficient (μ) was established. Finally, by converting the PM decisions for project-level pavement into a binary classification problem in machine learning, the optimal maintenance thresholds and intervals for PM of each index were determined using receiver operating characteristic (ROC) curve and Kolmogorov-Smirnov (K-S) curve. The optimal threshold represents the threshold when the index can separate the binary classification problem (PM decisions) with maximum probability. Based on confusion-regression model, the pavement performance can be evaluated more comprehensively, and the timing of PM can be accurately determined. The model helps airport managers develop accurate PM plans to address future maintenance needs.

Optimal preventive maintenance interval model with time value of money consideration

The search for a plant maintenance strategy to mitigate the impact of random factory machine failures has never been more challenging. Apart from the harsh global competition, manufacturing facilities have become more sophisticated and expensive; frequent and prolonged breakdowns may ruin a firm’s business. Consequently, many have turned to the Preventive Maintenance (PM) strategy for a solution. However, the efficacy of PM has been shown to depend on finding a maintenance time interval decision model capable of incorporating most of the relevant maintenance cost components. While past studies have considered maintenance system set-up, execution, and breakdown cost components, the literature is sparse on decision models incorporating the cost of borrowing money. Exploring the feasibility of developing such a model is the aim of this study. Accordingly, a maintenance-investment cost function was formulated in terms of PM time interval and plant reliability; a PM decision problem was then defined and solved as that of PM investment cost minimization. Using three cases from the literature, the optimal maintenance time intervals (238.11, 14695.28, and 2076.54), failure probabilities (0.71, 0.35, and 0.61), and costs for preventive maintenance (PM) (840950.87, 149352.55, and 33979.57) were found to be reasonable.

Joint optimization of condition-based performance control and maintenance policies for mission-critical systems

The failure behavior of mission-critical systems typically depends on their performance levels, which provides opportunities to control deterioration by adjusting the performance levels. In addition to performance level selection, preventive maintenance decision is another factor affecting system survivability and mission success probability, providing a new train of thought for joint optimization of preventive maintenance and performance control for effective risk control of mission-critical systems. In existing research, mission-based maintenance and performance control decisions are seldom considered. This paper focuses on mission-critical systems and investigates the joint optimization of maintenance and performance control policies to balance mission success probability and system survivability based on the workload and system state. The problem is formulated as a Markov decision process and structural properties are analyzed to determine the optimal maintenance and performance control policies. The maintenance strategies exhibit a threshold structure, which strongly depends on the relationship between the performance level and the degradation process. For the purpose of comparison, the performance of several heuristic strategies is analytically evaluated. The example of the data transmission satellite network is given to demonstrate the superiority of the proposed strategies in reducing operations costs.

A New Set of Indexes and Thresholds of Preventive Maintenance Decision Making for Airport Runway Composite Pavement

A New Set of Indexes and Thresholds of Preventive Maintenance Decision Making for Airport Runway Composite Pavement

On optimal condition based task termination policy for phased task systems

Phased task systems commonly perform different tasks in sequence and have been widely applied in various engineering fields. Failures of phased mission systems may result in irretrievable economic losses and significant damages. It is crucial to take effective measures to enhance the survivability of phased task systems. Existing literature mainly focuses on optimizing preventive maintenance policy upon the completion of each phase to mitigate the failure risk. In addition to carrying out preventive maintenance, task termination in case of high failure risk is another intuitive way to improve system survivability. We investigate the condition based task termination and preventive maintenance policies for phased task systems with observable internal degradation. Dynamic preventive maintenance and task termination decisions are considered based on the degradation level as well as the number of completed phases. The problem is formulated as a Markov decision process to minimize the expected costs of task failure and system failure. Some structural properties are derived and several heuristic policies are compared. Case studies are presented to illustrate the proposed policies.

Multi-objective optimization for preventive maintenance of offshore safety critical equipment integrating dynamic risk and maintenance cost

Safety-critical equipment (SCE) are installed on offshore installations as important safety barriers to prevent the occurrence of major accident. In order to ensure the specified safety function of SCE, preventive maintenance (PM) is an indispensable activity. However, PM decision making is still a challenge as it is influenced by various factors such as the risk in association with SCE degradation, risk in association with PM, and maintenance-related cost. Especially, the relevant risks are inherently dynamic in nature and the effects of these influence factors are conflicting. Therefore, this study focuses on the optimization of PM interval for SCE integrating the dynamic characteristics of risk and the conflicting effects among the increased risks due to PM and SCE degradation as well as maintenance-related cost. A systematic multi-objective optimization framework is proposed for the PM interval optimization. Two dynamic risk models are established for the evaluation of dynamic risk profiles of SCE in the operational phase and PM phase respectively. In combination with the lifecycle maintenance-related cost model of SCE, the multi-objective optimization with three objective functions is conducted for the PM interval optimization. The proposed framework is applied in the case study on a typical SCE (pressure safety valve, PSV) to optimize the PM interval. The effectiveness and availability of this framework is verified. It is noted that the common industrial practice of conducting PM once a year is acceptable for PSV once the risks in both operational and PM phases are given equal importance weight. However, a larger PM interval is recommended when the lifecycle maintenance-related cost is included in the optimization goal and further validation procedures are conducted, i.e. statistical analysis of optimal candidates and reassessment of risk profile with the optimal candidates. The proposed multi-optimization framework provides a useful tool for the optimal PM interval determination for the SCE on offshore installations.

Coordinated optimization of production scheduling and maintenance activities with machine reliability deterioration

<p style='text-indent:20px;'>In this paper, we investigate a coordinated optimization problem of production and maintenance where the machine reliability decreases with the use of the machine. Lower reliability means the machine is more likely to fail during the production stage. In the event of a machine failure, corrective maintenance (CM) of the machine is required, and the CM of the machine will cause a certain cost. Preventive maintenance (PM) can improve machine reliability and reduce machine failures during the production stage, but it will also cause a certain cost. To minimize the total maintenance cost, we must determine an appropriate PM plan to balance these two types of maintenance. In addition, the tardiness cost of jobs is also considered, which is affected not only by the processing sequence of jobs but also by the PM decision. The objective is to find the optimal job processing sequence and the optimal PM plan to minimize the total expected cost. To solve the proposed problem, an improved grey wolf optimizer (IGWO) algorithm is proposed. Experimental results show that the IGWO algorithm outperforms GA, VNS, TS, and standard GWO in optimization and computational stability.</p>

Big Data-Driven Preventive Maintenance Decision Support with Monte Carlo Simulation

Big Data-Driven Preventive Maintenance Decision Support with Monte Carlo Simulation

Remaining-useful-lifetime and system-remaining-profit based importance measures for decisions on preventive maintenance

We propose two types of importance measures for component selection in preventive maintenance. The first type evaluates the relative importance of a component in terms of how much the component restoration increases the remaining useful lifetime of the system. The second type of importance measures evaluates the contribution of a maintenance action on a component with respect to the profit that the system can generate during its remaining useful lifetime, considering system reliability, maintenance cost, and uncertain system profit over the remaining useful lifetime. The proposed importance measures take into account various maintenance actions including imperfect repair and replacement, combine the advantages of time-dependent and time-independent lifetime measures on evaluating component importance and are suitable to aid the preventive maintenance decisions on component selection at any time. A numerical example and an application in the preventive maintenance for a wind turbine system are provided to illustrate the proposed importance measures and to compare various time-dependent and time-independent lifetime importance measures.

Integrating preventive maintenance to two-stage assembly flow shop scheduling: MILP model, constructive heuristics and meta-heuristics

In this paper, flexible preventive maintenance (PM) activities are incorporated into two-stage assembly flow shop scheduling where m dedicated machines in the fabrication stage and one machine in the assembly stage. The operational status of each machine is described by a continuous variable, maintenance level. The maintenance level value is inversely proportional to the processing time. Once a PM activity is performed, this value will return to the initial value. Different from the PM at fixed predefined time intervals, flexible PM can be carried out at any time point, but the maintenance levels are not less than 0. Hence, a MILP model with maintenance level constraints is formulated to minimize the total completion time and maintenance time. Regarding the methods, a latest PM decision strategy is proposed to determine the execution time of PM activities. This new strategy is embedded into 15 constructive heuristics and 7 meta-heuristics (three variants of iterated local search, three variants of Q-learning-based ant colony system with local search and a Q-learning-based hyper-heuristics) to address this new problem. The final experimental analysis demonstrates the significance of the integrated model and the effectiveness of the proposed constructive heuristics and meta-heuristics.

Research on Pavement Preventive Maintenance Decision-making Method Based on BIM Technology

The essence of preventive maintenance decision-making is to make decisions for different preventive maintenance measures and different road conditions. Based on the principle of selecting preventive maintenance measures for asphalt pavement, this paper constructs an asphalt pavement preventive maintenance model. It relies on BIM technology and uses Analytic Hierarchy Process (AHP) as a research method to determine the preventive maintenance decision of asphalt pavement. It is obtained by matrix calculation. Develop the best preventive maintenance measures for asphalt pavement.

A preventive maintenance policy with usage-dependent failure rate thresholds under two-dimensional warranties

This article considers Preventive Maintenance (PM) under a two-dimensional (2-D) warranty contract with time and usage limits. From a manufacturer’s point of view, we develop a dynamic maintenance model with a random horizon to include the impact of random and dynamic usage rates on PM decisions. The model treats the cumulative amount of usage as a state variable that provides information about the failure rate and the expiration of the 2-D warranty. We characterize the optimal PM policy by a sequence of usage-dependent failure rate thresholds. Each threshold is a function of the cumulative usage. Our failure rate threshold policy chooses one of the following two actions in each period: performing perfect PM or no PM. Specifically, the manufacturer should bring the failure rate back to its original level when it exceeds the threshold in the corresponding period. This policy is also optimal under a constant usage rate. In the numerical experiments, we demonstrate the effectiveness of the proposed policy and conduct a sensitivity analysis to investigate how this policy is affected by the model parameters.

A two-stage integrating optimization of production scheduling, maintenance and quality

During the process of actual production, production scheduling, preventive maintenance and quality control have a close interaction with each other and thus need to be integrated for improving manufacturing system performance. The aim of this article is to jointly optimize the job sequence, the preventive maintenance locations, the preventive maintenance interval and decision variables of control chart such that the expected cost per unit time and penalty cost due to schedule delay are minimized. A two-stage integrating optimization model of production scheduling, maintenance and quality in a single machine system is developed. A control chart is adopted to monitor the whole process with Taguchi’s loss function estimating the quality cost of each condition and perfect preventive maintenance activity is conducted at the end of each interval. A genetic algorithm is designed to solve this model in order to obtain the optimal job sequence and the locations of preventive maintenance. Numerical examples and thorough sensitivity analyses are provided to illustrate the proposed integrated model. Finally, the efficiency of the proposed two-stage integration model is verified by the comparison of the stand-alone model under the same condition. Compared with the stand-alone model, the proposed integrated method can save the cost rate by 12%–42% under five different situations.

Imperfect Preventive Maintenance Policies With Unpunctual Execution

Traditional maintenance planning problems usually presume that preventive maintenance (PM) policies will be executed exactly as planned. In reality, however, maintainers often deviate from the intended PM policy, resulting in unpunctual PM executions that may reduce maintenance effectiveness. This article studies two imperfect PM policies with unpunctual executions for infinite and finite planning horizons, respectively. Under the former policy, imperfect PM actions are periodically performed and the system is preventively replaced at the last PM instant. The objective is to determine the optimal number of PM actions and associated PM interval so as to minimize the long-run average cost rate. However, the latter policy specifies that a system is subject to periodic PM activities within a finite planning horizon and there is no PM activity at the end of the horizon. The aim is then to identify the optimal number of PM activities to minimize the expected total maintenance cost. In this article, we discuss the modeling and optimization of the two unpunctual PM policies and then explore the impact of unpunctual executions on the optimal PM decisions and corresponding maintenance expenses in an analytical or numerical way. The resulting insights are helpful for practitioners to adjust their PM plans when unpunctual executions are anticipated.

Preventive Maintenance Decision Model of Urban Transportation System Equipment Based on Multi-Control Units

This paper studies the fault prediction of equipment and the decision of joint equipment maintenance in urban traffic system based on Internet of Things and big data as the background of multiple control units, and proposes a joint equipment monitoring model for multi-equipment systems composed of intelligent control units. The network method predicts the fault of the equipment and gives the equipment fault prediction process. Combining the multi-equipment system attributes of intelligent control unit, aiming at minimizing the total maintenance cost of control unit system, and taking the reliability of the whole system and the availability of equipment as constraints, a preventive maintenance decision model for joint equipment maintenance is established. Finally, the optimal preventive maintenance interval of the entire system is solved.