Maintenance Optimization Model Research Articles

Research on Status Assessment and Operation and Maintenance of Electric Vehicle DC Charging Stations Based on XGboost

With the rapid development of electric vehicles, the infrastructure for charging stations is also expanding quickly, and the failure rate of charging piles is increasing. To address the effective operation and maintenance of charging stations, a method based on the XGBoost algorithm for electric vehicle DC charging stations is proposed. An operation and maintenance system is constructed based on state analysis, considering the operational status of the charging stations and users’ charging habits. Factors such as driving and charging habits, road traffic, and charging station equipment are taken into account. The training sample data are established using historical data, online monitoring data, and external environmental data, and the charging station status evaluation model is trained using the XGBoost algorithm. Based on the condition assessment results, a risk assessment model is established in combination with fault parameters. Risk tracking of the charging stations is conducted using the energy not charged (ENC), evaluating the risk level of each station and determining the operation and maintenance order. The optimal operation and maintenance model for DC charging stations, aimed at achieving both economic and reliability goals, is constructed to determine the operation and maintenance schedule for each station. The results of the case study demonstrate that the state evaluation and operation and maintenance strategy can significantly improve the reliability of the system and the overall benefits of operation and maintenance while meeting the required standards.

A condition‐based maintenance optimization method with oscillating uncertain degradation process

AbstractCondition‐based maintenance (CBM) has gradually gained more attention, and the degradation process has been increasingly applied to maintenance optimization models. The insufficient data and the complex degradation process of the equipment conditions will contribute to epistemic uncertainty. Besides, the implementation of maintenance introduces oscillatory features into the equipment degradation process, deviating from a monotonically decreasing trend, complicating the optimization of CBM. In this article, to simultaneously address the problem of epistemic uncertainty and consider the influence of inspection and maintenance, we establish a new type of degradation model based on uncertainty theory to deal with epistemic uncertainty. Then an uncertain maintenance optimization model is proposed to give an optimal CBM strategy. Finally, a case study is provided to illustrate the proposed CBM optimization method.

An explainable artificial intelligence model for predictive maintenance and spare parts optimization

Maintenance strategies are vital for industrial and manufacturing systems. This study considers a proactive maintenance strategy and emphasizes using analytics and data science. We propose an Explainable Artificial Intelligence (XAI) methodology for predictive maintenance. The proposed method utilizes a machine learning project cycle and Python libraries to interpret the results using the Local Interpretable Model-agnostic Explanations (LIME) method. We also introduce an early concept of spare parts management, presenting insights from predictive maintenance outcomes and providing explanations for decision-makers to enhance their understanding of the influential factors behind predictions. This study demonstrates that utilizing machine learning models in predictive maintenance is highly beneficial; however, the binary outcomes of these models can be misunderstood by decision-makers. Detailed explanations provided to decision-makers will directly impact maintenance decisions and improve spare part management.

Optimal condition-based opportunistic maintenance policy for two-component systems considering common cause failure

This paper introduces a maintenance optimization model designed for a system comprising two distinct components that are arranged in series and susceptible to common cause failure. Both the components undergo dependent degradation and shock processes whose performance levels are periodically inspected. A condition-based opportunistic maintenance policy is considered, indicating that either preventive or corrective maintenance may be conducted depending on the deterioration state observed during inspections. Meanwhile, when maintenance is performed on one component, the other can be opportunistically maintained. An optimization problem is then formulated under the framework of semi-Markov decision processes, in order to find the optimal preventive and opportunistic maintenance thresholds for the two components. Three algorithms are introduced to address this problem, namely the improved genetic algorithm, the cyclic coordinate search algorithm, and the enumeration algorithm. Their effectiveness is demonstrated through a case study focusing on offshore wind turbines. The result shows that the efficiency of the improved genetic algorithm is significantly superior to the other two algorithms.

Lifetime prediction and replacement optimization for a standby system considering storage failures of spare parts

Spare parts redundancy is an effective way to improve system reliability and prolong system lifetime. Generally, preventive maintenance and inventory management of a standby system can significantly reduce operating and maintenance costs, particularly crucial in industrial systems. Additionally, during storage, spare parts may experience degradation failure due to internal mechanisms and sudden failure due to external shocks, complicating the health management of the standby system. Unfortunately, few existing studies consider the impact of spare parts’ competing failures in standby systems. To address this gap, this paper proposes a novel method for predicting the lifetime and optimizing the maintenance policy of nonlinear degradation standby systems, considering both degradation and sudden failures of spare parts. Firstly, we established the degradation model under the competing failure of spare parts and derived the analytical formula for life prediction of the standby system in the presence of competing failures, assuming that sudden failure follows the Weibull distribution. Furthermore, we developed a joint optimization model for replacement maintenance and inventory management based on predictive information, aiming to minimize the expected cost, in which the block replacement interval and the number of spare parts are treated as decision variables. Finally, the effectiveness and potential application value of the proposed method are verified through numerical simulation and a case study.

A multi‐agent reinforcement learning model for maintenance optimization of interdependent highway pavement networks

AbstractPavement segments are functionally interdependent under traffic equilibrium, leading to interdependent maintenance and rehabilitation (M&R) decisions for different segments, but it has not received significant attention in the pavement management community yet. This study developed a maintenance optimization model for interdependent pavement networks based on the simultaneous network optimization (SNO) framework and a multi‐agent reinforcement learning algorithm. The established model was demonstrated on a highway pavement network in the real‐world, compared to a previously built two‐stage bottom‐up (TSBU) model. The results showed that, compared to TSBU, SNO produced a 3.0% reduction in total costs and an average pavement performance improvement of up to 17.5%. It prefers concentrated M&R schedules and tends to take more frequent preventive maintenance to reduce costly rehabilitation. The results of this research are anticipated to provide practitioners with quantitative estimates of the possible impact of ignoring segment interdependencies in M&R planning.

Coordinated risk-averse distributionally robust optimization for maintenance and generation schedules of offshore wind farm cluster

The coordinated optimization of maintenance and generation schedules of multiple offshore wind farms (OWFs) bring great benefits in reducing the maintenance and operation cost of OWF cluster. Firstly, a two-stage coordinated risk-averse distributionally robust optimization (CRDRO) model for maintenance and generation schedules of wind turbines (WTs) in OWF cluster is proposed. This model takes into account uncertainties related to the prediction errors in WTs’ maximum available active power outputs, the travel time of maintenance vessels, and the high operational cost risks associated with these uncertainties. A feasible route generating algorithm is designed to obtain all feasible maintenance combinations for WTs and the corresponding routes of maintenance vessels for the CRDRO model. The risk-averse term, which is a weighted sum of expected operation costs and GlueVaR value, is used to measure the tail risk of the worst probability distribution. To solve the two-stage CRDRO model, the risk-averse term is simplified into the form of expected value calculation, which can be further transformed into the tractable form by using the strong duality theorem. Finally, the two-stage CRDRO model is solved by the column-and-constraint generation algorithm, with the nonconvex sub-problem being addressed by the outer approximation algorithm. Case studies on an real-world cluster comprising three OWFs verify the correctness and efficiency of the proposed method, and demonstrate that the CRDRO model enhances the overall economic efficiency and reduces the high operational cost risk under extreme scenarios.

Resource-constrained project scheduling with multiple states: Bi-objective optimization model and case study of aircraft maintenance

This paper introduces a new resource-constrained project scheduling problem in which the project has multiple possible states and whether an activity can be performed at a certain time depends on the state at that time. We are motivated by aircraft maintenance projects where activities need to be performed in particular aircraft states, such as power on/off and jack on/off. We formulate a bi-objective optimization model for this problem, which determines the schedule of activities and the selection of states over the planning horizon, subject to resource constraints, precedence relationship, and state restrictions. The model concerns both the minimization of the project duration and the minimization of the number of state changes over time. A heuristic algorithm, which utilizes genetic algorithm techniques, is developed to obtain Pareto efficient solutions of the model. Its effectiveness is demonstrated through a comparison with CPLEX and an adaptation of NSGA-II. Furthermore, we conduct a case study about aircraft maintenance C-check projects in a major airline. The case study demonstrates that our optimization-based approach is applicable and beneficial to the project scheduling practice with the consideration of states.

Machine Learning–Based Bridge Maintenance Optimization Model for Maximizing Performance within Available Annual Budgets

Machine Learning–Based Bridge Maintenance Optimization Model for Maximizing Performance within Available Annual Budgets

Research Paper on Role of Data Features and Data Collection Tools in Artificial Intelligence

Abstract: Artificial intelligence (AI) is revolutionizing various industries by enabling machines to learn, reason, and make decisions autonomously. However, the success of AI systems depends heavily on the quality and quantity of data used for training and testing. Therefore, data collection tools have become essential in AI development. In this paper, we will discuss some popular data collection tools in AI that facilitate the process of gathering large volumes of high-quality data for training and testing AI models. Robotics and sensors are increasingly being used to collect data for AI applications in various industries like healthcare, manufacturing, and agriculture. For instance, in healthcare, robots equipped with sensors can collect medical data like vital signs, blood pressure, and heart rate from patients. In agriculture, drones equipped with sensors can collect crop data like moisture levels, temperature, and nutrient content. These tools provide high-quality data that can be used to train AI models for diagnosis, prediction, and decision-making. Mobile apps are increasingly being used to collect user data for AI applications. Apps like Google Maps, Waze, and Uber collect location data that can be used to train AI models for navigation and traffic prediction. Healthcare apps like MyFitnessPal and Fitbit collect user health data that can be used to train AI models for personalized health recommendations. The Internet of Things is enabling the collection of vast amounts of real-time data from various devices like smart homes, smart cities, and smart factories. This data can be used to train AI models for predictive maintenance, energy management, and resource optimization.

Research on an Optimal Maintenance and Inventory Model Based on Carbon Tax Policy

The equipment in a factory will gradually deteriorate during production, leading to the production of defective products. Without appropriate maintenance, the defect rate will increase over time. Consequently, the production cost will rise, the inventory quality will be affected, the profit will decrease, and the risk of carbon emissions will increase, leading to more customer complaints and damaging the corporate image. In addition to focusing on preventive maintenance to ensure the quality of products, companies should also take carbon emissions into consideration. Furthermore, the frequency of maintenance must be carefully considered, as both carbon emissions and maintenance costs will increase if the frequency is too high; conversely, if the maintenance frequency is too low or non-existent, the defect rate may increase cumulatively, or production may be suspended due to equipment failure. Therefore, this research explores preventive maintenance and inventory management issues within an imperfect production system and develops an extended economic production quantity model that incorporates defective products as well as taking carbon tax and preventive maintenance into consideration. The main purpose is to determine the optimal maintenance frequency, production, and replenishment cycle length, so as to maximize the total profit under the carbon tax policy. This study demonstrates a computing process with relatively impractical product data based on the actual business situation of a disposable diaper manufacturer. Furthermore, a sensitivity analysis is implemented to the model parameters in the proposed model. The managemental insights are illustrated based on the results of theoretical analysis to provide a reference to policy makers during decision making, hence, to secure the sustainability and green transitions of corporates. The results of this study not only help to reduce environmental impact but can also improve the competitiveness and sustainable development of enterprises.

Optimizing the maintenance threshold in presence of shocks: A numerical framework for systems with non-monotonic degradation

Shocks have attracted considerable interest in reliability and maintenance engineering because of their impact on vulnerable systems. Most industrial systems suffer from both internal degradation caused by fatigue and wear-out, and external shocks that often occur randomly due to harsh weather conditions, overloading, etc. Developing maintenance optimization models without taking these stochastic shocks into account is often ineffective. This paper develops a model to optimize the maintenance alarm threshold for a single-component continuously monitored system which is exposed to both fatal and non-fatal shocks in the presence of lead time for hard time maintenance. The shocks occur randomly according to a homogeneous Poisson process during the whole degradation process and have a stochastic impact on the degradation level, while the system resistance to shocks decreases as the system approaches failure. We propose a new numerical maintenance optimization model to find the solution without Monte-Carlo simulation and the model is compared to the Wiener process. A numerical example and a real-time experimental case study on roller bearings are used to demonstrate the effectiveness of the model. The results show that the model is capable of improving maintenance decision-making in terms of failure probability and risk perspective.

Developing a bi-objective maintenance optimization model for process industries by prioritizing resilience and robustness using dynamic Bayesian networks

In this paper, we developed a new model that combines resilience concept with robust maintenance resource allocation, and team assignment strategies to evaluate system performance after disruption. This model offers insights for proactive preparation before disruptive events and facilitates optimal decision-making in the aftermath of such disruptions. Our approach involves a non-linear programming model that operates at both strategic and operational decision levels. It aims to simultaneously minimize total maintenance costs while maximizing resilience by determining the allocation of backup resources to system components before a disruption occurs and suggesting emergency maintenance team assignments post-disruption, all while adhering to resilience constraints.We quantify resilience using a dynamic Bayesian Network method and Markov process, utilizing metrics based on absorption, adaptation, and restoration performance (reliability) curves. We propose a bi-objective optimization model and leverage the genetic algorithm NSGA-III to obtain Pareto-optimal solutions. To address the inherent uncertainty of various disruption scenarios, we generate a range of possible scenarios and employ robust optimization techniques to derive solutions that can withstand these uncertainties. To demonstrate the effectiveness of our proposed model, we conduct a case study involving a City Gate Station in agas industry.

Joint optimization of maintenance and spares inventory policies for a series system with multiple voting subsystems supported by protective devices

The joint optimization of maintenance and spares inventory policies is a momentous topic in engineering domain due to its benefit for improving the system reliability. Equipping systems with protective devices is another effective way to enhance system reliability which has aroused the research interest of scholars in recent years. However, the joint optimization problem of maintenance and spare parts inventory for systems with protective devices has not been attached importance. Therefore, this paper develops a joint optimization model of maintenance and spares inventory strategies for a series system with multiple voting subsystems supported by protective devices. Internal degradation and external shocks are taken into consideration simultaneously to cause the deterioration of the system and devices. A limited number of repairmen is considered, and ( s, S) inventory policy is adopted for protective devices as well as each type of units. By applying the Markov process imbedding approach, system steady probability and relevant reliability probability indices including system availability, spares availability, and repairmen availability are obtained. The objective of developed joint optimization model is to derive the optimal repairmen allocation and spares inventory policies such that the system availability can be maximized while meeting the cost requirement. Finally, numerical examples based on the automobile engine system with cooling systems are presented to validate the superiority of the proposed joint policy of maintenance and spares inventory.

Optimizing multilevel maintenance in multi-component systems under s-dependent competing risks

This paper presents a novel reliability-centered multilevel maintenance optimization model tailored for multicomponent systems subjected to stochastic dependent (s-dependent) competing risks (CRs). Four types of maintenance actions, including minimal repair (MR), medium preventive maintenance (MPM), overhaul preventive maintenance (OPM), and preventive replacement (PR), are incorporated into the development of the multilevel maintenance model. The Copula function is utilized to quantify the s-dependence among failure risks, and subsequently, all unknown parameters are estimated via the inference function for margins (IFM) method. Three types of decision variables are designed to minimize the long-run expected cost rate of the system. Finally, sequential decision process method is utilized to solve the model, and a numerical example of a metro door system illustrates the effectiveness of our proposed model.

Multiple aspects maintenance ontology-based intelligent maintenance optimization framework for safety-critical systems

Abstract Maintenance optimization is a process for improving the efficiency of maintenance strategies and activities, considering various aspects of the target system and components, such as the probabilities of system failures and the cost of repair and replacement of a failed component. The improvement of maintenance optimization algorithms generally requires information from various data sources. For example, it may require the system risk information derived from risk analysis tools or the residual lifetime of a component from fault prognosis tools. The requirements of data acquisition (DAQ) and aggregation pose new challenges for maintenance management systems (MMSs) that implement and use these maintenance optimization algorithms. This paper proposes a multiple aspects maintenance ontology-based framework to facilitate DAQ from MMSs, online monitoring systems, fault detection and discrimination tools, risk assessment tools, decision-making tools, and component identification tools, and accelerate the implementation and verification of contemporary maintenance optimization models and algorithms. The proposed framework consists of a multi-aspect maintenance ontology with critical information for maintenance optimization and application interfaces for collecting information from various data sources, such as fault prognosis tools, online monitoring tools, risk assessment tools, and decision-making algorithms. In addition, this paper proposes a heuristic method for integrating concepts and properties from other existing ontologies into the proposed framework when the existing ontology is not fully compatible with the ontology under construction. Finally, the paper verifies the proposed ontology framework using a feedwater system designed for nuclear power plants with valves and filters as the components under maintenance.

Dynamic joint sensor selection and maintenance optimization in partially observable deteriorating systems

We consider a degrading system with costly but silent failures. The system can be partially observed using a set of heterogeneous noisy sensors at a given cost, where each sensor noise level is a function of the system state. The goal is to devise a dynamic joint sensor selection and maintenance optimization model to minimize the total expected discounted cost of the system. We develop an infinite-horizon discrete-time partially observable Markov decision process model to dynamically prescribe the sensor subsets for system monitoring and the timing of maintenance activities. We perform numerical experiments for a system with up to ten sensors and compare the proposed optimal policy with four heuristic policies. We observe that the proposed approach consistently outperforms all heuristic policies considered. Through a comprehensive analysis of numerical experiments, our study shows the efficacy of the proposed model’s optimal policy in strategically selecting sensors to achieve precise system state estimation while managing costs. Through these experiments, we find that it is optimal to use lower-cost, higher-variance sensors and often fuse them for more accurate estimations. However, the choice depends on the system state and sensor quality distribution. Importantly, our model excels in determining the best action by considering these factors, underscoring its practical applicability.

Multi-objective maintenance strategy for corroded pipelines considering the correlation of different failure modes

Corrosion is the leading cause of leakage and burst failures in long-distances gas pipelines. Periodic maintenance is often used to extend the service life of the pipeline. The presence of multiple performance indicators with competing objectives needs to be taken into account for pipeline maintenance strategy. To address these challenges, this paper proposes an approach based on multi-objective maintenance optimization. The copula function is applied to characterize the correlation of failure modes (leakage and burst). With the aims to optimize availability and cost rate, a multi-objective maintenance optimization model is established, and it is solved with the non-dominated sorting genetic algorithm II (NSGA II). The results show that the Pareto frontier of multi-objective optimization can provide more feasible maintenance schemes. Moreover, the effects of major variables on the availability and cost rate are investigated. It is found that compared with other parameters, downtime cost has the greater impact on performance indicators. The proposed method can provide theoretical reference for pipeline integrity management, thereby ensuring that the pipeline is in a safe state during operation.

A scalable multi-objective maintenance optimization model for systems with multiple heterogeneous components and a finite lifespan

Delivering after-sales maintenance services is a challenging task for original equipment manufacturers who must tailor their offers to customers’ needs. To accommodate this challenge, we propose a multi-objective optimization model to derive optimal maintenance policies for systems with a large number of heterogeneous components over a finite lifespan. Based on the practical assumption of a fixed time interval between two consecutive scheduled downs, we develop a decomposition approach that enables the fast computation of the optimal policy per component and the optimal time interval between two consecutive scheduled visits. We also analyze the structural properties of the optimal policies for both age-based and condition-based maintenance and prove that they have a non-static control-limit structure. Using a set of computational experiments, we first investigate the computational tractability of our model for systems with an increasing number of components. Then, we apply our model to a real case study to demonstrate how it can be used to derive optimal maintenance policies tailored to different customer needs.

Opportunistic maintenance optimization of continuous process manufacturing systems considering imperfect maintenance with epistemic uncertainty

Due to the production process for continuous process manufacturing system (CPMS) cannot be stopped, the “opportunities” for maintenance can only occur within the specified time intervals. To improve the completion rate of production process, the focus of opportunistic maintenance for CPMS is whether the maintenance is to be performed at known time. Meanwhile, several opportunistic maintenance optimization models assumed imperfect maintenance to develop more reasonable maintenance plan. However, the parameters of imperfect maintenance cannot be accurately assessed (namely epistemic uncertainty) due to inadequate knowledge of maintenance and degradation mechanisms. This epistemic uncertainty was ignored in previous studies. Therefore, a novel opportunistic maintenance optimization model for CPMSs is proposed. The opportunity time window (OTW) concept is introduced to constrain the production-constrained maintenance opportunity. Three types of maintenance actions, including do nothing, perfect maintenance, and imperfect maintenance with epistemic uncertainty, are considered during the OTW to improve the production efficiency and performance of the manufacturing system. In the context of random and epistemic uncertainty, a stochastic fuzzy flow manufacturing network (SFFMN) is established to describe dynamic production processes and evaluate machine reliability. Moreover, a simulated annealing-based adaptive immune algorithm (SAAIA) with multiple immune operators is developed to address the opportunity maintenance optimization model of CPMSs. Finally, a case study of the hot rolling manufacturing system is provided to better understand the proposed method and demonstrate its effectiveness.