Optimal Maintenance Strategy Research Articles

Optimization of a preventive maintenance strategy for a product with limited repair times

This paper proposes a base warranty and replacement warranty strategy for repairable products. It should be emphasized that the product failure rate is low in the early stage of the base warranty. Therefore, in order to reduce the manufacturer’s maintenance cost, the manufacturer does not carry out preventive maintenance in the early stage of the base warranty, and carries out regular preventive maintenance in the later stage of the base warranty. At the same time, if the number of product failures in the base warranty exceeds the specified limit, the manufacturer must replace products for customers free of charge according to the warranty contract. After the product is replaced, if the number of product failures does not exceed the limit, the manufacturer will continue to provide customers with the remaining base warranty period of the original product, and the warranty period will continue to be extended for a period of time. By minimizing the expected cost rate, it is shown that the optimal maintenance policy for warranty products is unique. Finally, we give a numerical example and study the effects of periodic preventive maintenance and other relevant parameters on the optimal solution.

Risk-based approach to choosing the production asset management strategy for energy company

RELEVANCE: The possibility of a reasonable choice of an alternative strategy for the organization of maintenance and repair (M&R) of the power company's equipment is a guarantee of the successful implementation of its strategic priorities. The tasks in this direction are quite relevant.PURPOSE: To develop a unified methodology that, from the general standpoint of a risk-based approach, would allow comparing two alternative strategies for managing the assets of an energy company "by periodicity, operating time" and "by technical condition", according to a set of key criteria for the effectiveness of M&R.METHODS: When solving problems, methods of forming and adjusting schedules for repairs of electrical equipment, calculating reliability and probabilities of failure in the power supply system of consumers, taking into account its circuit features, assessing the technical condition of equipment according to non-destructive testing and diagnostics, comparing the costs of maintaining and restoring reliability and damages from its violations were used.RESULTS: A risk-oriented methodology has been developed and verified, which makes it possible to evaluate and select the optimal equipment maintenance strategy for the energy company according to uniform efficiency criteria. An algorithmic implementation of the developed methodology is obtained, which is the basis of a computing complex for choosing and making decisions. The verification of the methodology and algorithm is carried out on the example of a real object – a power supply system for oil production consumers using reliable operational and diagnostic information.CONCLUSION: The results obtained fully compensate for the lack of methodological possibilities in comparing two basic alternative strategies for electrical equipment maintenance based on a single risk-based approach. The developed methodology is a unified decision-making tool at the stage of alternative analysis. The illustration of the methodology by a real numerical example demonstrates the consistency of the solutions obtained with the results of expert assessments and operational experience.

Advanced Data Analytics for Prognostics and Health Management (PHM) in Industrial Engineering: A Comprehensive Review

Prognostics and Health Management (PHM) is a crucial aspect of industrial engineering, aiming to enhance equipment reliability, reduce downtime, and optimize maintenance strategies. Advanced data analytics plays a pivotal role in PHM, enabling the analysis of equipment condition and performance to predict failures and prescribe proactive maintenance actions. This review article provides a comprehensive overview of advanced data analytics techniques used in PHM, including machine learning, statistical analysis, and predictive modeling. The article also discusses the application of these techniques in various industrial sectors, highlighting their benefits and challenges. Furthermore, the review identifies current trends and future directions in the field of PHM, emphasizing the importance of integrating advanced data analytics for improved industrial engineering practices.

Optimization of Preventive Maintenance Strategies for Electrical Equipment on Offshore Oil Support Vessels Based on Predictive Maintenance Algorithms in an Intelligent Platform

Optimization of Preventive Maintenance Strategies for Electrical Equipment on Offshore Oil Support Vessels Based on Predictive Maintenance Algorithms in an Intelligent Platform

A data-driven methodology with a nonparametric reliability method for optimal condition-based maintenance strategies

A data-driven methodology with a nonparametric reliability method for optimal condition-based maintenance strategies

An optimal maintenance strategy for machining system considering production rates

In this paper, a maintenance strategy is developed to determine the optimal number of preventive maintenance actions to carry out over the finite operating time span H for a manufacturing system satisfying several demands. The system is composed of dry machining which produces two types of products (steel products and aluminum products). At any given time, the machine is able to produce one type of product, and then switches to another. This is done by modeling and minimizing the expected total maintenance cost considering the influence of production rates on the system degradation. A numerical example is presented to illustrate the use of the proposed approach and to discuss the obtained results.

Innovation and Application of Reliability-Centered Maintenance Technology for Pumped Storage Power Plant

With the increasing capacity and scale of pumped storage power plant, the maintenance management and resource input of system equipment are continuously increasing. Exploring and establishing a system engineering method that balances safe production and maintenance resource input has become an important issue that enterprises urgently need to solve. Based on the reliability-centered maintenance (RCM) technology, this paper combines the characteristics of pumped storage unit operation and maintenance management and years of maintenance practice experience to improve and innovate the RCM technology method, forming a “reliability-centered pumped storage unit maintenance strategy optimization technology method” applicable to pumped storage power generation units. This technology method has been applied on the system equipment of pumped storage power generation unit. It shows the application of this technology method has made significant contribution to optimizing equipment maintenance strategies, reducing maintenance workload and the overhaul time.

Joint optimization of two-dimensional warranty period and maintenance strategy considering availability and cost constraints

Abstract Warranty can improve customer satisfaction and increase product sales, but it will bring additional economic burden to manufacturers, so making reasonable warranty decisions is particularly important. The current research focuses more on the interests of manufacturers, while there is less attention paid to indicators that consumers are concerned about, such as system availability. To solve this problem, a joint optimization model of the two-dimensional warranty period and preventive maintenance (PM) strategy considering availability and cost constraints was established. Based on the failure dependence analysis of multi-component systems, the actual failure rate function is constructed by using the failure dependence coefficient matrix. Based on the comprehensive consideration of imperfect PM and minimum maintenance, the two-dimensional warranty cost model and system availability model are established, respectively. Aiming at maximum availability and considering the warranty cost budget constraint, a joint optimization model of the two-dimensional warranty period and PM strategy was built, and a model-solving algorithm combining grid search and binary search was introduced. The effectiveness of the model is verified by the case analysis, and the necessity of the PM strategy and considering failure dependence are reflected in the model comparative analysis and parameter sensitivity analysis. Finally, reasonable suggestions are put forward for manufacturers’ warranty decisions through the result analysis.

Sustainable Operation and Maintenance of Offshore Wind Farms Based on the Deep Wind Forecasting

Offshore wind farms are becoming a pivotal solution to address the increasing energy demand worldwide and reduce carbon emissions to achieve a sustainable energy sector. Considering the higher operational and maintenance cost of offshore wind farms, it is important to make a good maintenance plan to guarantee the system’s reliability and reduce the total cost related to maintenance activities at the same time. Because maintenance planning is a long-term decision problem and the wind force is random, long-term wind force prediction is needed to help managers evaluate the loss caused by maintenances to be executed in the future. However, long-term wind force prediction is naturally complicated, which is much harder than the short-term (e.g., day-ahead) prediction widely investigated in the literature. In order to overcome this difficulty, we design a deep learning framework combining variational mode decomposition, a convolution neural network, long short-term memory network, and full-connected network. Using the public data from the city of Leeds, the prediction accuracy of the above framework is validated by comparing it with other prediction techniques. Then, the predicted wind force is input into the established optimization model determining preventive maintenances during a predefined period. Because the uncertainty of wind force is replaced by the prediction value, the optimization model can be established as a mixed-integer linear programing model, which only contains limited variables and can be solved quickly. Lastly, an abundance of numerical experiments are conducted to validate the effectiveness of the proposed optimization model, based on which some managerial insights are provided to the managers of offshore wind farms about the optimal operations and maintenance strategy. The research outcome will greatly promote the development of the wind power industry in the future.

Modeling the Optimal Maintenance Strategy for Bridge Elements Based on Agent Sequential Decision Making

In addressing the issues of low efficiency in bridge maintenance decision making, the inaccurate estimation of maintenance costs, and the lack of specificity in decision making regarding maintenance measures for specific defects, this study utilizes data from regular bridge inspections. It employs a two-parameter Weibull distribution to model the duration variables of the states of bridge elements, thereby enabling the prediction of the duration time of bridge elements in various states. Referring to existing bridge maintenance and repair regulations, the estimation process of maintenance costs is streamlined. Taking into account the specific types and development state of bridge defects, as well as considering the adequacy of maintenance and the restorative effects of maintenance measures, an intelligent agent sequential decision-making model for bridge maintenance decisions is established. The model utilizes dynamic programming algorithms to determine the optimal maintenance and repair measures for elements in various states. The decision results are precise, all the way down to the specific bridge elements and maintenance measures for individual defects. In using the case of the regular inspection data of 222 bridges along a highway loop, this study further validates the effectiveness of the proposed research methods. By constructing an intelligent agent sequential decision-making model for bridge element maintenance, the optimal maintenance measures for 21 bridge elements in different states are obtained, thereby significantly enhancing the efficiency of actual bridge maintenance and the practicality of decision results.

Evolutionary Optimization of Convolutional Extreme Learning Machine for Remaining Useful Life Prediction

Remaining useful life (RUL) prediction is a key enabler for making optimal maintenance strategies. Data-driven approaches, especially employing neural networks (NNs) such as multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs), have gained increasing attention in the field of RUL prediction. Most of the past research has mainly focused on minimizing the RUL prediction error by training NNs with back-propagation (BP), which in general requires an extensive computational effort. However, in practice, such BP-based NNs (BPNNs) may not be affordable in industrial contexts that normally seek to save cost by minimizing access to expensive computing infrastructures. Driven by this motivation, here, we propose: (1) to use a very fast learning scheme called extreme learning machine (ELM) for training two different kinds of feed-forward neural networks (FFNNs), namely a single-layer feed-forward neural network (SL-FFNN) and a Convolutional ELM (CELM); and (2) to optimize the architecture of those networks by applying evolutionary computation. More specifically, we employ a multi-objective optimization (MOO) technique to search for the best network architectures in terms of trade-off between RUL prediction error and number of trainable parameters, the latter being correlated with computational effort. In our experiments, we test our methods on a widely used benchmark dataset, the C-MAPSS, on which we search such trade-off solutions. Compared to other methods based on BPNNs, our methods outperform a MLP and show a similar level of performance to a CNN in terms of prediction error, while using a much smaller (up to two orders of magnitude) number of trainable parameters.

Optimal maintenance strategy for large-scale production systems under maintenance time uncertainty

Optimal maintenance strategy for large-scale production systems under maintenance time uncertainty

Decision-making optimization model for the targeted sustainable maintenance of a complex road network

With the continuous expansion of highway construction scale, a complex road network can be divided into multiple subnetworks in accordance with any criteria, such as highway class, traffic volume, natural zoning, or administrative subdivision. To realize the targeted maintenance and local–whole optimization of a road network, this study proposes a new type of optimization model for road network maintenance decisions based on the idea of a bi-level programming model. The model fully considers the heterogeneity of a subnetwork, adopts different maintenance standards for targeted maintenance, establishes a whole network maintenance fund allocation model and a subnetwork unit maintenance decision-making (DM) model, and obtains the optimal maintenance scheme through the iterative calculation of a genetic algorithm. Finally, the model is applied to the maintenance DM of a highway network in Zhejiang Province and compared with the traditional DM model without subnetworks. Results show that the model developed in this study can better solve the maintenance DM problem of large-scale complex road networks and achieve the targeted maintenance scheme under limited maintenance funds. Hence, this model can help the sustainable development of road network maintenance.

Optimal external opportunistic maintenance for wind turbines considering wind speed

ABSTRACT A novel optimal opportunistic maintenance strategy for wind turbines considering wind speed as a stochastic process is proposed in this paper. Under this strategy, periodic preventive maintenance is conducted to reduce the probability of downtime due to failure, whereas external opportunities are leveraged to reduce the cost of preventive maintenance. This combined maintenance approach can also reduce costs associated with the wind turbine lifecycle. The formulated expected costs per unit time considered two scenarios, i.e. regular operation and energy generation interruption, to obtain the optimal solution via a genetic algorithm. Furthermore, we illustrated the economic advantages of the proposed strategy by comparing various maintenance strategies, as well as a sensitivity analysis to determine the effects of the different parameters in the proposed model. Experimental results demonstrate that the proposed opportunistic maintenance strategy is more cost-effective for wind turbines than comparable methods, with an optimal solution that varies according to variations in wind speed.

RAMP up: Risk Adapted Post-Autologous Transplant Maintenance Therapy in MRD Positive Myeloma Patients

Background. Post-autologous stem cell transplant (ASCT) maintenance therapy for patients with newly diagnosed multiple myeloma (MM) continues to evolve. Currently, single agent lenalidomide maintenance remains standard of care but outcomes for patients with high-risk cytogenetics are inferior to those with standard risk disease; optimal maintenance strategies for these patients need to be developed. Minimal residual disease (MRD) has proven to be a powerful prognostic factor for PFS and OS but is not yet used to guide treatment. Isatuximab is a cytolytic CD38-directed, immunoglobulin G1 (IgG1) chimeric monoclonal antibody FDA-approved for the treatment of relapsed or refractory MM that is overall well tolerated and efficacious when used in combination regimens. Our upcoming trial, RAMP UP (NCT05344833), investigates the safety and efficacy of isatuximab combined with lenalidomide as a maintenance regimen in patients who are MRD-positive after autologous transplant. Study Design and Methods. This prospective, multicenter single-arm phase 2 (Figure 1) trial will enroll patients that are MRD-positive (10 -5) by Adaptive next generation sequencing within 90 days (+/- 30 days) post-autologous transplant. We plan to enroll: R-ISS stage 1, 2 or 3; <2 lines of induction therapy prior to transplant; > PR per IMWG criteria post-transplant; and ECOG Performance Status <2. Patients will be treated with isatuximab (10 mg/kg weekly for cycle 1 and every other week thereafter) and lenalidomide (10 mg daily on days 1-21) on 28-day cycles for a total of 3 years. Patients will be monitored for disease response every 3 months and for marrow MRD every 12 months. The primary endpoint is the 1-year rate of CR/MRD negativity (10 -5); secondary endpoints include 1-year rate of CR/MRD negativity (10 -6), IMWG-defined response rates, 3-year overall CR/MRD-negativity, PFS, OS, treatment-related adverse events, and health related quality of life (HRQoL) measured by EORTC-QLQ-C30, EQ-5D-5L, EORTC QLQ-MY20. We propose enrollment of 50 patients to allow for approximately 10% dropout rate in order to have 43 patients analyzed for the primary endpoint; for 50 patients to be treated, we estimate that 75-100 patients may have to be enrolled. Correlative objectives include correlation of isatuximab pharmacokinetics and receptor occupancy with MRD-negative response and time to progression, characterization of differences in the BM and peripheral blood T, B, and myeloid cell compartments using cellular indexing of transcriptomes and epitopes (CITE-Seq) between responders and nonresponders, and concurrent assessment of other disease biomarkers, including peripheral blood circulating multiple myeloma cells (CELLSEARCH), with MRD testing. Discussion. Our study started June 2023. One patient has been enrolled, and two have signed informed consent for enrollment. Ultimately, our study aims to inform MRD risk-adapted approaches for maintenance therapy in myeloma.

A novel maintenance strategy for manufacturing system considering working schedule and imperfect maintenance

Condition-based maintenance (CBM) strategies that consider product quality lack a thorough analysis of the impact of manufacturing enterprise’s working schedule, which does not align with real-life production scenarios. To address this gap, this study proposes a novel CBM strategy model for manufacturing systems that takes into account working schedule to determine the optimal balance between maintenance and production while considering product quality. The maintenance set includes imperfect maintenance and perfect maintenance to capture real-life manufacturing scenarios. The model establishes an optimal maintenance strategy using a Markov decision process (MDP) framework. A numerical study is conducted based on internal information and data collected by sensors from a commercial vehicle manufacturing enterprise to demonstrate the effectiveness of the proposed strategy. We proposed a dual-value iteration algorithm to solve the MDP model. Finally, a comprehensive sensitivity analysis is performed to investigate the impact of cost-related parameters on the strategy.

A Systematic Review for Switchgear Asset Management in Power Grids: Condition Monitoring, Health Assessment, and Maintenance Strategy

Asset management process and techniques can improve the cost-efficiency, balance the cost and risk, and prolong the service life of the aging switchgears in power grids, which have become increasingly important for electric utilities. This paper provides an insight into the recent developments in switchgear asset management and explore future research stream. Accordingly, three directions: condition monitoring, health assessment, and maintenance strategy have been addressed. We first present switchgear condition monitoring indicators and condition evaluation methods utilizing these condition data. Subsequently, we explain health index methodologies to achieve switchgear health assessment and remaining useful life estimation. With these results, we then present the maintenance strategy and life cycle cost optimization methods to address cost-efficient decision making. Finally, the limitation of existing methods and future research trend are discussed. This paper covers various asset management domains, attempting to create a common understanding and fill the gaps among the academic, industry, and technology area.

Optimal maintenance strategy of wind turbine subassemblies to improve the overall availability

Improving wind turbine performance, operation, and efficiency requires evolving Operation and Maintenance (O&M) methods. Different models are required for O&M choices. These models offer a broad variety of scenarios and variables to reduce energy costs and enhance wind farm profitability. In this regard, this paper proposes a detailed approach for maintenance decisions to pick an optimum maintenance strategy (MST) for different subassemblies of wind turbines based on failure analysis. This approach is predicated mostly on a vast field database of failures and repairs of several subassemblies of wind turbines. The maintenance model is comprised of many stages, including the data preparation stage, the availability optimization stage, and the optimum MST selection step. Consequently, this model aids in determining the appropriate MST for all subassemblies of wind turbines to achieve the necessary degree of availability.

Impact of agile, condition-based maintenance strategy on cost efficiency of production systems

Maintenance plays an increasingly important role in the life of production companies, as professional maintenance is an important prerequisite for the reliable operation of resources. A well-chosen maintenance strategy can make a major contribution to increased efficiency of production processes. The main goal of this research is to propose a novel optimization approach to define optimal maintenance strategy that ensures the efficient operation of the production process while reducing maintenance costs. The developed optimization method is based on Howard’s policy iteration and describes the objective of the planning as a Markov decision process. The novelty and the scientific contribution of the presented study is the application of Howard’s policy iteration methodology in a Markov decision process for agile, condition-based maintenance strategy optimization. As the results of the numerical analysis of the scenarios shows, the implementation of an optimized maintenance strategy based on the proposed approach can significantly increase the maintenance efficiency of the production process. The main reason for this is that the level and type of maintenance is always implemented depending on the current state of the system components, which reduces both the maintenance cost and the losses due to production downtime.

Opportunistic maintenance strategy optimization considering imperfect maintenance under hybrid unit-level maintenance strategy

Opportunistic maintenance is a widely adopted strategy for maintaining multi-unit systems, which has garnered significant attention from researchers. However, the current opportunistic maintenance still suffers from certain limitations, such as single preventive maintenance strategy at unit-level and lack of flexibility in optimization model. In this paper, an optimization model for scheduled maintenance (SM) and condition-based maintenance (CBM) at the unit-level is presented, and the associated maintenance costs are analyzed. Subsequently, a preventive opportunistic maintenance strategy optimization model under hybrid unit-level maintenance strategies is established by considering imperfect preventive maintenance. An optimization algorithm based on Monte Carlo simulation is designed to solve the model. Finally, the opportunistic maintenance strategy of CNC gear grinding machine is developed. Comparing the opportunistic maintenance strategy given in this paper with other maintenance strategies, the results show that the maintenance strategy presented in this paper can significantly reduce the maintenance cost of the CNC grinding machine. The opportunistic maintenance strategy optimization method proposed in this paper can provide guidance for relevant enterprises to formulate maintenance strategies.