Preventive Maintenance Actions Research Articles

Joint optimization of price, warranty and service investment for capital-intensive equipment considering maintenance capacity limits

The insufficient maintenance capacity has recently brought challenges to original equipment manufacturers (OEMs) for capital-intensive equipment in the service for new products. Different from the existing studies of the price and warranty strategy on the premise of unlimited maintenance capacity, this paper considers the influence of limited maintenance capacity and investigates the joint optimization of capacity investment and marketing strategy. For a static/dynamic market, the profit models capturing the interaction among price, warranty length and improved maintenance capacity are developed under two warranty options (with and without preventive maintenance). The proposed models characterize the dynamic negative word-of-mouth effect, the penalty for unmet maintenance demand and the maintenance capacity investment. By maximizing the profit models, OEMs can determine the most profitable strategy to deal with maintenance capacity limits. Furthermore, a case study is conducted verifying the methodology effectiveness and providing managerial insights. The results reveal the differences in strategy design between the scenarios with and without capacity limits. Meanwhile, the conditions determining whether to adopt preventive maintenance actions in the warranty are given. Finally, the sensitivity analysis demonstrates the influence of price/warranty sensitivity, providing practical guidelines for the design of the most profitable strategy responding to different environments.

Deep Reinforcement Learning for Distributed Flow Shop Scheduling with Flexible Maintenance

A common situation arising in flow shops is that the job processing order must be the same on each machine; this is referred to as a permutation flow shop scheduling problem (PFSSP). Although many algorithms have been designed to solve PFSSPs, machine availability is typically ignored. Healthy machine conditions are essential for the production process, which can ensure productivity and quality; thus, machine deteriorating effects and periodic preventive maintenance (PM) activities are considered in this paper. Moreover, distributed production networks, which can manufacture products quickly, are of increasing interest to factories. To this end, this paper investigates an integrated optimization of the distributed PFSSP with flexible PM. With the introduction of machine maintenance constraints in multi-factory production scheduling, the complexity and computation time of solving the problem increases substantially in large-scale arithmetic cases. In order to solve it, a deep Q network-based solution framework is designed with a diminishing greedy rate in this paper. The proposed solution framework is compared to the DQN with fixed greedy rate, in addition to two well-known metaheuristic algorithms, including the genetic algorithm and the iterated greedy algorithm. Numerical studies show that the application of the proposed approach in the studied production-maintenance joint scheduling problem exhibits strong solution performance and generalization abilities. Moreover, a suitable maintenance interval is also obtained, in addition to some managerial insights.

Novel Cyclo-Nonstationary Indicators for Monitoring of Rotating Machinery Operating Under Speed and Load Varying Conditions

Abstract Condition monitoring arises as a valuable industrial process in order to assess the health of rotating machinery, providing early and accurate warning of potential failures and allowing for the planning and effective realization of preventative maintenance actions. Nowadays, machinery (gas turbines, wind turbines, etc.) manufacturers adopt new business models, providing not only the equipment itself but also additionally taking on responsibilities of condition monitoring, by embedding sensors and health monitoring systems within each unit and prompting maintenance actions when necessary. Among others, rolling element bearings are one of the most critical components in rotating machinery. In complex machines, the failure indications of an early bearing damage are weak compared to other sources of excitations (e.g., gears, shafts, rotors). Vibration analysis is most widely used and various methods have been proposed, including analysis in the time and frequency domain. In a number of applications, changes in the operating conditions (speed/load) influence the vibration sources and change the frequency and amplitude characteristics of the vibroacoustic signature, making them nonstationary. Under changing environments, where speed and load vary, the assumption of quasi-stationary is not appropriate and as a result, a number of time-frequency and time-order representations have been introduced, such as the Short Time Fourier Transform and the Wavelets. Recently, an emerging interest has been focused on modeling rotating machinery signals as cyclostationary, which is a particular class of nonstationary stochastic processes. The classical cyclostationary tools, such as the Cyclic Spectral Correlation Density (CSCD) and the Cyclic Modulation Spectrum (CMS), can be used in order to extract interesting information about the cyclic behavior of cyclostationary signals, only under the assumption that the speed of machinery is constant or nearly constant. Global diagnostic indicators have been proposed as a measure of cyclostationarity under steady operating conditions. In order to overcome this limitation, a generalization of both SCD and CMS functions has been proposed displaying cyclic Order versus Frequency as well as diagnostic indicators of cyclo-nonstationarity in order to cover the speed-varying operating conditions. The scope of this paper is to propose a novel approach for the analysis of cyclo-nonstationary signals based on the generalization of indicators of cyclo-nonstationarity in order to cover the simultaneous and independently varying speed and load operating conditions. The effectiveness of the approach is evaluated on simulated and real signals captured on a dedicated test rig.

Optimization of Preventive Maintenance and Replacement Strategies for Nonrenewing Two-Dimensional Warranty Products Experiencing Degradation and External Shocks

“Vehicle damage insurance” in China, “Protection Plus Mobile Elite” launched by Samsung, “iPhone Apple Care +” offered by Apple, and so on are special warranty services aiming at external shocks. These warranty terms, named accident insurance, exist widely in the marketplace. Considering the effect of external shocks on degradation, a two-dimensional preventive maintenance and replacement strategy for products, sold with a nonrenewing and two-dimensional rectangle warranty service, is proposed in this paper. Under this strategy, preventive maintenance actions are scheduled based on units of age or usage, which occurs first. There is a reduction in the intensity function after a preventive maintenance action. Each shock before the Nth shock causes a failure of the product or an increase in product failure rate. The product is replaced by a new one on the Nth shock if it survives the N − 1 shocks. From the view of manufacturers, the mean warranty servicing cost over the whole warranty region is obtained by using the renewal theory. Based on direct numerical Riemann–Stieltjes integration, an approximation algorithm of the cost is also given. The mean cost is minimized by the optimization of preventive maintenance interval and the number of shocks N. A numerical example is given to illustrate the feasibility of the proposed strategy. The effects of maintenance cost, the arrival rate of the shocks, and other model parameters on the optimal strategy are also investigated numerically.

ADVANCED APPROACH IN SOLAR PV PLANT PROTECTION SYSTEM

Solar Photovoltaic (PV) technology has become one of the most promising and reliable source of renewable energy. The favorable conditions like decreasing prices of PV system, increased panel size and enhanced efficiency improved the solar PV power plants installations. PV Panel and Inverter are vital equipment’s in functioning of solar PV system. As the solar power plant has various power electronics and other electrical components, there might be chance for power interruptions due to improper functioning of switch gear. Ensuring protection measures of the solar power plant plays a key role in smooth functioning of the system. The main objective of the paper is to explain various protection issues faced in solar roof top system and the necessary measures taken for resolving the issues with root cause analysis. This technical paper also showcases various preventive maintenance activities followed in the solar PV plant

A dynamic “predict, then optimize” preventive maintenance approach using operational intervention data

We investigate whether historical machine failures and maintenance records may be used to derive future machine failure estimates and, in turn, prescribe advancements of scheduled preventive maintenance interventions. We model the problem using a sequential predict, then optimize approach. In our prescriptive optimization model, we use a finite horizon Markov decision process with a variable order Markov chain, in which the chain length varies depending on the time since the last preventive maintenance action was performed. The model therefore captures the dependency of a machine’s failures on both recent failures as well as preventive maintenance actions, via our prediction model. We validate our model using an original equipment manufacturer data set and obtain policies that prescribe when to deviate from the planned periodic maintenance schedule. To improve our predictions for machine failure behavior with limited to no past data, we pool our data set over different machine classes by means of a Poisson generalized linear model. We find that our policies can supplement and improve on those currently applied by 5%, on average.

Optimal maintenance policy for equipment leased with base and extended warranty

ABSTRACT In this paper, we consider an equipment leased with a warranty contract with the possibility to extend the warranty at a given price that depends on its duration. During the warranty period, the lessor (who possesses the equipment) performs and pays for repairs at failure and for preventive maintenance (PM) actions whenever the equipment reliability reaches a specific limit. After the warranty ends, repairs and PM actions are still performed by the lessor, but they are billed to the lessee (who rents the equipment). Furthermore, in case the total average equipment downtime due to repair and PM actions during the lease period surpasses a certain pre-specified limit agreed on in the lease contract, a penalty is supported by the lessor. A mathematical model and numerical procedure are proposed to determine the PM intervals durations that maximise the lessor’s expected total profit during the lease period. The optimal solution is obtained by determining the combination between the optimal equipment reliability threshold that triggers a PM action and the optimal extended warranty period. A numerical example is given to illustrate the use of the proposed model and a sensitivity analysis is performed.

Solving a bi-objective flexible flow shop problem with transporter preventive maintenance planning and limited buffers by NSGA-II and MOPSO

This study deals with a bi-objective flexible flow shop problem (BOFFSP) with transportation times and preventive maintenance (PM) on transporters via considering limited buffers. The PM actions on transporters are a missing part of the literature of the flexible flow shop problem (FFSP) which before the breakdown occurs, each transporter at each stage is stopped and the PM action is performed on it. The capacity of each intermediate buffer is limited and each job has to wait in the intermediate buffers. By including all these features in the proposed BOFFSP, not only processing times affect the objective functions, but also, the transportation times of jobs, the waiting time of jobs in the intermediate buffers, and availability of transporters in the system are considered in the model and make it a sample of a real-world FFSP. The presented BOFFSP has simultaneously minimized the total completion time and the unavailability of the system. As the problem is NP-hard, a non-dominated sorting genetic algorithm II (NSGA-II) and a multi-objective particle swarm optimization (MOPSO) is proposed to solve the model for large size problems. The experimental results show that the proposed MOPSO relatively outperforms the presented NSGA-II in terms of five different metrics considered to compare their performance. Afterwards, two one-way ANOVA tests are performed. It can be observed MOPSO achieves relatively better results than NSGA-II. Finally, sensitivity analysis is conducted to investigate the sensitivity of the objective functions to the number of jobs and their transportation time at each stage.

Mixed Integer Linear Programming formulations for the permutation flow shop scheduling problem with preventive maintenance activities

Mixed Integer Linear Programming formulations for the permutation flow shop scheduling problem with preventive maintenance activities

Joint preventive maintenance and extended warranty strategy for leased unreliable equipment submitted to imperfect repair at failure

This paper examines the maintenance policy and the length of the extended warranty for leased equipment from the lessor's perspective. When the equipment fails within the base and extended warranty periods, imperfect repairs are carried out with a given efficiency following a decreasing quasi-renewal process. To reduce the number of failures, the lessor performs imperfect periodic preventive maintenance (PM) actions restoring the equipment to the state ‘as good as new’ with probability p and keeping it at state ‘as bad as old’ with probability q. A mathematical model and a numerical algorithm are developed to jointly determine the optimal PM period T* and the optimal extended warranty period we* maximizing the lessor's expected total profit over a finite time horizon. A numerical example is presented to illustrate the use of the developed model.

Improving the availability of Australian hospitals’ critical medical devices

Maintenance of Australian hospitals’ Critical Medical Devices (CMDs) can be somewhat more demanding than conventional assets from other industries. This is primarily driven by the requirement for CMDs to operate with exceptional levels of reliability. This study proposes a combined Reliability Centred Maintenance (RCM) and prioritisation maintenance strategy with the objective of improving the availability of CMDs. Reliability functions were used in this study as CMDs exhibit Weibull failure distributions identical to general products. The Analytical Hierarchy Process (AHP) was chosen as the maintenance prioritisation strategy because of its ability to analyse complex decisions using subjective and objective criteria. An online survey targeted at hospital managers and Biomedical Engineering Technicians (BMET) was developed to determine the priority of Preventive Maintenance (PM) activities for certain CMD and propose a range of optimal PM intervals for a variety of reliabilities. Results from the prioritisation study have shown that the external environmental effects from COVID-19 had significantly increased the priority for PM of ventilators over other CMDs. Ventilator manufacturers recommend conducting PM once over 12 months or every 5000 hours of operation. The proposed study has revealed that the PM of ventilators can be scheduled once every 14 months to obtain reliabilities close to 100%. Similar outcomes were observed for other CMDs as well. The aftermath of this study will ensure better availability of CMDs, as well as will help to alleviate complications with PM scheduling for managers and BMET departments.

Maintenance Digital Twin using vibration data

Maintenance represents a critical aspect of manufacturing systems. Its optimization may lead companies to save costs related to production losses and can extend the whole lifecycle of assets or components. This paper aims at proposing a methodology for evaluating the behavior of systems for maintenance purpose by means of analysis carried out on real vibration data collected in the work environment. To this purpose, a digital twin approach has been developed and the statistical method of the control charts has been integrated to conduct the analysis about the vibration data. The methodology has been applied to a real case study in order to analyze the behavior of an electric motor used in the industrial sector and the results show that the method is effective in predicting possible failures that can lead to apply preventive maintenance actions.

Integrated stochastic bicriteria flow shop scheduling problem with preventive maintenance

In this paper, the concept of flexible and multiple preventive maintenance activities is introduced by reformulating classical bicriteria permutation flow shop scheduling problem into stochastic scheduling with objective to minimise system utilisation time with minimum makespan. The mathematical model is formulated to handle the uncertainties in job processing time and the time interval for machine maintenance. The problem of stochastic flow shop scheduling environment with maintenance activities, is NP-hard. Therefore, the advanced metaheuristic is implemented to solve large scale instances of referred problem. Extensive computational analysis is carried out to depict the superiority of proposed metaheuristic in terms of effectiveness and efficacy.

ANALISIS INTERVAL PEMELIHARAAN KOMPONEN KRITIS UNIT FUEL CONVEYOR DENGAN PENDEKATAN RELIABILITY CENTERED MAINTENANCE (RCM

The scheduling of the machine maintenance system is a system that can assist companies in preventing machine damage which results in disrupted production processes. Corrective treatment methods have not been able to guarantee a smooth production process. This research will plan preventive maintenance activities to increase the reliability of production machines using the Reliability Centered Maintenance (RCM) approach. The result shows the highest downtime was boiler station with a percentage of 22.25%. The machine that works at the boiler station which has the highest level of damage was the fuel conveyor 2 with a percentage of 35.10%. The critical components which are the root causes of the highest damage problems in the fuel conveyor 2 machine were electromotor, chain coupling, and gearbox. In the electromotor, chain coupling, and gearbox components, preventive maintenance scheduling based on the results of each simulation were when t = 158, t = 190, and t = 67, respectively. The results of critical component maintenance scheduling indicated the achievement of the reliability value from before. After doing preventive maintenance, the reliability value of each component increased by 12%, 32%, and 8%, respectively. The frequency of periodic inspection every month on electromotor, chain coupling, and gearbox components were at least 4 times, 3 times, and 10 times, respectively. Keywords: downtime, maintenance, preventive maintenance. reliability, scheduling

Asset/mechanical integrity: A PSM element that still bedevils

AbstractSince the original version of this paper was published at the CCPS conference in 2006, the quality and health of asset integrity/mechanical integrity (AI/MI) programs in the process safety community have improved. However, it continues to be a difficult element to develop and implement. In many respects, it is still the “last frontier” of process safety and has been the last element to be fully addressed in the PSM community. This is not to say that inspection, testing, and preventive maintenance and other related activities that are part of AI/MI programs do not exist at facilities with process safety programs. Preventive and predictive maintenance programs have existed in the chemical/process industry for many years. What has been lacking in some cases are complete integrated AI/MI management system programs that address all of the subelements of AI/MI. There are several reasons for this continuing situation: Understanding the requirements. Which RAGAGEPs are relevant? Common difficulties with mechanical integrity. The impacts of process safety culture.

Deep multi-agent reinforcement learning for multi-level preventive maintenance in manufacturing systems

Designing preventive maintenance (PM) policies that ensure smooth and efficient production for large-scale manufacturing systems is non-trivial. Recent model-free reinforcement learning (RL) methods shed lights on how to cope with the non-linearity and stochasticity in such complex systems. However, the action space explosion impedes RL-based PM policies to be generalized to real applications. In order to obtain cost efficient PM policies for a serial production line that has multiple levels of PM actions, a novel multi-agent modeling is adopted to support adaptive learning by modeling each machine as cooperative agent. The evaluation of system-level production loss is leveraged to construct the reward function. An adaptive learning framework based on value-decomposition multi-agent actor–critic algorithm is utilized to obtain PM policies. In simulation study, the proposed framework demonstrates its effectiveness by leading other baselines on a comprehensive set of metrics whereas the centralized RL-based methods struggles to converge to stable policies. Our analysis further demonstrates that our multi-agent reinforcement learning based method learns effective PM policies without any knowledge about the environment and maintenance strategies.

A two-stage assembly flow-shop scheduling problem with bi-level products structure and machines’ availability constraints

ABSTRACT This paper incorporates the preventive maintenance activities into the two-stage assembly flow-shop scheduling problem, which has m machines at the production stage and an assembly machine at the second one. In this paper, three maintenance policies are employed based on the maximization of machine’s reliability and availability. This problem is NP-hard. So, two hybrid optimization methods, namely variable neighborhood search together with simulated annealing algorithm, and variable neighborhood search along with tabu search algorithm, are used to find the proper job sequencing. Statistical methods are conducted based on the hypothetical testing and analysis of variance to determine the better solution method and sensitivity analysis. Also, the performances of the presented algorithms on the problems of different sizes are analyzed. Results have shown that variable neighborhood search with simulated annealing outperforms another algorithm in the quality of solutions and computational time.

An Intelligent Preventive Maintenance Method Based on Reinforcement Learning for Battery Energy Storage Systems

Preventive maintenance (PM) activities in battery energy storage systems (BESSs) aim to achieve a better status in long-term operation. In this article, we develop a reinforcement learning-based PM method for the optimal PM management of BESSs equipped with prognostics and health management capabilities. A multilevel PM framework is established to generate a PM action strategy considering costs, capacity, and reliability simultaneously. Finite costs are the constraints, and reliability is the objective according to capacity degradation, respectively. The proposed PM agent with an integrated Monte Carlo tree search and a deep neural network (DNN) utilizes the state-of-health information of large-scale batteries in the BESS and selects optimal maintenance actions. The DNN is used as the state-action value function to extend the ability to address PM problems with large state-action spaces. The case of a BESS with 9 × 12 × 4 batteries in a fleet is simulated via Python. The results show that the PM agent can achieve efficient and steady decision-making proficiency in BESS PM management.

A condition-based maintenance policy for multi-component systems subject to stochastic and economic dependencies

Condition-based maintenance (CBM) optimization utilizing prognostic information and methods for complex systems has attracted increasing attention. This paper presents a bi-level approach to optimize a CBM policy for multi-component systems subject to stochastic and economic dependencies. The objective of the decision rule at the system level is to address if preventive and/or corrective maintenance actions are necessary regarding the predictive reliability of the system. At the component level, the aim is to identify the optimal group of components to be preventively maintained when maintenance is triggered due to the decision made at the system level. A maintenance efficacy indicator is introduced to prioritize components to be maintained by taking into account both the resulting reliability improvement quantity and the maintenance cost incurred. The optimal inter-inspection interval, the thresholds of system and component conditional reliability for triggering maintenance are jointly determined for minimization of the long-run average cost rate. A numerical study and sensitivity analysis on a 2oo3:G system are carried out to validate the performance of the proposed maintenance policy. Compared to another opportunistic maintenance policy without considering the system health condition, the proposed CBM policy leads to more cost gain and effectiveness in the maintenance decision-making.

Optimizing imperfect preventive maintenance in multi-component repairable systems under [formula omitted]-dependent competing risks

Existing maintenance optimization models for single-component repairable systems are extensively studied. However, maintenance optimization in multicomponent reparable systems (MCRS) is still a challenging problem, especially when dealing with stochastic dependent (s-dependent) competing risks between components. This paper develops a novel reliability-centered maintenance optimization model for MCRS operating under s-dependent competing risks. The s-dependency is captured by the joint reliability function constructed using Copula method and unknown parameters are estimated by maximum likelihood estimations (MLE). Maintenance strategies are carried out both at components and system levels. At components level, a preventive maintenance (PM) is performed whenever the reliability of the MCRS reaches a given threshold. PM actions are imperfect and modeled using the hybrid hazard rate approach. At system level, the whole system is preventively replaced after a certain number of PM cycles. The objective of the proposed maintenance strategies is to determine the optimal reliability threshold together with the optimal number of PM cycles that minimize the total expected maintenance cost rate in the infinite time horizon. The optimality conditions of the resulting maintenance optimization problem are formally discussed via two propositions. A case study that investigates a ball screw mechanism with multiple components is provided to validate the proposed approaches.