Condition-based Preventive Maintenance Research Articles

Knowledge-based system and expectation-maximization to discovering causes of imperfect labels in vehicular networks clustering

This paper focuses on the development of a knowledge-based system for automatically diagnosing issues in Vehicular ad hoc networks (VANETs). VANETs enable communication between vehicles and infrastructure, enhancing road safety and efficiency through timely information exchange. The proposed system aims to efficiently maintain and ensure the continuity of network service by leveraging innovative pattern recognition methods tailored to VANETs. The automatic diagnosis problem in VANETs involves estimating the operating class of network components based on sensor observations. This entails associating sensor measurements with specific operating modes. By implementing condition-based preventive maintenance procedures, potential component failures can be detected early, mitigating network disruptions. Various approaches, such as expert systems, fault trees, network state models, and statistical learning through pattern recognition, can be employed to address this problem. This paper primarily focuses on the statistical learning approach, where a classification or regression function is learned from a set of examples to assign operation modes to new measurements. It discusses relevant metrics and preprocessing techniques to simplify the decision-making process. The diagnostic system's results are determined based on the formulation of the classification or regression problem. The learning base is constructed, and an appropriate classification method is selected to develop and validate the automatic diagnosis system. While non-parametric models like support vector machines are commonly used, this article emphasizes the significance of considering assumptions and leveraging additional information to enhance performance. It proposes a more specific formalization of the problem, integrating the unique characteristics of VANETs. The contributions of this article revolve around the theory of belief functions, a generative approach, and the utilization of parametric models defined using graphical models. Experimental studies conducted on artificial datasets have demonstrated the benefits of the semi-supervised approach within the context of VANET networks.

Advanced diagnostic techniques for turbo compressors: A spectral analysis approach for preventive maintenance

This paper introduces an innovative spectral analysis control approach aimed at monitoring and diagnosing machine malfunctions to prevent potential failures. The research was conducted on a critical machine in a major industrial enterprise. The proposed method involves the use of a new indicator, called Overall Level (OL), that evaluates the machine’s condition before any operation. This study showcases practical methodologies for transitioning from time-based maintenance to predictive strategies, furnishing actionable insights into machine condition. This yields tangible advantages for the industry in terms of optimizing maintenance practices and enhancing asset productivity. Additionally, various methods, including vibration analysis, performance monitoring, and data analysis, are employed to identify the causes of issues and recommend solutions to enhance the reliability of the turbo compressor. The results provide a clear representation of the machine’s vibration state for diagnostic purposes. This noteworthy intervention underscores the potential of incorporating the measured and calculated values of the OL indicator across three specifically chosen frequency bands. To achieve this objective, the average value is employed as an indicator, contributing to the enhancement of reliability and longevity of critical industrial machinery. In this context, the novelty of the findings resides in the advanced diagnostic capabilities of the turbocompressor, thereby augmenting the efficacy of condition-based preventive maintenance for the BP 103 J turbine. The ultimate goal is to extend the equipment’s lifespan, improve the efficiency of the rotating machinery fleet, reduce maintenance costs, and enhance parameters such as availability and reliability through the support of an electronic maintenance system.

Robust job shop scheduling with machine unavailability due to random breakdowns and condition-based maintenance

This paper presents a novel solution approach for a variant of the job shop scheduling problem with machine unavailability due to both condition-based preventive maintenance and corrective maintenance following random breakdowns. We first provide an exact mathematical formulation of the problem under simplifying assumptions, namely that the number of breakdowns for each job position on each machine is known, the degradation rates are fixed, and the preventive and corrective maintenance durations are deterministic parameters. Moreover, to handle the more realistic case of stochastic machine degradation, random breakdowns, and uncertain maintenance durations, a simulation-optimisation algorithm is proposed. The real makespan function is first approximated using multiple surrogate measures, which are optimised through independent genetic algorithms. Then, the fittest solutions obtained from these surrogate measures are simulated, and the best among them is added to an elite list, which is included in the genetic algorithms' populations for the next iteration. Schedule robustness is ensured by using an objective function that consists of the weighted average of the expected makespan and its 90th percentile. Furthermore, to reduce the likelihood of falling into a local optimum, a stopping criterion based on simulated annealing is implemented. Numerical experimentation on extended benchmark instances confirmed the validity of the mathematical formulation and the favourable performance of the proposed simulation-optimisation algorithm in terms of computational time and solution quality.

Integrated optimization of condition-based preventive maintenance and production rescheduling with multi-phase processing speed selection and old machine scrap

With the usage and aging of machine, condition-based preventive maintenance (CBPM) and old machine scrap are two common phenomena in the actual production, and the latter may lead to the original production-maintenance planning no longer available. Under this context, this paper addresses an integrated optimization problem of CBPM and production rescheduling with multi-phase processing speed selection and old machine scrap. More precisely, (1) a CBPM policy with sixteen inspection strategies and multi-phase processing speed selection is proposed to find some selectable maintenance plans for each machine; (2) a hybrid rescheduling strategy (HRS) is designed for responding to the dynamic event, and a rescheduling strategy is adaptively selected according to the average utilization rate (A1) of idle time of existing machines; and (3) an adaptive clustering-based bi-population co-evolutionary algorithm (ACBCA) is developed to solve the studied problem. In the numerical simulation, Taguchi method is first employed to find the optimal parameter setting for the proposed ACBCA. Second, the effect of predefined threshold of A1 is analyzed, and the optimal value is 0.3. Next, the superiority and competitiveness of the proposed ACBCA, CBPM policy and HRS are all demonstrated by comparing with other algorithms, CBPM policies and rescheduling strategies, respectively.

Maintenance policy optimization for buffered serial systems considering energy-saving based on dual time windows

This paper proposes a novel optimal maintenance policy considering energy-saving based on dual time windows is proposed for a serial production system with limited buffering. The machines suffer from degradation, and the degradation process obeys the Gamma random process. Based on the dual time windows, condition-based preventive maintenance and opportunistic maintenance are activated: when a machine reaches a set state (i.e., threshold deterioration state), the preventive maintenance action is taken, and the time of preventive maintenance performed is determined by the time window w; meanwhile, the time window W is used to determine whether the other machines need opportunity maintenance. To reduce energy consumption, and increase the proportion of effective energy in the manufacturing process, the energy-saving time window is used to find the energy-saving opportunities for the system. The impact of different maintenance thresholds and dual time windows on the maintenance cost per effective product is discussed through Monte Carlo simulation. A practical example of an automotive manufacturing system is provided, and comparative analyses with other maintenance policies are used to illustrate the superiority of the proposed policy in energy saving, cost reduction, and quality improvement.

General Independent Competing Risks for Maintenance Analysis

Abstract Repairable systems are submitted to corrective maintenance and condition-based preventive maintenance actions. Condition-based preventive maintenance occurs at times which are determined according to the results of inspections and degradation or operation controls. The generalization of the models suggested makes it possible to integrate the dependence between corrective and preventive maintenances. In order to take into account this dependency and the possibility of imperfect maintenances, generalized competing risks models have been presented in Doyen and Gaudoin (2006). In this study, we revise the general case in which the potential times to next corrective and preventive maintenance are independent conditionally to the past of the maintenance process. We address the identifiability issue and we find a result similar to that of Zhou, Lu, Shi and Cheng (2018) for usual competing risks. We propose realistic models with exponential risks and derive their likelihood functions.

Additive manufacturing process design for complex aircraft components

The process of metal additive manufacturing (AM) is now widely used in fabricating complex parts in today’s industry. The scope of this paper is to redesign a manufacturing process for complex aircraft components using wing ribs as example by considering embedded Internet of Things (IoT) sensory capability that can be used in an Industry 4.0 ecosystem for moving away from a condition-based preventive maintenance system to a data-driven predictive maintenance-based system. This work is based on a previous study that considered the part design stage which deals with finding the best design solution for a single part. Considering a wing rib geometry of 3-mm web thickness with 6-mm upper and lower caps, the manufacturing process is designed and assessed using the Simufact Additive™ software. The use of AM when embedding IoT sensors allows more flexibility without compromising the structural integrity of parts, as well as the advantage of design freedom and limited cost when modifying geometries. The outcomes show that the manufacturing process depends strongly on hot isostatic pressing (HIP) for the wing rib, but for the sensory covers it presented no significant improvement. The results also show that the support optimisation can lead to an important reduction of mass and volume as well as an improvement of the structural performance.

Analysis of a production line subject to degradation and preventive maintenance

This paper considers a continuous flow manufacturing system with two machines subjected to condition-based preventive maintenance, and separated by an intermediate buffer of finite capacity. Each machine can degrade into several discrete states characterized by different degradation levels and performance parameters, ranging from perfect functioning to complete failure. Unlike the existing literature, the proposed approach considers various side effect costs, including the cost related to quality deterioration. A methodology is developed to describe the degradation stochastic process, and to analyze the complex trade-off between the condition-based preventive maintenance and the buffer capacity. The obtained results show the importance of considering quality-related and other possible costs when selecting preventive maintenance policy to optimize the performance of the manufacturing system. It is also shown that the selection of preventive maintenance actions should be considered from the view of the whole system, rather than individual machines. The optimal solution depends on the different degradation levels of the upstream and downstream machines.

A hybrid multi-objective evolutionary algorithm for solving an adaptive flexible job-shop rescheduling problem with real-time order acceptance and condition-based preventive maintenance

Production scheduling and maintenance planning are two of the most important tasks in the modern manufacturing workshop. Meanwhile, due to the dynamic order arrival and real-time machine monitoring information updating, the integrated optimization of them becoming more complex and meaningful. Therefore, this study intends to address an adaptive flexible job-shop rescheduling problem with real-time order acceptance (ROA) and condition-based preventive maintenance (CBPM). More precisely, the main innovative works are described as follows: (1) a CBPM policy with both imperfect preventive maintenance (PM) and four inspection strategies is designed to find the optimal maintenance planning for each production machine; (2) a multi-objective optimization model is developed for the concerned problem; and (3) a hybrid multi-objective evolutionary algorithm (HMOEA) with hybrid initialization method, hybrid local search operators and adaptive rescheduling strategies is proposed. In the numerical simulation, the performance and competitiveness of the proposed CBPM policy are first demonstrated by comparing with other maintenance policies. Second, the effectiveness and superiority of parameter setting, order sorting rules, improved operators and overall performance of the proposed algorithm are verified by internal analysis of the algorithm. Third, an adaptive rescheduling strategy pool is constructed by running three rescheduling strategies on all rescheduling scenarios. Finally, a comprehensive sensitivity analysis is performed to illustrate the impact of several critical parameters on the adaptive rescheduling problem, and the results and comparisons show that the proposed HMOEA algorithm and order acceptance strategy have good robustness in most parameters.

A Hybrid Method to Predict the Remaining Useful Life of Scroll Wheel of Control Rod Drive Mechanism

As one of the rotating components in the reluctance motor type control rod drive mechanism (CRDM), the life of the scroll wheel is closely related to the service life of the CRDM. In addition, the prediction of the remaining useful life of the scroll wheel helps to optimize the maintenance process of the CRDM. This paper proposes a hybrid method to predict its remaining useful life when the available degradation data are rare and the failure threshold cannot be accurately defined. First, the particle filtering algorithm, whose state transfer equation is established on the segmental damage physical model, is used to predict the degradation state of the scroll wheel. Second, the proportional hazard model for the relationship between the scroll wheel damage characteristics and reliability model is established to predict the remaining useful life of it. The proposed method focuses on the establishment of segmental damage physical model and the clustering analysis of damage characteristics extracted from vibration signals, which can be used to predict the remaining useful life of the scroll wheel. In addition, the results provide an opportunity for the condition-based preventive maintenance of the CRDM.

A Review of In-Service Coating Health Monitoring Technologies: Towards “Smart” Neural-Like Networks for Condition-Based Preventive Maintenance

In line with the recent industrial trends of hyperconnectivity, 5G technology deployment, the Internet of Things (IoT) and Industry 4.0, the ultimate goal of corrosion prevention is the invention of smart coatings that are able to assess their own condition, predict the onset of corrosion and alert users just before it happens. It is of particular interest to tackle corrosion that occurs in non-accessible areas where human inspectors or handheld devices are useless. To accomplish this, a variety of technologies that are embedded or could potentially be embedded into the coatings are being developed to monitor coating condition, which are based, for instance, on the evolution of electrochemical or mechanical properties over time. For these technologies to be fully embedded into the coatings and work remotely, solutions are needed for connectivity and power supply. A paradigm shift from routine prescheduled maintenance to condition-based preventive maintenance could then become a reality. In this work, the technologies that enable the in-service monitoring of organic anticorrosion coatings were compiled. Soon, some of them could be integrated into the sensing elements of autonomous, connected neural-like networks that are capable of remotely assessing the condition of the anticorrosion protection of future infrastructures.

Online-monitoring of motor operated valves

Abstract Traditionally, evaluating the running behaviour of motor operated valves (MOV) is based upon a non-continuous and demand oriented method. Gundremmingen Nuclear Power Plants has improved this strategy over the last 3 years. At MOVs within the safety system, diagnostics modules were installed for an online monitoring of active power during every run on demand. In the near future, functionality will be further enhanced in order to increase the particular knowledge, as a basis for both a safety oriented, but optimised, condition-based preventive maintenance approach and a plant life management strategy. Furthermore, during spring outage of unit B in 2002, a benchmark was implemented at four MOVs, which includes both comparison between two different kinds of power monitoring as well as active control of one of the systems.

Condition-based Maintenance Optimization of Degradable Systems

This paper develops a mathematical model for condition-based maintenance optimization of multi-state systems. The majority of the existing literature on maintenance optimization assume that there is no additional cost incurred because of side effects of equipment degradation. Nevertheless, as the operating cost increases with equipment age and degradation, it is important to consider the degradation side effects in the maintenance decision-making process. An important feature of the proposed model lies in the fact that it incorporates side effect of degradation process into condition-based preventive maintenance optimization. We develop a continuous-time discrete-state Markov chain model describing the deterioration stochastic process of a single component. The component is modeled as a multi-state system, where each discrete state is characterized by a degradation level. Numerical examples show the importance of considering such side effect costs when optimizing the choice of maintenance policy. The proposed model is extended to deal with multi-state series systems. Using an example of a series system with two components, it is shown that preventive maintenance and side effect costs should not be optimized for each component individually, but from the perspective of the series system as a whole.

Multiobjective Multistate System Preventive Maintenance Model with Human Reliability

Modern equipment is designed to operate under deteriorating performance conditions resulting from internal ageing and/or external environmental impacts influencing downstream maintenance. This study focuses on the development of a multistate system (MSS) that considers a human reliability factor associated with maintenance personnel—a condition-based multiobjective MSS preventive maintenance model (MSSPMM). The study assumes that no more than one maintenance activity is performed to achieve the most appropriate preventive maintenance (PM) strategy and easy implementation and to reduce maintenance error due to human reliability. The MSS performance based on mean system unavailability and total maintenance cost is evaluated using a stochastic model approach, and then, the MSSPMM is used for optimisation. A customised version of the nondominated sorting genetic algorithm III is employed to ensure efficient solution of the PM model with human reliability—which is considered a constrained multiobjective combinatorial optimisation problem. The optimised solutions are determined from the nondominated Pareto frontier comprising the diversified PM alternatives. A helicopter power transmission system is used as an example to illustrate the efficacy and applicability of the proposed approach through sensitivity analyses with relevant parameters.

Modeling the effects of dependence between competing failure processes on the condition-based preventive maintenance policy

This paper explores how the dependence between competing failure processes affects the condition-based preventive maintenance policy. The exposed failures caused by degradation and random shock are explicitly modeled respectively through two stochastic processes, i.e. Gamma process and compound Poisson process. Condition-based inspections are scheduled by introducing a convex function describing the relationship between degradation level and inspection interval. The preventive maintenance policy is planned to improve the operation efficiency which is adversely affected by the existing failures. The effect of failure dependence on the condition-based maintenance is analyzed through the preventive maintenance threshold of which initial value is fixed and is weaken by the following arrived shocks then. Imperfect maintenance effect is also considered to describe the irreversible aging process. Monte Carlo simulation technique and genetic algorithm are both employed to obtain the optimal parameters which determine the frequencies of inspection and maintenance. An illustrate example of a gearbox in the wind power industry is studied to demonstrate how the proposed maintenance policy balances the conflicting objectives in engineering practice.

Integrated scheduling and flexible maintenance in deteriorating multi-state single machine system using a reinforcement learning approach

This paper studies an integrated optimization problem of production scheduling and flexible preventive maintenance (PM) in a multi-state single machine system with deteriorating effects. A flexible PM strategy is proposed to proactively cope with machine failures while ensuring relatively regular PM intervals, which is composed of time-based PM (TBPM) and condition-based PM (CBPM). TBPM is conducted within every flexible time window and CBPM is implemented immediately after the most deteriorated yet still functional state. An illustrative case is presented using the enumeration approach to demonstrate the integration of production scheduling and machine maintenance. Then, Q-learning-based solution framework (QLSF) is further designed with proper state and action sets and reward functions to facilitate the determination of appropriate production scheduling rule under the constraint of the flexible maintenance. Numerical experiments show that the proposed QLSF outperforms the other four state-of-the-art scheduling rules in different scenarios. Moreover, the performance of the proposed flexible PM strategy is also examined and validated in comparison with three candidate maintenance strategies, i.e., run-to-failure corrective maintenance (CM), combination of TBPM and CM, and CBPM. The proposed flexible maintenance and solution approach can enrich the relevant academic knowledge base, and provide managerial insights and guidance in practical production systems.

Identifying key performance indicators for healthcare facilities maintenance

Hospitals and health centers use a lot of energy due to 24/7 al l-round year working hours and using different equipment. It has highlighted the importance of Facilities Management (FM) in hospitals, because the unexpected and dynamic nature of maintenance management not only increases energy usage but also decreases hospital functionality. Considering the significance of energy consumption in FM, particularly maintenance management and hospital functionality, the aim of this paper is to identify key performance indicators that lead to energy savings while improving functionality and reducing maintenance costs. In this regard, the relevant data are qualitatively examined through expert interviews and a literature review, accompanied by a questionnaire survey to produce quantitative performance data, which are analyzed with Partial Least Squares Structural Equation Modeling (PLS-SEM). The importance of individual indicators and their relationship to three categories of “energy savings,” “improving functionality,” and “reducing maintenance costs” are then investigated. The findings demonstrated the direct link between energy savings and improving functionality and reducing costs. It develops an appropriate framework for evaluating hospital performance based on FM in hospitals focused on maintenance and functionality and its impact on energy consumption. Moreover, a case study is conducted to investigate the impact of the identified indicators on saving energy in public hospitals in Iran and comparing electricity and gas bills in two consecutive years. The results show “gradual replacement of old electrical appliances and equipment concerning the age of the appliances”, “condition-based preventive maintenance”, “utilizing maintenance instructions and standards”, and “considering the impact of experienced and qualified managers” are the most important key performance indicators.

Automated Machine Health Monitoring at an Expert Level

Machine health condition monitoring is evidently a crucial challenge nowadays. Unscheduled breakdowns increase operating costs due to repairs and production losses. Scheduled maintenance implies taking the risk of replacing fully operational components. Human expertise is a solution for an outstanding expertise but at a high cost and for a limited quantity of data only, the analysis being time-consuming. Industry 4.0 and digital factory offer many alternatives to human monitoring. Time, cost and skills are the real stakes. The key point is how to automate each part of the process knowing that each one is valuable. Leaving aside scheduled maintenance, this paper copes with condition-based preventive maintenance and focuses on one fundamental step: the signal processing. After a brief overview of this specific area in which numerous technologies already exist, this paper argues for an automated signal processing at an expert level. The objective is to monitor a system over days, weeks, or years with as great accuracy as a human expert, and even better in regard to data investigation and analysis efficiency. After a data validation step most often ignored, any multimodal signal (vibration, current, acoustic, …) is processed over its entire frequency band in view of identifying all harmonic families and their sidebands. Sophisticated processing such as filtering and demodulation creates relevant features describing the fine complex structures of each spectrum. A time–frequency feature tracking constructs trends over time to not only detect a failure but also to characterize and localize it. Such an automated expert-level processing is a way to raise alarms with a reduced false alarm probability.

Optimal condition-based preventive maintenance policy for balanced systems

Reliability evaluation of balanced systems has been extensively studied in recent years. However, the research on maintenance optimization for balanced systems is still underexplored. This paper makes a novel contribution to existing literature by proposing a condition-based preventive maintenance (PM) policy for balanced systems with identical components. Each component is subject to continuous degradation and the states of all components are simultaneously detected at discrete time epochs. The system state is evaluated based on the deterioration levels of all components. The system is out of balance once the deterioration level of any component reaches a critical value or the difference between the deterioration levels of two components on the symmetric positions exceeds a specific threshold, whichever occurs first. In this research, PM activities are employed to avoid competing failures. The optimal PM thresholds are determined by minimizing the system maintenance cost within the framework of semi-Markov decision process. An illustrative example is provided to demonstrate the application of the proposed PM policy for balanced systems.

Strain monitoring based bridge reliability assessment using parametric Bayesian mixture model

Bridge condition assessment by use of structural health monitoring (SHM) data has been recognized as a promising approach towards the condition-based preventive maintenance. In-service bridges are normally subjected to multiple types of loads such as highway traffic, railway traffic, wind and thermal effect, resulting in heterogeneous and multimodal data structure of strain/stress responses. This study aims to develop an SHM-based bridge reliability assessment procedure in terms of parametric Bayesian mixture modelling. The parametric mixture model admits representation of multimodal structural responses, while the Bayesian paradigm enables both aleatory and epistemic uncertainties to be accounted for in modelling. By defining appropriate priors for the mixture parameters that are viewed as random variables to interpret the model uncertainty, an analytical form of the full conditional posteriors is derived. A Markov chain Monte Carlo (MCMC) algorithm in conjunction with Bayes factor is explored to determine the optimal model order and estimate the joint posterior of the mixture parameters. In full compliance with the Bayesian framework, a conditional reliability index is elicited with the parametric Bayesian mixture model by using the first-order reliability method. The estimated value of the reliability index, which serves as a quantitative measure of health condition for the in-service bridge, can be successively updated with the accumulation of monitoring data. The proposed method is exemplified by using one-year strain monitoring data acquired from the instrumented Tsing Ma Suspension Bridge, in which the evolution of the estimated reliability index is obtained.