Optimal Maintenance Schedule Research Articles

Joint optimization of production and maintenance scheduling for unrelated parallel machine using hybrid discrete spider monkey optimization algorithm

This paper considers an unrelated parallel machine scheduling problem with variable maintenance based on machine reliability to minimize the maximum completion time. To obtain the optimal solution of small-scale problems, we firstly establish a mixed integer programming model. To solve the medium and large-scale problems efficiently and effectively, we develop a hybrid discrete spider monkey optimization algorithm (HDSMO), which combines discrete spider monkey optimization (DSMO) with genetic algorithm (GA). A few additional features are embedded in the HDSMO: a three-phase constructive heuristic is proposed to generate better initial solution, and an individual updating method considering the inertia weight is used to balance the exploration and exploitation capabilities. Moreover, a problem-oriented neighborhood search method is designed to improve the search efficiency. Experiments are conducted on a set of randomly generated instances. The performance of the proposed HDSMO algorithm is investigated and compared with that of other existing algorithms. The detailed results show that the proposed HDSMO algorithm can obtain significantly better solutions than the DSMO and GA algorithms.

Taguchi-Grey Relational Analysis Method for Parameter Tuning of Multi-objective Pareto Ant Colony System Algorithm

In any metaheuristic, the parameter values strongly affect the efficiency of an algorithm’s search. This research aims to find the optimal parameter values for the Pareto Ant Colony System (PACS) algorithm, which is used to obtain solutions for the generator maintenance scheduling problem. For optimal maintenance scheduling with low cost, high reliability, and low violation, the parameter values of the PACS algorithm were tuned using the Taguchi and Grey Relational Analysis (Taguchi-GRA) method through search-based approach. The new parameter values were tested on two systems. i.e., 26- and 36-unit systems for window with operational hours [3000-5000]. The grey relational grade (GRG) performance metric and the Friedman test were used to evaluate the algorithm’s performance. The Taguchi-GRA method that produced the new values for the algorithm’s parameters was shown to be able to provide a better multi-objective generator maintenance scheduling (GMS) solution. These values can be benchmarked in solving multi-objective GMS problems using the multi-objective PACS algorithm and its variants.

Cost-Effectiveness Oriented Intelligent Maintenance Scheduling Optimization for Traction Power Supply System of High-Speed Railway

In the context of increasing construction of new railways and uninterrupted operation of existing railways in China, maintenance supervisors are facing great challenges to achieve as much maintenance workloads as possible in an efficient and economical way within the required maintenance cycle. Therefore, a cost-effectiveness oriented intelligent maintenance scheduling optimization method for the traction power supply system (TPSS) of high-speed railways (HSRs) is proposed. First, the skill levels of maintenance operators are evaluated by the skill evaluation model, and the workflow model of TPSS maintenance tasks is established to describe the relation between the operator deployment and the maintenance efficiency. Then the bi-objective optimization model which simultaneously maximizes maintenance workload and minimizes cost subject to available resources during a prescribed period is established. A modified bi-objective genetic algorithm is applied to obtain the Pareto solutions of the model and thus optimized maintenance scheduling strategies are formulated. A case study dealing with the maintenance scheduling optimization of a catenary system in China shows that, compared with the current scheme, the proposed strategy can effectively improve maintenance efficiency and meanwhile reduce cost. Furthermore, a prototype of an intelligent maintenance scheduling system (IMSS) for HSR TPSS is developed. The application of IMSS with field data indicates it can help operators formulate highly efficient yet economical maintenance strategies, and meanwhile motivate the transition of current maintenance decision-making policy from traditional experience-based strategies towards scientific “cost-effective” ones.

An exact MILP model for joint switch placement and preventive maintenance scheduling considering incentive regulation

Power delivery with high reliability is one of the main objectives of any distribution system. In this regard, system operators are adapting the traditional distribution systems with sectionalized switches and optimal preventive maintenance (PM) scheduling techniques as two effective methods for reliability improvement. However, they suffer due to the lack of a practical model in which switch placement (SP) and PM scheduling problems are considered simultaneously. Furthermore, consideration of incentive regulation schemes, such as reward-penalty scheme (RPS) is highly questionable in the separated reliability improvement problems. In this paper, a mix-integer linear programming model is presented wherein both SP and PM scheduling problems are considered. Rather than using conventional methods for linearization, an exact formulation is proposed to avoid the impact of approximations on the final decision. Moreover, RPS is also regarded as an incentive regulation scheme to balance the reliability level and financial performance. The results of test and real network implementation confirm that a higher performance is reached in terms of reliability and financial issues when the proposed model is utilized compared to the other ones. Besides, analysis demonstrates that the proposed model behaves effectively in both mid and long terms.

Integrated Multi-objective Optimization of Predictive Maintenance and Production Scheduling: Perspective from Lead Time Constraints

For the integrated optimization of job-shop production scheduling and predictive maintenance, this paper fully considers such constraints as product delivery time and changing machine failure rate, and establishes a multi-objective optimization model aiming to minimize the processing cost and the product processing time. The model includes the changing machine failure rate into the integrated optimization of job-shop production scheduling and predictive maintenance, and enables the prediction of the machine state according to the processing time of the current job, laying the basis for the decision-making of the machine activity and the reasonable and effective production planning. In addition, the non-dominated sorting genetic algorithm (NSGA)-II was designed to solve the proposed model. The algorithm performance was improved through the operator crossover and mutation by the simulated binary crossover algorithm (SBX). The proposed strategy was verified through a case study.

Integrating machine learning techniques into optimal maintenance scheduling

Poor maintenance regimes often contribute to unplanned downtimes, quality defects and accidents; thus it is crucial to apply an effective maintenance strategy to achieve efficient and safe processes. Industry 4.0 has brought about a proliferation of digital data and with it new opportunities to advance and improve the way maintenance activities are planned. Here, we propose a novel methodology that utilises machine learning to predict both machine faults and repair time, and uses this data to underpin the scheduling of maintenance activities. This can be used to plan maintenance, and optimise the schedule with a cost objective within the constraints of labour availability and plant layout. When applied to a dataset obtained using a simulated Fischertechnik (FT) model, this methodology reduced the overall plant maintenance costs by decreasing unplanned downtimes and increasing maintenance efficiency. This work provides a promising first step towards improving the way maintenance tasks are approached in Industry 4.0.

Accelerated optimal maintenance scheduling for generation units on a truthful platform

Maintenance of generation units is a measure to ensure the reliability of power systems. In this paper, a novel blockchain-based truthful condition-based maintenance of generation units (T-CBMGU) platform is proposed to innovate and upgrade state-of-the-art CBMGU. In addition, two valid inequalities are proposed to accelerate the convergence speed of Benders decomposition in maintenance scheduling process. The proposed valid inequalities are formulated based on technical/physical analysis and greedy-based heuristic initialization. More specifically, for data acquisition and failure rate diagnosis/prognosis processes, T-CBMGU can ensure the immutability of the collected operational data. In this way, the influence of tampered data on the diagnosis/prognosis results in state-of-the-art CBMGU can be reduced. For maintenance scheduling and bidding to change scheduled time slot processes, in state-of-the-art CBMGU, the decision makers, i.e., independent system operators (ISOs), may not be trusted. However, in T-CBMGU, the scheduling and bidding processes are implemented automatically via smart contracts rather than by the ISOs; as such, incentives to manipulate data can be avoided. Finally, regarding performance of maintenance actions, in contrast to state-of-the-art CBMGU, the implementation process can be truthfully recorded by the T-CBMGU platform, which facilitates backtracking of responsibility. Then, the T-CBMGU platform and the valid inequalities are tested for the IEEE 300-bus power system. Furthermore, cases with tampered data and distrust caused by fairness manipulation are simulated to show the importance of using T-CBMGU. Finally, the Benders decomposition algorithm with valid inequalities is compared with other solvers to demonstrate its fast convergence speed.

Practice Summary: GE Optimizes for Aircraft Engine Overhaul Scheduling and Shop Assignment

We present an optimization-based decision support system to generate optimal aircraft engine maintenance schedules that reflect qualitative and quantitative trade-offs from customer, business, and shop perspectives. The approach is currently implemented at GE Aviation Services for global overhaul network induction planning for all commercial product lines.

Jet Engine Optimal Preventive Maintenance Scheduling Using Golden Section Search and Genetic Algorithm

Jet engines are critical assets in aircraft, and their availability is crucial in the modern aircraft industry. Therefore, their maintenance scheduling is one of the major tasks an airline has to make during an engine’s lifetime. A proper engine maintenance schedule can significantly reduce maintenance costs without compromising the aircraft's reliability and safety. Different maintenance scheduling approaches have been used for jet engines, such as corrective, preventive, and predictive maintenance strategies. Regarding the safety demands in aircraft industries, preventive maintenance is a frequent maintenance method for jet engines. However, preventive maintenance schedules are often use fixed maintenance intervals, which is usually suboptimal. This paper focuses on minimizing a jet engine's overall maintenance cost by optimizing its preventive maintenance schedule based on an engine’s comprehensive reliability model. A hierarchical optimization framework including the golden section search and genetic algorithms is applied to find the optimal set of preventive maintenance number and their times and the components to be replaced at those times during the jet engine's overall lifetime. The Monte Carlo simulation is used to estimate the engine’s failure times using their lifetime distributions from the reliability model. The estimated failure times are then used to determine the engine's overall corrective and preventive maintenance costs during its lifetime. Finally, an optimal preventive maintenance schedule is proposed for an RB 211 jet engine using the presented method. In the end, comparing the proposed method's overall maintenance cost with two other maintenance methods demonstrates the proposed schedule's effectiveness. The method presented in this paper is generic, and it can be used for other similar engineering systems.

철도차량의 좌우측절단자료를 이용한 2단계 상태기반 점검주기 연구

Purpose: This paper introduces two-phase condition-based maintenance by analyzing left-truncated and right-censored field data, with characteristics managed by the existing maintenance schedule.BRMethods: The failure rate was initially observed as a constant failure rate (CFR) and, after a certain point, as an increasing failure rate (IFR). Therefore, a two-phase condition-based maintenance policy with each stage maintenance cycle was proposed. In addition, a maintenance model was developed to determine the optimal maintenance schedule in terms of economic feasibility.BRResults: The optimal maintenance schedule was derived by minimizing the total cost, including the inspection cost, failure cost, and improvement factor. Further, changes in the optimal maintenance schedule were examined based on the ratios of the inspection cost, failure cost, and improvement factor.BRConclusion: Designing a maintenance policy to evaluate the system conditions and mutual adequacy between the cost and improvement effect in terms of light and medium maintenance is essential.

Unlocking the Potential of Permeable Pavements in Practice: A Large-Scale Field Study of Performance Factors of Permeable Pavements in The Netherlands

Infiltrating pavements are potentially effective climate adaptation measures to counteract arising challenges related to flooding and drought in urban areas. However, they are susceptible to clogging causing premature degradation. As part of the Dutch Delta Plan, Dutch municipalities were encouraged to put infiltrating pavements into practice. Disappointing experiences made a significant number of municipalities decide, however, to stop further implementation. A need existed to better understand how infiltrating pavements function in practice. Through 81 full-scale infiltration tests, we investigated the performance of infiltrating pavements in practice. Most pavements function well above Dutch and international standards. However, variation was found to be high. Infiltration rates decrease over time. Age alone, however, is not a sufficient explanatory factor. Other factors, such as environmental or system characteristics, are of influence here. Maintenance can play a major role in preserving/improving the performance of infiltrating pavements in practice. While our results provide the first indication of the functioning of infiltrating pavement in practice, only with multi-year measurements following a strict monitoring protocol can the longer-term effects of environmental factors and maintenance actually be determined, providing the basis for the development of an optimal maintenance schedule and associated cost–benefit assessments to the added value of this type of climate adaptation.

SO-21 Optimal maintenance treatment strategy following an anti-EGFR-based first-line induction therapy in patients with RAS wild type metastatic colorectal cancer: An individual patient data pooled analysis of clinical trials

In metastatic colorectal cancer (mCRC), after a first-line induction with doublet/triplet chemotherapy plus bevacizumab, fluoropyrimidine+bevacizumab is the recommended maintenance option. The combination of anti-EGFR agents and chemotherapy is a guideline-endorsed first-line option for RAS/BRAF wild-type (wt) mCRC patients, but the optimal maintenance schedule has not been defined, yet. The Valentino trial showed that, after 4-month FOLFOX+panitumumab induction, single-agent panitumumab induced inferior progression-free survival (PFS) than FUFA+panitumumab, though slightly reducing toxicity. The Panama study demonstrated that, after 3-month FOLFOX+panitumumab induction, FUFA+panitumumab induced a significantly superior PFS than FUFA alone. We performed a pooled analysis of the Valentino and Panama trials including RAS wt mCRC patients who received first-line FOLFOX/panitumumab followed by a maintenance strategy. Only patients who received treatment as per-protocol (namely those who started the maintenance phase according to the assigned study treatment arm) were included. Data on patients, disease characteristics and treatment received were pooled. Patients were stratified per maintenance treatment arm considering monotherapy (FUFA or panitumumab) vs combo (FUFA+panitumumab). PFS and overall survival (OS) were calculated from the start of induction and of maintenance therapy and toxicity was evaluated by NCI CTCAE any grade and grade 3/4 adverse events (AEs) during maintenance therapy. A total of 412 patients were included in the pooled analysis, 248 and 164 from Panama and Valentino study, respectively. Overall, 123, 79 and 210 patients received maintenance with FUFA, panitumumab and FUFA+panitumumab, respectively, thus 202 patients received monotherapy and 210 combo. Baseline patients and disease characteristics were well balanced between the 3 arms except for ECOG PS, with a higher rate of ECOG PS 0 in panitumumab only arm. When calculating survival outcomes from the start of maintenance therapy, PFS was significantly superior in combo versus monotherapy arm (median PFS: 9.0 versus 5.8 months; HR 0.77, 95% CI 0.63-0.95; P=0.016), while OS showed a non-significant consistent trend (median OS: 28.0 versus 26.1; HR 0.87, 95% CI 0.68-1.11; P=0.258). The safety profile was consistent with the singular trial reports, with an increase of grade 3/4 AEs in the combo arm (25%, 20% and 42% in FUFA, panitumumab and FUFA+panitumumab arms, respectively). This pooled analysis including two randomized phase II trials showed that a combination schedule with 5-FU plus folinic acid and panitumumab is superior in PFS with a consistent trend in OS as compared to single-agent maintenance. The results mirror the available evidence on the guideline-recommended maintenance strategy after bevacizumab-based first-line therapy. Updated results might be presented at the meeting.

Optimization of preventive maintenance schedule of subway train components based on a game model from the perspective of failure risk

With the sustainable development of urban transportation systems, the safety and economy of subway trains have become important criteria. However, in the process of formulating the operation and maintenance strategy of subway trains, there is always a conflict of interest between the operator, who aims to improve the operation reliability, and the maintainer, who aims to reduce the maintenance cost. To resolve this conflict, this paper proposes a preventive maintenance decision-making method for subway train components based on a game model. A failure-rate model based on the memory factor was developed and combined with the dynamic attenuation law of a subway train. The failure risk of subway train components was quantitatively evaluated, and a risk penalty cost model was established. Next, a maintenance cost model based on the maintenance reliability and economy was developed. Then, a non-cooperative dynamic game model with operators and maintainers as players was developed, and the balance was solved using the particle swarm optimization algorithm. Finally, the preventive maintenance of the bogie axle box of a subway train was examined for validation. The validation results indicated that the proposed method can balance the interests of the subway train operation and maintenance departments and improve the operation and maintenance decision-making in the field of sustainable cities. • Multiple failure consequences are considered in preventive maintenance cost model. • The influence of multi-parameter combination on maintenance strategy is applied. • Conflicts of interest among decision-making participants are resolved. • The policy recommendations are provided at both the operational and strategic levels.

Intuitionistic fuzzy modelling-based integrated framework for performance analysis of juice clarification unit

The current work seeks to propose an Intuitionistic Fuzzy (IF) modelling based integrated framework for analysing the performance issues of a Juice Clarification Unit (JCU) in a sugar mill industry. IF-Lambda Tau approach based mathematical modelling has been developed using AND/OR gate transitions expression for both membership and non-membership functions. Membership and non-membership function-based reliability parameters have been tabulated at different spreads. Availability of the considered system shows decreasing trend with the increase in spread values. Furthermore, for improving the system’s availability, risk analysis has been carried by implementing IF-Failure Mode & Effect analysis (IF-FMEA) approach. IF Hybrid Weighted Euclidean Distance (IFHWED) based IF-FMEA output scores for all listed failure causes has been tabulated for identifying the most critical failure causes responsible for decrease in system’s availability. IF-Technique for Order of Preference by Similarity to Ideal Solution (IF-TOPSIS) approach was also applied within IF-FMEA approach, and the obtained ranking results are compared for effective decision making of critical failure causes. The proposed IF modelling based integrated framework is highly capable in considering the indeterminacy/hesitation effect involved in the collected raw data/information beside the presence of vagueness/fuzziness, which is missing with the well existed fuzzy set theory based models. The capability of considering the indeterminacy/ hesitation effect in the raw data/information with proposed model results in high accuracy in the performance evaluation of the considered system, and will be further useful for developing an optimum maintenance schedule. Sensitivity analysis has also been carried out to evaluate the robustness of proposed integrated framework.

From knowledge-based to big data analytic model: a novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0

The Internet of Things (IoT), Big Data and Machine Learning (ML) may represent the foundations for implementing the concept of intelligent production, smart products, services, and predictive maintenance (PdM). The majority of the state-of-the-art ML approaches for PdM use different condition monitoring data (e.g. vibrations, currents, temperature, etc.) and run to failure data for predicting the Remaining Useful Lifetime of components. However, the annotation of the component wear is not always easily identifiable, thus leading to the open issue of obtaining quality labeled data and interpreting it. This paper aims to introduce and test a Decision Support System (DSS) for solving a PdM task by overcoming the above-mentioned challenge while focusing on a real industrial use case, which includes advanced processing and measuring machines. In particular, the proposed DSS is comprised of the following cornerstones: data collection, feature extraction, predictive model, cloud storage, and data analysis. Differently from the related literature, our novel approach is based on a feature extraction strategy and ML prediction model powered by specific topics collected on the lower and upper levels of the production system. Compared with respect to other state-of-the-art ML models, the experimental results demonstrated how our approach is the best trade-off between predictive performance (MAE: 0.089, MSE: 0.018, R^{2}: 0.868), computation effort (average latency of 2.353 s for learning from 400 new samples), and interpretability for the prediction of processing quality. These peculiarities, together with the integration of our ML approach into the proposed cloud-based architecture, allow the optimization of the machining quality processes by directly supporting the maintainer/operator. These advantages may impact to the optimization of maintenance schedules and to get real-time warnings about operational risks by enabling manufacturers to reduce service costs by maximizing uptime and improving productivity.

Hypergraph-based joint optimization of spare part provision and maintenance scheduling for serial-parallel multi-station manufacturing systems

This paper studies the joint modeling of spare part provision and maintenance scheduling for Serial-Parallel Multi-station Manufacturing Systems (SPMMS), where the spare part connections are especially investigated. In the SPMMS, multiple types of spare parts are retained for uncertain failures of the stations, and multiple stations may share the spare parts in inventory. To describe the spare part connections among the stations, a hypergraph-based model is introduced. In the system-level maintenance, the SPMMS is formulated to be a multi-connection hypergraph, with the Spare Part Hyperedges (SPH), the cost-saving hyperedges and the capacity-loss hyperedge involved. Based on the multi-connection hypergraph, a Combination-Spread Opportunistic Maintenance (CSOM) policy is proposed. To obtain the optimal alternatives of the maximum inventory levels, the length of the combination window and the length of the spread window, a hierarchical optimization method is developed. The case study and the comparisons show that the proposed hypergraph-based CSOM policy is more cost-effective than the traditional maintenance policy, the station-level maintenance policy and the fixed-group maintenance policy. Finally, the discussion shows that the traditional maintenance model is a special scenario of the hypergraph-based model.

An approach for bi-objective maintenance scheduling on a networked system with limited resources

Preventive maintenance activities are often the cause of downtime of technical multi-component systems. To minimize maintenance costs and maximize productivity, maintenance tasks are often grouped and carried out simultaneously. We consider the problem of obtaining an optimal maintenance schedule when the multi-component system is also a networked system and can be modeled as a directed graph, where nodes represent machines or workers, and edges represent the exchange of material, information, or work between these nodes. To find efficient maintenance schedules, we formulate a bi-objective optimization problem, which considers the limited availability of maintenance personnel, and we propose an algorithm that finds a set of maintenance schedules, which are a good approximation of the Pareto front in terms of costs and productivity. Through sensitivity analysis we show the extent to which adding maintenance personnel improves system productivity at the expense of increased maintenance costs and idle time of some resources. Besides solving the Pareto-optimal schedules, we show how the developed model is useful in maintenance personnel planning, and we outline limitations and future developments of the present work.

STEWART: STacking Ensemble for White-Box AdversaRial Attacks Towards more resilient data-driven predictive maintenance

Industrial Internet of Things (I-IoT) is a network of devices that focus on monitoring industrial assets and continuously collecting data. This data can be utilized by Machine Learning (ML) methods to perform Predictive Maintenance (PDM) which identifies an optimal maintenance schedule for the industrial assets. The computational systems in the I-IoT are usually not designed with security in mind. Their limited computational power creates security vulnerabilities that attackers can exploit to prevent asset availability, sabotage communication, and corrupt system data. In this work, we first demonstrate that cyber-attacks can impact the performance of ML-based PDM methods significantly, leading up to 120 × prediction performance loss. Next, we develop a stacking ensemble learning-based framework that stays resilient against various white-box adversarial attacks. The results show that our framework performs well in the presence of cyber-attacks and has up to 60% higher resiliency compared to the most resilient individual ML method.

Optimal selective maintenance scheduling for series–parallel systems based on energy efficiency optimization

With the industry sustainable development and increasing awareness of energy conservation, many manufacturing enterprises prefer to develop the operation and maintenance (O&M) with high production throughput and low energy consumption. In reality, many manufacturing systems are required to conduct a sequence of predefined missions with finite breaks between any two consecutive missions. To successfully complete the next mission production, maintenance actions are arranged and performed on machines during each scheduled break. In this paper, an energy-oriented selective maintenance policy (ESMP) for series–parallel systems is investigated. At each break, multiple maintenance actions with different impacts on machine degradation are available under limited maintenance resources. To obtain the throughput-and-energy based maintenance scheme, we first model the system energy efficiency based on system throughput and energy consumption. Then, we integer the energy efficiency modeling, production throughout analysis, and selective maintenance scheduling into an optimization model. And the model objective is to find the appropriate maintenance action for each machine at each break subject to cost and duration constraints. Numerical examples have been addressed to demonstrate the performance and adaptability of our proposed ESMP in long-term selective maintenance scheduling. Finally, a comparative analysis with traditional reliability-oriented policy shows the significant improvement of energy efficiency.

Developing an exhaustive optimal maintenance schedule for offshore wind turbines based on risk-assessment, technical factors and cost-effective evaluation

Maintenance scheduling is one of the most challenging issues of offshore wind system, because the maintenance decision may impact greatly to cost-effectiveness. The process of maintenance decision making is confronting with uncertainties, including economic, technical, safety and environmental uncertain that make conventional maintenance optimization insufficient. The conventional maintenance optimization in the existing studies only consider factors related to technical and economic aspects in maintenance optimization. No existing study analyzes the effects of health and safety risks of the technicians and the environmental risks of the maintenance activities under the impacts of the complex weather conditions in the marine environment. The occurrence of environmental and safety risks causes catastrophic consequences, especially in harsh weather condition, that make the conventional maintenance techniques insufficient. This paper proposes an approach to optimize maintenance schedule that is designed to maximize the cost-effectiveness while minimizing the environmental and safety risks. The proposed model utilizes fuzzy probabilities to assess the environmental and safety risks. This paper also presents a mathematical model to derive the optimal individual maintenance schedule and group maintenance schedule for various components by considering a number of impacted factors. The results demonstrated that the number of maintenance activities when considering environmental and safety risks is higher than that without considering environmental and safety risks. For example, the number of maintenance activities with and without considering the environmental and safety risks at the location of 25 km of distance to shore is 75 and 86 activities respectively. The effect of risk-assessment model was more apparent for vulnerable components and was less apparent for the durable components.