Preventive Maintenance Tasks Research Articles

Remaining useful life prediction based on time-series features and conformalized quantile regression

Abstract The remaining useful life (RUL) prediction is a key task in the field of prognostics and health management (PHM) and plays a crucial role in preventive maintenance tasks. Traditional prediction methods have mostly focused on point prediction issues, neglecting the uncertain factors in the prediction task, thus failing to ensure the credibility of the prediction. In light of this, this paper focuses on improving the accuracy of point prediction models for RUL and interval prediction issues, proposing the introduction of multi-scale convolutional neural networks (MCNN), decomposed time-sequential linear layers (DL), and conformal quantile regression (CQR) techniques into the RUL prediction task of aero-engines. The aim is to provide timely and accurate failure warnings for aero engines, effectively ensure their reliability and safety, and reduce maintenance costs throughout their life cycle. In response to the limitations of current point prediction models in capturing the temporal features of life data, a MCNN-DL-based RUL prediction model is proposed to capture life data's long-term trends and local variations for precise point predictions. Furthermore, an interval estimation approach for RUL is presented, which integrates the MCNN-DL model with CQR to account for prediction uncertainty. Finally, the method in this paper is verified using the CMAPSS dataset, and the results show that the method has achieved excellent results in both RUL point prediction and interval prediction tasks.

AI and the Future of Network Administrator (LAN) Preventive Maintenance

This paper delves into the pivotal role of AI in predictive maintenance strategies for industrial systems, focused in the filed of LAN operation and maintenance. It will shed some insight on the current methodology and how AI will transform the traditional ways for conducting preventive maintenance tasks.

Wireless Power Transfer for Unmanned Underwater Vehicles: Technologies, Challenges and Applications

Unmanned underwater vehicles (UUVs) are key technologies to conduct preventive inspection and maintenance tasks in offshore renewable energy plants. Making such vehicles autonomous would lead to benefits such as improved availability, cost reduction and carbon emission minimization. However, some technological aspects, including the powering of these devices, remain with a long way to go. In this context, underwater wireless power transfer (UWPT) solutions have potential to overcome UUV powering drawbacks. Considering the relevance of this topic for offshore renewable plants, this work aims to provide a comprehensive summary of the state of the art regarding UPWT technologies. A technology intelligence study is conducted by means of a bibliographical survey. Regarding underwater wireless power transfer, the main methods are reviewed, and it is concluded that inductive wireless power transfer (IWPT) technologies have the most potential. These inductive systems are described, and their challenges in underwater environments are presented. A review of the underwater IWPT experiments and applications is conducted, and innovative solutions are listed. Achieving efficient and reliable UWPT technologies is not trivial, but significant progress is identified. Generally, the latest solutions exhibit efficiencies between 88% and 93% in laboratory settings, with power ratings reaching up to 1–3 kW. Based on the assessment, a power transfer within the range of 1 kW appears to be feasible and may be sufficient to operate small UUVs. However, work-class UUVs require at least a tenfold power increase. Thus, although UPWT has advanced significantly, further research is required to industrially establish these technologies.

An integrated framework of preventive maintenance and task scheduling for repairable multi-unit systems

Preventive maintenance and task scheduling are both crucial activities in industrial practice. Although they are interdependent and mutually influential, most existing studies typically analyze them separately. In this paper, an integrated framework of preventive maintenance planning and task scheduling is explored. On one hand, while most scholars focus on the system as a whole in scheduling studies, we further take into account the degradation and maintenance of multiple units during the task scheduling process. On the other hand, instead of only using "direct replacement" as the main maintenance method, we further consider the repairability of the unit by incorporating imperfect maintenance effects into the maintenance modeling. Additionally, the lifecycle partitioning method is proposed to analyze the maintenance groups for multiple units at the completion of scheduling tasks and their corresponding probabilities. Based on this foundation, an integrated decision model is established with the preventive maintenance threshold and scheduling task sequence as decision variables to minimize the total weighted expected completion time. Finally, a novel genetic algorithm based on hybrid encoding is proposed, and the effectiveness of integrated decision-making was validated using a practical example.

Maintenance study on WCLL-TBS ancillary systems in process room

The Water-Cooled Lithium Lead Test Blanket System (WCLL-TBS) is one of the European TBS candidates for being installed and operated in ITER. The ongoing activities toward the Preliminary Design Review of the WCLL-TBS Ancillary Systems include the reallocation of their units in the reserved space, also in the view of the proper execution of the maintenance activities. Starting from the available documentation (System Design Description, Process Flow Diagrams, Process and Instrumentation Diagrams), detailed 3D CAD models have been developed for two Ancillary Systems to be installed in the Process room: the Tritium Extraction System (TES) and the Tritium Accountancy System (TAS). In the Process room (PR), the largest part of the TES process units is placed inside a Glove-box, as enclosure to avoid the contamination of the room in case of radioactive release due to failure of units. Based on the expected radioactivity content, all the TAS units are placed inside the Glove-box. Maintainability studies have been performed, focusing on the preventive (i.e. planned) and corrective (i.e. required by failures) maintenance tasks on the units installed inside the Glove-box. They were based on the 3D CAD models and supported using Virtual Reality as intuitive and immersive human-computer interface. They provided insights for the iterative improvement and consolidation of the Systems design and information for the evaluation of their availability.

Human performance consequences of normative and contrastive explanations: An experiment in machine learning for reliability maintenance

Decision aids based on artificial intelligence and machine learning can benefit human decisions and system performance, but can also provide incorrect advice, and invite operators to inappropriately rely on automation. This paper examined the extent to which example-based explanations could improve reliance on a decision aid that is based on machine learning. Participants engaged in a preventive maintenance task by providing their diagnosis of the conditions of three components of a hydraulic system. A decision aid based on machine learning provided advice but was not always reliable. Three explanation displays (baseline, normative, normative plus contrastive) were manipulated within-participants. With the normative explanation display, we found improvements in participants' decision time and subjective workload. With the addition of contrastive explanations, we found improvements in participants' hit rate and sensitivity in discriminating between correct and incorrect ML advice. Implications for the design of explainable interfaces to support human-AI interaction in data intensive environments are discussed.

Research on Combination Optimization Method of Equipment Maintenance Task Package based on Maintenance Cost Analysis

This paper proposes a maintenance task package determination method based on the analysis of generalized maintenance cost (including maintenance cost, loss cost and maintenance time), aiming at the preventive maintenance task of aircraft. In the constructed maintenance task packaging model, practical issues such as approach, workload, logical sequence of maintenance tasks and the will of operators are considered in the implementation process of preventive maintenance tasks, to clarify the priority of packaging strategy and avoid problems such as excessively large workload distribution of each task package and even the inability to be realized in the actual field due to the pursuit of low cost. Based on the actual requirements of maintenance engineering, make preventive maintenance task package to meet the requirements of operators.

A New Integrated Risk-Assessment Model for Minimizing Human-Machine Error Consequences in a Preventive Maintenance System

In this paper, a risk-assessment model for minimizing human-machine error consequences during the implementation of preventive maintenance tasks has developed. The developed model aimed to find the optimal preventive maintenance interval (PMI) and corresponding minimum risk consequences costs per unit of time. Based on expert judgment, a human error probability (HEP) model was developed using the success likelihood index methodology (SLIM). In addition, we developed a system failure probability (SFP) model based on the failure and repair data of the system. The HEP model was integrated with an SFP model to develop a human-machine error model. Then, the risk-assessment model was developed based on the consequences of system failure and human error. The effectiveness of the developed human-machine error model was shown by applying a numerical example for a multi-component series system. The optimization toolbox from MATLAB R2022b was applied to solve the developed human-machine model. The results showed that the optimal PMI can be implemented after 24 working hours to 105 hours under the acceptable limit of risk in the system which is 100 SR/h. Finally, the developed model is an effective method that can be applied to a wide range of manufacturing systems to minimize financial risks related to system inspection and maintenance while meeting safety and availability requirements.

Optimal Preventive Maintenance Planning for Electric Power Distribution Systems Using Failure Rates and Game Theory

Current electric utilities must achieve reliability enhancement of considerable distribution feeders with an economical budget. Thus, optimal preventive maintenance planning is required to balance the benefits and costs of maintenance programs. In this research, the proposed method determines the time-varying failure rate of each feeder to evaluate the likelihood of future interruptions. Meanwhile, the consequences of feeder interruptions are estimated using interruption energy rates, customer-minutes of interruption, and total kVA of service areas. Then, the risk is assessed and later treated as an opportunity for mitigating the customer interruption costs by planned preventive maintenance tasks. Subsequently, cooperative game theory is exploited in the proposed method to locate a decent balance between the benefits of reliability enhancement and the costs required for preventive maintenance programs. The effectiveness of the proposed method is illustrated through case studies of large power distribution networks of 12 service regions, including 3558 medium-voltage distribution feeders. The preventive maintenance plans resulting from the proposed method present the best compromise of benefits and costs compared with the conventional approach that requires a pre-specified maintenance budget.

Improving the Operational Output of Marine Vessel MainEngine System through Cost Reduction using Reliability Technique

This research seeks to use reliability technique to improve operational output through cost reduction of the main engine system of a ship. The various subsystems of the marine vessel main engine were identified. The failure mode effect and criticality index of the engine system and their root causes were analyzed. The reliability of the main engine system was analyzed using exponential reliability model and a maintenance task that reduces the operational cost of main engine system was generated thereby improving output. The reliability centred maintenance technique identified all the perspectives of failures in the ship main engine systems and employed the appropriate maintenance approach for each failure respectively. The results of the reliability analysis performed on the main engine systems generated the proposed preventive maintenance (PM) tasks and plan. Decrease in the rate of Run-To-Failure (RTF) data remains inevitable and programmed performance of condition based, task demand and fault finding (CD, TD and FF) was recommended. The projected work program if implemented will decrease labour cost from N177, 600,000.00/year to N100, 800,000.00/year (approximately 43.24% of the total annual labour expenditure). The projected PM scheduling outcomes showed a 44.64% saving in the total cost of maintenance when compared with the existing RTF practice. The main engine systems reliability increases with decreased labour cost. The proposed spare parts plan for the main engine systems was generated and the results showed that approximately 55.42% of the yearly costs of spare parts are saved when projected PM scheduling is adopted.

Infrared thermography in steam trap inspection

Steam traps play a significant role in condensate evacuation from steam as well as in heating ventilation and cooling systems (HVAC), i.e., industrial climate chambers. Preventive maintenance and periodical audit of steam traps increase reliability and reduce the number of facility off hours. In some elements of the system, condensate can damage some parts, which means that monitoring their function is one of the basic preventive maintenance tasks. One way of checking steam traps is by using infrared thermography. The paper presents the simplicity of steam trap control by using an infrared thermography camera.

A reliability-and-cost-based framework to optimize maintenance planning and diverse-skilled technician routing for geographically distributed systems

We present an agile maintenance framework where technician assignment and maintenance schedules are planned jointly to ensure timely operation and maintenance (O&M) services. Such an agile framework can quickly respond to organizational scheduling requirements while controlling service costs and not compromising machine reliability. For preventive maintenance (PM) and replacement tasks, a diverse-skilled technician organizing and routing model (D-STORM) is developed for geographically distributed systems with the following decision variables: (1) the scheduled maintenance start time, (2) the appropriate maintenance level (i.e. PM or replacement) for a network of machines, (3) the composition of technician teams subject to constraints controlling the number of technicians per team and their skill levels, (4) the optimal service route for each team. And the two objectives are: (1) maximizing the total reliability improvement and (2) minimizing the total service cost. Other than traditional maintenance policies, we propose a machine-team-technician assignment approach to provide a flexible and unified maintenance framework that can incorporate diverse-skilled technicians and multi-level maintenance operations. Numerical studies show significant advantages in terms of improved reliability and reduced costs, providing a set of alternative solutions for global original equipment manufacturers (OEMs). Moreover, Pareto solutions help OEMs to adopt the most appropriate maintenance scheme for their practices.

Robust job-shop scheduling under deterministic and stochastic unavailability constraints due to preventive and corrective maintenance

This paper presents a modeling and solution approach for a robust job-shop scheduling problem (JSP) under deterministic and stochastic machine unavailability caused, respectively, by planned preventive maintenance (PM) and unplanned corrective maintenance (CM) following random breakdowns. The goal is to optimize the sequence of jobs and run-based planned preventive maintenance tasks in a robust manner while considering the degradation of machines over time. The time to failure for each machine is assumed to follow a Weibull distribution. The robust objective function to be minimized is a weighted sum of the expected values of the makespan and the gross positive deviation between the actual and planned start times of the jobs, as proxies for quality robustness and solution robustness, respectively. Two metaheuristic algorithms that aim at providing a good balance between performance quality and solution robustness are developed. In both algorithms, the “true” makespan objective function (with both PM and CM) is approximated using three surrogate measures. Genetic algorithm (GA) is first used to optimize the surrogate functions, then the fittest solutions from the three oracles are simulated with random breakdown scenarios and the best among them is introduced as an elite member in the next GA iteration. The first algorithm terminates as soon as the solution obtained is worse than the best know solution or when the maximum number of iterations is reached, whereas the second algorithm applies a rule inspired by Simulated Annealing for termination. Numerical experimentation on benchmark instances from the literature showed excellent performance of the proposed algorithms in terms of average marginal improvement and runtime. These results show that the proposed framework can generate high-quality robust job shop schedules under deterministic and stochastic machine unavailability constraints. Moreover, the sensitivity analysis results recommended some key insights and directions for future research.

The enriched median routing problem and its usefulness in practice

Emergency response fleets often have to simultaneously perform two types of tasks: (1) urgent tasks requiring immediate action, and (2) non-urgent preventive maintenance tasks that can be scheduled upfront. In Huizing et al. (2020), Huizing et al. proposed the Median Routing Problem (MRP) to optimally schedule agents to a given set of non-urgent tasks, such that the response time for urgent tasks remains minimal. They proposed both an exact MILP-solution and a fast, scalable and accurate heuristic. However, when implementing the MRP-solution in a real-life pilot with a Dutch railway provider, we found that the model needed to be extended by including additional practical objectives and constraints. Therefore, in this paper, we extend the MRP to the so-called Enriched Median Routing Problem (E-MRP), making the model much better aligned with considerations from practice. Accordingly, we extend the MRP-based solutions to the E-MRP. This allows us to compare the performance of our proposed E-MRP solutions to performance obtained in the current operational practice of our partnering railway infrastructure company. We conclude that the E-MRP solution leads to a strong reduction in emergency response times compared to current practice by smartly scheduling the same volumes of non-urgent tasks.

Optimization of maintenance strategies for steam boiler system using reliability-centered maintenance (RCM) model – A case study from Indian textile industries

PurposeThis study focuses on the application of reliability-centered maintenance (RCM) to a textile industry steam boiler. The study aims to demonstrate the development and application of RCM to a steam boiler used in the textile industry.Design/methodology/approachRCM is a structured process that develops maintenance activities needed on physical resources in their operational environment to realize their inherent reliability by logically incorporating an appropriate mixture of reactive, preventive, condition-based and proactive maintenance methods. A detailed analysis of the RCM approach is presented to develop preventive maintenance (PM) program and improve the reliability and availability of the steam boiler system.FindingsThe research reveals that the identification of PM tasks is a good indicator of the PM program's efficiency and can serve as an important maintenance-related downtime source. It is also discovered that the majority of maintenance programs that claim to be proactive are, in fact, reactive. This article also shows how RCM may be successfully implemented to any system, resulting in increased system reliability.Research limitations/implicationsThe paper focuses on a pilot study of the development and implementation of the RCM technique to a textile industry steam boiler. It is suggested that the developed RCM model can be applied to the entire plant.Originality/valueThe paper presents a comprehensive RCM model framework as well as an RCM decision framework, providing maintenance managers and engineers with a step-by-step approach to RCM implementation. The proposed framework is significant in that it may be utilized for both qualitative and quantitative analysis at the same time.

Application of RCM and FMEA Methodology to Improve Industrial Maintenance Management: A Case Study of Fibers for Mattresses

In industrial manufacturing, there are techniques that can identify certain risks in the processes that cause inconsistencies in the operation of equipment, hazards for the operator and waste. One of the supports of industrial engineering in the company are the Preventive Maintenance (PM) tasks that focus their efforts on analyzing the operation of critical devices that could degrade the quality of the products obtained. Companies that have an average system of attention to machinery and equipment perform corrective maintenance (CM) or preventive maintenance tasks that are not very successful, due to a deficient knowledge or training in repair, which generates high percentages of waste, low quality, and even reprocessing. Failure mode and effects analysis and reliability-centered maintenance are systematic tools based on team working which usually can be used for identify, prevent, eliminate or control the potential errors causes of failure in a system or process. In this paper, it is intend to reorganize preventive maintenance planning and obtain effective results with all the information and data available specifically on a machine dedicated to the transformation of a raw material to obtain fibers used in mattress filling. Keywords: Preventive Maintenance, Failure mode and effect analysis, reliability centered maintenance. DOI: 10.7176/IEL/12-1-04 Publication date: January 31 st 2022

Integrated planning framework for preventive maintenance grouping: A case study for a conveyor system in the Chilean mining industry

Increasingly complex production environments pose new challenges and require the development of new methodological approaches in the search for effective and cost-efficient maintenance planning, taking into account their applicability in real industrial environments. In this context, this article proposes an extension of the integrated framework for opportunistic preventive maintenance (PM) planning, proposed originally in Viveros et al. integrating non-negligible execution times of PM activities and time-window tolerances criterion for the generation of opportunistic grouping schemes. This work offers the implementation of the proposed framework in a practical case within the Chilean mining industry, expanding the analysis on scarce resource availability scenarios for PM tasks to be performed on conveyor belts in the grinding process. The proposed planning optimization model is formulated under the mixed-integer linear programming (MILP) paradigm, and searches minimizing the asset unavailability under several tolerance levels for the case study analyzed. The results show a 35% downtime reduction for a maximum tolerance factor of 10% considering an unconstrained maintenance resource scenario, which confirms the ability of the model to increase asset availability, minimizing system interruptions, improving its cost efficiency, and enhancing productivity levels in the mining industry.

Hierarchical multi-agent predictive maintenance scheduling for trains using price-based approach

While the progress of predictive maintenance has been rising in various application fields and several feasibility studies and prototypes have been developed, the operational implementation of predictive maintenance requires a more flexible and adaptive scheduling of the predicted maintenance interventions. Contrary to the traditional preventive maintenance tasks that are typically known long in advance, predictive maintenance may require very short-term schedule changes which are also affecting the operation. Railway rolling stock has some special requirements in terms of time table adherence and vehicle scheduling and routing that make the operational implementation of predictive maintenance particularly challenging. In this paper, we propose a hierarchical multi-agent framework for the predictive maintenance scheduling of passenger railway wagons. Besides fulfilling the requirement of scheduling the maintenance of a wagon before it fails (and potentially causes delays), also the passenger demand must be satisfied and the trains must be accordingly assigned to different routes following the time table. We propose a hierarchical distributed learning algorithm using dual decomposition and mechanism design approach. The proposed framework enables to preserve local preferences and particularities and to avoid high computational cost. In the proposed method, first, we decompose the centralized problem using the dual decomposition method, and handle the passenger demand fulfillment constraints by Lagrange multiplier (“shadow price”). Furthermore, the wagons with the private information on the system health need to perform the maintenance before their failure time (with a predicted remaining useful lifetime (RUL) and the corresponding uncertainty). To achieve this aim, we propose a mechanism design approach to align the wagons’ objective function to the aim of the central system using an incentive signal. The incentive signal creates a non-cooperative game among the wagons. We prove that the Nash Equilibrium (NE) of this game is the optimal solution of the predictive maintenance scheduling. The effectiveness of the proposed method is demonstrated on a case study of a small railway network.

Optimization of preventive maintenance intervals integrating risk and cost for safety critical barriers on offshore petroleum installations

Preventive maintenance (PM) of safety critical barriers on offshore petroleum installations is an important activity for protecting against major offshore accidents. However, it is worth noting that the increased risk and maintenance cost during the PM task is often left out in the determination of PM interval. In this paper, a multi-objective optimization approach is proposed with newly-defined risk, cost criteria and constraints to determine the optimum PM intervals for safety critical barriers on offshore petroleum installations. The proposed framework is comprehensive and quantitative, which comprises three main modules: initialization of PM interval set, risk assessment & maintenance cost evaluation, and multi-objective optimization with PSO. Details and the related results of the three modules are given. The case study validates the effectiveness of the proposed framework and reveals that the increased risk during the PM task has a significant impact in the determination of PM intervals. The results also demonstrate that a longer interval can be recommended when the risk increase, risk reduction and maintenance cost are taken into consideration comprehensively. The presented approach achieves the optimization of PM intervals integrating risk and cost for safety critical barriers on offshore petroleum installations, which is capable of guiding the PM implementation with higher accuracy for the offshore petroleum enterprises.

Joint optimization of preventive maintenance and production scheduling for multi-state production systems based on reinforcement learning

Preventive maintenance and production scheduling are two important and interactive activities in production systems. In this work, the integrated optimization problem of production scheduling for multi-state single-machine production systems experiencing degradation processes is investigated. Preventive maintenance tasks and jobs scheduling are jointly considered to find the optimal production policy by considering the processing costs, the maintenance costs, and the completion rewards, simultaneously. We formulate the integrated optimization problem as Markov decision process framework. R-learning algorithm is introduced to maximize the long-run expected average rewards per time unit over infinite horizon. On the basis of the analysis of the optimal stationary policy, the appropriate condition to perform preventive maintenance following optimal stationary policy is presented. This provides the basis for the improvement in R-learning algorithm. Furthermore, a novel heuristic reinforcement learning method is proposed to deal with the integrated model more efficiently. Finally, we present the simulation results and analysis of the proposed algorithm's performance in terms of the number of job types and machine states. The simulation results and analysis show the effectiveness of the proposed approach for solving the integrated problems.