Maintenance Planning Decisions Research Articles

Developing hybrid machine learning models to assign health score to railcar fleets for optimal decision making

A large amount of data is generated during the operation of a railcar fleet, which can easily lead to dimensional disaster and reduce the resiliency of the railcar network. To solve these issues and offer predictive maintenance, this research introduces a hybrid fault diagnosis expert system method that combines density-based spatial clustering of applications with noise (DBSCAN) and principal component analysis (PCA). Firstly, the DBSCAN method is used to cluster categorical data that are similar to one another within the same group. Secondly, PCA algorithm is applied to reduce the dimensionality of the data and eliminate redundancy in order to improve the accuracy of fault diagnosis. Finally, we explain the engineered features and evaluate the selected models by using the Gain Chart and Area Under Curve (AUC) metrics. We use the hybrid expert system model to enhance maintenance planning decisions by assigning a health score to the railcar system of the North American Railcar Owner (NARO). The model is based on data from one specific railcar type. We utilize the results of data-driven models to assign a health rate to each railcar. Finally, we use data from NARO to evaluate and verify our proposed framework.

Optimising O&M scheduling in offshore wind farms considering weather forecast uncertainty and wake losses

Offshore wind farms, while strategically positioned to maximise wind energy capture, are exposed to harsh environments, impacting their reliability and accessibility. Low reliability and accessibility in turn translate into high Operation and Maintenance (O&M) costs, which represent approximately 30% of the total lifetime costs of the project. One approach to reduce O&M costs is to improve maintenance planning decisions. The present paper presents a novel O&M scheduling methodology for offshore wind farm operations based on wind and wave forecasts. The methodology forecasts farm yield considering farm wake effects to identify optimal operation schedules, vessel routing, and turbine maintenance sequences that minimise costs and revenue losses due to downtime. Weather forecast uncertainty is modelled and integrated into the decision-making process to minimise weather risks. A case study inspired by the WindFloat Atlantic floating wind project was used to demonstrate the optimisation potential. Results suggest that adopting the proposed methodology over business-as-usual scheduling significantly boosts offshore wind farm operational profits during the forecasted period, with increases ranging from 2% to 24%, depending on the scenario considered. It was found that integrating the wind farm wake losses into the scheduling decisions can improve the optimal scheduling solution and further minimise total operation costs.

A Joint Optimization Model of Production Scheduling and Maintenance Based on Data Driven for a Parallel-Series Production Line

The maintenance of a production line is becoming more important with the development of demanding higher operational efficiency and safety in industrial system. However, a production line often operates under dynamically operational and environmental conditions and the production scheduling is also a very important factor for the maintenance of a production line. First, this paper proposes an integrated data-driven model that coordinates maintenance planning decisions with production scheduling decisions to solve the problem of scheduling and maintenance planning for a parallel-series production line. The degradation information is considered, and the total cost is to be minimized in the proposed model. Also, the total cost is related with production process and maintenance considering reliability of equipment. Then, in order to better describe the relationship between production and maintenance, the accumulative processing time of equipment is used as the input of its failure function. Also, an ability factor is developed to control its reduced level by adopting preventive maintenance. Finally, a case study is used to demonstrate the implementation and potential applications of the proposed model. The long-term wear test experiments are conducted at a research laboratory facility of Shanghai Pangyuan Machinery Co., Ltd. The result proves that the proposed method is feasible and efficient to solve the joint decision-making problem for a parallel-series production line with multivariety and small batch production. The proposed model in this paper is suitable for semiconductor manufacturing.

The Impact of Maintenance Planning on Large Project Management Performance

Structured methodologies and tools for the tailored design of factories are adopted by suppliers of manufacturing systems but usually discontinued after the design phase. The use of an ontology-based virtual factory, continuously synchronised with the real plant, is proposed to guarantee digital continuity and enable in-situ simulation during the operating phase. This digital counterpart of the system can be used for integrated shop-floor simulations to assess production and maintenance planning decisions' future impact. An industrial application is provided in the context of roll shops, i.e., systems devoted to the grinding of cylinders for rolling mills.

Optimizing the integrated production and maintenance planning using genetic algorithm

In spite of the interdependence between them, production and maintenance planning decisions are generally studied and used independently in the majority of the manufacturing systems. Our contribution is summarized to obtain a maintenance policy including preventive replacement in each maintenance cycle and minimal repair in case of unplanned failure, and on the other side, for a set of products and in each period, specify the quantity to be produced and when is the production set up, also the stock and the breaking on demand level, so that to minimize the total cost. The purpose of the research was aimed at achieving the optimization of an integrated planning of preventive maintenance and production in a multi-period, multiproduct, and single-line production system. To achieve this purpose, our model is configured as a mixed integer linear programming and solved by IBM ILOG CPLEX OPL studio 12.6 (USA), and we propose our own genetic algorithms (GAs) using Python solver with respect to resolution time and the quality of results. Then, to find the performance of the model and the usefulness of the proposed resolution method, a numerical example is considered to produce two products for a finite horizon with 11 periods. The results of the analysis show that this GA provides a new tool for the integrated planning in the industrial sector. These results reflect the experiences of single-line system and further studies are needed for generalizability in the multiline cases, also we will compare the proposed GA with other evolutionary algorithms.

Aircraft routing with generalized maintenance constraints

The literature on aircraft maintenance routing generally ignores the full range of maintenance requirements by only considering the most frequent maintenance type. The range of maintenance types and variety of individual aircraft's ages and utilization rates means the maintenance demand for each aircraft differs from one period to another, thus complicating aircraft routing decisions. This study proposes a new formulation of the aircraft maintenance routing problem in which maintenance requirements are built as generalized capacity constraints, ensuring sufficient maintenance opportunities are available within the planned routes to satisfy the maintenance demands of individual aircraft. Our new approach suggests minimizing maintenance misalignment using an interactive mechanism between aircraft routing and maintenance planning decisions. The computational results using real datasets reveal continuous reduction and convergence in maintenance misalignment through the proposed interactive mechanism. The lack of an effective interaction between the abovementioned decisions significantly increases the maintenance misalignment costs.

Investigating the impact of social sustainability within maintenance operations

Purpose – The purpose of this paper is to primarily focus on labor in maintenance areas, addressing human rights issues, labor standards and safety standards. The main issue is to investigate how these factors are considered to drive the prioritization of maintenance interventions within maintenance plans. In particular, a method for criticality analysis of production equipment is proposed considering specific labor issues like age and gender, which can be useful to steer maintenance plans toward a more social perspective. Design/methodology/approach – The authors focus on the two main social issues of SA 8000 norms, age and gender, exploring how these issues may drive the selection of maintenance policies and the relative maintenance plans. The research is conducted through fuzzy analytical hierarchy process (AHP) implemented within a failure mode effects analysis (FMEA). Findings – The research is conducted through fuzzy AHP implemented within a FMEA. The maintenance plans resulting from the FMEA driven by social issues are evaluated by a benchmark of three different scenarios. The results obtained allowed the firm to evaluate maintenance plans, considering the impact on workers’ health and safety, the environment, social issues like gender and age. Research limitations/implications – One of the main limitation of this research is that it should also encompass maintenance costs under social and safety perspective. The method developed should be extended by further study of maintenance planning decisions subject to budget constraints. Moreover, it would be worth evaluating the effect of adopting more proactive maintenance policies aimed at improving plant maintainability in view of what emerged during the test case in the presence of an aged workforce and the subsequent need to prevent and/or protect people from hidden risks. Practical implications – With reference to the results obtained from the two models of this scenario, the authors observed an increase of equipment criticality, from B class to the A class, and similarly from C class to B class. No equipment has reduced its criticality. This depends on the particular context and the relative weights of drivers indicated in its AHP matrixes. Social implications – The paper addressed the main social implication as well as other social issues represented by age and gender factors, which are normally neglected. The Action Research (AR) proved the effects resulted from considering either gender factor or gender and age factors at the same time for maintenance policy selection. All in all, an increase of criticality is evident even if “people” is a driver with less importance than “environment” and “structures.” Originality/value – The present work focussed on a new definition of a criticality ranking model to assign a maintenance policy to each component based on workers’ know-how and on their status. The approach is conceived by the application of a fuzzy logic structure and AHP to overcome uncertainties, which can rise during a decision process when there is a need to evaluate many criteria, ranging from economic to environmental and social dimensions.

A Dynamic Maintenance Planning Framework Based on Fuzzy TOPSIS and FMEA: Application in an International Food Company

A maintenance planning framework is developed in this study to reduce and stabilize the maintenance costs of the manufacturing companies. The framework is based on fuzzy technique for order preference by similarity to ideal solution(TOPSIS) and failure mode and effects analysis (FMEA) techniques and supports maintenance planning decisions in a dynamic way. The proposed framework is general and can easily be adapted to a host of manufacturing environments in a variety of sectors. To determine the maintenance priorities of the machines, fuzzy TOPSIS technique is employed. In this regard, ‘risk priority number’ obtained by FMEA and ‘current technology’, ‘substitutability’, ‘capacity utilization’, and ‘contribution to profit’ are used as the criteria. Performance of the resulting maintenance plan is monitored, and maintenance priorities of the machines are updated by the framework. To confirm the viability of the proposed framework, a real‐world implementation in an international food company is presented. The results of the application reveal that the proposed maintenance planning framework can effectively and efficiently be used in practice. Copyright © 2015 John Wiley & Sons, Ltd.

A virtual factory approach for in situ simulation to support production and maintenance planning

Structured methodologies and tools for the tailored design of factories are more and more adopted by suppliers of manufacturing systems but usually discontinued after the design phase. The use of an ontology-based virtual factory, continuously synchronized with the real plant, is proposed to guarantee digital continuity and enable in situ simulation during the operating phase of a factory. This digital counterpart of the system can be used for integrated shop-floor simulations to assess future impact of production and maintenance planning decisions. An industrial application is provided in the context of roll shops, i.e., systems devoted to the grinding of cylinders for rolling mills.

A model for optimal maintenance interval incorporating the cost of rejections in manufacturing

PurposeThe purpose of this paper is to develop a model that incorporates the effect of rejection cost on optimal maintenance planning decisions. Such a model will help in further modelling the interrelationships between preventive maintenance and quality control policy.Design/methodology/approachIn this paper a model is developed for obtaining optimal preventive maintenance interval based on block replacement policy to incorporate the effect of rejection cost. An illustrative example is presented to compare economic performance of the proposed model (M2) and the conventional model (M1). Model M1 stands for optimal preventive maintenance interval without considering the rejection cost and model M2 stands for optimal preventive maintenance interval considering the rejection cost. The comparison is done for different production rates, costs of rejection and cost of lost production. The impact of control chart parameters on preventive maintenance decision is also studied.FindingsIn this paper it is found that model M2 gives better results as compared to model M1. The improvements are more significant at higher production rate, lower cost of lost production and higher rejection cost. The impact of control chart parameters on preventive maintenance planning decision becomes significant as the cost of rejection increases.Research limitations/implicationsConventionally only the down time cost and the cost of repair/replacement are considered for optimal maintenance interval determination. However in the case of machine tools, failure may not always bring the system immediately under complete breakdown but may lead to the functioning of system with degraded performance like process shift from in‐control state to out‐of‐control state. It results into poor quality and thus may lead to higher rejection cost. The cost of rejections may be significantly high in some production systems and, if not incorporated properly during maintenance planning decision may adversely affect the effectiveness of the maintenance planning. Hence the approach presented in this paper gives a better way of maintenance planning. Though the work presented here is illustrated through a simple example considering a single component operating as a part of machine, the approach can be extended to multi‐component system.Originality/valueThe outcome is of significant value as it opens up a new perspective into the development of integrated model for maintenance planning and quality control decisions for reducing the operating costs associated with the manufacturing processes.