Preventive Maintenance Planning Research Articles

Research on joint scheduling method of order grading and machine maintenance

AbstractIn the multi‐variety and large‐scale order production mode, enterprises must balance delivery deadlines and maintain customer satisfaction while also considering the health status of machines. Therefore, the authors propose a method for jointly optimising production scheduling and machine maintenance. Before machine processing, an order value grading and sorting model and a machine health‐status group partitioning model are constructed to classify orders into different production value levels and machines into different health‐status groups, respectively. During machine processing, based on the Weibull distribution theory, a ‘health evaluation function value’ constraint machine preventive maintenance (PM) model and PM strategy are proposed to account for the changing health status of machines; these are integrated with the order allocation machine strategy as decision‐making elements in the production schedule. Finally, two case studies are used to verify the effectiveness of this proposed model and method. The results show that compared to general scheduling schemes, the proposed method can reduce total delay and improve customer satisfaction. Additionally, the PM plan proposed in this method can improve production efficiency and line stability compared to periodic maintenance.

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.

Advancing predictive maintenance for gas turbines: An intelligent monitoring approach with ANFIS, LSTM, and reliability analysis

Gas turbine malfunctions can significantly impact production and safety. This study proposes an intelligent monitoring system for MS5002C gas turbines using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Long Short-Term Memory (LSTM) algorithms for real-time anomaly detection and predictive maintenance. Based on extensive historical data (1985–2021), the system predicts component degradation and calculates failure probabilities. This enables the development of an effective preventive maintenance plan, extending turbine life and optimizing performance.

Kaizen: Improving Productivity and Reducing Waste in a Manufacturing Company: a Practical Case Study

Purpose: The goal of the research article is to reduce waste in the bandage winding machine. This is achieved through the application of the Kaizen methodology, which is based on continuous improvement and the participation of all employees by presenting a case study in a manufacturing company. Theoretical Framework: The article presents a solid theoretical framework, including a review of the literature on Kaizen methodology and waste in production. The author cites well-known authors in these areas, such as J.A. García and J.L. Marín-García, who have researched the application of the Kaizen methodology in manufacturing companies. Design/Methodology/Approach: The article uses a quantitative and descriptive approach. The author collects data by diagnosing the current situation, implementing strategies, applying the Kaizen methodology, and developing a preventive maintenance plan. Findings: The results of the article are positive. The author manages to reduce the waste in the bandage winding machine by 1%. This is because the changes made in the speed of operation, the implementation of strategies, the application of the Kaizen methodology and the establishment of a preventive maintenance plan have all contributed to reducing machine downtime and defects in the bandages. Research, Practical & Social Implications: The author demonstrates that the research is original and creative. The article presents a novel approach to reducing waste in production, which combines the Kaizen methodology with preventive maintenance. The results of the article have significant practical and social implications. Reducing waste in production can help improve efficiency, reduce costs, and increase product quality. In addition, the Kaizen methodology can be applied to other productive contexts, which could generate similar benefits. Originality/Value: The item is original and valuable. The author presents a novel approach to reducing waste in production, which combines the Kaizen methodology with preventive maintenance. The results of the article are positive and have significant practical and social implications. Value in proposing concrete actions to address identified problems and improve the production process.

Optimal Preventive Maintenance Scheduling for Wind Turbines under Condition Monitoring

Renewable energy sources, such as wind and solar, are positioned to play a pivotal role in future energy systems. In this paper, we propose a mathematical model for calculating and regularly updating the next preventive maintenance plan for a wind farm. Our optimization criterion considers various factors, including the current ages of key components, major maintenance costs, eventual energy production losses, and available data monitoring the condition of the wind turbines. Employing Cox proportional hazards analysis, we develop a comprehensive approach that accounts for the current ages of critical components, significant maintenance costs, potential energy production losses, and data collected from monitoring the condition of wind turbines. We illustrate the effectiveness of our approach through a case study based on data collected from multiple wind farms in Sweden. Our results demonstrate that preventive maintenance planning yields positive effects, particularly when the wind turbine components in question have significantly shorter lifespans than the turbine itself.

Reliability-Centered Preventive Maintenance Optimization for a Single-Component Mechanical Equipment

Due to the high failure rates of mechanical equipment with complex structures and numerous moving parts, devising an effective preventive maintenance (PM) plan and avoiding the influence brought by failure is crucial. However, some PM efforts are disorganized, unpractical, and unscientific, leading to prolonged downtime and significant cost losses. The challenge in creating PM plans is exacerbated by the asymmetry between maintenance and failure data. Therefore, focusing on single-unit mechanical equipment, the reliability-centered maintenance (RCM) idea is put forward to find out the key parts to implement preventive maintenance, and PM models are built to draw up a more reasonable PM plan. Such strategies aim to lower maintenance costs and enhance economic performance. Data on past maintenance and failures are analyzed to determine the life distribution and maintenance effect functions, helping to quantify the uncertainty caused by data asymmetry. Two PM optimization models considering time-varying failure rates are proposed: one focuses on minimizing costs, while the other aims to maximize availability. A PM plan example is demonstrated using a component from a tire-building machine including six parts, which proves the validity of the models. The availability results of two parts corresponding to the maintenance strategy obtained by the availability maximization model are above 0.99, and the results of total costs per unit time of the remaining four parts obtained by the cost minimization model are under 5.69.

Prediction method for the truck's fault time in open-pit mines based on exponential smoothing neural network

The transport truck is one of the important equipment for open-pit mines, and predicting the truck's fault time is of great significance in improving the economic benefits of open-pit mines. In this paper, we discuss the reason for the large prediction error of the exponential smoothing method. Then, we propose a novel nonlinear exponential smoothing method (ESNN) for predicting the truck's fault time, and demonstrate the equivalence between our approach and the neural network structure. Finally, based on the augmented Lagrange function, the solving method of ESNN is proposed. We conduct experiments on real-world datasets and our results demonstrate the effectiveness of ESNN in comparison to existing state-of-the-art methods. Our approach makes it easier for maintenance personnel to predict fault situations in advance and provides a basis for enterprises to develop preventive maintenance plans.

Intervention strategies to implement a preventive conservation and maintenance plan in concrete buildings in the modern period of Bogotá

Reinforced concrete was the material of choice for many architects of the modern era, exploiting the material in a multitude of creative and innovative ways. Many of the most extraordinary structures of the modern era demonstrate the potential of reinforced concrete and illustrate the rapid evolution of the material throughout the 20th century. It is the most used material in the construction industry due to its high resistance and its ease of molding when it is prepared, it also contains steel in the form of rod and wire, with a useful life of its components, built as a system, for more of one hundred years as long as they are well designed, well built and above all they are given adequate maintenance. However, the durability of concrete structures depends on several main environmental factors, the quality of the raw material and its maintenance. Some of the studies and research projects on the subject of Concrete focus on the historiography of reinforced concrete in Colombia, where some authors highlight aspects of construction processes, technical innovations, construction companies, and architecture and engineering projects that were pioneers in the 20th century. In Colombia, a historical context of this material and the most representative projects in the city of Bogotá, Colombia are detailed below.

Application of XGB-based metaheuristic techniques for prediction time-to-failure of mining machinery

Mining equipment is a critical component in the success of mining operations, and unplanned downtime can be costly. Efficient and intelligent maintenance planning is therefore essential to minimize downtime and maximize productivity. Consecutive time-to-failure (TTF) is an important indicator of machine reliability, and accurate TTF predictions enable effective preventive maintenance planning. Therefore, this study proposes hybrid models of extreme gradient boosting (XGB), optimized by particle swarm optimization (PSO) and gray wolf optimization (GWO), for the prediction of TTF in mining machinery. Additionally, validation of the hybrid model was conducted using support vector regression (SVR) method. Historical data on mining machine failures were collected, and a case study was conducted to investigate shovels in an open-pit mine. The PSO-XGB method was found to be the most accurate predictor of failure time with R2 values of 0.99, RMSE values of 50.66 and 51.77, MAE values of 4.52 and 10.81, and AARE values of 1.15 and 1.24 in the training and testing phases. This research highlights the importance of efficient and intelligent maintenance planning to minimize downtime and optimize productivity in mining operations.

Preventive maintenance optimization for key components of subway train bogie with consideration of failure risk

With the acceleration of urbanization, the number of urban rail transit trains has increased dramatically, and the economy and safety of subway trains have become important standards. As an essential subsystem of the subway train, the bogie has a long maintenance process and serious failure consequences. So, it is essential to formulate a reasonable maintenance strategy to ensure its operation. To solve the above problems, a preventive maintenance (PM) strategy for key components of train bogie is established with consideration of failure risk in this paper. Firstly, the failure risk factors of the bogie components are scored and weighted, and the failure risk cost model and PM cost model are established. Next, a Weibull distribution parameter estimation method for bogie components based on the improved beluga whale optimization algorithm (IBWO) is proposed, providing a theoretical basis for PM decision-making optimization. Then, the Lévy flight is introduced into particle swarm optimization to enhance the optimization performance of the model and obtain the optimal solution. Finally, the bogie key components of Nanning Metro line 1 are selected as a case study. The results show that the IBWO algorithm has strong applicability and feasibility, and can accurately calculate the Weibull parameter values of the bogie key components. Compared with the PM plan without considering the failure risk, the proposed method is more economical and safer, which can provide necessary theoretical support for the maintenance decision optimization of urban rail transit train components.

Refined evaluation methods for preventive maintenance of project-level asphalt pavement based on confusion-regression model

Accurate evaluation of the performance of airport pavement can help managers make scientific and systematic preventive maintenance (PM) decisions, ensuring pavement safety and extending service life. To this end, firstly, this paper sorted out the pavement performance evaluation index system, based on which a multi-dimensional evaluation system for PM was proposed, including control indexes, macroscopic indexes, and microscopic indexes. Then, the pavement decay model based on the pavement condition index (PCI) was developed, and the regression model between PCI and International roughness index (IRI) and friction coefficient (μ) was established. Finally, by converting the PM decisions for project-level pavement into a binary classification problem in machine learning, the optimal maintenance thresholds and intervals for PM of each index were determined using receiver operating characteristic (ROC) curve and Kolmogorov-Smirnov (K-S) curve. The optimal threshold represents the threshold when the index can separate the binary classification problem (PM decisions) with maximum probability. Based on confusion-regression model, the pavement performance can be evaluated more comprehensively, and the timing of PM can be accurately determined. The model helps airport managers develop accurate PM plans to address future maintenance needs.

Scheming preventive maintenance assignments for mass rapid transit (MRT): Taoyuan Metro MRT system

Mass rapid transit (MRT) maintenance systems enable owners to make optimal decisions for site selection and preventive maintenance plans while considering the total operating costs. To ensure that the MRT planning system is effective, it is essential to construct a maintenance cost plan. This study implements the mathematical planning method to establish a comprehensive plan for route maintenance and preventive maintenance for the Taoyuan MRT based on the minimum total operating cost as the target, and meets the practical emergency repair time limit, site location distance and other relevant constraints. This study developed and evaluated novel heuristic algorithms with CPLEX software. Sensitivity analysis was also conducted to test the model’s effectiveness. The proposed model establishes the optimum maintenance cost and finds the critical parameters that affect overall cost within 1% error, maintaining service quality. The proposed model is an accurate tool for engineers to reduce time-consuming procedures.

Optimal production and non-periodic maintenance plan for a degrading serial production system with uncertain demand

Over the past few decades, economic globalisation has intensified the competition among international enterprises. So, firms are working hard to improve their performances to stay competitive in markets. In the industrial domain, firms are continuously looking for the improvement of their production systems’ availability and the optimisation of production planning to assure the satisfaction of a random demand. Therefore, joint maintenance and production optimisation have been receiving increasing attention from researchers and firms. This study deals with joint nonperiodic preventive maintenance and production planning optimisation with regard to a manufacturing system composed of several machines mounted in series. The relationship between failure rate and production is considered to indicate the influence of variation of the production rate on the failure rate along with the average number of failures. The non-periodic preventive maintenance with respect to the production planning is proposed, to assure the continuity of the machines’ reliability by minimising the failures. In this paper, a mixed-integer-linear programme is developed to jointly find the optimal planning of integrated non-periodic preventive maintenance to production by minimising the total cost. Experimental results are presented to study the impact of the failure rate threshold on the number and periods of preventive maintenance actions.

An integrated automated guided vehicle design problem and preventive maintenance planning

An integrated automated guided vehicle design problem and preventive maintenance planning

Proposal of a predictive and preventive maintenance plan in electrical substations through the use of thermography

The objective of this study was to make a proposal for a predictive and preventive maintenance plan in the electrical substations La Propicia, Las Palmas, and La Pradera belonging to CNEL-EP Esmeraldas Business Unit through the use of thermography. The methodology was of a qualitative approach, under the type of documentary-bibliographical research. The search for information was carried out online in scientific and academic databases. It was found that the information on the maintenance plans in the subtransmission system of CNEL EP Esmeraldas Business Unit, is meager, preventive and predictive maintenance actions are carried out such as revision, washing, readjustment and replacement of elements in poor condition, but no information was found on the analysis technique used leading to the maintenance activities of electrical equipment and installations. The results of the consulted investigations agree that the thermographic technique and its tools such as drones, infrared cameras and software programs are very useful for the diagnosis, collection and processing of data in electrical systems to determine maintenance requirements. Finally, the investigation yielded substantial information that allowed the preparation of a maintenance plan for the aforementioned La Propicia, Las Palmas and La Pradera electrical substations of CNEL-EP Esmeraldas Business Unit through the use of infrared thermography, to assist in their better operation. and performance by allowing the evaluation of the state of the equipment that makes up the electrical system of the aforementioned substations.

Advanced Fault-Detection Technique for DC-Link Aluminum Electrolytic Capacitors Based on a Random Forest Classifier

In recent years, significant technological advances have emerged in renewable power generation systems (RPGS), making them more economical and competitive. On the other hand, for the RPGS to achieve the highest level of performance possible, it is important to ensure the healthy operation of their main building blocks. Power electronic converters (PEC), which are one of the main building blocks of RPGS, have some vulnerable components, such as capacitors, which are responsible for more than a quarter of the failures in these converters. Therefore, it is of paramount importance that the design of fault diagnosis techniques (FDT) assess the capacitor’s state of health so that it is possible to implement predictive and preventive maintenance plans in order to reduce unexpected stoppage of these systems. One of the most commonly used capacitors in power converters is the aluminum electrolytic capacitor (AEC) whose aging manifests itself through an increase in its equivalent series resistance (ESR). Several advanced intelligent techniques have been proposed for assessing AEC health status, many of which require the use of a current sensor in the capacitor branch. However, the introduction of a current sensor in the capacitor branch imposes practical restrictions; in addition, it introduces unwanted resistive and inductive effects. This paper presents an FDT based on the random forest classifier (RFC), which triggers an alert mechanism when the DC-link AEC reaches its ESR threshold value. The great advantage of the proposed solution is that it is non-invasive; therefore, it is not necessary to introduce any sensor inside the converter. The validation of the proposed FDT will be carried out using several computer simulations carried out in Matlab/Simulink.

Optimization of maintenance for complex manufacturing systems using stochastic Remaining Useful Life prognostics

This paper leverages Remaining Useful Life (RUL) prognostic information for preventive maintenance planning in complex manufacturing factories. Such a factory consists of multiple complex systems that use redundant components as backups to ensure system availability. The purpose is to minimize production fluctuations in the factory due to maintenance or system breakdown. To achieve this, we propose a Mixed-Integer Linear Programming (MILP) model that minimizes the overall production loss. Furthermore, we incorporate random RUL decrease rates according to reliability theory and extend the MILP model using chance-constrained programming. A novel approximation method for dealing with chance constraints is proposed to solve the stochastic model and approximation properties are analyzed. Computational results show that (i) our MILP model can provide more reasonable maintenance decisions compared to the literature. (ii) Sensitivity analysis reports that RUL prognostics and thresholds significantly impact maintenance decisions. (iii) The analysis of the impacts of confidence levels in chance constraints provides decision-makers with the flexibility to adjust maintenance planning under different levels of uncertainty.

A Multicriteria Method to Form Optional Preventive Maintenance Plans: A Case Study of a Large Fleet of Vehicles

Motor vehicles are composed of a large number of parts, and planning the maintenance activities of different parts is a crucial decision that affects system reliability, operation costs, and capacity requirements of service providers. We propose a systematic method to determine the critical parts that should be handled with extra preventive maintenance (PM) and prepare alternative PM plans with different levels of cost and capacity usage. Our method uses a multicriteria decision-making approach to determine the critical parts and conducts statistical reliability analysis with failure data and expert knowledge to create the maintenance plans. We use the proposed method in a case study to determine optional PM packages that would support regular PM practices in the after-sales service of a large motor vehicle manufacturer. The main aim of the case study is to increase the satisfaction of customers who are more sensitive to failures, such as carriers of food and medical supplies. The results show that the optional PM packages can decrease the cost of failures while obeying the capacity limitation of the company.

Improving Cultural Heritage conservation: LSTM neural networks to effectively processing end-user’s maintenance requests

Preventive conservation of cultural heritage can avoid or minimize future damage, deterioration, loss and consequently, any invasive intervention. Recently, Machine Learning methods were proposed to support preventive conservation and maintenance plans, based on their ability to predict the future state of the built heritage by collected data. Several data sources were used, such as structural data and images depicting the evolution of the deterioration state, but till now textual information, exchanged by people living or working in historical buildings to require maintenance interventions, was not used to support conservation programmes. This work proposes a method to support preventive conservation programs based on the analysis of data collected into CMMS (computer maintenance management software). In a Cultural Heritage building in Italy, hosting a University Campus, data about end-user’s maintenance requests collected for 34 months were analysed, and LSTM neural networks were trained to predict the category of each request. Results show a prediction accuracy of 96.6%, thus demonstrating the potentialities of this approach in dynamically adapting the maintenance program to emerging issues.

Improving Cultural Heritage conservation: LSTM neural networks to effectively processing end-user’s maintenance requests

Preventive conservation of cultural heritage can avoid or minimize future damage, deterioration, loss and consequently, any invasive intervention. Recently, Machine Learning methods were proposed to support preventive conservation and maintenance plans, based on their ability to predict the future state of the built heritage by collected data. Several data sources were used, such as structural data and images depicting the evolution of the deterioration state, but till now textual information, exchanged by people living or working in historical buildings to require maintenance interventions, was not used to support conservation programmes. This work proposes a method to support preventive conservation programs based on the analysis of data collected into CMMS (computer maintenance management software). In a Cultural Heritage building in Italy, hosting a University Campus, data about end-user’s maintenance requests collected for 34 months were analysed, and LSTM neural networks were trained to predict the category of each request. Results show a prediction accuracy of 96.6%, thus demonstrating the potentialities of this approach in dynamically adapting the maintenance program to emerging issues.