Machine Maintenance Research Articles

Enhancing manual inspection in semiconductor manufacturing with integrated augmented reality solutions

On-site routine inspection often remains a manual operation in the semiconductor manufacturing industry because implementing automated solutions can be costly and technically challenging in such a highly controlled and complex environment. The manual inspection is prone to errors due to the impact of demanding physical and mental workloads. This paper presents an integrated Augmented Reality (AR) solution developed to assist manual inspection tasks in the supporting areas of semiconductor manufacturing, referred to as the sub-fab. The solution is accessible to a human worker wearing an AR headset during the inspection process at the location. We propose a system framework to deploy computational intelligences of varying granularity provided by the solution across cloud, edge, and device levels, accommodating constraints within the sub-fab. A machine maintenance module helps estimate and monitor the health condition of running scrubbers. Incorrect intentions performed by the worker on the scrubber control panel are detected through hand gesture recognition. This instantly prompts warning messages in the AR headset to prevent subsequent wrong actions. The solution can also identify abnormal device states through 6D pose estimation of objects enabled by machine learning models. A test scenario demonstrates how these functional features enhance the inspection efficiency and quality by reducing human workloads. This work demonstrates that semiconductor manufacturing may require AR-assisted functions different from those needed or common in other industrial sectors. It also highlights the potential of AR technology for reducing operational human errors in manual tasks.

Perbaikan Nilai Overall Equipment Effectiveness dengan Metode Total Productive Maintenance pada PT. Electric Vehicle Trimotorindo

This research was conducted to increase the Overall Equipment Effectiveness (OEE) value at PT Electric Vehicle Trimotorindo, which is an electric vehicle manufacturing company. The main problem faced by the company is the decline in OEE value every month due to lack of machine maintenance and deterioration in production quality. The method used in this study is Total Productive Maintenance (TPM), which involves identifying the factors that cause production losses through the analysis of Six Big Losses. The results show that the OEE value has increased from 78.61% to 80.36% after improvements through TPM, especially in increasing the quality rate from 88.48% to 92.23%. The conclusion of this study is that the application of TPM can improve the effectiveness of machine use and production quality, which ultimately contributes to the improvement of the company's productivity.

Knowledge Graph Completion for High-Speed Railway Turnout Switch Machine Maintenance Based on the Multi-Level KBGC Model

The incompleteness of the existing knowledge graphs in the railway domain creates information gaps, impacting their quality and effectiveness in the operation and maintenance of high-speed railway turnout switch machines. To address this, we propose a multi-layer model (KBGC) that combines KG-BERT, graph attention network (GAT), and Convolutional Embedding Network (ConvE) for knowledge graph completion in railway maintenance. KG-BERT fine-tunes a pre-trained BERT model to extract deep semantic features from entities and relationships, converting them into graph structures. GAT captures key structural relationships between nodes using an attention mechanism, producing enriched semantic and structural embeddings. Finally, ConvE reshapes and convolves these embeddings to learn complex entity interactions, enabling accurate link prediction. Extensive experiments on the HRTOM dataset, containing triplet data from high-speed railway turnout switch machines, demonstrate the model’s effectiveness, achieving an MRR of 50.8% and a Hits@10 of 60.7%. These findings show that the KBGC model significantly improves knowledge graph completion, aiding railway maintenance personnel in decision making and preventive maintenance, and providing new tools for railway maintenance applications.

Optimized Manufacturing and Construction Site Machines Maintenance Prediction using Machine Learning and Crayfish Algorithm

Efficient maintenance prediction is critical for ensuring the operational continuity and longevity of industrial machinery. This paper presents a comparative analysis of diverse machine-learning algorithms for the task of machine maintenance prediction. Through rigorous experimentation and evaluation, we assess the performance of algorithms including AdaBoost, Random Forest, Gradient Boosting, and Support Vector Machines (SVM). Additionally, to enhance predictive accuracy, we integrate an optimizer algorithm, Cuckoo Search,into our framework. This optimization technique fine-tunes algorithm parameters, further improving accuracy. Our findings offer valuable insights into optimizing machine maintenance prediction, empowering industries with proactive maintenance strategies to mitigate downtime and enhance productivity.

Infrared Imaging Analysis as Non-Destructive Maintenance of Food Processing Equipment

The use of infrared imaging is a recently developed non-destructive tool to assess the safety, quality and efficiency of the food industry. This article explores the application areas and benefits of using infrared imaging in the maintenance of machinery used in the food industry. Applications covered include food quality control, packaging inspection, temperature monitoring and control, hygiene and sanitation control, foreign object detection, energy saving through optimization, baking, as well as cooking process monitoring and research. By using infrared cameras to their full potential, it is possible to reveal defects, check the level of cleanliness, optimize the maintenance of machines, and examine the thermal attributes of food. This article also provides an in-depth analysis of the historical development of infrared imaging technology. We also explore the basic ideas behind infrared image analysis. This includes the Stefan-Boltzmann Law, Planck's Law, and Wien's displacement law. Infrared image analysis has many advantages and some disadvantages. Despite these drawbacks, infrared imaging analysis has continued benefits. It saves costs, ensures equipment longevity and increases productivity. This makes it very important for the safety of food industry machinery.

Integrated optimization of production and maintenance scheduling with third-party worker resource constraints in distributed parallel machines environment

Outsourcing machine maintenance to third parties has been a trend due to the increasing complex of machines and the benefits of maintenance outsourcing. However, this new phenomenon is ignored in previous studies pertaining to the integrated optimization of production and maintenance scheduling (IOPMS) problems, resulting the lack of theoretical guidance for production managers to formulate optimal scheduling schemes under this new trend. In this study, we investigate an IOPMS problem considering maintenance outsourcing in a distributed parallel machine environment, referred as IOPMSTW, which requires the use of third-party worker resources to perform preventive maintenance. Makespan and total cost are two optimization objectives. We first formulate the problem by developing a mixed integer linear programming. Then a memetic algorithm incorporating iterated greedy method (IG) is proposed to solve the IOPMSTW, in which an improved decoding method and a problem-dependent local search operator based on IG are designed to respectively ensure the feasibility of new generated individuals and improve the searching efficiency. The validity of proposed mathematical model is verified by CPLEX based on eight small instances. Based on 240 constructed instances, a set of comprehensive experiments are conducted. The results demonstrate that the local search operator improved the searching performance of the proposed algorithm by 100%. Comparison results with other well-known algorithms show that the proposed algorithm achieved the best results on more than 85% of the tested instances.

Decomposing maintenance actions into sub-tasks using natural language processing: A case study in an Italian automotive company

Industry 4.0 has led to a huge increase in data coming from machine maintenance. At the same time, advances in Natural Language Processing (NLP) and Large Language Models provide new ways to analyse this data. In our research, we use NLP to analyse maintenance work orders, and specifically the descriptions of failures and the corresponding repair actions. Many NLP studies have focused on failure descriptions for categorising them, extracting specific information about failure, or supporting failure analysis methodologies (such as FMEA). Whereas, the analysis of repair actions and its relationship with failure remains underexplored. Addressing this gap, our study makes three significant contributions. Firstly, we focused on the Italian language, which presents additional challenges due to the dominance of NLP systems that are mainly designed for English. Secondly, it proposes a method for automatically subdividing a repair action into a set of sub-tasks. Lastly, it introduces an approach that employs association rule mining to recommend sub-tasks to maintainers when addressing failures. We tested our approach with a case study from an automotive company in Italy. The case study provides insights into the current barriers faced by NLP applications in maintenance, offering a glimpse into the future opportunities for smart maintenance systems.

A IMPORTÂNCIA DA MANUTENÇÃO PREDITIVA NA INDÚSTRIA 4.0

In the era of Industry 4.0, technological evolution has significantly transformed the management and maintenance practices of industrial equipment. The integration of advanced technologies has enabled a more sophisticated and efficient approach to machine and facility maintenance. In this context, it becomes crucial to investigate how these innovations impact the operational efficiency of industries. How can the adoption of predictive maintenance techniques affect operational efficiency in the Industry 4.0 era? This study aimed to review the existing literature on predictive maintenance, exploring its main techniques, associated technologies, benefits, challenges, and practical applications. The investigation was conducted through databases such as thesis and dissertation repositories, Google Scholar, and Emerald Insight, analyzing 29 relevant pieces of evidence. The review was organized into three chapters, each addressing different aspects of predictive maintenance. The conclusion indicated that predictive maintenance, by allowing continuous monitoring and forecasting of failures before they occur, significantly enhances operational efficiency in industries. Its main benefits include reduced operational costs, increased production efficiency, improved safety, and optimized spare parts inventory. However, its implementation presents challenges such as initial investment in technologies and the need for specialized skills. Therefore, predictive maintenance is crucial for the competitiveness and sustainability of industrial operations in the current technological era.

Hybrid predictive maintenance model – study and implementation example

Abstract In this paper, the concept of hybrid predictive maintenance for a single industrial machine is presented. A review of the solutions in the area of machine maintenance (especially predictive maintenance) which have been described in the literature is provided. The assumptions of the hybrid predictive maintenance model for modules, machines, or systems are presented. The methods used within the developed methodology are described. This includes the use of diagnostic data, experience, and a mathematical model. A case study of an industrial machine on which a system for collecting diag-nostic data has been pilot-implemented, using, among others, vibration sensors and drive system pa-rameters for damage detection is presented. The registered data can be used to precisely determine the time of upcoming failure after detection of the characteristic symptoms resulting from component wear In addition, an analysis of the durations of correct operation and failure events was performed and indicators describing these values were determined. The values of the aforementioned indicators were determined based on empirical data and described using a gamma distribution. The objective of the research was to prepare, implement and draw conclusions on a hybrid predictive maintenance model. A real industrial machine was used in the research study. The hybrid predictive maintenance model presented in this paper enables the use of data of different types (diagnostic, historical and mathemat-ical model-based) in scheduling machine downtime for maintenance actions. On the basis of the re-search conducted, it was determined which machine operating parameters are characterised by varia-bility that enables the detection of upcoming failure. This allows for precise planning of maintenance activities and minimization of unplanned downtime.

Dynamic scheduling of hybrid flow shop problem with uncertain process time and flexible maintenance using NeuroEvolution of Augmenting Topologies

AbstractA hybrid flow shop is pivotal in modern manufacturing systems, where various emergencies and disturbances occur within the smart manufacturing context. Efficiently solving the dynamic hybrid flow shop scheduling problem (HFSP), characterised by dynamic release times, uncertain job processing times, and flexible machine maintenance has become a significant research focus. A NeuroEvolution of Augmenting Topologies (NEAT) algorithm is proposed to minimise the maximum completion time. To improve the NEAT algorithm's efficiency and effectiveness, several features were integrated: a multi‐agent system with autonomous interaction and centralised training to develop the parallel machine scheduling policy, a maintenance‐related scheduling action for optimal maintenance decision learning, and a proactive scheduling action to avoid waiting for jobs at decision moments, thereby exploring a broader solution space. The performance of the trained NEAT model was experimentally compared with the Deep Q‐Network (DQN) and five classical priority dispatching rules (PDRs) across various problem scales. The results show that the NEAT algorithm achieves better solutions and responds more quickly to dynamic changes than DQN and PDRs. Furthermore, generalisation test results demonstrate NEAT's rapid problem‐solving ability on test instances different from the training set.

Penerapan Mesin Pencetak Pelet Untuk Pakan Ternak Di Desa Sambigede Pakisaji Malang

Sambigede Village, District. Pakisaji is one of the areas that has high potential in the livestock sector in Malang Regency, the potential is around 20 thousand poultry, 100 cattle, and there are also 3 fish farming groups. So far, the animal feed pellets given by breeders are natural feed in the form of bran and other grains. Animal feed pellets, which are often referred to as pellets, are one of the most important things to pay attention to in the livestock industry, Pellets are a source of nutrition that has a huge impact on livestock, especially poultry breeders, but breeders in this village still have difficulty producing pellets because limited knowledge and technology. So it is necessary to implement an animal feed pellet printing technology machine to provide animal feed pellets in the form of feed pellets independently. The aim of this community service is to diffuse Appropriate Technology for animal feed pellet printing machines by providing knowledge and skills about how to make feed pellet products, and operation and maintenance of animal feed pellet printing machines to partners. Based on the implementation that has been carried out, production increases can be actualized to increase the production of feed pellets 40 kg/hour, so that the implementation of an animal feed pellet printing machine can provide a relatively large contribution to increasing productivity, quality, and turnover for community groups in Sambigede Village, Pakisaji, Malang.. Kata Kunci: pellet machine, pellet press machine, appropriate technology

A learning-driven multi-objective cooperative artificial bee colony algorithm for distributed flexible job shop scheduling problems with preventive maintenance and transportation operations

In recent years, distributed production scheduling problems receive much attention from both scholars and practicers. Nevertheless, existing research on such problems commonly ignores machine maintenance and job transportation operations. This work proposes a distributed flexible job shop scheduling problem with preventative maintenance and transportation operations in consideration of sequence-dependent setup time. First, a mixed integer programming model is formulated to minimize maximum completion time of jobs and maximum workload of factories. Second, a learning-driven multi-objective cooperative artificial bee colony algorithm is developed to deal with the model. A Q-learning-based cooperation strategy between population and obtained non-dominated individuals is devised to strengthen the exploration and exploitation performance. Furthermore, heuristic-based population initialization, crossover operations in employed bee phase and iterated local search methods in onlooker bee phase are specially developed considering the problem characteristics. Finally, the proposed method is compared against three well-known meta-heuristics from existing literature and an exact solver CPLEX by using a set of benchmark instances. The results confirm the competitive performance of the developed model and algorithm for addressing the studied problems.

Design Maintenance System on Mixer Machine to Prevent the Breakdown Using Reliability Centered Maintenance

Equipment, machinery, and labor are fundamental assets of an organization. Therefore, companies must have an appropriate and scheduled maintenance system. However, many manufacturing companies neglect maintenance, leading to frequent machine breakdowns that can result in machine downtime and financial losses. This research aims to determine the machine maintenance interval and the types of actions to be taken. The method employed is Reliability Centered Maintenance with the Failure Mode and Effect Analysis approach to identify failure patterns in a system and formulate the best strategies for designing a maintenance system. The results indicate that the CS-20 Type B mixer is the most critical machine, which can significantly reduce the company's production output due to machine downtime during the repair process. Based on the Reliability Maintenance method, the maintenance interval for components with potential failures is 273.17 hours for the bearing component, experiencing breakdowns three times with the highest damage occurrence within one year.

Research on Machine Tool Fault Diagnosis and Maintenance Optimization in Intelligent Manufacturing Environments

Research on Machine Tool Fault Diagnosis and Maintenance Optimization in Intelligent Manufacturing Environments

Enhanced measurement and optimization of railway profile parameters for large tamping machine operations

Abstract In the realm of modern railway maintenance, the employment of large tamping machine for the enhancement of track geometry and elasticity, and the minimization of disturbance to the roadbed, has become a key operational approach. However, factors such as repeated load applications, changes in topography and geology, and ongoing maintenance activities have been known to cause significant deviations of the actual track location from its original design. These deviations present challenges, such as increased construction difficulty and workload, during tamping operations predicated on the original design. Moreover, methods based on manual intervention have rendered large machine maintenance operations inefficient. In this paper, an optimisation method for railway profile parameters suitable for large tamping machine operations is proposed. The method integrates the total least squares method and the direct search method, enabling the accurate fitting of slope segments preceding and following the slope change points and the alignment of circular curve segments to determine the optimal curve radius. Consequently, optimised profile parameters for the continuous track section are obtained. Focusing on the Beijing–Guangzhou line, the operational efficacy of the proposed optimisation method is compared with that of the artificial slope method. The results showed that the proposed optimisation method is not only more accurate and efficient but also adheres to the principle of ‘prefer lifting rather than descending’ of the railways. The method further provides a theoretical basis and practical guidance for the optimisation of railway profile, underscoring the potential for improved maintenance efficiency and enhanced safety in train operations.

Deep reinforcement learning-based preventive maintenance for repairable machines with deterioration in a flow line system

Deep reinforcement learning-based preventive maintenance for repairable machines with deterioration in a flow line system

Cost analysis for machine repair problem under triadic policy with discouragement and multiple working vacations

ABSTRACT This study portrays the steady-state assessment of controlling the service of two removable repairmen for a machine maintenance problem with discouragement and multiple working vacations under a triadic policy. The L operating machines constitute the entire system, and it is believed that failing machines will be repaired in accordance with triadic policy and repairmen will take multiple working vacations. During the working vacation period, one repairman continues providing service and goes for another vacation as soon as queue of failed machines becomes empty. The system steady state equations are solved recursively and various performance metrics are established for constructing a system total expected cost function. Cost optimization is performed, and the optimal cost is compared using several approaches, including Particle Swarm Optimisation (PSO), the Artificial Bee Colony (ABC) algorithm, and the Genetic Algorithm (GA). The convexity behavior of the expected cost function, among choice variables with restricted region also presented graphically. Furthermore, the paper includes computational findings illustrating the impact of different parameters on the estimated optimal service rate and optimal thresholds, as well as a case study demonstrating the practical use of the designed model.

MODIFIKASI SISTEM ERETAN PADA EMCO COMPACT 5-PC CNC LATHE

The EMCO Compact 5-PC CNC Lathe engine made in Austria in the laboratory majoring in Mechanical Engineering, Sam Ratulangi University has not been operating due to the use and maintenance of machines that have been lasted for years so that they are not maintained and cannot be operated anymore. In order to be operated again, the machine needs to be repaired and modified. The purpose of this study is the modification of the eretan system in the EMCO Compact 5-PC CNC Lathe by adding a belt transmission system and calibrateing the motor stepper using a computer, so that a more precise product can be produced. Modification of the EMCO Compact 5-Pc CNC Lathe eretan system has been successful. The Modification Process of EMCO Compact 5-Pc CNC Lathe carried out is the replacement of old components with new components and assembling the grade system components based on the CAD image that has been created. Then the machine is connected to a computer/laptop to calibrate and adjust the speed of the stepper motor on the X axis, Y axis, and X axis through the GRBL Controller Software so that the resulting movements are the same as those programmed. Keywords: Modification, CNC Lathe, CAD, Calibration, Stepper Motor, GRBL, Arduino Microcontroller

Design a Mobile Application for the Maintenance of Hemodialysis Machines using Flutter Framework

Design a Mobile Application for the Maintenance of Hemodialysis Machines using Flutter Framework

Sequential testing in batches with resource constraints

This paper studies a problem of determining the state of a system through costly tests of its components, where components can be tested simultaneously in batches to exploit economies of scale. This problem is a generalization of the classical sequential testing problem and it has applications in various settings, including machine maintenance, disease diagnosis, and new product development. We prove that the problem is strongly NP-hard, model it as a mixed-integer programming formulation, and we also propose a dynamic program for it. Additionally, we design a tabu search and a hybrid solution method that combines a tabu search metaheuristic and a proximity search matheuristic. Based on extensive computational experiments, we find that the dynamic program can solve instances with up to 25 components within a 15-minute time limit and 16 GB of RAM. With respect to larger instances, the proposed metaheuristic and hybrid method are better than a greedy heuristic.