Maintenance Applications Research Articles

Natural Language Processing Approaches in Industrial Maintenance: A Systematic Literature Review

Industrial maintenance plays a crucial role in manufacturing by significantly reducing machine failure time and minimizing costs, especially in the revolution of Industry 4.0. Consequently, researchers and industrial engineers have continuously focused on this area. Manufacturing companies possess extensive maintenance reports or logs containing valuable textual information, which offers a new avenue for exploring effective industrial maintenance methods. Natural Language Processing (NLP), a subfield of Artificial Intelligence, has demonstrated remarkable potential in analyzing maintenance reports and achieving promising results in various tasks. This paper presents a comprehensive systematic literature review that specifically concentrates on the applications of NLP approaches employed in the field of industrial maintenance. Additionally, this review analyzed the datasets utilized in previous studies and the evaluation measures adopted, which can serve as a valuable resource for other researchers seeking potential solutions in maintenance. Furthermore, the paper discusses the challenges encountered in applying NLP to industrial maintenance and outlines future research directions in this domain. By conducting this systematic literature review, we provide a comprehensive understanding of the current state of NLP applications in industrial maintenance, identify gaps in the existing literature, and guide future research efforts in leveraging NLP techniques for enhanced maintenance practices.

Leveraging industry 4.0 techniques for predictive equipment maintenance: From concept to commissioning

In recent decades, lean manufacturing has significantly impacted the manufacturing industry, gaining widespread adoption. Companies have increasingly recognised the competitive advantages of implementing flow-oriented production layouts, demand-flow technologies, and just-in-time production. This shift has also transformed the approach to maintenance, moving away from reactive strategies. With production cells becoming more susceptible to system disturbances, maintenance managers are now focused on strategic maintenance development to ensure reliable production equipment. The emergence of Industry 4.0 technologies has further reshaped plant maintenance, providing companies with accurate and dependable tools for proactive maintenance. This paper proposes a hypothesis of research conducted at the University of Malta, focusing on the potential application of predictive maintenance (PdM) in the upkeep of automation machinery. It suggests the use of a novel data management and acquisition system, grounded in simulation and deep learning modelling, to predict the remaining useful life (RUL) of machinery early during the design machine realisation. This exploration lays the groundwork for potential development of a comprehensive maintenance tool. Such a tool would optimise automation designs, estimate maintenance costs throughout the machine’s lifecycle, and prevent machine breakdown through proactive interventions.

A Review of Soft Crawling Robots with Different Driving Methods

Background: Traditional rigid robots are difficult to adapt to complex unstructured environments due to their limited degree of freedom and lack of flexibility. Therefore, soft crawling robots are concerned widely by their powerful deformation ability, infinite number of degrees of freedom, and effective interaction with humans. Objective: This paper aims to report the recent progress of soft crawling robots and provide a reference for readers in this field. Methods: By reading and summarizing the patents and papers related to soft crawling robots in recent years, they are divided into three categories according to different driving methods. The structure, motion mechanism, characteristics, and applications of each class of robots are compared and analyzed. Results: The advantages and disadvantages of each driving method are analyzed, and the key issues in soft crawling robots are pointed out. Based on this, the future development direction of this research field is predicted. Conclusion: The study shows that according to the driving method, soft crawling robots are classified as pressure driven, motor-wire driven, and soft active material driven. In addition, the characteristics of each drive are summarized. In the future, soft crawling robots will have more potential applications in biomedicine, outdoor survey, rescue search, and inspection and maintenance of equipment.

Multiple aspects maintenance ontology-based intelligent maintenance optimization framework for safety-critical systems

Abstract Maintenance optimization is a process for improving the efficiency of maintenance strategies and activities, considering various aspects of the target system and components, such as the probabilities of system failures and the cost of repair and replacement of a failed component. The improvement of maintenance optimization algorithms generally requires information from various data sources. For example, it may require the system risk information derived from risk analysis tools or the residual lifetime of a component from fault prognosis tools. The requirements of data acquisition (DAQ) and aggregation pose new challenges for maintenance management systems (MMSs) that implement and use these maintenance optimization algorithms. This paper proposes a multiple aspects maintenance ontology-based framework to facilitate DAQ from MMSs, online monitoring systems, fault detection and discrimination tools, risk assessment tools, decision-making tools, and component identification tools, and accelerate the implementation and verification of contemporary maintenance optimization models and algorithms. The proposed framework consists of a multi-aspect maintenance ontology with critical information for maintenance optimization and application interfaces for collecting information from various data sources, such as fault prognosis tools, online monitoring tools, risk assessment tools, and decision-making algorithms. In addition, this paper proposes a heuristic method for integrating concepts and properties from other existing ontologies into the proposed framework when the existing ontology is not fully compatible with the ontology under construction. Finally, the paper verifies the proposed ontology framework using a feedwater system designed for nuclear power plants with valves and filters as the components under maintenance.

Digitization Workflow for Data Mining in Production Technology applied to a Feed Axis of a CNC Milling Machine

Condition monitoring and predictive maintenance applications receive ongoing scientific attention in production technology. Larger companies, especially machine and component manufacturers, already offer related products. Small and medium-sized enterprises (SMEs) in particular show interest in developing and offering solutions in this market themselves to gain economic advantages, to improve resource utilization of their machines or to be able to offer these advantages to their own customers. In the development process, however, they often encounter problems already in the digitization of the machines. The first hurdle is to obtain an analysis-capable data set. This is due to the fact that common and established general data mining development process models, such as CRISP-DM, do not focus on production technology, causing difficulties for engineers during deployment. A problem with existing process models is the limited practicality in the engineering domain due to restricted adaptability. In a previous paper, a guideline for engineers for data mining suitable digitization of production machines was developed in order to solve these problems. The related results were provided in the context of a project for condition monitoring of mixing machines. In this paper, the proposed method is applied to components of a 5-axis CNC milling machine in three different monitoring use cases. A complete workflow is presented, including effect analysis, sensor selection, formulation of predictive scenarios, data preparation, training of machine learning algorithms and vizualization. Data and documentation are provided alongside this publication.

Ontology-based Digital Twin for maintenance decisions in manufacturing systems: an application at laboratory scale

In the Industry 4.0 environment, the maintenance of industrial assets is of increasing importance, and, in this domain, the recently emerged technology of Cognitive Digital Twin (CDT) is particularly suitable for the satisfaction of today’s manufacturers’ needs for flexibility, dynamism, broad vision of the systems, and responsiveness to stimuli. Although this technology shows considerable potential in supporting the execution of maintenance applications with minimum human intervention, in most cases the to-date technological level is not capable of achieving full automation, making the human role still fundamental in relation to the existing Digital Twin (DT) technologies. In this context, this paper proposes the development of an ontology-based DT aiming at supporting the maintenance fault diagnosis decision-making process in manufacturing systems through the synergistic exploitation of the maintenance ontology KARMA supported by algorithms and database technologies integrated with human knowledge. The solution is meant to enable the cognitive capabilities leading toward the CDT concept. The ontology-based Digital Twin has been applied and assessed in the reality-like facility TELMA, at the Research Center for Automatic Control (CRAN) in Nancy, through the implementation of a fault scenario.

Mechanization and import substitution in zimbabwean farmers' equipment: A case study of the revitalization of an abandoned tractor trailer

Abandonment of equipment on Zimbabwean A1 and A2 farms has significant costs for both farmers and the national economy, as farmers often continue using outdated or traditional farming methods. Maintenance practices, innovation, research, design, and modern machinery have evolved considerably over the past hundred years, shifting from old maintenance applications to planned maintenance strategies combined with Import Substitution Industrialization (ISI). For Zimbabwean farmers, adopting this approach is crucial, particularly for revitalizing farm implements and machinery. Currently, it is evident that many farm implements and equipment have been abandoned. These implements and equipment could be assessed and mechanically restored to their operational state. A mechanical assessment of abandoned equipment was conducted, focusing on main components such as the chassis and suspension to facilitate the revitalization process. This was followed by a product development plan outlined in the methodology. The abandoned trailer was dismantled, with selected components purchased locally, and then reassembled using mechanical methods. The mechanical activities involved included cutting with grinders, joining through arc welding, and using bolts and nuts. As a developing country striving to adopt modern technologies, Zimbabwe's application of Import Substitution Industrialization is a crucial strategy for embracing sustainable development. Farmers are advised to integrate basic welding knowledge into their farming activities and acquire essential machinery, such as CO2 welding machines and workbenches, for their mechanical workshops. Large-scale farmers in Zimbabwe typically have workshops equipped with these basic machining tools. The abandoned trailer was reconditioned to a functional state using basic machining methods and tools, as detailed in this paper.

Proposal of a human-in-the-loop-based framework for advancing maintenance applications for collaborative robots

Manufacturing companies are improving shop floor tasks, especially related to assembly, thanks to the installation of collaborative robots, shortly cobots. Despite their reliability, they experience intrinsic difficulties in extending the CBM (condition-based maintenance) solutions from traditional machinery. The inherent challenges are due to the cobot flexibility, on-the-job training from operator, and internal control for trajectory optimization in cobot operations. Therefore, this research work tackles the issue of developing CBM by leveraging on the human-machine collaborative setting, proposing a human-in-the-loop (HIL)-based framework. The framework is demonstrated via a laboratory-scale application through induced functional failures. The demonstration shows that, via entropy-controlled prompting, the operator can provide feedback about CBM algorithms’ prediction accuracy. Based on the current outcomes, a roadmap for further improving the HIL-based solution for cobot maintenance is proposed, with the end purpose of promoting complete monitoring of all the equipment on the companies’ shop floor fostering the smart manufacturing paradigm.

TINJAUAN PRODUCTIVE MAINTENANCE MESIN LAMINASI PACKAGING PADA PT. ULTRA PRIMA PLAST

This research was conducted to measure the effectiveness and application of the Total Productive Maintenance (TPM) method, especially on the Focused Improvement pillar on the Printing Packaging machine at PT. Ultra Prima Plast. The research was conducted using quantitative data and an Overall Equipment Effectiveness (OEE) analysis approach. The OEE value was analyzed using Six Big Losses (SBL) to find the dominant factor causing the loss. The loss factor is then classified with the 80/20% formula as a reference for making Fishbone Diagrams. Fishbone Diagram analysis is carried out to find the cause and effect or root cause of each loss. The root of the problem obtained is then given a suggestion for improvement and analyzed using the 5W+1H method. The results of the study obtained an average value of Overall Equipment Effectiveness (OEE) of 28%. This value is obtained from several calculations including the Availability Rate 97%, Performance Rate 20% and Quality Rate 98%. This value is still below the world category that has been seet by JIPM. which is 85%. The losses on the printing packaging machine are yield losses wich is 58% and reduce speed losses which is 23%. The roots on the problem found were the absence of planed maintenance and autonomus maintenance on Laminasi packaging machine and unmaintained environment inadequate knowlage of human resources and negligance of work procedures in the field.

Unknown Health States Recognition with Collective-Decision-Based Deep Learning Networks in Predictive Maintenance Applications

At present, decision-making solutions developed based on deep learning (DL) models have received extensive attention in predictive maintenance (PM) applications along with the rapid improvement of computing power. Relying on the superior properties of shared weights and spatial pooling, convolutional neural networks (CNNs) can learn effective representations of health states from industrial data. Many developed CNN-based schemes, such as advanced CNNs that introduce residual learning and multi-scale learning, have shown good performance in health states recognition tasks under the assumption that all the classes are known. However, these schemes have no ability to deal with new abnormal samples that belong to state classes not part of the training set. In this paper, a collective decision framework for different CNNs is proposed. It is based on a one-vs.-rest network (OVRN) to simultaneously achieve classification of known and unknown health states. OVRNs learn class-specific discriminative features and enhance the ability to reject new abnormal samples incorporated to different CNNs. According to the validation results on the public dataset of the Tennessee Eastman process (TEP), the proposed CNN-based decision schemes incorporating an OVRN have outstanding recognition ability for samples of unknown heath states while maintaining satisfactory accuracy on known states. The results show that the new DL framework outperforms state-of-the-art CNNs, and the one based on residual and multi-scale learning has the best overall performance.

Maturity level of predictive maintenance application in small and medium-sized industries: Case of Morocco

In order to remain competitive in the long term and to push the company's efficiency to its limits, entrepreneurs are more and more open to the idea of integrating into Industry 4.0 aiming mainly at filling the important downtimes and the associated productivity losses by implementing predictive maintenance. This concept, common in developed countries, is much less widespread in Morocco and even less in small and medium-sized Moroccan companies. The objective of this article is to study the maturity level of predictive maintenance in Moroccan small and medium-sized enterprises, through a questionnaire validated by experts and made available to several companies. Valid data from 115 companies throughout the kingdom operating in different sectors were collected and processed by descriptive and factorial analysis under SPSS software. The results obtained show that only 33% of our sample were able to implement predictive maintenance, and that the expected benefits of this approach are the minimization of downtime at 96.5% and the increase in productivity at 94.8%, The main challenges observed are the lack of team motivation and a corporate culture unsuited to digitalization, which represents 42.277% of the total variance, lack of financial resources at 12.916% of the total variance and lack of data protection at 11.644% of the total variance. This analysis indicates that the level of maturity regarding the application of predictive maintenance in Moroccan small and medium-sized companies is low, these rates can be used to improve the root causes.

MACHINE LEARNING INNOVATIONS IN PREDICTIVE MAINTENANCE: A COMPREHENSIVE REVIEW OF APPLICATIONS IN THE MINING SECTOR

In recent years, machine learning (ML) has burgeoned as a transformative tool, particularly within predictive maintenance applications. The mining sector, characterized by its heavy machinery and capital-intensive equipment, stands to benefit immensely from advancements in predictive maintenance techniques. This comprehensive review delves into the recent innovations in ML-driven predictive maintenance and their significant applications within the mining industry. Drawing from an array of case studies and empirical analyses, this paper underscores the tangible operational efficiencies and cost-saving benefits brought about by these ML methodologies. Furthermore, it offers critical insights into the challenges, best practices, and the potential future trajectory of this intersection of machine learning and mining operations.

Factors Determinant Behavior Masters Student in Adopt OJS Website

Study this aim for confirmation factors determinant master student in adoption of the Online Journal System (OJS) website. To compose a skeleton conceptual about behavior adoption technology information , researcher use two theory base i.e. acceptance model technology (TAM) and theory acceptance and use technology integrated (UTAUT). Sample in study this is Master of Management students at University X amounted to 105 students. Structural model testing techniques using LISREL for verify structural model and validation hypothesis research. Research results identify that there is correlation between 8 factors determinant behavior student in OJS website adoption, factor the is (1) facilitating conditions; (2) perceived usefulnes; (3) perceived easy to use; (4) social approval; (5) result demonstrability; (6) innovation awareness and (8) voluntariness of use. Ability factor determinant the by simultaneously capable shape behavior adoption by 73%. Test results hypothesis reported that four factor like condition facilitating condition, perceived usefulness, perceived easy to use and social approval have significant influence to adoption of OJS websites, and social approval have most significant influence to adoption of OJS website. Implication practical on results study this is important for OJS manager for designing convenient OJS features and templates user to submit articles, as well as important for to do maintenance application.

UNJUK KERJA MESIN VERTICAL RAW MILL PLANT 10

PT X. is a cement manufacturing company. which experiences production losses due to the high value of downtime. Based on downtime data, the largest machine downtime value is found in the Raw Mill, so the Raw Mill machine becomes the object of research. This study aims to measure the effectiveness of the Raw Mill machine in the application of Total Productive Maintenance (TPM). The method used is Overall Equipment Effectiveness (OEE) to measure machine effectiveness and loss factor analysis with the Six Big Losses method. The results found that the average OEE value in 2022 was below the international OEE standard of 85%, namely 78% for Raw Mill Plant 10 in the 2019 period and 74% in the 2022 period. The low performance of the Raw Mill Plant 10 machine is caused by the breakdown loss factor and the reduced speed loss factor. The root causes found are lack of mechanical training and lack of control for spare parts. The recommendations given are the implementation of predictive maintenance, improving training facilities, and creating a spare parts inventory management system.

Perawatan Preventif Mesin Pompa Air

The Planned maintenance activities can make the production process run smoothly. The object of the research was pump machine with three phase. Based on obsevations, pumps often experience damage to critical components. This study aims to implement preventive maintenance on pump. The advantage of using preventive maintenance can determine the optimal type of maintence and maintenance time intervals for each critical component. The research stages include determining the probability density function (pdf) and reliability, determining the maintenance interval for critical component using the downtime minimization criteria that will be used to schedule maintenance and determining the cost of corrective and preventive for each critical component. The result of the application of preventive maintenance, there were three component that experienced a decrease in maintenance costs, namely the electromotor component experiencing a 23,7% cost reduction with a 52% reliability level, the radial bearing component experiencing a cost reduction by 24% with a reliability level of 66,64% and the impeller component experiencing a decrease 19,5% cost with a 69% reliability rate. While the maintenance time interval for the electromotor component is 142,4 hours, the radial bearing component is 153,5 hours and the impeller component is 168,8 hours.

Evaluation of a Deep Learning-Based Index for Prognosis of a Vessel’s Propeller-Hull Degradation

Vessels frequently encounter challenging marine conditions that expose the propeller-hull to corrosive water and marine fouling. These challenges necessitate innovative approaches to optimize propeller-hull performance. This study aims to assess a method for predicting propeller-hull degradation. The proposed solution revolves around an innovative Key Performance Indicator (KPI) based on Artificial Neural Networks (ANNs). Our objective is to validate the findings; thus, a thorough comparison is conducted between the proposed method and the baseline solution derived from the ISO-19030. Emphasis is placed on determining the optimal parameters for computing the KPI, which involves applying various features, filters, and pre-processing techniques. The proposed method is tested on real data collected by an Internet of Things (IoT) system installed in different types of vessels. Four distinct experiments with ANNs are conducted. Results demonstrate that the ANN-based indicator offers greater accuracy in predicting propeller-hull degradation compared to the baseline method. Additionally, it is demonstrated that selecting a diverse set of features and implementing consistent filtering and preprocessing techniques enhance the performance of the traditional indicator. The utilization of Deep Learning (DL) in the maritime industry is of great significance, as it enables a comprehensive and dynamic assessment of predictive maintenance of the propeller-hull. The DL index method holds potential for diverse maintenance applications, providing a holistic platform with anticipated environmental and financial benefits.

Hierarchical framework for interpretable and specialized deep reinforcement learning-based predictive maintenance

Deep reinforcement learning holds significant potential for application in industrial decision-making, offering a promising alternative to traditional physical models. However, its black-box learning approach presents challenges for real-world and safety-critical systems, as it lacks interpretability and explanations for the derived actions. Moreover, a key research question in deep reinforcement learning is how to focus policy learning on critical decisions within sparse domains. This paper introduces a novel approach that combines probabilistic modeling and reinforcement learning, providing interpretability and addressing these challenges in the context of safety-critical predictive maintenance. The methodology is activated in specific situations identified through the input–output hidden Markov model, such as critical conditions or near-failure scenarios. To mitigate the challenges associated with deep reinforcement learning in safety-critical predictive maintenance, the approach is initialized with a baseline policy using behavioral cloning, requiring minimal interactions with the environment. The effectiveness of this framework is demonstrated through a case study on predictive maintenance for turbofan engines, outperforming previous approaches and baselines, while also providing the added benefit of interpretability. Importantly, while the framework is applied to a specific use case, this paper aims to present a general methodology that can be applied to diverse predictive maintenance applications.

Analysis of Pavement Performance Data for Determining the Initial Application of Preventive Maintenance of Pavements

Analysis of Pavement Performance Data for Determining the Initial Application of Preventive Maintenance of Pavements

Tackling Industrial Downtimes with Artificial Intelligence in Data-Driven Maintenance

The application of Artificial Intelligence (AI) approaches in industrial maintenance for fault detection and prediction has gained much attention from scholars and practitioners. This survey systematically assesses and classifies the state-of-the-art algorithms applied to data-driven maintenance in recent literature. The taxonomy provides a so far not existing overview and decision aid for research and practice regarding suitable AI approaches for each maintenance application. Moreover, we consider trends and further research demand in this area. Finally, a newly developed holistic maintenance framework contributes to a practice-oriented implementation of AI and considers crucial managerial aspects of an efficient maintenance system.

The Study of Trends in AI Applications for Vehicle Maintenance Through Keyword Co-occurrence Network Analysis

The increasing complexity of a vehicle's digital architecture has created new opportunities to revolutionize the maintenance paradigm. The Artificial Intelligence (AI) assisted maintenance system is a promising solution to enhance efficiency and reduce costs. This review paper studies the research trends in AI-assisted vehicle maintenance via keyword co-occurrence network (KCN) analysis. The KCN methodology is applied to systematically analyze the keywords extracted from 3153 peer-reviewed papers published between 2011 and 2022. The network metrics and trend analysis uncovered important knowledge components and structure of the research field covering AI applications for vehicle maintenance. The emerging and declining research trends in AI models and vehicle maintenance application scenarios were identified through trend visualizations. In summary, this review paper provides a comprehensive high-level overview of AI-assisted vehicle maintenance. It serves as a valuable resource for researchers and practitioners in the automotive industry. This paper also highlights potential research opportunities, limitations, and challenges related to AI-assisted vehicle maintenance.