Predictive Maintenance System Research Articles

Status Monitoring System of Reciprocating Hydrogen Compressor Based on Hilbert−Huang Transform

ABSTRACTA reciprocating hydrogen compressor status monitoring system for predictive maintenance is developed based on HHT (Hilbert−Huang Transform) with multiple functions, strong applicability, and high accuracy to address the problem of difficulty in identifying fault signals and failure to provide advance warning before faults occur in the reciprocating hydrogen compressor state monitoring system. Design framework of monitoring system is confirmed, and function modules are designed based on LabView platform. HHT is applied to monitor the status of reciprocating hydrogen compressor based on LabView platform. A reciprocating hydrogen compressor is selected as research object, status monitoring analysis is carried out. Five working states of reciprocating hydrogen compressor are collected, which conclude normal state, filler malfunction, cross‐head malfunction, air valve malfunction, and piston rod malfunction. HHT is carried out for five signals, and results show that HHT marginal spectrum of five signals has different characteristics. Based on comparison results, precision of HHT ranges from 0.757 to 0.784, recall of HHT ranges from 0.738 to 0.766, F1‐score of HHT ranges from to 0.788 to 0.804, HHT has better performance than other two methods. Proposed monitoring system designed in this study provides a comprehensive and efficient online monitoring and data analysis solution for reciprocating hydrogen compressors, which can achieve fault prediction of reciprocating hydrogen compressor, reduce failure rate, and effectively improve the reliability of the compressor oil injection system.

AI-enhanced fault-tolerant control and security in transportation and logistics systems: addressing physical and cyber threats

Transportation and logistics systems are becoming increasingly complex and critical to modern infrastructure. This paper proposes a novel AI-enhanced fault-tolerant control framework to address the dual challenges of physical malfunctions and cyber threats. By leveraging advanced machine learning algorithms and real-time data analytics, the proposed methodology aims to enhance the reliability, safety, and security of transportation and logistics systems. This research explores the foundations and practical implementations of AI-driven anomaly detection, predictive maintenance, and autonomous response systems. The findings demonstrate significant improvements in system resilience and robustness, making a substantial contribution to the field of intelligent transportation management.

Forecasting models analysis for predictive maintenance

IntroductionThis study explores the shift toward predictive maintenance through real-time data analytics to minimize machine downtime and improve machinery insights in industrial environments. Predictive maintenance aims to enable proactive interventions by predicting failures, enhancing operational efficiency.MethodsThe research was conducted in three stages. First, BA Glass equipment was sensorized using OPC Router and PowerStudio SCADA to facilitate real-time data extraction. A predictive maintenance algorithm was then developed in Python to analyze sensor data, predict failures, and trigger alarms. Finally, various forecasting models, including Linear and Polynomial Regression, Simple and Double Exponential Smoothing, ARIMA, and Prophet, were evaluated using a combination of blocked cross-validation and rolling window methodologies. The algorithm calculated performance metrics such as MSE, RMSE, and MAE for different parameter configurations and training sizes.ResultsA comparative analysis between wired and wireless sensors concluded that wireless sensors, although more expensive, were more practical and interchangeable in the factory setting. The results from the evaluation of prediction models showed that the Double Exponential Smoothing (DES) model with an additive damped trend and linear models performed best for datasets with daily seasonality and gradual oscillations. For datasets with stable trends and higher frequency oscillations, ARIMA and Prophet models proved to be more accurate.DiscussionThese findings suggest that the choice of sensors and prediction models can significantly impact the effectiveness of predictive maintenance systems. Wireless sensors offer long-term benefits in terms of flexibility and practicality, while the DES model and ARIMA/Prophet models are optimal depending on the dataset characteristics. This research highlights the value of real-time data analytics and predictive models in industrial environments for reducing downtime and improving decision-making.

Fault stands out in contrast: Zero-shot diagnosis method based on dual-level contrastive fusion network for control moment gyroscopes predictive maintenance

Control moment gyroscopes (CMGs) are the most common control actuators in spacecraft. Their predictive maintenance is crucial for on-orbit operations. However, due to the scarcity of CMG fault data, constructing a diagnosis system for predictive maintenance with CMGs poses significant challenges. Therefore, a zero-shot fault diagnosis method based on a dual-level contrastive learning fusion network was proposed. First, to address the difficulty in training CMG fault diagnosis models without fault data, a contrastive learning method based on CMG clusters was proposed to extract invariant features from healthy CMGs and achieve zero-shot diagnosis for predictive maintenance. Second, considering the limitations of information from a single sensor, a cross-sensor contrastive learning method was proposed to fuse features from different sensors. Third, to tackle the challenges of extracting weak potential fault features, a dual-level joint training method was introduced to enhance the model’s feature extraction capability. Finally, the proposed method was validated using real dataset collected from CMGs serviced on an in-orbit spacecraft. The results demonstrate that the method can achieve zero-shot fault diagnosis for control moment gyroscopes predictive maintenance. The code is available at https://github.com/IceLRiver/DCF.

Artificial Intelligence in Maritime Transportation: A Comprehensive Review of Safety and Risk Management Applications

Maritime transportation is crucial for global trade but faces significant risks and operational challenges. Ensuring safety is essential for protecting lives, the environment, and economic stability. This review explores the role of artificial intelligence (AI) in enhancing maritime safety and risk management. Key AI applications include risk analysis, crew resource management, hazardous material handling, predictive maintenance, and navigation systems. AI systems identify potential hazards, provide real-time decision support, monitor hazardous materials, predict equipment failures, and optimize shipping routes. Case studies, such as Wärtsilä’s Fleet Operations Solution and ABB Ability™ Marine Pilot Vision, illustrate the benefits of AI in improving safety and efficiency. Despite these advancements, integrating AI poses challenges related to infrastructure compatibility, data quality, and regulatory issues. Addressing these is essential for successful AI implementation. This review highlights AI’s potential to transform maritime safety, emphasizing the need for innovation, standardized practices, and robust regulatory frameworks to achieve safer and more efficient maritime operations.

A comparative study of ensemble methods and multi-output classifiers for predictive maintenance of hydraulic systems

The maintenance and upkeep of hydraulic systems play a pivotal role in various industrial applications, from manufacturing processes to heavy machinery operations. Traditional strategies often face significant limitations, particularly concerning intervention time and the costs associated with delays between fault occurrence and maintenance. Over the past decades, proactive strategies have emerged with promising potential, primarily due to their predictive capabilities. These proactive approaches aim to anticipate faults and maintenance needs, thereby mitigating costs and operational disruptions associated with reactive approaches. This study explores the applicability of single output, ensemble methods, and the integration of multi-output classifiers in hydraulic predictive maintenance problems with relatively limited data. First, data is analyzed using Pearson correlation coefficients, and then feature extraction is conducted using recursive feature extraction, aiming to optimize the performance of predictive models, particularly Random Forest and CatBoost. Results show that the stacking ensemble method, incorporating LightGBM, XGBoost, CatBoost, and Random Forest, yields the most notable improvement, achieving a final accuracy of 98.63%. The results obtained in this study show satisfying performances for single-output models, ensemble methods, and multi-output models in predicting the health of hydraulic systems. Moreover, combining single output, ensemble methods, and the integration of multi-output classifiers has created a relatively reliable and robust predictive maintenance system.

Design, Building and Deployment of Smart Applications for Anomaly Detection and Failure Prediction in Industrial Use Cases

This paper presents a comparative analysis of deep learning techniques for anomaly detection and failure prediction. We explore various deep learning architectures on an IoT dataset, including recurrent neural networks (RNNs, LSTMs and GRUs), convolutional neural networks (CNNs) and transformers, to assess their effectiveness in anomaly detection and failure prediction. It was found that the hybrid transformer-GRU configuration delivers the highest accuracy, albeit at the cost of requiring the longest computational time for training. Furthermore, we employ explainability techniques to elucidate the decision-making processes of these black box models and evaluate their behaviour. By analysing the inner workings of the models, we aim at providing insights into the factors influencing failure predictions. Through comprehensive experimentation and analysis on sensor data collected from a water pump, this study contributes to the understanding of deep learning methodologies for anomaly detection and failure prediction and underscores the importance of model interpretability in critical applications such as prognostics and health management. Additionally, we specify the architecture for deploying these models in a real environment using the RAI4.0 metamodel, meant for designing, configuring and automatically deploying distributed stream-based industrial applications. Our findings will offer valuable guidance for practitioners seeking to deploy deep learning techniques effectively in predictive maintenance systems, facilitating informed decision-making and enhancing reliability and efficiency in industrial operations.

Machine Learning Models for Predictive Maintenance in Industrial Engineering

Purpose: The general objective of this study was to investigate machine learning models for predictive maintenance in industrial engineering. Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.Findings: The findings reveal that there exists a contextual and methodological gap relating to machine learning models for predictive maintenance in industrial engineering. The research highlighted the transformative potential of machine learning models in optimizing predictive maintenance for industrial engineering, demonstrating significant reductions in unplanned downtime and maintenance costs. It identified the strengths of various machine learning approaches, such as supervised, unsupervised, and reinforcement learning, in predicting equipment failures and optimizing maintenance schedules. Despite the benefits, challenges such as data quality, integration complexity, and the need for specialized skills were noted. Future advancements in machine learning, IoT data, and computational power were expected to further enhance predictive maintenance systems, making them more accurate, efficient, and widely adopted across industries.Unique Contribution to Theory, Practice and Policy: The Systems Theory, Diffusion of Innovations Theory and Resource-Based View (RBV) Theory may be used to anchor future studies on machine learning models for predictive maintenance in industrial engineering. This study provided several recommendations that contributed to theory, practice, and policy. It emphasized the development of hybrid machine learning models, integration of domain-specific knowledge, and real-time data collection using IoT technologies. It suggested standardized data protocols and personnel training for better implementation and efficiency. Policy recommendations included regulatory frameworks, incentives for technology adoption, data sharing, and robust data privacy guidelines. These contributions aimed to enhance the accuracy and applicability of predictive maintenance models, improve industrial maintenance practices, and support technological innovation through supportive policies.

The Big Role of Data Analytics in the Industrial Internet of Things

An IoT architecture is presented in the article which is a predictive way to maintain a group of buses using J1939 sensor data[1]. The authors adopted a minimally viable prototype (MVP) at the Socie´te´ de Transport de l’Outaouais (STO) garage in Gatineau, Canada, which was able to capture around 1 GB of uncompressed J1939 data per bus every day.[1] Data is a combination of the sensor reading and consists of data for the wheel speed, vehicle distance, driver pedal positions, engine information, oil information, coolant information, and transmission fluid information. The authors are trying to come up with a variant of Consensus Self-Organized Models (COSMO) named ICOSMO, which can self-fit the sensor selection for anomaly detection. The fourth industrial revolution has changed the face of ancient manufacturing by bringing in new technologies such as sensors, AI, IoT, and big data analytics. This equipment is used to convert factories into intelligent and interconnected systems that generate a huge amount of data. The data collected, when properly processed, can be utilized to improve decision making and reliability and safety. In addition, it makes predictive maintenance inevitable, thus minimizing the downtime and optimization of the performance[2]. Industrial big data is identified by the ”5V” elements: volume, velocity, variety, veracity, and value. Due to these characteristics, traditional data processing techniques become inadequate, so these circumstances require novel approaches to the treatment of the numerous and diverse data types that are produced in industry 4.0. The Proposed ICOSMO Infrastructure for IoT Predictive Maintenance consists of the following key activities: 1) finding out which sensor classes are the reasons for the faulty components, 2) adaptation of the sensor class (SC) and the sensor prediction capability (SPC) using fault detection abilities and 3) COSMO sensor configuration has to be rearranged after a certain period of time. ICOSMO has been verified with data from a minimally viable prototype (MVP) deployed on buses at the Socie´te´ de Transport de l’Outaouais in Canada. Furthermore, the interviewees said that the framework also includes techniques for the composition and the characterization of industrial big data, which is essential to make a practical predictive maintenance system that can work in smart manufacturing environments

Resilient Supply Chains in Industry 5.0: Leveraging AI for Predictive Maintenance and Risk Mitigation

This integrative literature review investigates the transformative impact of artificial intelligence (AI) on supply chain management, addressing the pressing need for efficiency and robustness through AI-driven predictive maintenance, machine learning (ML), and decision support systems. By examining current literature, the study highlights AI's potential to automate and revolutionize supply chain operations, enhancing speed, accuracy, and risk management capabilities while identifying significant challenges such as bias mitigation, algorithmic transparency, and data privacy. The methodology involves a comprehensive review of scholarly articles, reports, and academic publications, focusing on AI applications in predictive maintenance, risk mitigation, and decision-making processes. The analysis reveals significant improvements in operational efficiency and accuracy due to AI, alongside concerns about biases, transparency, and implementation issues. The findings confirm AI's transformative potential in supply chain management but emphasize the necessity for ongoing supervision, regular audits, and the development of AI models capable of detecting and rectifying operational anomalies. The study proposes creating roles such as AI Supply Chain Oversight Officer (AISCO), AI Supply Chain Compliance Officer (AISCCO), and AI Supply Chain Quality Assurance Officer (AISQAO) to ensure responsible AI utilization, maintaining the integrity and efficiency of supply chain operations while addressing implementation challenges. The review concludes that AI is promising for transforming supply chains; however, careful implementation is crucial to uphold operational integrity and resilience. Future research should prioritize longitudinal studies to evaluate AI's long-term impact, focus on addressing implementation concerns, and ensure fair and transparent integration of AI technologies. These findings have significant implications for practice and policy, underscoring the need for robust frameworks and regulatory measures to guide the effective use of AI in supply chains.

Cycling into the workshop: e-bike and m-bike mobility patterns for predictive maintenance in Barcelona’s bike-sharing system

Bike-sharing systems have emerged as a significant element of urban mobility, providing an environmentally friendly transportation alternative. With the increasing integration of electric bikes alongside mechanical bikes, it is crucial to illuminate distinct usage patterns and their impact on maintenance. Accordingly, this research aims to develop a comprehensive understanding of mobility dynamics, distinguishing between different mobility modes, and introducing a novel predictive maintenance system tailored for bikes. By utilising a combination of trip information and maintenance data from Barcelona’s bike-sharing system, Bicing, this study conducts an extensive analysis of mobility patterns and their relationship to failures of bike components. To accurately predict maintenance needs for essential bike parts, this research delves into various mobility metrics and applies statistical and machine learning survival models, including deep learning models. Due to their complexity, and with the objective of bolstering confidence in the system’s predictions, interpretability techniques explain the main predictors of maintenance needs. The analysis reveals marked differences in the usage patterns of mechanical bikes and electric bikes, with a growing user preference for the latter despite their extra costs. These differences in mobility were found to have a considerable impact on the maintenance needs within the bike-sharing system. Moreover, the predictive maintenance models proved effective in forecasting these maintenance needs, capable of operating across an entire bike fleet. Despite challenges such as approximated bike usage metrics and data imbalances, the study successfully showcases the feasibility of an accurate predictive maintenance system capable of improving operational costs, bike availability, and security.

Revolutionizing indoor air quality monitoring through IoT innovations: a comprehensive systematic review and bibliometric analysis.

Indoor air quality (IAQ) in the built environment is significantly influenced by particulate matter, volatile organic compounds, and air temperature. Recently, the Internet of Things (IoT) has been integrated to improve IAQ and safeguard human health, comfort, and productivity. This review seeks to highlight the potential of IoT integration for monitoring IAQ. Additionally, the paper details progress by researchers in developing IoT/mobile applications for IAQ monitoring, and their transformative impact in smart building, healthcare, predictive maintenance, and real-time data analysis systems. It also outlines the persistent challenges (e.g., data privacy, security, and user acceptability), hampering effective IoT implementation for IAQ monitoring. Lastly, the global developments and research landscape on IoT for IAQ monitoring were examined through bibliometric analysis (BA) of 106 publications indexed in Web of Science from 2015 to 2022. BA revealed the most significant contributing countries are India and Portugal, while the top productive institutions and researchers are Instituto Politecnico da Guarda (10.37% of TP) and Marques Goncalo (15.09% of TP), respectively. Keyword analysis revealed four major research themes: IoT, pollution, monitoring, and health. Overall, this paper provides significant insights for identifying prospective collaborators, benchmark publications, strategic funding, and institutions for future IoT-IAQ researchers.

Latest Innovations in Internet of Things (IoT): Digital Transformation Across Industries

This research article explores recent advances in IoT technology and its huge impact on various sectors. This research method uses a qualitative research approach involving in-depth interviews and thematic analysis. This research explores key IoT innovations such as wearable devices, smart medical devices, predictive maintenance systems, and IoT-based transportation solutions. The research findings highlight how these innovations are driving digital transformation across industries, leading to improved healthcare delivery, increased manufacturing efficiency, optimized transportation operations, sustainable agricultural practices, and personalized retail experiences. This study also aligns these empirical findings with theoretical frameworks regarding IoT, digital transformation, and industry-specific applications, emphasizing the strategic importance of leveraging IoT as a catalyst for innovation, competitiveness, and value creation. This research provides valuable insights for businesses, policymakers and researchers looking to leverage IoT technology to drive digital transformation and achieve sustainable growth across industries.

A Novel Advanced IoT System for Predictive Maintenance Systems and Supply Chain Optimization Solutions for Manufacturing Industries

This paper presents a pioneering approach to revolutionize manufacturing industries through the development of a novel advanced Internet of Things (IoT) system tailored for predictive maintenance and supply chain optimization. Leveraging the vast array of data generated within manufacturing environments, the proposed system integrates cutting-edge IoT technologies with advanced predictive analytics to enable proactive identification of equipment failures and optimization of supply chain operations. The research encompasses a comprehensive dataset comprising sensor data, maintenance records, and supply chain information sourced from industrial pumps, facilitating the creation of robust predictive maintenance models and insightful supply chain optimization strategies. Experimental procedures involve data pre-processing, feature engineering, and model development, followed by rigorous evaluation against ground truth data. The results showcase significant enhancements in equipment up-time; maintenance cost reduction, and supply chain responsiveness, demonstrating the efficacy and scalability of the IoT-based solutions. Through this innovative approach, manufacturing industries can achieve unprecedented levels of operational efficiency, cost savings, and competitive advantage, paving the way for transformative advancements in predictive maintenance and supply chain management paradigms.

Predictive maintenance system for high-end equipment in nuclear power plant under limited degradation knowledge

To ensure the safe operation of high-end equipment, the three-stage maintenance strategy comprising unplanned shutdown, temporary shutdown, and scheduled shutdown is currently employed in nuclear power plants. However, this strategy hinders the acquisition of degradation knowledge (run-to-failure data or degradation mechanism), thereby impeding the application of traditional predictive maintenance systems. Hence, the responsibility for determining the maintenance stage primarily lies with experienced field engineers, and an incorrect decision could potentially result in an unplanned shutdown. To this challenge, we integrate the three-stage maintenance strategy and prognosis methods to form a predictive maintenance system for nuclear power plants. The system framework is first established, and prognosis methods, including sensor selection, degradation trend prediction for short-term prognosis, and remaining useful life (RUL) prediction for long-term prognosis, are then developed under limited degradation knowledge. Finally, the system is deployed in the circulating water pump of a nuclear power plant utilizing an Internet of Things (IoT) architecture. An industry case study verifies that the proposed system can provide decision-making support and further achieve predictive maintenance for high-end equipment in nuclear power plants.

THEORETICAL FRAMEWORKS OF ECOPFM PREDICTIVE MAINTENANCE (ECOPFM) PREDICTIVE MAINTENANCE SYSTEM

The Frameworks of EcoPFM Predictive Maintenance (PM) System presents a novel approach to maintenance optimization within eco-friendly power facilities, addressing the critical need for sustainable, efficient asset management. This paper introduces an integrated framework leveraging advanced predictive analytics, machine learning algorithms, and Internet of Things (IoT) technology to enable proactive maintenance interventions based on real-time data insights. Focusing on the context of the United States it highlights the significance of implementing such a system in the realm of eco-friendly energy infrastructure. The automotive and heavy-duty truck industries in the United States grapple with the challenge of optimizing maintenance strategies to ensure vehicle reliability, safety, and environmental sustainability. Traditional maintenance approaches, primarily reactive or scheduled maintenance, fall short in addressing the complexities of modern vehicle operations. The U.S. Department of Transportation reports that heavy-duty trucks transport approximately 70% of the nation's freight by weight, underscoring the sector's critical role in the economy. However, inefficiencies in maintenance strategies contribute to significant economic and operational setbacks. According to the American Transportation Research Institute, unscheduled truck maintenance and repairs are leading operational costs for fleets, with an average expense of 16.7 cents per mile in 2020, highlighting the financial strain of current maintenance practices. In the United States, the demand for eco-friendly power solutions is rapidly increasing, driven by a growing awareness of environmental sustainability and the imperative to reduce carbon emissions. As the nation transitions towards renewable energy sources and eco-friendly power facilities, the effective management of these assets becomes paramount to ensuring reliability, performance, and longevity. The EcoPFM PM System integrates diverse data sets sourced from eco-friendly power facilities across the USA, encompassing historical operational data, sensor readings, and environmental parameters. Through predictive analytics, the system identifies patterns and trends within these data sets to forecast equipment failures and performance degradation accurately. By prioritizing maintenance tasks based on risk assessment models and condition monitoring, the system enables organizations to optimize resource allocation, minimize downtime, and extend asset lifespan. Embracing the Frameworks of EcoPFM Predictive Maintenance System holds immense promise for organizations operating eco-friendly power facilities in the United States. By harnessing data-driven insights and proactive maintenance strategies, this system offers a pathway towards enhanced operational efficiency, cost reduction, and sustainability, ultimately contributing to the advancement of eco-friendly energy infrastructure in the nation.
 Keywords: Predictive Maintenance, System, ECOPFM, Technology.

DESIGN AND DEVELOPMENT OF AUTOMATIC LUBRICATION SYSTEM USING IOT

The integration of Internet of Things (IoT) technology into lubrication systems has revolutionized maintenance practices in industrial settings. This abstract explores the capabilities and benefits of IoT-based automatic lubrication systems. By employing sensors and connected devices, these systems enable real-time monitoring and control of lubrication levels, thereby ensuring optimal performance of machinery. Through data collection and analysis, potential failures can be predicted and prevented, leading to reduced downtime and maintenance costs. Remote monitoring and control via a web-based interface facilitate convenient management of lubrication processes. Moreover, the interoperability of IoT-based lubrication systems with other IoT platforms, such as predictive maintenance systems, enhances overall machine performance and further minimizes downtime. This abstract underscore the efficiency, cost-effectiveness, and predictive maintenance capabilities offered by IoT-based automatic lubrication systems, positioning them as integral components in modern industrial maintenance strategies. Keyword: - Lubrication, Machinery, Interoperability

THE ROLE OF PRECISION METROLOGY IN ENHANCING MANUFACTURING QUALITY: A COMPREHENSIVE REVIEW

Precision metrology plays a pivotal role in modern manufacturing processes by ensuring the attainment of high-quality standards and the optimization of production efficiency. This comprehensive review delves into the significance of precision metrology in enhancing manufacturing quality across diverse industries. The review encompasses an examination of advanced metrological techniques, their applications, challenges, and future prospects. The review begins by elucidating the fundamental principles of precision metrology, emphasizing its critical role in quantifying dimensional accuracy, surface finish, and other crucial parameters in manufacturing. It explores the evolution of metrology from conventional methods to state-of-the-art technologies such as coordinate measuring machines (CMMs), optical metrology, and 3D scanning systems. The integration of these techniques into modern manufacturing environments has revolutionized quality control processes, enabling real-time monitoring and rapid feedback mechanisms. Furthermore, the review highlights the multifaceted applications of precision metrology across various industries, including automotive, aerospace, electronics, and medical devices. It elucidates how metrological advancements have facilitated the production of intricate components with tight tolerances, thereby enhancing product performance, reliability, and safety. Additionally, the review examines the role of metrology in ensuring compliance with regulatory standards and certifications, crucial for industries with stringent quality requirements. Despite its numerous benefits, precision metrology also poses challenges, such as measurement uncertainties, calibration complexities, and data interpretation issues. The review discusses these challenges in detail and explores emerging strategies and technologies aimed at mitigating them. Furthermore, it addresses the need for standardized metrological practices and international collaboration to foster interoperability and harmonization in global manufacturing ecosystems. Looking ahead, the review outlines future directions and opportunities in precision metrology, including advancements in artificial intelligence, machine learning, and Internet of Things (IoT) integration for predictive maintenance and autonomous quality control systems. It underscores the importance of continued research and innovation in metrology to address evolving manufacturing demands and ensure sustained improvements in product quality and competitiveness. In conclusion, this comprehensive review underscores the indispensable role of precision metrology in enhancing manufacturing quality, driving innovation, and shaping the future of modern industry.
 Keywords: Precision, Metrology, Manufacturing, Quality, Review.

A SPECIALTY LITERATURE REVIEW OF THE PREDICTIVE MAINTENANCE SYSTEMS

Within the industrial standard 4.0, predictive maintenance has an essential role in production activities, by increasing equipment uptime and decreasing maintenance costs. Predictive maintenance monitors assets through sensors for optimal planning of maintenance operations to keep assets functional. In this paper, the authors perform an analysis of predictive maintenance system, proposed in the specialized literature, highlighting their component elements.

Screening of Machine Learning Techniques on Predictive Maintenance: a Scoping Review

Predictive maintenance (PdM) is a set of actions and techniques to early detect failures and defects on machines before they occur, and the usage of machine learning and deep learning techniques in predictive maintenance has increased during the last years. Even with this increase of the literature, there is still a gap concerning the application of such techniques for PdM in the industry, as there are no clear guidelines about which information to use for a PdM system, how to process the information, and what machine learning techniques should be used in order to obtain acceptable results. This scoping review is performed in order to observe the current status on the use of Machine Learning and Deep Learning in predictive maintenance in academia and provide answer to the questions related to these guidelines. For this purpose, a literature review of the last five years is carried out, using those articles that cover information about sources of information used for PdM, the treatment given to such data and the machine learning (ML) methods or techniques used. The Web of Science: Core Collection database is used as a source of information, specifically the Science Citation Index Expanded (SCIE). The review shows that there are different information sources used for machine learning and deep learning in PdM, depending on the origin of the data and the availability of it, and as well whether the data sets are private or public. Also, we can observe that data used for both training and making predictions does not only use traditional pre-processing techniques, but that about one fifth of the articles even propose new techniques in this field. Additionally, we compare a wide range of techniques and algorithms which are used in Deep Learning -being ANN the most used- and in Machine Learning, being SVM the most used algorithm, closely followed by Random Forest. Based on the results, we provide indications about how to apply ML for PdM in industry. Keywords: machine learning, predictive maintenance, artificial intelligence, deep learning, data processing, data collection