Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey

Even if measuring the ROI (Returns-on-Investment) of predictive equipment maintenance is essential for discerning whether the manufacturing entity is overspending or underspending on equipment maintenance, most manufacturing executives often do not bother to measure the ROI of their equipment maintenance. This affects decisions on the improvement initiatives that can be adopted. To address such a problem, this study used integrative review to evaluate insights from the existing studies about the techniques, values, and limitations of measuring the ROI of predictive manufacturing equipment’s maintenance. The research was a qualitative study based on content analysis of articles retrieved primarily through Google searches as the major search engine. After predictive maintenance, findings from the analysis indicated the financial metrics to measure the financial gains obtained since the introduction of predictive machine maintenance. It evaluates the benefits and advantages so far attained as compared to the costs incurred in the application of predictive maintenance. Apart from ROI, some of the commonly used financial metrics were found to encompass cost-benefit analysis and net present value (NPV). ROI analysis seeks to evaluate the benefits gained against the costs incurred in the use of predictive machine maintenance. However, findings<i> </i>indicated the major inhibitors of measuring the ROI of predictive machine maintenance to often arise from cost, poor data utilization culture, and ignoring predictive maintenance. Unless management is able to deal with such challenges, they may never get to understand the returns on investment generated from the expenditure on predictive equipment maintenance. From these findings, this study has contributed to changing the general perception of predictive maintenance as an expenditure rather than an investment.

This study aims to develop an effective method of classification concerning time series signals for machine state prediction to advance predictive maintenance (PdM). Conventional machine learning (ML) algorithms are widely adopted in PdM, however, most existing methods assume that the training (source) and testing (target) data follow the same distribution, and that labeled data are available in both source and target domains. For real-world PdM applications, the heterogeneity in machine original equipment manufacturers (OEMs), operating conditions, facility environment, and maintenance records collectively lead to heterogeneous distribution for data collected from different machines. This will significantly limit the performance of conventional ML algorithms in PdM. Moreover, labeling data is generally costly and time-consuming. Finally, industrial processes incorporate complex conditions, and unpredictable breakdown modes lead to extreme complexities for PdM. In this study, similarity-based multi-source transfer learning (SiMuS-TL) approach is proposed for real-time classification of time series signals. A new domain, called "mixed domain," is established to model the hidden similarities among the multiple sources and the target. The proposed SiMuS-TL model mainly includes three key steps: 1) learning group-based feature patterns, 2) developing group-based pre-trained models, and 3) weight transferring. The proposed SiMuS-TL model is validated by observing the state of the rotating machinery using a dataset collected on the Skill boss manufacturing system, publicly available standard bearing datasets, Case Western Reserve University (CWRU), and Paderborn University (PU) bearing datasets. The results of the performance comparison demonstrate that the proposed SiMuS-TL method outperformed conventional Support Vector Machine (SVM), Artificial Neural Network (ANN), and Transfer learning with neural networks (TLNN) without similarity-based transfer learning methods.

This paper presents a comprehensive review of the developments made in rotating bearing fault diagnosis, a crucial component of a rotatory machine, during the past decade. A data-driven fault diagnosis framework consists of data acquisition, feature extraction/feature learning, and decision making based on shallow/deep learning algorithms. In this review paper, various signal processing techniques, classical machine learning approaches, and deep learning algorithms used for bearing fault diagnosis have been discussed. Moreover, highlights of the available public datasets that have been widely used in bearing fault diagnosis experiments, such as Case Western Reserve University (CWRU), Paderborn University Bearing, PRONOSTIA, and Intelligent Maintenance Systems (IMS), are discussed in this paper. A comparison of machine learning techniques, such as support vector machines, k-nearest neighbors, artificial neural networks, etc., deep learning algorithms such as a deep convolutional network (CNN), auto-encoder-based deep neural network (AE-DNN), deep belief network (DBN), deep recurrent neural network (RNN), and other deep learning methods that have been utilized for the diagnosis of rotary machines bearing fault, is presented.

Many industries are evaluating the use of the Internet of Things (IoT) technology to perform remote monitoring and predictive maintenance on their mission-critical assets and equipment, for which mechanical bearings are their indispensable components. Although many data-driven methods have been applied to bearing fault diagnosis, most of them belong to the supervised learning paradigm that requires a large amount of labeled training data to be collected in advance. In practical applications, however, obtaining labeled data that accurately reflect real-time bearing conditions can be more challenging than collecting large amounts of unlabeled data. In this paper, we thus propose a semi-supervised learning scheme for bearing fault diagnosis using variational autoencoder (VAE)-based deep generative models, which can effectively leverage a dataset when only a small subset of data have labels. Finally, a series of experiments were conducted using the University of Cincinnati Intelligent Maintenance System (IMS) Center dataset and the Case Western Reserve University (CWRU) bearing dataset. The experimental results demonstrate that the proposed semi-supervised learning schemes outperformed some mainstream supervised and semi-supervised benchmarks with the same percentage of labeled data samples. Additionally, the proposed methods can mitigate the label inaccuracy issue when identifying naturally-evolved bearing defects.

With the evolution of fifth generation (5G) network technologies, network maintenance strategies have become increasingly complex, necessitating the use of predictive analysis enabled by Machine Learning (ML) algorithms. This paper emphasizes exploring how ML algorithms can further enhance predictive maintenance in 5G and future networks. It reviews the current literature on this interdisciplinary topic, identifying key ML models such as Decision Trees, Neural Networks, and Support Vector Machines, and discussing their benefits and limitations. Special attention is given to the methodologies in applying these models, handling of data stages, and the training process. Major challenges in implementing ML in the context of network maintenance, such as data privacy, data gathering, model training, and generalizability, are discussed. Furthermore, the research aims to go beyond predicting maintenance needs to introduce a proactive approach in improving overall network performance and pre-empting potential issues based on ML predictions. The paper also discusses possible future trends including advancements in ML algorithms, Automated Machine Learning (AutoML), Explainable AI, and others. The objective is to provide a comprehensive understanding of the current ML-based predictive maintenance field and outline possibilities for future research. The study finds that the application of ML algorithms continues to show promise in transforming the landscape of network management by improving predictive maintenance and proactive performance enhancement strategies. It remains a challenging yet important area in the context of 5G networks.

Predictive group maintenance for multi-system multi-component networks

The rapid advancement of information and communication technologies (ICT) and artificial intelligence (AI) has catalysed a significant shift in maintenance practices within the building industry, paving the way for a data-driven paradigm. Predictive maintenance (PdM) has emerged as a critical approach to anticipating failures and reducing unscheduled maintenance tasks. However, the surge in ICT implementations within building-related infrastructure presents several challenges for PdM research and development. Current frameworks are often constrained to specific facilities and lack scalability and generality. Additionally, existing studies focus on condition monitoring and fault detection, with insufficient attention to failure prediction. The effectiveness of PdM has also been hindered by the dependence on labelled datasets, which are expensive and time-consuming to generate. Furthermore, indoor climate management is crucial to building performance. However, it has received less attention than facilities maintenance in PdM research despite its integral role in occupant comfort and environmental sustainability. In response to these challenges, this thesis introduces a unified framework that integrates Industry 4.0 technologies within a digital twin (DT) structure, grounded in the innovative Six M methodology—Machine, Manpower, Material, Measurement, Milieu, and Method. This approach emphasises the entire building lifecycle, enabling stakeholders to optimise operations, resource allocation, and decision-making across multiple facets of building management. The 6M methodology is crucial for transforming PdM by providing a structured and holistic approach to integrating diverse building assets and operational processes within the DT environment, thereby enhancing system scalability and operational efficiency. The research also employs a Three-by-Three M analysis methodology and a keywords network analysis to identify key research clusters and critical factors in existing DT-enabled PdM-related studies. This analysis underscores the transformative potential of DTs in revolutionising PdM applications across the building industry. These fundamental studies pave the way for future PdM applications in the building and construction (B&C) industry, significantly advancing maintenance strategies. Following a comprehensive investigation, this thesis introduces a pioneering failure prediction methodology that addresses the challenge of limited labelled datasets by leveraging semi-supervised generative adversarial networks (GANs). This innovative approach enables the model to utilise labelled and unlabelled data, reducing the reliance on costly manual labelling while improving prediction accuracy. Based on publicly available datasets from building facilities, empirical results demonstrate the model's superior performance in predicting failures, enhancing the system’s proactive maintenance capabilities. An online platform was also developed to integrate real-time monitoring with predictive alarms, allowing for efficient, data-driven decision-making in building maintenance. In addition to traditional facilities maintenance, this thesis extends PdM applications to include indoor climate management, addressing the gap in existing research. Indoor climate, particularly air quality, directly impacts occupant well-being, comfort, and productivity and can be an essential indicator of system failures or inefficiencies. Proper PdM ensures optimal air quality by predicting and preventing system malfunctions that could lead to poor ventilation, temperature control, or humidity levels. The proposed framework incorporates remaining useful life (RUL) and time shift (TS) methods, dividing the prediction tasks into supervised and unsupervised subtasks. A parallel prediction model, combining long short-term memory (LSTM) networks and autoencoders (AE), is developed to handle this complex task. An innovative DT-enabled PdM framework for indoor climates is validated through an online platform that reconstructs 3D building models and provides real-time monitoring and alerts. Experimental results demonstrate the framework’s ability to accurately predict faults at varying warning times and severities using practical datasets from buildings in Singapore. In conclusion, this thesis explores the integration of DT and PdM in the building industry through a comprehensive analysis of four academic papers, leading to significant contributions in system scalability, efficiency, and sustainability. The proposed methodologies enhance building maintenance practices and extend PdM’s impact to encompass critical indoor climate factors, paving the way for more resilient, cost-effective, and sustainable building operations.

The convergence of mobile technologies with predictive maintenance (PdM) systems represents a transformative paradigm in Industry 4.0 manufacturing environments, enabling real-time fault detection, remote diagnostics, and intelligent maintenance scheduling. This study presents a comprehensive bibliometric analysis mapping the intellectual structure, research trends, and knowledge evolution of mobile technologies in predictive maintenance applications from 2016 to 2025. Using systematic methodology adhering to PRISMA guidelines, 167 peer-reviewed publications were extracted from the Scopus database and analyzed using advanced bibliometric techniques, including citation analysis, co-authorship networks, keyword co-occurrence mapping, and thematic evolution assessment. The findings reveal exponential research growth from 1 publication in 2016 to 43 publications in 2024, representing a 3,900% increase and indicating rapid field maturation. India emerges as the dominant research contributor (49 publications, 29.3%), followed by the USA (18 publications, 10.8%) and Italy (15 publications, 9.0%), demonstrating significant geographic concentration in Asia- Pacific (39.5%) and European (22.4%) regions. Thematic analysis identifies augmented reality, the Internet of Things, and machine learning as core technological enablers, while co-citation analysis reveals Mourtzis D as the central intellectual hub connecting diverse research streams. The intellectual structure reveals four major research clusters: IoT-enabled mobile sensing, augmented reality applications, machine learning algorithms, and digital twin integration. Strategic thematic mapping positions predictive maintenance, augmented reality, and IoT as motor themes driving field advancement while identifying emerging opportunities in the industrial metaverse and 6G technologies. International collaboration analysis reveals hub-and-spoke patterns centred on India, with limited cross-cluster integration suggesting opportunities for enhanced global knowledge exchange. This bibliometric analysis provides the first comprehensive mapping of the mobile predictive maintenance (PdM) research landscape, offering evidence-based insights for researchers, practitioners, and policymakers navigating the evolving intersection of mobile technologies and smart manufacturing systems in Industry 4.0 contexts.

Maintenance can be divided into reactive and preventive. In reactive maintenance damage is corrected after it has occurred. On the other hand, predictive maintenancePredictive maintenance anticipates the damage in the future. Predictive maintenance can be periodic with fixed time intervals or predictive with forecasted failure times. Maintenance planningMaintenance planning is intelligent when maintenance needs are predicted and optimised. Intelligent maintenance systems require data collection, data transfer, data storage, data processing and Decision Support Systems to be in place. Machine learning algorithms in forecasting and optimisation can take increasing quantity of collected data into consideration in intelligent maintenance planning. Two types of forecasting models—time-series and causal methods can be used for intelligent maintenanceMaintenance optimization planning. Optimisation algorithms can be divided into local and population search methods. Hybrid methods combining more than one algorithm have been used efficiently for maintenance planning. Maintenance planning is important in the transport sector and various models and methods have been applied both in road and vehicle maintenance. In practice, it is important to have accurate deterioration and cost models in place. In research, both data-driven and mathematical models have been applied, but data-driven methods are becoming more practical as computation is increasingly more feasible.

A Novel Predictive Selective Maintenance Strategy Using Deep Learning and Mathematical Programming

This study covers new trends and techniques in the field of predictive maintenance, which has been superseding traditional management policies, at least in part. It also presents suggestions for how to implement a predictive maintenance programme in a factory/premise and so on. Predictive maintenance primarily involves foreseeing breakdown of the system to be maintained by detecting early signs of failure in order to make maintenance work more proactive. In addition to the aim of acting before failure, it also aims to attend to any fault, even if there is no immediate danger of failure, to ensure smooth operation and reduce energy consumption. Predictive maintenance has been adopted by various sectors in manufacturing and service industries in order to improve reliability, safety, availability, efficiency and quality as well as to protect the environment. It also has created a separate sector, which specializes in developing predictive maintenance instruments, offering dedicated predictive maintenance solutions and training predictive maintenance experts. Predictive maintenance techniques are closely associated with sensor technologies but for efficient predictive maintenance applications, a comprehensive approach, which integrates sensing with subsequent maintenance activities, is needed to be adapted in accordance with the needs of the particular organization. Recent advances in information, communication and computer technologies, such as Internet of Things and radio-frequency identifications, have been enabling predictive maintenance applications to be more efficient, applicable, affordable, and consequently more common and available for all sorts of industries. Researches on remote maintenance and e-maintenance have been supporting predictive maintenance activities especially in unsafe working environments and scattered locations.

This paper examines the use of machine learning and deep learning algorithms in the aviation industry, with a specific emphasis on aircraft diagnosis/prognosis, predictive maintenance, feature selection, and flight data monitoring (FDM). This study highlights the potential use of these algorithms in enhancing the efficacy and effectiveness of various aircraft operations. In the field of aviation prognosis and diagnosis, many designs have been acknowledged as efficient for defect identification, calculation of remaining usable life, and prediction of excessive vibration in aero-engines. The architectural models discussed in this paper include deep autoencoders, deep belief networks, long short-term memory networks, and convolutional neural networks. The use of feature selection and scalar feature selection methodologies has been seen to augment the efficacy of FDM (Feature Detection and Matching) algorithms by means of identifying noteworthy features and detecting highly linked features. The application of machine learning algorithms in the domain of predictive maintenance enables real-time assessment of equipment health, hence reducing possible hazards and improving overall equipment performance. The research results emphasize the importance of flight data monitoring in improving safety and operational efficiency in the field of civil aviation. The application of machine learning approaches, namely classification algorithms, facilitates the analysis of flight data for the aim of identifying unsafe behaviors or violations from established operational standards.

The study looks at the application of AI-driven predictive maintenance in IoT systems. Predictive device failure, efficient reduction in system downtime, reduced maintenance costs, and overall efficiency in connected devices will be enabled through machine learning and deep learning algorithms. The AI models developed within this research were able to provide a prediction accuracy of 92%, while the traditional methods of maintenance were far behind at 78%. It resulted in a 35% reduction in system downtime and a 28% decrease in maintenance costs while reducing the error rate to 8%. The above results bring out the potential of AI-based solutions for real-time predictive maintenance over complex IoT networks. It concludes by indicating some further research vectors, such as the refinement of the model and the extension of AI-driven predictive maintenance for broader applications in IoT, such as smart cities and healthcare systems.

A smart factory is a highly digitized and connected production facility that relies on smart manufacturing. Additionally, artificial intelligence is the core technology of smart factories. The use of machine learning and deep learning algorithms has produced fruitful results in many fields like image processing, speech recognition, fault detection, object detection, or medical sciences. With the increment in the use of smart machinery, the faults in the machinery equipment are expected to increase. Machinery fault detection and diagnosis through various deep learning algorithms has increased day by day. Many types of research have been done and published using both open-source and closed-source datasets, implementing the deep learning algorithms. Out of many publicly available datasets, Case Western Reserve University (CWRU) bearing dataset has been widely used to detect and diagnose machinery bearing fault and is accepted as a standard reference for validating the models. This paper summarizes the recent works which use the CWRU bearing dataset in machinery fault detection and diagnosis employing deep learning algorithms. We have reviewed the published works and presented the working algorithm, result, and other necessary details in this paper. This paper, we believe, can be of good help for future researchers to start their work on machinery fault detection and diagnosis using the CWRU dataset.

A systematic review of time series algorithms and analytics in predictive maintenance