Predictive Maintenance Applications Research Articles

Daily Engine Performance Trending using Common Flight Regime Identification

Abstract Accurate flight regime identification is critical for enhancing aircraft efficiency and safety. Traditionally, predictive models for aircraft operation have relied on complex, black-box machine learning techniques that lack transparency. This study introduces a more interpretable approach by leveraging the New Comprehensive Modular Aero-propulsion System Simulation (N-CMAPSS) dataset and combining expanding window classification, voting schemes, and spectral clustering to detect distinct flight regimes. The method applies elastic registration to align time-shifted patterns and Functional Principal Component Analysis (FPCA) to reduce dimensionality, capturing core dynamics across flight regimes. These transformed features are fed into a genetic algorithm-assisted orthogonal matching pursuit for sparse feature selection. Through evolutionary selection, crossover, and mutation, the most informative features are identified, enabling accurate predictions while maintaining transparency. This method outperforms more complex models in certain test cases, offering a balance between accuracy and interpretability that is essential for predictive maintenance and safety applications.

Serverless Computing in the Edge-Cloud Continuum : Challenges, Opportunities, and a Novel Framework

This article explores the integration of serverless computing across the edge-cloud continuum, addressing the growing demand for low-latency, data-intensive applications in the era of the Internet of Things (IoT). We present EdgeServe, a novel framework that extends the serverless paradigm to encompass edge devices and cloud resources, overcoming the limitations of traditional cloud-centric approaches. Through comprehensive simulations and real-world case studies, including a smart city traffic management system, an industrial IoT predictive maintenance application, and a mobile augmented reality gaming platform, we evaluate the performance, scalability, and cost-effectiveness of our proposed framework. Our results demonstrate significant improvements in application response times, with latency reductions of up to 82% in time-critical functions, and an average cost reduction of 43% compared to cloud-only serverless deployments. We also observe a 28% decrease in overall energy consumption in certain scenarios. The article addresses key challenges in resource management, data consistency, adaptive function placement, and security in distributed environments. Our findings have important implications for application architects and cloud service providers, paving the way for a new generation of edge-native serverless platforms. This research contributes to the growing body of knowledge on distributed systems and offers insights into the future evolution of serverless computing in heterogeneous computing environments.

Improving the blade tip clearance measurement method based on blade tip timing: Accounting for rotor speed variations and non-uniform blade-by-blade tip clearance

The Blade Tip Clearance (BTC) measurement method based on Blade Tip Timing (BTT) suffers from poor accuracy under changing speed conditions and in the determination of blade-by-blade tip clearance. To address these challenges, this paper presents the Time of Arrival Polynomial Fitting (ToA-PF) method for achieving high-precision tip clearance measurements under variable speed conditions. Additionally, a correction method is introduced to effectively mitigate measurement errors in blade-by-blade tip clearance. Experimental validation on an academic test rig demonstrates significant improvements. The ToA-PF method enhances clearance measurement accuracy by 77% compared to traditional methods under low and rapidly changing rotational speeds. Furthermore, the correction method for blade-by-blade tip clearance notably enhances measurement accuracy, particularly for the shortest blade, by over 50%. These proposed methods show promise in enhancing the accuracy and practicality of the BTC measurement method based on BTT, offering substantial value for turbine blade health monitoring and predictive maintenance applications.

From fault detection to anomaly explanation: A case study on predictive maintenance

Predictive Maintenance applications are increasingly complex, with interactions between many components. Black-box models are popular approaches based on deep-learning techniques due to their predictive accuracy. This paper proposes a neural-symbolic architecture that uses an online rule-learning algorithm to explain when the black-box model predicts failures. The proposed system solves two problems in parallel: (i) anomaly detection and (ii) explanation of the anomaly. For the first problem, we use an unsupervised state-of-the-art autoencoder. For the second problem, we train a rule learning system that learns a mapping from the input features to the autoencoder’s reconstruction error. Both systems run online and in parallel. The autoencoder signals an alarm for the examples with a reconstruction error that exceeds a threshold. The causes of the signal alarm are hard for humans to understand because they result from a non-linear combination of sensor data. The rule that triggers that example describes the relationship between the input features and the autoencoder’s reconstruction error. The rule explains the failure signal by indicating which sensors contribute to the alarm and allowing the identification of the component involved in the failure. The system can present global explanations for the black box model and local explanations for why the black box model predicts a failure. We evaluate the proposed system in a real-world case study of Metro do Porto and provide explanations that illustrate its benefits.

Steps and Challenges in Analyzing Real Sensor Data from a Productive Press Shop and its Value for Predictive Maintenance Application

This paper highlights the significance of AI-powered maintenance strategies in modern industry for operational optimization and reduced downtime. It emphasizes the crucial role of sensor data analysis in identifying anomalies and predicting failures. The research specifically examines sensor data from an automotive press shop, addressing questions related to data selection, collection challenges, and knowledge generation. By utilizing unsupervised learning on compressed air data from a press line, the study identifies patterns, anomalies, and correlations. The results offer insights into the potential for implementing an effective predictive maintenance strategy. Additionally, a systematic literature review underscores the importance of data analysis in production systems, particularly in the context of maintenance.

A REVIEW OF PREDICTIVE MAINTENANCE APPROACHES FOR CORROSION DETECTION AND MAINTENANCE OF MARINE STRUCTURES

Corrosion is a natural phenomenon that deteriorates and damages the surface of metallic material. Over time, the surface of the material deteriorates due to electrochemical reactions with the surrounding environment. If corrosion is not identified early on, it can become a major financial burden for industries, costing billions of dollars. Despite swift technological developments, preventing and maintaining corrosion progression with reactive maintenance remains difficult. Due to that, predictive maintenance has been developed to predict the deterioration, degradation, and fault over the remaining useful life of the material by using real-time data, historical data, simulation, modelling, and failure probability. Predictive maintenance allows inspectors to monitor the health and predict the corrosion level of the material. However, it is hard to predict the unexpected degradation of the material from the developed prediction model without considering the harsh environment and other external factors. Hence, there is a need to investigate these problems and their effect on predictive maintenance for corrosion detection and maintenance. Therefore, this paper reviews and compares the state-of-the-art predictive maintenance solutions developed to solve corrosion issues in various applications, industries, and academic research. The challenges and opportunities for the predictive maintenance application of corrosion detection and maintenance are also presented. This review will provide new and additional knowledge that can be used to develop prediction models for corrosion detection and maintenance, which will help prevent unexpected failures.

Systematic review of predictive maintenance and digital twin technologies challenges, opportunities, and best practices.

Maintaining machines effectively continues to be a challenge for industrial organisations, which frequently employ reactive or premeditated methods. Recent research has begun to shift its attention towards the application of Predictive Maintenance (PdM) and Digital Twins (DT) principles in order to improve maintenance processes. PdM technologies have the capacity to significantly improve profitability, safety, and sustainability in various industries. Significantly, precise equipment estimation, enabled by robust supervised learning techniques, is critical to the efficacy of PdM in conjunction with DT development. This study underscores the application of PdM and DT, exploring its transformative potential across domains demanding real-time monitoring. Specifically, it delves into emerging fields in healthcare, utilities (smart water management), and agriculture (smart farm), aligning with the latest research frontiers in these areas. Employing the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) criteria, this study highlights diverse modeling techniques shaping asset lifetime evaluation within the PdM context from 34 scholarly articles. The study revealed four important findings: various PdM and DT modelling techniques, their diverse approaches, predictive outcomes, and implementation of maintenance management. These findings align with the ongoing exploration of emerging applications in healthcare, utilities (smart water management), and agriculture (smart farm). In addition, it sheds light on the critical functions of PdM and DT, emphasising their extraordinary ability to drive revolutionary change in dynamic industrial challenges. The results highlight these methodologies' flexibility and application across many industries, providing vital insights into their potential to revolutionise asset management and maintenance practice for real-time monitoring. Therefore, this systematic review provides a current and essential resource for academics, practitioners, and policymakers to refine PdM strategies and expand the applicability of DT in diverse industrial sectors.

A survey of deep learning-driven architecture for predictive maintenance

Over the past decades, deep learning techniques have attracted increased attention from various research and industrial domains aligned with the development of Industry Internet-of-Things(IIoT). Specifically, with the advantage of data-driven methods, industrial organizations are seeking novel proactive strategies supported by analytic models to guarantee the quality of their production by observing degradation or predicting failure ahead of the occurrence of the component or asset. Predictive strategies are expected to promise the influence of unnecessary maintenance interruptions and mitigate the consequence of that, hence, extending the remaining useful life of products. This paper conducts a survey of the utilization of deep learning technologies on engineering applications where they provide satisfactory solutions with respect to specific data types or input signals. 106 primary papers are reviewed on deep learning–driven approaches which mainly explore five of the most popular architectures in the application of predictive maintenance. The main content of this paper summarizes the common advantages of each architecture and, accordingly, points out their limitations, as well as describes the application scopes of fully connected deep neural networks, convolutional neural networks, stacked autoencoders, deep belief networks, and deep recurrent neural networks. Based on the technique discussion for each of them, we intend to provide a comprehensive understanding and guidance of the appropriate usage of deep learning architectures to devise an effective predictive maintenance strategy for the scientific and industrial developers whose expertise lies in the prior domain knowledge of multi-source isomerization data. Moreover, the main content demonstrated the summarization of the decisive factor by which the incremental stages of the approaches were determined, fundamentally including the dataset specification, feature extraction, and the integration of deep learning approaches.

Artificial Intelligence for Predictive Maintenance Applications: Key Components, Trustworthiness, and Future Trends

Predictive maintenance (PdM) is a policy applying data and analytics to predict when one of the components in a real system has been destroyed, and some anomalies appear so that maintenance can be performed before a breakdown takes place. Using cutting-edge technologies like data analytics and artificial intelligence (AI) enhances the performance and accuracy of predictive maintenance systems and increases their autonomy and adaptability in complex and dynamic working environments. This paper reviews the recent developments in AI-based PdM, focusing on key components, trustworthiness, and future trends. The state-of-the-art (SOTA) techniques, challenges, and opportunities associated with AI-based PdM are first analyzed. The integration of AI technologies into PdM in real-world applications, the human–robot interaction, the ethical issues emerging from using AI, and the testing and validation abilities of the developed policies are later discussed. This study exhibits the potential working areas for future research, such as digital twin, metaverse, generative AI, collaborative robots (cobots), blockchain technology, trustworthy AI, and Industrial Internet of Things (IIoT), utilizing a comprehensive survey of the current SOTA techniques, opportunities, and challenges allied with AI-based PdM.

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.

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.

AI-Driven Predictive Maintenance for Energy Infrastructure

The growing complexity and critical importance of energy infrastructure necessitate the adoption of advanced maintenance strategies to ensure reliability, efficiency, and sustainability. Traditional maintenance approaches, such as reactive and preventive maintenance, have proven inadequate in addressing the challenges posed by modern energy systems, particularly with the integration of renewable energy sources. This research explores the potential of artificial intelligence (AI)-driven predictive maintenance (PdM) as a transformative solution for the energy sector. By leveraging historical maintenance records and real-time sensor data, AI models, including machine learning and deep learning techniques, were developed to predict equipment failures with high accuracy. The study employed a mixed-methods approach, combining quantitative analysis of data and qualitative insights from case studies conducted in wind farms, solar power plants, and thermal power plants. The results demonstrated that AI-driven PdM significantly reduces unplanned downtime, lowers maintenance costs, and extends the lifespan of critical energy assets. Deep learning models, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), outperformed traditional models in terms of predictive accuracy, with F1-scores exceeding 90%. Despite the promising results, the research also identified challenges related to data quality, system integration, and organizational adoption. These challenges highlight the need for further research in areas such as explainable AI, the integration of IoT and digital twins, and the exploration of PdM applications across different sectors. The findings underscore the potential of AI-driven PdM to revolutionize maintenance practices in the energy sector, offering a pathway to more reliable, efficient, and sustainable energy systems.

Predictive Maintenance Using Artificial Intelligence in Critical Infrastructure: A Decision-Making Framework

Critical infrastructure supports essential services across energy, transportation, water management, and telecommunications sectors. The degradation or failure of assets in these sectors can have serious economic and safety consequences. Predictive maintenance (PdM), driven by artificial intelligence (AI), has emerged as a transformative approach to optimize maintenance activities and prevent failures. This paper reviews current AI-based PdM applications in critical infrastructure and presents a decision-making framework for evaluating when AI should be used. By addressing technical capabilities, economic impacts, and regulatory concerns, the framework helps guide decision-makers in adopting AI for PdM.

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.

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.

Explainable Predictive Maintenance is Not Enough: Quantifying Trust in Remaining Useful Life Estimation

Machine learning (ML)/deep learning (DL) has shown tremendous success in data-driven predictive maintenance (PdM). However, operators and technicians often require insights to understand what is happening, why it is happening, and how to react, which these black-box models cannot provide. This is a major obstacle in adopting PdM as it cannot support experts in making maintenance decisions based on the problems it detects. Motivated by this, several researchers have recently utilized various post-hoc explanation methods and tools, such as LIME, SHAP, etc., for explaining the predicted RUL from these black-box models. Unfortunately, such (post-hoc) explanation methods often suffer from the \emph{disagreement problem}, which occurs when multiple explainable AI (XAI) tools differ in their feature ranking. Hence, explainable PdM models that rely on these methods are not trustworthy, as such unstable explanations may lead to catastrophic consequences in safety-critical PdM applications. This paper proposes a novel framework to address this problem. Specifically, first, we utilize three state-of-the-art explanation methods: LIME, SHAP, and Anchor, to explain the predicted RUL from three ML-based PdM models, namely extreme gradient boosting (XGB), random forest (RF), logistic regression (LR), and one feed-forward neural network (FFNN)-based PdM model using the C-MAPSS dataset. We show that the ranking of dominant features for RUL prediction differs for different explanation methods. Then, we propose a new metric \emph{trust score} for selecting the proper explanation method. This is achieved by evaluating the XAI methods using four evaluation metrics: fidelity, stability, consistency, and identity, and then combining them into a single \emph{trust score} metric through utilizing Kenny and Borda rank aggregation methods. Our results show that the proposed method effectively selects the most appropriate explanation method from a set of explanation methods for estimated RULs. To the best of our knowledge, this is the first work that attempts to address and solve the disagreement problem in explainable PdM.

Economic fatigue damage monitoring for vehicle fleets using the scattering transform

AbstractVehicle monitoring is an important prequisite for predictive maintenance applications. Virtual sensors can be deployed to establish relationships between fatigue related quantities of interest and readily available measurement data, which reduces the costs of monitoring for vehicle fleets. This work describes a data‐driven virtual sensing approach using the scattering transform and principal component analysis. These data transformations are used to obtain a reduced representation of acceleration data, which is suitable for the identification of fatigue critical events during vehicle operation. Results of a previous study using an eBike demonstrator are summarized and the methodology is applied to experimental data of a sensor equipped light rail vehicle. In both applications, fictitious fatigue damage contributions are estimated accurately and physical interpretations of the reduced representation are found.

Anomaly Detection in Airliner Centrifugal Compressor Using Sensor Data during the Climb Phase

In recent years, aircraft have been able to quickly acquire vast and diverse sensor data, leading to the expansion of predictive maintenance applications. Centrifugal compressors are crucial to aircraft air conditioning systems, which has a high need for anomaly detection due to the impact of failures. However, due to non-stationary behavior, there is a challenge in anomaly detection of the air conditioning system. In this study, we propose a method of detecting anomalies by comparison of actual and predicted behavior of centrifugal compressors for non-stationary time-series data. Multiple failure cases confirmed that bearing deterioration results in changes in behavior.