Prescriptive Maintenance Research Articles

Industry 4.0 for passenger railway companies: A maturity model proposal for technology management

The railway sector is a relevant segment for the transportation of people and goods, and its efficiency and sustainability are crucial for fostering economic development and minimizing environmental impact. This research proposes an Industry 4.0 maturity model for passenger railway companies to manage emerging technologies, aiming to enhance them holistically to leverage the internal and external business dimensions. An exploratory and qualitative approach was employed, involving semi-structured interviews with experts in Brazilian railway transport. Based on the opportunities and Key Performance Indicators identified within the sector, we developed an Industry 4.0 maturity model for companies and subsequently tested it in collaboration with a transport operator. The findings suggest that the proposed Industry 4.0 maturity model can effectively guide practitioners in applying advanced technologies for robust and efficient train operations, prescriptive maintenance, strong supply chain management, and improved passenger experience and worker performance. This research provides a noteworthy and substantial contribution by introducing unprecedented frameworks that offer a holistic view of Industry 4.0 in the context of passenger railways. The study's practical impact is aiding passenger railway companies to navigate their Industry 4.0 journey. Academically, the research contributes to advancing the holistic understanding of Industry 4.0 as an ongoing phenomenon, enriching the academic discourse by discussing published works and presenting empirical data from railway companies.

A framework for conceptualizing integrated prescriptive maintenance and production planning and control models

Goal: This study aims to support researchers and managers in conceptualising new integrated prescriptive maintenance (PxM) and production planning and control (PPC) models. Design / Methodology / Approach: We perform a systematic literature review based on Thomé et al. (2016) and analyse literary findings using qualitative content analysis and quantitative correlation analyses. Results: This work identifies 94 integrated PxM and PPC planning models and 47 outcomes, 16 decision variables and 34 environment entities. Based on the quantitative analyses of these components, we derive a normative framework to guide researchers and practitioners in conceptualising integrated models. Limitations of the investigation: The study is limited to only one scientific database. Additionally, the quantitative analyses might be sensitive due to a low sample size for some components, and we only measure the linear dependency between two components. Lastly, we do not address solution algorithms. Practical implications: The framework constitutes a tool for managers to construct integrated models tailored to their specific planning problems, fostering alignment between production and maintenance departments, plans and controls. Originality / Value: We provide a descriptive overview and normative guidance in the selection of components that can or should be used for future PxM-aligned PPC planning studies, pinpointing possible research gaps.

PRESCRIPTIVE MAINTENANCE SYNCHRONIZED TO THE CHARACTERISTICS OF INDUSTRY 5.0: A THEORETICAL DISCUSSION

This article aims to examine and understand the current scope of Prescriptive Maintenance integrated with the human-centric characteristics of Industry 5.0. Therefore, the main research question is the following: “In the view of the managers of the companies visited, located in the Southeast Region of Brazil, what are the main technical and administrative difficulties that companies encounter in successfully implementing proactive combinations on the factory floor, such as Prescriptive Maintenance integrated with the characteristics of Industry 5.0”?. The evolution of industrial processes in recent decades and the advent of Industry 4.0 integrated with human-centered characteristics have placed maintenance as one of the protagonists of industrial processes. In a scenario where automation and humans are gaining more and more space, the future of industries lies in Prescriptive Maintenance. To achieve the objective of the article, professional experiences from participation in congresses, seminars and technical visits to several factories located in the Southeast Region of Brazil are used. In data collection, we explored documentary observation and bibliographic research in the Science Direct and Web of Science databases. The study focuses on research areas related to maintenance integration, Industry 4.0 (Techno centric) and human-centric characteristics (Industry 5.0). The article brought important conclusions, as it addresses the impact and trends on the factory floor so that managers can develop competitiveness and productivity. The article highlights the role of maintenance methods in improving factory floor performance, emphasizing human knowledge and Prescriptive Maintenance practices to ensure operations within World Class standards.

Joint Prescriptive Maintenance and Production Planning and Control Process Simulation for Extrusion System

Production planning and control (PPC) is the mainstay of every manufacturer and ensures flawless production processes. However, PPC is jeopardized by breakdowns that can only be tackled with appropriate maintenance. In the past, static strategies, such as reactive and scheduled maintenance, have been used. Yet, with growing system complexity, Industry 4.0, and abundant sensor data, dynamic strategies through PHM have emerged. The most advanced maintenance strategy is prescriptive maintenance (PxM), which allows manufacturers not only to predict failures but also to establish condition-based production plans and controls. To this end, our study explores the integration of PxM with PPC. First, we propose a fault prediction model based on health indicators and future loads of a single-machine system. The proposed fault prediction is integrated into a joint PxM and PPC simulation model that compares the make­span of three joint PxM and PPC strategies inter se and versus reactive and scheduled maintenance. A simulation study using industrial data from an extrusion process evaluates the different strategies across different time horizons (one month to a year). The findings indicate that joint PxM and PPC outperform other strategies, providing significant time savings over traditional methods. Further, a sensitivity analysis is conducted to assess the robustness of the PxM strategies under varying levels of measurement noise, revealing potential challenges under high noise conditions. The study contributes to the field of PHM by providing insights into the effectiveness of joint PxM and PPC strategies and offering a comprehensive analysis of their performance under different conditions.

Diagnostic and prognostic for prescriptive maintenance and control of PEMFC systems in an industrial framework

This paper designed and defined the framework of prescriptive maintenance and its four axes, for hydrogen-energy systems, considering the constraints of actual systems, to improve durability, availability, reliability, performance, safety and operating costs of these systems. Different data-driven approaches for diagnostic and different approaches for prognostic of Remaining Useful Life (RUL) for Proton Exchange Membrane Fuel Cell (PEMFC) systems are discussed. The use of measures always available on actual systems allows to validate the approach in an industrial framework. Several diagnostic algorithms (classification and clustering) are compared to find the best compromise between computation time and accuracy in an online diagnostic framework. For the prognostic part, the data set comes from experimental tests performed under steady load for a PEMFC stack. A degradation trend of PEMFC stack voltage is extracted from these data and two well-known prediction algorithms namely Bidirectional Echo State Network (BiESN) and Bidirectional Long-Short Term Memory network (BiLSTM) are tested and compared to evaluate the robustness of the PEMFC voltage prediction for RUL estimation. The diagnostic and prognostic approaches proposed in this paper are first steps towards future work related to prescriptive maintenance for hydrogen-energy systems (PEMFC, Proton Exchange Membrane Water Electrolyzer and hybridization of the two).

A novel AI-powered method for robust identification of operational phases in refrigerators

Refrigerators are essential appliances in our daily lives, while the accurate identification of their operational phase is crucial for various applications, such as energy management and maintenance. This paper introduces a novel method to predict the operational phase of refrigerators based on power consumption data, exploiting artificial intelligence (AI) and pattern recognition techniques. Specifically, the proposed method initially identifies the driving speed of the compressor (fixed or variable speed) utilizing an Adaptive Boosting, (AdaBoost) classifier. Following that, a Long Short-Term Memory (LSTM) classifier was designed for each type of compressor based on extracted statistical features. This classifier is used to categorize daily power consumption into the different operational phases. Moreover, the proposed AI-driven diagnostic tool facilitates operational-based prescriptive maintenance by addressing periodic and phase-specific maintenance actions while providing homeowners with informed suggestions on alternative refrigerator models that offer greater cost savings and reduced annual energy consumption. The proposed method was tested on real and simulated data for over 20 years, with the AdaBoost classifier achieving an accuracy close to 97% and an F1 score close to 97% and the LSTM nodes achieving an accuracy of approximately 95% in all cases. Finally, the method demonstrated robustness when applied to new datasets, showing comparable performance on unknown data, rendering it a powerful tool for refrigerator management and maintenance.

LP-OPTIMA: A Framework for Prescriptive Maintenance and Optimization of IoT Resources for Low-Power Embedded Systems.

Low-power embedded systems have been widely used in a variety of applications, allowing devices to efficiently collect and exchange data while minimizing energy consumption. However, the lack of extensive maintenance procedures designed specifically for low-power systems, coupled with constraints on anticipating faults and monitoring capacities, presents notable difficulties and intricacies in identifying failures and customized reaction mechanisms. The proposed approach seeks to address the gaps in current resource management frameworks and maintenance protocols for low-power embedded systems. Furthermore, this paper offers a trilateral framework that provides periodic prescriptions to stakeholders, a periodic control mechanism for automated actions and messages to prevent breakdowns, and a backup AI malfunction detection module to prevent the system from accessing any stress points. To evaluate the AI malfunction detection module approach, three novel autonomous embedded systems based on different ARM Cortex cores have been specifically designed and developed. Real-life results obtained from the testing of the proposed AI malfunction detection module in the developed embedded systems demonstrated outstanding performance, with metrics consistently exceeding 98%. This affirms the efficacy and reliability of the developed approach in enhancing the fault tolerance and maintenance capabilities of low-power embedded systems.

A Prescriptive Model for Failure Analysis in Ship Machinery Monitoring Using Generative Adversarial Networks

In recent years, advanced methods and smart solutions have been investigated for the safe, secure, and environmentally friendly operation of ships. Since data acquisition capabilities have improved, data processing has become of great importance for ship operators. In this study, we introduce a novel approach to ship machinery monitoring, employing generative adversarial networks (GANs) augmented with failure mode and effect analysis (FMEA), to address a spectrum of failure modes in diesel generators. GANs are emerging unsupervised deep learning models known for their ability to generate realistic samples that are used to amplify a number of failures within training datasets. Our model specifically targets critical failure modes, such as mechanical wear and tear on turbochargers and fuel injection system failures, which can have environmental effects, providing a comprehensive framework for anomaly detection. By integrating FMEA into our GAN model, we do not stop at detecting these failures; we also enable timely interventions and improvements in operational efficiency in the maritime industry. This methodology not only boosts the reliability of diesel generators, but also sets a precedent for prescriptive maintenance approaches in the maritime industry. The model was demonstrated with real-time data, including 33 features, gathered from a diesel generator installed on a 310,000 DWT oil tanker. The developed algorithm provides high-accuracy results, achieving 83.13% accuracy. The final model demonstrates a precision score of 36.91%, a recall score of 83.47%, and an F1 score of 51.18%. The model strikes a balance between precision and recall in order to eliminate operational drift and enables potential early action in identified positive cases. This study contributes to managing operational excellence in tanker ship fleets. Furthermore, this study could be expanded to enhance the current functionalities of engine health management software products.

Data-Driven Models Applied to Predictive and Prescriptive Maintenance of Wind Turbine: A Systematic Review of Approaches Based on Failure Detection, Diagnosis, and Prognosis

Wind energy has achieved a leading position among renewable energies. The global installed capacity in 2022 was 906 GW of power, with a growth of 8.4% compared to the same period in the previous year. The forecast is that the barrier of 1,000,000 MW of installed wind capacity in the world will be exceeded in July 2023, according to data from the World Association of Wind Energy. In order to support the expected growth in the wind sector, maintenance strategies for wind turbines must provide the reliability and availability necessary to achieve these goals. The usual maintenance procedures may present difficulties in keeping up with the expansion of this energy source. The objective of this work was to carry out a systematic review of the literature focused on research on the predictive and prescriptive maintenance of wind turbines based on the implementation of data-oriented models with the use of artificial intelligence tools. Deep machine learning models involving the detection, diagnosis, and prognosis of failures in this equipment were addressed.

A data-driven prioritisation framework to mitigate maintenance impact on passengers during metro line operation

The application of artificial intelligence (AI) techniques may lead to significant improvements in different aspects of rail sector. Considering asset management and maintenance, AI can improve data analysis and asset status forecasting and decision-making processes, fostering predictive and prescriptive maintenance strategies. A prescriptive approach should be able to predict future scenarios as well as to suggest a course of actions. Nevertheless, the decision-making in rail asset management is often based on the classical asset-oriented approach, concentrating on the function of the asset itself as a main key performance indicator (KPI), whereas a user-oriented approach could lead to improved performance in terms of level of service. This paper is aimed at integrating the passengers’ perspective in the decision-making process for asset management to mitigate the impact that service interruptions may have on the final users. A data-driven prioritisation framework is developed to prioritise maintenance interventions taking into account asset status and criticality. In particular, a three-step approach is proposed, which focuses on the analysis of passenger data to evaluate the failure impact on the service, the analysis of alarms and anomalies to evaluate the asset status, and the suggestion of maintenance interventions. The proposed approach is applied to the maintenance of the metro line M5 in the Italian city of Milan. Results show the usefulness of the proposed approach to support infrastructure managers and maintenance operators in making decisions regarding the priority of maintenance activities, reducing the risk of critical failures and service interruptions.

Resilience and Sustainability plants improvement through Maintenance 4.0: IoT, Digital Twin and CPS framework and implementation roadmap

The Fouth Industrial Revolution is the new innovative wave that touches any sector, bringing great innovation. As the benefits that Industry 4.0 can create are very high, it is mandatory to deeply investigate it and elaborate full applications. Digital technologies require to be faced with a correct pace, beginning with a small pilot, able to generate quick and valuable results. A domain in which Industry 4.0 can bring a great and positive effect is Maintenance, with predictive and prescriptive maintenance. In this research, it is analyzed how Internet of Things (IoT), Digital Twins (DT) and Cyber Physical System (CPS) can enhance maintenance and how they can be integrated to create the Maintenance 4.0 framework, with a clear focus on Resilience and environmental Sustainability, applied with a 6 steps roadmap based on the “starting small” authors’ approach and initial assumption.

Design and Control for High-Reliability Power Electronics: State-of-the-Art and Future Trends

Electrification is a mega-trend in the modern economy, urged by the need for a more ecological and sustainable impact of new technologies, among many other merits related to the process of electrification. The widespread adoption of renewable energy, transportation electrification, energy storage systems and smart manufacturing is remarkable. As a result, power electronics has become the critical enabling technology for improving energy efficiency and sustainability. In recent years, the reliability of power electronic equipment has been under scrutiny, especially in mission-critical applications of power electronics converters. Recently, special attention has been paid to the development of lifetime models of the main electronic components, which could then be applied to probabilistic analysis based on the mission profile of system-level reliability. This prediction methodology has some limitations because it does not consider external factors and agents other than the wear itself. Redundancy has been the typical approach to improve the availability of mission critical power electronic systems, which could be associated with considerable extra cost. Fault-tolerant converters were proposed as a more cost-effective alternative solution that could also extend the service life. The maintenance cost could be reduced by using active thermal control, which allows the balancing of wear damage in modular power electronic converters and, consequently, the scheduling of maintenance events. A further step could be taken with the application of real-time condition monitoring of systems, which has evolved into the concepts of predictive and prescriptive maintenance that allows for prediction and mitigation of faults. These techniques are under active development and are expected to benefit from new methods and technologies from rapidly progressing areas of artificial intelligence and digital twin. This paper provides a detailed overview on the recent trends and advances in the field of high-reliability power electronics systems.

TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework

TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework

Planning of prescriptive maintenance types for generator with fuzzy logic-based genetic algorithm in a hydroelectric power plant

The move to predictive and prescriptive maintenance underlines the need for cost-effective methods to monitoring degradation and predicting failures. It is in hydroelectric power plants (HPPs) where the most powerful and unique techniques of this evolution were observed. The final premise of this transition is the need to improve the decision-making process for planning activities in the Prescriptive Maintenance Planning (MP). This encourages the use of fuzzy set theory in process management. Although there are many studies on MP in the literature, these studies do not fully reflect the real life as they ignore potential schedule delays and the indirect impact of sustainable strategy on revenues. Therefore, in the first stage of this study, it is aimed to weight the maintenance types (MTs) on a plant basis for the generator, which is the most critical system of the pumped storage HPP, and in the second stage, it is aimed to create MPs that minimize delays due to system shutdowns with weighted MTs. For this purpose, in the first stage, the MTs for the HPP were weighted by AHP-TOPSIS combination augmented with Pythagorean fuzzy numbers, and in the second stage, a Genetic Algorithm model was designed for the problem of coordinating maintenance durations and deadlines in addition to these weights. Averaged over 50 iterations, the average number of delayed MPs is 142.55, indicating that the algorithm is successful in reducing delayed MPs, while the average weighted delay value is 172.85, indicating that more work is needed in terms of weighted delay.

Optimal operation and maintenance of energy storage systems in grid-connected microgrids by deep reinforcement learning

The operation of microgrids, i.e., energy systems composed of distributed energy generation, local loads and energy storage capacity, is challenged by the variability of intermittent energy sources and demands, the stochastic occurrence of unexpected outages of the conventional grid and the degradation of the Energy Storage System (ESS), which is strongly influenced by its operating conditions. To effectively address these challenges, a novel method for combined operation and maintenance management of ESS has been developed. Unlike the currently available solutions, which typically address the one-day-ahead scheduling problem, the present work considers, for the first time, the realistic case of a microgrid in which the ESS degrades and unexpected outages of the conventional grid can occur along the long-time horizons of the entire microgrid lifetimes. The proposed method, which is based on deep reinforcement learning, is tested on a simulated grid-connected microgrid of a residential building equipped with photovoltaic modules and an ESS. The method outperforms other state-of-the-art approaches based on heuristics and metaheuristics by increasing the profit by 15% and reducing the average number of ESS replacements during its lifetime. Therefore, it can be concluded that the proposed DRL-based framework allows achieving prescriptive maintenance since the suggested actions are optimal from the point of view of effectively maximizing the profit and minimizing the maintenance interventions over the entire lifetime of the microgrid.

Prescriptive maintenance for complex products with digital twin considering production planning and resource constraints

Maintenance is a critical aspect of complex products through entire life cycle, often requiring coordination of production planning and available resources, while previous studies appear to have rarely addressed. With this in mind, this paper presents a prescriptive maintenance framework based on digital twins (DTs) for reducing operational risk and maintenance costs of complex equipment clusters. Virtual entities are firstly constructed for each single asset in multiple dimensions, which use real-time or historical sensing data collected from the physical entities to predict the corresponding remaining useful life (RUL). Then such RUL information is incorporated into a stochastic programming model with chance constraints to enable dynamic decision making. In particular, a risk-based optimization model is formulated to take full account of the physical distances between facilities and production gaps. Further, a dual-sense pyramidal transformer model is proposed to sense important details of data in both time and space while capturing temporal dependencies at different scales. Compared to existing data-driven approaches, the proposed DT-based alternative achieves dynamic real-time interaction between physical and virtual units driven by both models and data, while virtual verification based on high-fidelity models ensures high reliability of maintenance decisions, which has also been validated in an aero-engine maintenance case study.

Deep reinforcement learning with combinatorial actions spaces: An application to prescriptive maintenance

In this paper, we leverage a prescriptive analytics approach based on deep reinforcement learning and adapt it for sequential decision-problems with large, noisy state spaces and combinatorial actions spaces. We implement a novel mechanism that uses deep learning to reduce the action space and apply the approach to the context of maintenance management. We show that our method substantially outperforms established baseline methods from practice and research, closing more than 90 percent of the cost gap between the next-best solution and the optimum under perfect information. In addition to reducing costs, the specifically-designed reward function incentivizes bundling maintenance actions in a way that fully utilizes the available number of workers. Thereby, the number of time steps in which any maintenance action occurs is reduced. This decreases the organizational and operational impact of maintenance in real-world settings as disruptions can be limited to a few days. Beyond this context, our work illustrates the potential of prescriptive approaches based on deep reinforcement learning in other applications that face similarly challenging problem settings.

AI-based Prescriptive Maintenance for Sustainable Operation

AI-based Prescriptive Maintenance for Sustainable Operation

Artificial Intelligence Supported Aircraft Maintenance Strategy Selection with q-Rung Orthopair Fuzzy TOPSIS Method

In the aviation sector as unscheduled maintenance, repair and overhaul cost too much and these activities also negatively affect the prestige of the companies, deciding the most appropriate maintenance strategy is crucial. Today artificial intelligence methods, especially machine learning techniques facilitate failure detection and predict the wear and tear of the equipment before the occurrence of a serious failure. In this paper, artificial intelligence-supported corrective, predictive, and prescriptive maintenance methods are examined. Those most common aircraft maintenance approaches are compared regarding cost, reliability, failure detection, and downtime period using decision makers' subjective evaluations with the help of the q-rung orthopair fuzzy TOPSIS method which mitigates the drawbacks of uncertainty in human decision making. Stable and efficient results are obtained regarding the selection of an appropriate maintenance strategy. This article might be the first quantitative research that evaluates and compares AI-supported aircraft maintenance strategies.

Evaluating Vector Representations of Short Text Data for Automating Recommendations of Maintenance Cases

Nuclear power is a carbon-free source of energy, and features as a key component in the mix of energy towards meeting ambitious decarbonization goals. However, as it currently stands, nuclear power generation is orders of magnitude more expensive when compared to fossil energy sources. Recently, there has been a significant push, by both the US government and the power industry, towards identifying and addressing opportunities for cost reductions in nuclear power generation. While capital costs are being addressed through innovative Smart Modular Reactor (SMR) designs, reductions in Operations and Maintenance (O&M) costs is an equally important opportunity. Enhanced methods for remote monitoring and health management-based maintenance optimization has been recognized as a key element for reducing preventive and corrective maintenance costs. Beyond sensor data and signal processing, there is also significant potential for reducing manual efforts and improving productivity in maintenance scheduling and planning activities. By utilizing state-of-the-art Technical Language Processing (TLP) methods to analyze large volumes of historical maintenance case data, there is the potential to automate the generation of maintenance recommendations to reduce human effort and accelerate maintenance processes. This paper presents our efforts towards developing a prescriptive maintenance system that integrates with and enhances state-of-the-art asset performance management software available in the industry. The goal of prescriptive maintenance is to analyze the behavior of an asset, assess its condition, and recommend specific actions to maximize the utility of that asset. Specifically, this work evaluates three approaches of different complexities for vectorization of short-text maintenance case titles for kNN-based recommendation of cases relevant to a new input case title. Industrial text must first be vectorized to build automated and/or machine learning-based prediction and recommendation models. The choice of vectorization methods heavily dictates how the language gets modeled and consequently impacts the performance of downstream prediction and recommendation models. The objective of the nearest neighbor case recommendations is to reduce manual Subject Matter Expert (SME) effort and increase consistency of recommended maintenance actions on industrial assets by reusing actions performed on the identified nearest neighbor cases from past maintenance work. Four models based on three text vectorization approaches are evaluated, quantitatively and qualitatively, using real data from a large variety of utility customers from the energy domain. A single tier (WVEC-1tier) and a three-tier (WVEC-3tier) approach that represent case titles in word-based vector spaces each significantly outperform a more complex bag-of-phrases topic vector space-based approach (TVEC-K-topics). We present our findings and challenges identified so far in building such a recommendation system.