Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Browser

Overcoming the Obstacles to Predictive Maintenance

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 January 2022) | Viewed by 33443

Share This Special Issue

Special Issue Editors

Prof. Sofie Van Hoecke

E-Mail Website
Guest Editor

IDLab, Ghent University - imec, AATower, 9052 Zwijnaarde, Belgium
Interests: innovative machine learning solutions, as well as hybrid machine learning solutions that combine machine learning with semantics, expert knowledge and/or physical knowledge, with applications in predictive maintenance and predictive healthcare, more particularly focusing on anomaly detection, root cause analysis, and complex event detection

Dr. Femke Ongeane

E-Mail Website
Guest Editor

IDLab, Ghent University - imec, iGent, 9052 Zwijnaarde, Belgium
Interests: My main research interests lie in a) hybrid machine learning techniques that combine expert knowledge, i.e., knowledge graphs or rules, with relation machine learning techniques, and (b) expressive reasoning across high-velocity streaming data, i.e., federated reasoning, stream reasoning, and cascading reasoning. The main application domains of this research are predictive maintenance and healthcare, with a particular focus on anomaly detection, root cause analysis and complex event detection

Special Issue Information

Dear Colleagues,

In recent years, sensor monitoring systems have found their way into almost all industries. Such Industry 4.0 systems can yield valuable insights into a company’s physical assets and the interaction of these assets with their environment.

Technological advances such as increased computing power and pervasive connectivity combined with declining sensor costs and higher sensor reliability present opportunities to meet the rising demand for operational efficiency and productivity. Already, a surge in both the number and the diversity of deployed sensors can be ascertained. Industry digitization is further accelerating this trend: The global predictive maintenance market size is estimated to grow to € 1.75bn by 20201.

Today’s state-of-the-art data visualization and analytics tools are, however, unable to cope with the corresponding increase in complexity nor do they allow for end-to-end visualization. Challenges related to large-scale parallel system and technical challenges still need to be addressed. Maintenance in general and predictive maintenance strategies in particular are facing significant challenges in dealing with the evolution of the equipment, instrumentation, and manufacturing processes they support. For example, the volatility of market demands is intensified by the manufacturing trends of mass customization and individualization. Such a trend combined with pressure to harness production costs implies that manufacturing configurations need to change more frequently and dynamically. The dynamism and unpredictability of the challenges posed by constant changes in customer demand and capabilities of available resources add to the complexity of planning and control of production systems, leading to a fall in productivity. This, it is clear that preventive maintenance strategies designed for traditional highly repetitive and stable mass production processes based on predefined components and machine behavior models are no longer valid, and more adaptive and responsive (predictive-prescriptive) maintenance strategies are needed.

Advanced technology, such as artificial intelligence, machine learning, and hybrid machine learning, is deemed to be at the forefront of innovation, and the development of intelligent maintenance systems for increased reliability of production systems is considered to be crucial for securing competitive advantage for manufacturing companies. The success of those adaptive and responsive maintenance strategies highly depends on real-time and operation-synchronous information from the production system, the production process, and the individual product, which should enrich and extend more traditional techniques and models. Companies need to create an integrated information layer fed by their core systems to access the right information, at the right time, from anywhere in the supply chain. By building anomaly detection, fault classification, and/or end-of-life prediction solutions on top of the enriched and context-aware sensor data, companies are empowered to take the essential decisions required to embrace predictive maintenance. Especially, a high reactivity, agility, and adaptability that is required by modern production systems can only be reached by empowering human operators to react to predicted situations, to plan their further actions, to learn, and to gain experience and to communicate with others. Thus, new decision support systems are required that support autonomy in the planning processes and control systems of maintenance operations of production systems.

Proposed topics include:

Predictive maintenance using AI, deep learning, and machine learning;
Hybrid machine learning for improved predictive maintenance;
Anomaly detection, fault diagnosis, remaining useful life (RUL) prediction;
Structural health monitoring, condition monitoring, and decision support systems;
Time series-based predictive maintenance;
Predictive maintenance with live streaming data;
Preprocessing and data analysis, characteristic fault features;
Industrial systems and cloud architectures for predictive maintenance;
Intelligent dashboards for decision support;
Interoperability in predictive maintenance applications;
Condition-based maintenance;
Internet of Things for predictive maintenance;
Industry 4.0 technologies for predictive maintenance;
Implementation methodologies;
Architectures;
Predictive maintenance case studies;
Predictive maintenance applications;

Process modeling and reasoning for predictive maintenance of complex assets.

Prof. Sofie Van Hoecke
Dr. Femke Ongeane
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Predictive maintenance
Machine learning
Predictive maintenance architectures
Anomaly detection
Fault classification
RUL
Industry 4.0

Published Papers (9 papers)

Download All Papers

Research

Jump to: Other

17 pages, 10179 KiB

Open AccessArticle

Latent Dimensions of Auto-Encoder as Robust Features for Inter-Conditional Bearing Fault Diagnosis

by Chandrakanth R. Kancharla, Jens Vankeirsbilck, Dries Vanoost, Jeroen Boydens and Hans Hallez

Appl. Sci. 2022, 12(3), 965; https://doi.org/10.3390/app12030965 - 18 Jan 2022

Cited by 6 | Viewed by 1850

Abstract

Condition-based maintenance (CBM) is becoming a necessity in modern manufacturing units. Particular focus is given to predicting bearing conditions as they are known to be the major reason for machine down time. With the open-source availability of different datasets from various sources and certain data-driven models, the research community has achieved good results for diagnosing faults in bearing fault datasets. However, existing data-driven fault diagnosis methods do not focus on the changing conditions of a machine or assume all conditional data are available all the time. In reality, conditions vary over time. This variability can be based on the measurement noise and operating conditions of the monitored machines such as radial load, axial load, rotation speed, etc. Moreover, the availability of the data measured in varying operating conditions is scarce, as it is not always feasible to collect in-process data in every possible condition or setting. Considering such a scenario, it is necessary to develop methodologies that are robust to conditional variability, i.e., methodologies to transfer the learning from one condition to another without prior knowledge of the variability. This paper proposes the usage of latent values of an auto-encoder as robust features for inter-conditional fault classification. The proposed robust classification method MLCAE-KNN is implemented in three steps. First, the time series data are transformed using Fast Fourier Transform. Using the transformed data of any one condition, a Multi-Layer Convolutional Auto-Encoder (MLCAE) is trained. Next, a K-Nearest Neighbors (KNN) classifier is trained based on the latent features of MLCAE. The so-trained MLCAE-KNN is then used to predict the fault class of any new observation from a new condition. The results of using the latent features of the Auto-Encoder show superior inter-conditional classification robustness and superior accuracies compared to the state-of-the-art. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

24 pages, 1071 KiB

Open AccessFeature PaperArticle

Event-Driven Dashboarding and Feedback for Improved Event Detection in Predictive Maintenance Applications

by Pieter Moens, Sander Vanden Hautte, Dieter De Paepe, Bram Steenwinckel, Stijn Verstichel, Steven Vandekerckhove, Femke Ongenae and Sofie Van Hoecke

Appl. Sci. 2021, 11(21), 10371; https://doi.org/10.3390/app112110371 - 04 Nov 2021

Cited by 3 | Viewed by 1769

Abstract

Manufacturers can plan predictive maintenance by remotely monitoring their assets. However, to extract the necessary insights from monitoring data, they often lack sufficiently large datasets that are labeled by human experts. We suggest combining knowledge-driven and unsupervised data-driven approaches to tackle this issue. Additionally, we present a dynamic dashboard that automatically visualizes detected events using semantic reasoning, assisting experts in the revision and correction of event labels. Captured label corrections are immediately fed back to the adaptive event detectors, improving their performance. To the best of our knowledge, we are the first to demonstrate the synergy of knowledge-driven detectors, data-driven detectors and automatic dashboards capturing feedback. This synergy allows a transition from detecting only unlabeled events, such as anomalies, at the start to detecting labeled events, such as faults, with meaningful descriptions. We demonstrate all work using a ventilation unit monitoring use case. This approach enables manufacturers to collect labeled data for refining event classification techniques with reduced human labeling effort. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

11 pages, 1081 KiB

Open AccessArticle

A Dynamic Methodology for Setting Up Inspection Time Intervals in Conditional Preventive Maintenance

by Rui Assis and Pedro Carmona Marques

Appl. Sci. 2021, 11(18), 8715; https://doi.org/10.3390/app11188715 - 18 Sep 2021

Cited by 3 | Viewed by 1422

Abstract

In periodic condition monitoring, the main problem lies in determining the inspection time intervals. This paper presents a new method for setting an optimum calendar to inspect a critical component that fails due to wear and tear as described by a Weibull probability function. By considering a set of inspection intervals, such that reliability between every two inspections is kept equal or below a pre-set threshold while keeping the total costs of inspection, degraded production, consequences of failure, and repair to a minimum. The resulting calendar may be adjusted dynamically over time as inspections take place and test results are found to be negative, by considering the inspector’s confidence in the test and the likelihood of the method’s yielding false negatives. Consequently, the method becomes self-adjustable as it returns a new calendar after the observations of each test are known and properly interpreted. There are several studies that deal with this issue, but none addresses the concept of safe and unsafe time windows which results from merging two other concepts: descendant inspection time intervals and the time delay between a potential failure and a functional failure (the P–F period). Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

18 pages, 1111 KiB

Open AccessArticle

SOPRENE: Assessment of the Spanish Armada’s Predictive Maintenance Tool for Naval Assets

by David Fernández-Barrero, Oscar Fontenla-Romero, Francisco Lamas-López, David Novoa-Paradela, María D. R-Moreno and David Sanz

Appl. Sci. 2021, 11(16), 7322; https://doi.org/10.3390/app11167322 - 09 Aug 2021

Cited by 5 | Viewed by 3647

Abstract

Predictive maintenance has lately proved to be a useful tool for optimizing costs, performance and systems availability. Furthermore, the greater and more complex the system, the higher the benefit but also the less applied: Architectural, computational and complexity limitations have historically ballasted the adoption of predictive maintenance on the biggest systems. This has been especially true in military systems where the security and criticality of the operations do not accept uncertainty. This paper describes the work conducted in addressing these challenges, aiming to evaluate its applicability in a real scenario: It presents a specific design and development for an actual big and diverse ecosystem of equipment, proposing an semi-unsupervised predictive maintenance system. In addition, it depicts the solution deployment, test and technological adoption of real-world military operative environments and validates the applicability. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

24 pages, 4605 KiB

Open AccessArticle

Integrating Predictive Maintenance in Adaptive Process Scheduling for a Safe and Efficient Industrial Process

by Orhan Can Görür, Xin Yu and Fikret Sivrikaya

Appl. Sci. 2021, 11(11), 5042; https://doi.org/10.3390/app11115042 - 29 May 2021

Cited by 5 | Viewed by 3893

Abstract

Predictive maintenance (PM) algorithms are widely applied for detecting operational anomalies on industrial processes to schedule for a maintenance intervention before a possible breakdown; however, much less focus has been devoted to the use of such prognostics in process scheduling. The existing solutions mostly integrate preventive approaches to protect the machines, usually causing downtimes. The premise of this study is to develop a process scheduling mechanism that selects an acceptable operating condition for an industrial process to adapt to the predicted anomalies. As PM is largely a data-driven approach (hence, it relies on the setup), we first compare different PM approaches and identify a one-class support vector machine (OCSVM) as the best performing option for the anomaly detection on our setup. Then, we propose a novel pipeline to integrate maintenance predictions into a real-time, adaptive process scheduling mechanism. According to the abnormal readings, it schedules for the most suitable operation, i.e., optimizing for machine health and process efficiency, toward preventing breakdowns while maintaining its availability and operational state, thereby reducing downtimes. To demonstrate the pipeline on the action, we implement our approach on a small-scale conveyor belt, utilizing our Internet of Things (IoT) framework. The results show that our PM-based adaptive process control retains an efficient process under abnormal conditions with less or no downtime. We also conclude that a PM approach does not provide sufficient efficiency without its integration into an autonomous planning process. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

30 pages, 6674 KiB

Open AccessArticle

A Metric and Visualization of Completeness in Multi-Dimensional Data Sets of Sensor and Actuator Data Applied to a Condition Monitoring Use Case

by Iris Weiß and Birgit Vogel-Heuser

Appl. Sci. 2021, 11(11), 5022; https://doi.org/10.3390/app11115022 - 29 May 2021

Viewed by 2073

Abstract

The so-called ‘Industrie 4.0’ provides high potential for data-driven methods in automated production systems. However, sensor and actuator data gathered during normal operation of the system is often limited to a narrow range of single, specific operating points. This limitation also restricts the significance of condition-based maintenance models, which are trained to the narrow data. In order to reveal the structure of such multi-dimensional data sets and detect deficiencies, this paper derives a data quality metric and visualization. The metric observes the feature space and evaluates the completeness of data. In the best case, the observations utilize the whole feature space, meaning all different combinations of the variables are present in the data. Low metric values indicate missing combinations, reducing the representativeness of the data. In this way, appropriate countermeasures can be taken if relevant data is missing. For evaluation, a data set of an industrial test bed for condition monitoring of control valves is used. It is shown that the state-of-the-art metrics and visualizations cannot detect deficiencies of completeness in multi-dimensional data sets. In contrast, the proposed heat map enables the expert to locate limitations in multi-dimensional data sets. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

19 pages, 311 KiB

Open AccessArticle

PrimaVera: Synergising Predictive Maintenance

by Bram Ton, Rob Basten, John Bolte, Jan Braaksma, Alessandro Di Bucchianico, Philippe van de Calseyde, Frank Grooteman, Tom Heskes, Nils Jansen, Wouter Teeuw, Tiedo Tinga and Mariëlle Stoelinga

Appl. Sci. 2020, 10(23), 8348; https://doi.org/10.3390/app10238348 - 24 Nov 2020

Cited by 10 | Viewed by 6373

Abstract

The full potential of predictive maintenance has not yet been utilised. Current solutions focus on individual steps of the predictive maintenance cycle and only work for very specific settings. The overarching challenge of predictive maintenance is to leverage these individual building blocks to obtain a framework that supports optimal maintenance and asset management. The PrimaVera project has identified four obstacles to tackle in order to utilise predictive maintenance at its full potential: lack of orchestration and automation of the predictive maintenance workflow, inaccurate or incomplete data and the role of human and organisational factors in data-driven decision support tools. Furthermore, an intuitive generic applicable predictive maintenance process model is presented in this paper to provide a structured way of deploying predictive maintenance solutions. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

27 pages, 2847 KiB

Open AccessArticle

Empowering Predictive Maintenance: A Hybrid Method to Diagnose Abnormal Situations

by Dennys Wallace Duncan Imbassahy, Henrique Costa Marques, Guilherme Conceição Rocha and Alberto Martinetti

Appl. Sci. 2020, 10(19), 6929; https://doi.org/10.3390/app10196929 - 03 Oct 2020

Cited by 5 | Viewed by 3519

Abstract

Aerospace systems are composed of hundreds or thousands of components and complex subsystems which need an appropriate health monitoring capability to enable safe operation in various conditions. In terms of monitoring systems, it is possible to find a considerable number of state-of-the-art works in the literature related to ad-hoc solutions. Still, it is challenging to reuse them even with subtle differences in analogous subsystems or components. This paper proposes the Generic Anomaly Detection Hybridization Algorithm (GADHA) aiming to build a more reusable algorithm to support anomaly detection. The solution consists of analyzing different supervised machine learning classification algorithms combined in ensemble techniques, with a physical model when available, and two levels of a decision to estimate the current state of the monitored system. Finally, the proposed algorithm assures at least equal, or, more typically, better, overall accuracy in fault detection and isolation than the application of such algorithms alone, through few adaptations. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

► Show Figures

Figure 1

Other

Jump to: Research

27 pages, 430 KiB

Open AccessSystematic Review

On Microservice Analysis and Architecture Evolution: A Systematic Mapping Study

by Vincent Bushong, Amr S. Abdelfattah, Abdullah A. Maruf, Dipta Das, Austin Lehman, Eric Jaroszewski, Michael Coffey, Tomas Cerny, Karel Frajtak, Pavel Tisnovsky and Miroslav Bures

Appl. Sci. 2021, 11(17), 7856; https://doi.org/10.3390/app11177856 - 26 Aug 2021

Cited by 23 | Viewed by 7314

Abstract

Microservice architecture has become the leading design for cloud-native systems. The highly decentralized approach to software development consists of relatively independent services, which provides benefits such as faster deployment cycles, better scalability, and good separation of concerns among services. With this new architecture, one can naturally expect a broad range of advancements and simplifications over legacy systems. However, microservice system design remains challenging, as it is still difficult for engineers to understand the system module boundaries. Thus, understanding and explaining the microservice systems might not be as easy as initially thought. This study aims to classify recently published approaches and techniques to analyze microservice systems. It also looks at the evolutionary perspective of such systems and their analysis. Furthermore, the identified approaches target various challenges and goals, which this study analyzed. Thus, it provides the reader with a roadmap to the discipline, tools, techniques, and open challenges for future work. It provides a guide towards choices when aiming for analyzing cloud-native systems. The results indicate five analytical approaches commonly used in the literature, possibly in combination, towards problems classified into seven categories. Full article

(This article belongs to the Special Issue Overcoming the Obstacles to Predictive Maintenance)

Journal Menu

Journal Browser

Overcoming the Obstacles to Predictive Maintenance

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI