Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics

Jimenez, Juan José Montero; Schwartz, Sébastien; Vingerhoeds, Rob A.; Grabot, Bernard; Salaün, Michel

doi:10.1016/j.jmsy.2020.07.008

Cited by 173 publications

(84 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Predictive maintenance (PdM) [1] of manufacturing assets offer a number of benefits to industry, including proactive asset health management and reduced downtime [2] which are key components for cost effective operation of manufacturing systems. One application of PdM is the ability to forecast an asset's remaining useful lifetime (RUL) in terms of the number of remaining running cycles from the point of prediction beyond which the asset will no longer be able to operate.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Aware Resource Sharing in Cross-Device Federated Model Training for Collaborative Predictive Maintenance

Bharti¹,

McGibney

2021

IEEE Access

View full text Add to dashboard Cite

The proliferation of Industry 4.0 has made modern industrial assets a rich source of data that can be leveraged to optimise operations, ensure efficiency, and minimise maintenance costs. The availability of data is advantageous for asset management, however, attempts to maximise the value of this data often fall short due to additional constraints, such as privacy concerns and data stored in distributed silos that is difficult to access and share. Federated Learning (FL) has been explored to address these challenges and has been demonstrated to provide a mechanism that allows highly distributed data to be mined in a privacy-preserving manner and offering new opportunities for a collaborative approach to asset management. Despite the benefits, FL has some challenges that need to be overcome to make it fully compatible for asset management or more specifically predictive maintenance applications. FL requires a set of clients that participate in the model training process, however, orchestration, device heterogeneity and scalability can hinder the speed and accuracy in the context of collaborative predictive maintenance. To address this challenge, this work proposes a split-learning-based framework (SplitPred) that enables FL clients to maximise available resources within their local network without compromising the benefits of a FL approach (i.e., privacy and shared learning). Experiments performed on the benchmark C-MAPSS dataset demonstrate the advantage of applying SplitPred in the FL process in terms of efficient use of resources, i.e., model convergence time, accuracy, and network load.

show abstract

Section: Introductionmentioning

confidence: 99%

Privacy-Aware Resource Sharing in Cross-Device Federated Model Training for Collaborative Predictive Maintenance

Bharti¹,

McGibney

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Those features that show the highest degree of information are selected [11]. To enable For complex systems, approaches that take multiple models into account are preferred for condition monitoring tasks, since they are able to combine different aspects and advantages of the single models [30]. Often, these multi-model approaches aim at a fault detection and isolation [31][32][33].…”

Section: Introductionmentioning

confidence: 99%

A Multi-Model-Particle Filtering-Based Prognostic Approach to Consider Uncertainties in RUL Predictions

Bender

2021

Machines

View full text Add to dashboard Cite

While increasing digitalization enables multiple advantages for a reliable operation of technical systems, a remaining challenge in the context of condition monitoring is seen in suitable consideration of uncertainties affecting the monitored system. Therefore, a suitable prognostic approach to predict the remaining useful lifetime of complex technical systems is required. To handle different kinds of uncertainties, a novel Multi-Model-Particle Filtering-based prognostic approach is developed and evaluated by the use case of rubber-metal-elements. These elements are maintained preventively due to the strong influence of uncertainties on their behavior. In this paper, two measurement quantities are compared concerning their ability to establish a prediction of the remaining useful lifetime of the monitored elements and the influence of present uncertainties. Based on three performance indices, the results are evaluated. A comparison with predictions of a classical Particle Filter underlines the superiority of the developed Multi-Model-Particle Filter. Finally, the value of the developed method for enabling condition monitoring of technical systems related to uncertainties is given exemplary by a comparison between the preventive and the predictive maintenance strategy for the use case.

show abstract

“…Different maintenance strategies have been proposed in the literature. The general maintenance strategies are summarized in Figure 1 (Jimenez, Schwartz, Vingerhoeds, Grabot, and Salaün, 2020). Reactive (or after failure) approach refers to a maintenance when equipment breakdown occurs.…”

Section: Introductionmentioning

confidence: 99%

Maki̇ne Öğrenmesi̇ Yaklaşimlari İle İndüksi̇yon Motorlari İçi̇n Akilli Hata Tespi̇ti̇ Ve Siniflandirmada Deneysel Bi̇r Değerlendi̇rme

Kasap

Çinar

Yazıcı

et al. 2021

Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

The concept of Industry 4.0 aims fully digital and autonomous production. For manufacturing systems to work properly, their maintenance must be done correctly. However, while unnecessary maintenance causes waste of money and time, skipping necessary maintenance can also cause unexpected down times in production. Predictive maintenance (PdM) aims to predict and diagnose faults at an early stage and also the time remaining for future failures of equipment which might provide significant cost savings compared to traditional maintenance approaches. Today's sensor and data collection technologies have become more accessible and reliable which paved the way for manufacturers to continuously monitor their equipment, collect and store large volume of data in their production systems. Using this data with machine learning (ML) algorithms and analyzing the fingerprints of equipment faults can help making more informed decision regarding maintenance in manufacturing which might help increasing production quality and capacity. In our study, induction motors (IM) which are widely used in factories for different purposes and their failure scenarios are targeted. Triaxial vibration data collected from two similar induction motors under different operating conditions are examined. Various features of vibration data are extracted, scaled and labeled with a status information of the operation state. The obtained dataset is analyzed with six different ML algorithms. Performances are examined and compared against each other. In this study, we present our promising experimental results and experimentally show that the abnormal operating conditions of IMs can be successfully detected utilizing ML algorithms for a PdM application.

show abstract

Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics

Cited by 173 publications

References 143 publications

Privacy-Aware Resource Sharing in Cross-Device Federated Model Training for Collaborative Predictive Maintenance

Privacy-Aware Resource Sharing in Cross-Device Federated Model Training for Collaborative Predictive Maintenance

A Multi-Model-Particle Filtering-Based Prognostic Approach to Consider Uncertainties in RUL Predictions

Maki̇ne Öğrenmesi̇ Yaklaşimlari İle İndüksi̇yon Motorlari İçi̇n Akilli Hata Tespi̇ti̇ Ve Siniflandirmada Deneysel Bi̇r Değerlendi̇rme

Contact Info

Product

Resources

About