Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective

Wen, Yuxin; Rahman, Md. Fashiar; Xu, Honglun; Tseng, Tzu-Liang

doi:10.1016/j.measurement.2021.110276

Cited by 96 publications

(57 citation statements)

References 170 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other diagnosis are executed as Part 2.2 described without any changes. In terms of reference samples update and extension, the comparisons of compressed-sensing-based (CS-based) [23,24]and machine-learning-based (ML-based) diagnosis methods [25,26] are shown in Table 2. From this perspective, the method presented in this study is suitable for online fault diagnosis in field data processing and edge computing [27].…”

Section: Online Sample Updating and Its Application In Fault Diagnosismentioning

confidence: 99%

Fault Diagnosis Based on Compressed Sensing of Multisource Data

You

Deng

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

With the development of the internet of things (IoT) and the application of 5G communication, fault diagnosis of massive multisource sensor data becomes more and more important. In this study, a compressed multisource sensor data-based fault diagnosis scheme is proposed, and its advantages include high data compression and fusion efficiency, low computational cost, and a fast online training sample updating rate. The method includes reference matrix construction, reference matrix compression and fusion, sparse vectors calculation, testing sample reconstruction, and quality evaluation. First, a reference matrix is constructed with labeled multisource sensor data, and each column in the matrix is composed of data samples collected from different sources. Then, the reference matrix is compressed using a measurement matrix, meanwhile, the multisource data samples are fused based on weighted summation during the compression. Later, sparse representation based on batch matching pursuit algorithm is conducted, in this step, the compressed testing sample is represented by the compressed reference matrix, and the output of the sparse representation is a sparse vector. After that, elements in the sparse vector corresponding to different patterns are retained exclusively while other elements are set to zero, respectively, and estimated testing samples are reconstructed with the compressed reference matrix and the processed sparse vector. Finally, based on reconstruction quality evaluation, the pattern of the testing sample is determined. Two cases are employed to validate the effectiveness of the proposed approach, including landfill gas power generator maintenance pattern recognition and multiple redundancy aileron actuator fault diagnosis, and the detection accuracy is 96.13% and 96.67%, respectively.

show abstract

Section: Online Sample Updating and Its Application In Fault Diagnosismentioning

confidence: 99%

Fault Diagnosis Based on Compressed Sensing of Multisource Data

You

Deng

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the improved particle swarm optimization (IPSO-LSSVM), an intelligent diagnosis method for bearing faults was proposed which can effectively improve the recognition accuracy and convergence rate. There are many fault diagnoses for various types of equipment, but there is little feedback and application of the output after fault diagnosis [35], such as system platform [36,37], intelligent maintenance [38], maintenance response after fault diagnosis, and how to carry out maintenance work [39].…”

Section: Introductionmentioning

confidence: 99%

Research on Comprehensive Operation and Maintenance Based on the Fault Diagnosis System of Combine Harvester

et al. 2022

View full text Add to dashboard Cite

In view of the difficulty in diagnosing and discriminating fault conditions during the operation of combine harvesters, difficulty in real-time processing of health status, and low timeliness of fault processing, a comprehensive operation and maintenance platform for combine harvesters was developed in this study which realized the functions of data monitoring and the full operation and maintenance of a combine harvester. At the same time, through the comprehensive operation and maintenance platform, the harvester information was obtained in real-time, the diagnosis results were obtained, and the maintenance service was effectively carried out through the platform. The IPSO-SVM fault diagnosis algorithm was proposed, and the performance of the fault diagnosis of the combine harvester was verified by the simulation test. The experimental verification showed that the system met the requirements of remote monitoring of combine harvesters, and the prediction accuracy of this method was 97.96%. Compared with SVM (87.51%), GA-SVM (89.44%), and PSO-SVM (92.56%), this system had better generalization ability and effectively improved the management level of the comprehensive operation and maintenance of the combine harvester. A theoretical basis and technical reference will be provided for the follow-up research for the comprehensive operation and maintenance platform of the combine harvester in this paper.

show abstract

“…Ones for which online decisions have to be made about upcoming events, optimizing both the expected accuracy of the predictions and the cost of delaying the decisions. In particular, in the experimental part, we address in a novel way the challenge of decision making in the field of predictive maintenance, raised in a recent survey [15]. As another example, an autonomous car must interpret online the scene in front of it.…”

Section: Introductionmentioning

confidence: 99%

ECOTS: Early Classification in Open Time Series

Achenchabe¹,

Bondu²,

Cornuéjols³

et al. 2022

Preprint

View full text Add to dashboard Cite

Learning to predict ahead of time events in open time series is challenging. While Early Classification of Time Series (ECTS) tackles the problem of balancing online the accuracy of the prediction with the cost of delaying the decision when the individuals are time series of finite length with a unique label for the whole time series. Surprisingly, this trade-off has never been investigated for open time series with undetermined length and with different classes for each subsequence of the same time series. In this paper, we propose a principled method to adapt any technique for ECTS to the Early Classification in Open Time Series (ECOTS). We show how the classifiers must be constructed and what the decision triggering system becomes in this new scenario. We address the challenge of decision making in the predictive maintenance field. We illustrate our methodology by transforming two state-of-the-art ECTS algorithms for the ECOTS scenario and report numerical experiments on a real dataset for predictive maintenance that demonstrate the practicality of the novel approach.

show abstract

Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective

Cited by 96 publications

References 170 publications

Fault Diagnosis Based on Compressed Sensing of Multisource Data

Fault Diagnosis Based on Compressed Sensing of Multisource Data

Research on Comprehensive Operation and Maintenance Based on the Fault Diagnosis System of Combine Harvester

ECOTS: Early Classification in Open Time Series

Contact Info

Product

Resources

About