Fault diagnosis of complex hydraulic system based on fast Mahalanobis classification system with high-dimensional imbalanced data

Mei, Ting; Wen-he, Chen; Fu, Liqun; Yao, Qi-Feng; Cheng, Longsheng

doi:10.1016/j.measurement.2023.112773

Cited by 4 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While their method achieves good results in multi-classification, it does not consider different fault levels in the presence of multiple faults. Liu et al [8] incorporated a multi-output strategy into a hybrid kernel extreme value learning machine (HKELM), enabling simultaneous output of fault level states for multiple components and facilitating Mao et al [31] Fast Mahalanobis 92 multi-output fault diagnosis. However, their feature extraction process relies on experiential time-domain feature extraction and subsequent dimensionality reduction using LDA.…”

Section: Comparison With Published Articlesmentioning

confidence: 99%

“…However, their method employed a problem transformation technique based on fault fusion, which necessitates sample segmentation into distinct groups according to different fault labels, leading to segmentation issues. Mao et al [31] introduced a fast Mahalanobis classification system for fault diagnosis, focusing on the overall operating state of the system. The method uses symmetric uncertainty and Mahalanobis kernel PCA.…”

Section: Comparison With Published Articlesmentioning

confidence: 99%

See 1 more Smart Citation

A multi-output fault diagnosis framework for hydraulic system using a CNN-SVM hierarchical learning strategy

Liang,

Yuan,

Kang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Achieving asymptotic and concurrent fault diagnosis in hydraulic system remains a challenging endeavor due to the inherent attributes of the hidden occurrence, simultaneous manifestation, coupling, and limited sample size. To address the above issues, this paper proposes a hierarchical multi-output fault detection and diagnosis framework, namely, HMDF, based on a hierarchical learning strategy to leverage an improved convolutional neural network (CNN) and support vector machine (SVM). Both a multi-channel CNN and a multi-branch CNN are employed to extract and downscale features collected by the sensors at diverse sampling frequencies first, and then, such features are subsequently subjected to classification using SVM. The hierarchical learning strategy enables the identification of different fault states, both at the component and the intra-component level. Additionally, a modified whale optimization algorithm (WOA) is also utilized to optimize the classification process of SVM. Extensive experiments are conducted to test the proposed HMDF with the hydraulic system datasets. Results show that HMDF achieves a diagnostic accuracy of up to 98.9% for the dataset, surpassing traditional methods reliant on manual extraction of time-frequency features, and it also exhibits superior classification performances with a small sample size. The HMDF is expected to offer a generalized framework for the multi-output fault detection and diagnosis in hydraulic systems and other complex components. 

show abstract

Section: Comparison With Published Articlesmentioning

confidence: 99%

Section: Comparison With Published Articlesmentioning

confidence: 99%