Locally Linear Embedding on Grassmann Manifold for Performance Degradation Assessment of Bearings

Ma, Meng; Chen, Xuefeng; Zhang, Xiaoli; Ding, Baoqing; Wang, Shibin

doi:10.1109/tr.2017.2691730

Cited by 46 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first block in TABLE II lists the results from the classical machine learning methods, the random forest (RF) [32] and support vector machine (SVM) [33]. Especially for SVM, we adopted three different forms of input signals, i) the raw signals of length 2048, ii) 29 statistical features of time and frequency domain extracted by Ma et al [34], and iii) the same manually extracted features but the signals are decomposed into 8 components by the wavelet packet (sym4) before feature extraction. However, according to the result, it is implicit that SVM and RF can not recognize the raw signals well (the accuracies are 53.48% and 64.66%, respectively), and even with the help of WPD and manual feature extraction, it is not improved much (less than 5%).…”

Section: A Defect Classification With Sufficient Labeled Datamentioning

confidence: 99%

Deep Learning based Intelligent Coin-tap Test for Defect Recognition

Li¹,

Jiang²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

The coin-tap test is a convenient and primary method for non-destructive testing, while its manual on-site operation is tough and costly. With the help of the latest intelligent signal processing method, convolutional neural networks (CNN), we achieve an intelligent coin-tap test which exhibited superior performance in recognizing the defects. However, this success of CNNs relies on plenty of well-labeled data from the identical scenario, which could be difficult to get for many real industrial practices. This paper further develops transfer learning strategies for this issue, that is, to transfer the model trained on data of one scenario to another. In experiments, the result presents a notable improvement by using domain adaptation and pseudo label learning strategies. Hence, it becomes possible to apply the model into scenarios with none or little (less than 10%) labeled data adopting the transfer learning strategies proposed herein. In addition, we used a benchmark dataset constructed ourselves throughout this study. This benchmark dataset for the coin-tap test containing around 100,000 sound signals is published at https://github.com/PPhub-hy/torch-tapnet.

show abstract

Section: A Defect Classification With Sufficient Labeled Datamentioning

confidence: 99%

Deep Learning based Intelligent Coin-tap Test for Defect Recognition

Li¹,

Jiang²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Li et al (2017) extended the traditional mathematical morphological particle (MMP), which responds to bearing performance degradation, to a general MMP (GMMP) based on mathematical morphology theory to improve the reliability of bearing performance degradation assessment. Ma et al (2017) proposed a new manifold learning Glasmann manifold-locally linear embedding (LLE) method based on LLE, which can better capture the nonlinear and dynamic information in equipment vibration data. Zhang et al (2017) used short-time Fourier transform (STFT) with nonnegative matrix factorization (NMF) to generate time-frequency features and constructed more sensitive health indicators (HIs) of bearing performance degradation using SOM networks.…”

Section: Introductionmentioning

confidence: 99%

Bearing performance degradation assessment using adversarial fusion convolutional autoencoder based on multi-source information

Wang,

Zhou,

Wen

et al. 2023

Transactions of the Institute of Measurement and Control

Self Cite

View full text Add to dashboard Cite

Bearing operation states will directly determine the performance of the equipment; thus, monitoring operation status and degradation indicators is the key to ensuring continuous and healthy operation of the equipment. However, most of the research uses single-source information data, which makes it difficult to model when dealing with multi-source information, complex data distribution, and noise. In this paper, a bearing performance degradation assessment method based on multi-source information is proposed to comprehensively utilize the data signals of different structures, spaces, types, and sources. First, the adversarial fusion convolutional autoencoder is constructed for obtaining the degradation index of the bearing, while the adversarial learning strategy is applied to achieve the effect of enhancing the robustness and sensitivity of the degradation indicators extracted by the network. Then the degradation index is input into the support vector data description to determine the fault anomalies of the degradation index adaptively and the fuzzy c-means algorithms to obtain the final rolling bearing performance degradation evaluation results. Through the verification results of two experiment datasets, it is found that the proposed model can achieve accurate evaluation and quantitative analysis of the performance degradation process of bearings. As a result, the entire network ensures the reconstruction accuracy of normal samples while simultaneously stretching the reconstruction error of abnormal samples to achieve accurate monitoring of degradation onset.

show abstract

“…Instead of using purely data-driven methods, we principally embed well-known physical principles into the recurrent neural networks. As stated in [13], the degradation process of mechanical systems is monotonic, which means that components can't heal without repairing. Thus, an ideal degradation indicator should be monotonic over time.…”

Section: Introductionmentioning

confidence: 99%

Physics-Informed Deep Neural Network for Bearing Prognosis with Multisensory Signals

Chen

Zhao

et al. 2022

JDMD

Self Cite

View full text Add to dashboard Cite

Prognosis of bearing is critical to improve the safety, reliability and availability of machinery systems, which provides the health condition assessment and determines how long the machine would work before failure occurs by predicting the remaining useful life (RUL). In order to overcome the drawback of pure data-driven methods and predict RUL accurately, a novel physics-informed deep neural network, named degradation consistency recurrent neural network, is proposed for RUL prediction by integrating the natural degradation knowledge of mechanical components. The degradation is monotonic over the whole-life of bearings, which is characterized by temperature signals. To incorporate this knowledge of monotonic degradation, a positive increment recurrence relationship is introduced to keep the monotonicity. Thus, the proposed model is relatively well-understood and capable to keep the learning process consistent with physical degradation. The effectiveness and merit of the RUL prediction using the proposed method are demonstrated through vibration signals collected from a set of run-to-failure tests.

show abstract

Locally Linear Embedding on Grassmann Manifold for Performance Degradation Assessment of Bearings

Cited by 46 publications

References 43 publications

Deep Learning based Intelligent Coin-tap Test for Defect Recognition

Deep Learning based Intelligent Coin-tap Test for Defect Recognition

Bearing performance degradation assessment using adversarial fusion convolutional autoencoder based on multi-source information

Physics-Informed Deep Neural Network for Bearing Prognosis with Multisensory Signals

Contact Info

Product

Resources

About