A novel transfer learning method for robust fault diagnosis of rotating machines under variable working conditions

Qian, Weiwei; Li, Shunming; Yi, Ping; Zhang, Kaicheng

doi:10.1016/j.measurement.2019.02.073

Cited by 140 publications

(61 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the convolution layer, two convolution kernels are used. As illustrated in [21], the high frequency noise commonly in vibration signals disturbs the local feature extraction, and the kernels of the first layer should be wide for suppressing the noise. Therefore, a wide kernel is used in the first layer and the size is 2 × 64, following a convolution kernel of 1 × 8 in the second layer.…”

Section: Parameters Of the Proposed Modelmentioning

confidence: 99%

“…For example, Long et al [20] used maximum mean discrepancy (MMD) to joint distribution alignments in deep networks. Qian et al [21] proposed a novel transfer learning method to align both the marginal and conditional distributions of both source and target domain datasets. In addition, the method is proved to be effective for fault diagnosis on roller bearing and gearbox.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Fault Diagnostic Scheme Based on Capsule Network for Rolling Bearing under Different Rotational Speeds

Zhang

Wang

2020

Sensors

View full text Add to dashboard Cite

Deep learning-based intelligent fault diagnosis methods have attracted increasing attention for their automatic feature extraction ability. However, existing works are usually under the assumption that the training and test dataset share similar distributions, which unfortunately always violates real practice due to the variety of working conditions. In this paper, an end-to-end scheme of joint use of two-direction signals and capsule network (CN) is proposed for fault diagnosis of rolling bearing. With the help of the superior ability of CN in capturing the spatial position information between features, more valuable information can be mined. Aiming to eliminate the influence of different rotational speeds, vertical and horizontal vibration signals are fused as the input to CN, so that invariant features can be extracted automatically from the raw signals. The effectiveness of the proposed method is verified by experimental data of rolling bearing under different rotational speeds and compared with a deep convolutional neural network (DCNN). The results demonstrate that the proposed scheme is able to recognize the fault types of rolling bearing under scenarios of different rotational speeds.

show abstract

Section: Parameters Of the Proposed Modelmentioning

confidence: 99%

mentioning

confidence: 99%

A Fault Diagnostic Scheme Based on Capsule Network for Rolling Bearing under Different Rotational Speeds

Zhang

Wang

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Lu et al [10] added a maximum mean discrepancy term to the loss function of auto-encoders to force them to learn features that are not affected by operating conditions. Qian et al [11] proposed a new transfer learning method and solved data distribution problems caused by rotating speed variation. Peng et al [12] proposed a novel deeper 1D CNN based on 1D residual block and the experimental results show that this method is effective in the case of strong noise and variable load.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of rotating machinery under time-varying speed based on order tracking and deep learning

Wang¹,

Zhang²,

Qiao³

et al. 2020

J. vibroeng.

View full text Add to dashboard Cite

Due to the disadvantages that rely on prior knowledge and expert experience in traditional order analysis methods and deep learning cannot accurately extract the features in time-varying conditions. A fault diagnosis method for rotating machinery under time-varying conditions based on tacholess order tracking (TOT) and deep learning is proposed in this paper. Firstly, frequency domain periodic signals and estimated speed information are obtained by order tracking. Secondly, the frequency domain periodic signal is speed normalized using the estimated speed information. Finally, normalized features are extracted by deep learning network to form feature vector. The feature vector is fed into a softmax layer to complete fault diagnosis of the gearbox. The fault diagnosis of the gearbox results are compared with other traditional methods and show that the proposed fault diagnosis method can effectively identify the faults and obtain higher fault diagnosis accuracy under time-varying speed.

show abstract

“…After reducing the dimension of the dataset, a new dataset with a low dimension can enhance the effectiveness and accuracy of bearing diagnosis. Some researchers have applied the JDA to model classification, such as (JDA improved by sparse filtering, joint distribution optimal deep domain adaptation, Deep transfer network with JDA, joint-space force distribution) in [26][27][28][29][30]. JDA is mainly used for feature distribution in image processing, but rarely in signal processing.…”

Section: Introductionmentioning

confidence: 99%

A Fault Diagnosis Method Based on Improved Adaptive Filtering and Joint Distribution Adaptation

2020

View full text Add to dashboard Cite

In the real environment of industrial equipment, the vibration signals of essential components show deviations due to the fault and noise. Notably, the noise in the signal will interfere with the diagnosis process of the signal and reduce the accuracy of fault diagnosis. Based on the above problem, adaptive filtering (AF) is used as an excellent method to attenuate noise without specifying the noise type. However, how to define the most appropriate length and type of morphological filter element is the most inherent problem which needs to be solved first. This paper proposed a cooperative diagnosis method of rolling bearings vibration signal based on improved adaptive filtering and joint distribution adaptation (JDA). First, the kurtosis under different element types and lengths is calculated as an index. The structural element corresponding to maximum kurtosis is selected as the most suitable morphological filter element because the different morphological filter elements reflect the effect of feature extraction. Then, JDA aims to improve both the marginal distribution and the conditional distribution to solve the chaotic distribution of time-domain features under variable working conditions. Finally, the improved least squares support vector machine (LSSVM) verified the effectiveness and improvement of the proposed method under bearing acceleration signal. At the same time, the comparative experiment proved that the proposed method not only directly corrects the most appropriate elements greatly optimizes the feature structure, but also enhances the accuracy of fault diagnosis. INDEX TERMS adaptive filters, morphological operation, time domain features, transfer learning, joint distribution adaptation, LSSVM, fault diagnosis.

show abstract

A novel transfer learning method for robust fault diagnosis of rotating machines under variable working conditions

Cited by 140 publications

References 18 publications

A Fault Diagnostic Scheme Based on Capsule Network for Rolling Bearing under Different Rotational Speeds

A Fault Diagnostic Scheme Based on Capsule Network for Rolling Bearing under Different Rotational Speeds

Fault diagnosis of rotating machinery under time-varying speed based on order tracking and deep learning

A Fault Diagnosis Method Based on Improved Adaptive Filtering and Joint Distribution Adaptation

Contact Info

Product

Resources

About