Intelligent fault diagnosis of hydroelectric units based on radar maps and improved GoogleNet by depthwise separate convolution

Wang, Yunhe; Zou, Yidong; Hu, Wenqing; Chen, Jinbao; Xiao, Zhihuai

doi:10.1088/1361-6501/ad05a3

Cited by 7 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depthwise separable convolution. Depthwise separable convolution is a lightweight convolution structure that divides traditional convolution into channel by channel convolution and point by point convolution [31][32][33][34][35]. Channel dimension information and spatial dimension information are mapped separately to realize joint mapping of traditional convolution in two steps.…”

Section: Depthwise Separable Residual Convolutional Neural Network (D...mentioning

confidence: 99%

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

Yang,

Lin,

Ruan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Diagnosis of compound mechanical faults for power circuit breakers (CBs) is a challenging task. In traditional fault diagnosis methods, however, all fault types need to be collected in advance for the training of diagnosis model. Such processes have poor generalization capabilities for industrial scenarios with no or few data when faced with new faults. In this study, we propose a novel zero-shot learning method named DSR-AL to address this problem. An unsupervised neural network, namely, depthwise separable residual convolutional neural network (DSRCNN), is designed to directly learn features from 3D time-frequency images of CB vibration signals. Then we build fault attribute learners (ALs), for transferring fault knowledge to the target faults. Finally, the ALs are used to predict the attribute vector of the target faults, thus realizing the recognition of previously unseen faults. The orthogonal experiments are designed and conducted on real industrial switchgear to validate the effectiveness of the proposed diagnosis framework. Results show that it is feasible to diagnose target faults without using their samples for training, which greatly saves the costs of collecting fault samples. This will help to accurately identify the various faults that may occur during CB's life cycle, and facilitate the application of intelligent fault diagnosis system.

show abstract

Section: Depthwise Separable Residual Convolutional Neural Network (D...mentioning

confidence: 99%

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

Yang,

Lin,

Ruan

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…With the development of CNN, many classic models have also emerged, such as LeNet [19,20], ResNet [21][22][23], AlexNet [24,25], DenseNet [26][27][28], Vgg [29,30], GoogleNet [31][32][33], etc. Their advantages and disadvantages are shown in table 1.…”

Section: Principles Of Cnnsmentioning

confidence: 99%

A review on convolutional neural network in rolling bearing fault diagnosis

Li,

Ma,

Yuan

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The health condition of rolling bearings has a direct impact on the safe operation of high-speed trains. And their working environment is harsh and the working condition is complex, which brings challenges to fault diagnosis. With the development of computer technology, deep learning has been applied in the field of fault diagnosis and has rapidly developed. Among them, convolutional neural network (CNN) has received great attention from researchers due to its powerful data mining ability and feature adaptive learning ability. Based on recent research hotspots, the development history and trend of CNN is summarized and analyzed. Firstly, the basic structure of CNN is introduced and the important progress of classical CNN models for rolling bearing fault diagnosis in recent years is studied. The problems with the classic CNN algorithm have been pointed out. Secondly, to solve the above problems, combined with recent research achievements, various methods and principles for optimizing CNN are introduced and compared from the perspectives of deep feature extraction, hyperparameter optimization, network structure optimization. Although significant progress has been made in the research of fault diagnosis of rolling bearings based on CNN, there is still room for improvement and development in addressing issues such as low accuracy of imbalanced data, weak model generalization, and poor network interpretability. Therefore, the future development trend of CNN networks is discussed finally. And transfer learning models are introduced to improve the generalization ability of CNN and interpretable CNN is used to increase the interpretability of CNN networks.

show abstract

“…With the rapid development of machine learning and deep learning, data-driven fault diagnosis methods represented by convolutional neural networks (CNNs) are widely used in the field of fault diagnosis [11][12][13][14]. These intelligent algorithms do not require too much expert experience.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Kolar et al use Bayesian optimization to optimize the hyperparameters of convolutional neural networks; by using the optimized hyperparameters, the CNN model can classify eight different machine states and two rotational speeds, which effectively improves the diagnostic accuracy [11]. Wang et al proposed an intelligent fault diagnosis method based on Radargram and GoogleNet, improved using depth-separated convolution, to solve the problems of low recognition accuracy and slow computation speed in the current hydroelectric generator fault diagnostic model [12].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis in Hydroelectric Units in Small-Sample State Based on Wasserstein Generative Adversarial Network

Sun,

Zou,

Wang

et al. 2024

Water

Self Cite

View full text Add to dashboard Cite

In the practical production environment, the complexity and variability of hydroelectric units often result in a need for more fault data, leading to inadequate accuracy in fault identification for data-driven intelligent diagnostic models. To address this issue, this paper introduces a novel fault diagnosis method tailored for unbalanced small-sample states in hydroelectric units based on the Wasserstein generative adversarial network (W-GAN). Firstly, the fast Fourier transform is used to convert the signal from the time domain to the frequency domain to obtain the spectral data, and the W-GAN is trained to generate false spectral data with the same probability distribution as the real fault data, which are combined with the actual data and inputted into the 1D-CNN for feature extraction and fault diagnosis. In order to assess the effectiveness of the proposed model, a case study was conducted using actual data from a domestic hydropower plant, and the experimental results show that the sample features can be effectively enriched via data enhancement performed on small-sample data to improve the accuracy of fault diagnosis, which verifies the effectiveness of the method proposed in this paper.

show abstract

Intelligent fault diagnosis of hydroelectric units based on radar maps and improved GoogleNet by depthwise separate convolution

Cited by 7 publications

References 48 publications

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

A zero-shot fault attribute transfer learning method for compound fault diagnosis of power circuit breakers

A review on convolutional neural network in rolling bearing fault diagnosis

Fault Diagnosis in Hydroelectric Units in Small-Sample State Based on Wasserstein Generative Adversarial Network

Contact Info

Product

Resources

About