AI-enabled and multimodal data driven smart health monitoring of wind power systems: A case study

Yang, Zhao; Zhang, Yanjie; Li, Zeqiang; Bu, Lingguo; Su, Han

doi:10.1016/j.aei.2023.102018

Cited by 5 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning has been successfully applied in multiple fields due to its powerful feature extraction ability [12][13][14]. The use of deep learning enables adaptive feature extraction of data and directly complete end-to-end intelligent fault diagnosis, which greatly reduces the need for feature extraction expertise and the uncertainty caused by human involvement [15,16]. Yan et al [17] employed the seagull optimization algorithm to optimize important parameters of a stacked variational denoising self-encoder and effectively extract important features from one-dimensional bearing vibration data.…”

Section: Introductionmentioning

confidence: 99%

Deep transfer learning rolling bearing fault diagnosis method based on convolutional neural network feature fusion

Yu,

Fu,

Song

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Current deep-learning methods are often based on significantly large quantities of labeled fault data for supervised training. In practice, it is difficult to obtain samples of rolling bearing failures. In this paper, a transfer learning-based feature fusion convolutional neural network approach for bearing fault diagnosis is proposed. Specifically, the raw vibration signal features and the corresponding time-frequency image features of the input data are extracted by a one-dimensional convolutional neural network and a pre-trained ConvNeXt, respectively, and connected by a feature fusion strategy. Then, the fine-tuning method based on transfer learning can effectively reduce the reliance on labeled samples in the target domain. A wide convolution kernel is introduced in the time-domain signal feature extraction to increase the receptive field, which is combined with the channel attention mechanism to further optimize the feature quality. Finally, two common bearing datasets are utilized for fault diagnosis experiments. The experimental results show that the proposed model achieves an average accuracy of more than 98.63% in both cross-working conditions and cross-device diagnosis tasks. Meanwhile, anti-noise experiments and ablation experiments further validate the accuracy and robustness of the proposed method.

show abstract