2026-10-11T23:31:23Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33956224 2026-09-21T17:30:35Z category_21 category_272 category_734 category_106 category_132 portal_5 item_type_3 month_year_09_2026

<p>Variable working condition task description.</p> Yamei Zhang (2935029) Xiaohu Liu (588029) Biotechnology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Science Policy Infectious Diseases variable working conditions progressive weighting strategy fixed receptive fields feature distribution shift different receptive fields 5 db snr dual attention multi working condition fluctuations suppress redundant ones fault feature submersion channel attention branch scale convolution module peak diagnostic accuracy scale convolution parallel multi suppress interference highlight fault condition tasks cascaded channel xlink "> weighted features strong noise softmax classifier significant decline sensitive channels residual connection paper proposes outperforming bitcn max pooling designed following damscnn achieves damscnn ). background noise &# 8722 <div><p>To address the significant decline in the accuracy of rolling bearing fault diagnosis under variable working conditions and strong noise, which is caused by feature distribution shift and fault feature submersion, this paper proposes a bearing fault diagnosis method based on the Dual Attention Multi-Scale Convolutional Neural Network (DAMSCNN). First, a parallel multi-scale convolution module with multiple kernel sizes extracts fault features under different receptive fields, overcoming the limitation of fixed receptive fields in single-scale convolution. Second, a cascaded channel-spatial dual attention mechanism is designed following a progressive weighting strategy. A residual connection is embedded in the channel attention branch to highlight fault-sensitive channels and suppress redundant ones. The spatial attention branch fuses global average pooling and max pooling to strengthen fault impulse regions and suppress interference from working condition fluctuations and background noise. Finally, the weighted features are classified by a Softmax classifier. Experiments on the CWRU bearing dataset demonstrate that DAMSCNN achieves a peak diagnostic accuracy of 99.69% in cross-condition tasks and maintains accuracy above 92% under −5 dB SNR, outperforming BiTCN-Transformer, MTFC-T, and CTCA in accuracy, recall, and F1-score, while also offering lower computational cost and faster inference speed.</p></div> 2026-09-21T17:30:16Z Dataset Dataset 10.1371/journal.pone.0358253.t003 https://figshare.com/articles/dataset/_p_Variable_working_condition_task_description_p_/33956224 CC BY 4.0