基于并行优化CBAM的轻量级故障诊断模型

doi:10.3969/j.issn.0255-8297.2025.01.007

摘要/Abstract

摘要： 在工程实践中，故障诊断模型的性能受到多种因素的影响，如强噪声干扰、小样本、模型参数规模较大等，对现有的数据驱动设备诊断智能模型的应用提出了挑战。本文提出一种基于并行优化卷积块注意力模块（convolutional block attention module,CBAM）的轻量级模型PCSA-Net。首先，采用多尺度信号特征提取器（signal feature extractor,SFE）将输入的传感器信号转换为特征映射。然后，优化传统的CBAM，开发协同注意力块，设计一种可学习的层缩放策略，并行化感知数据特征，使用点卷积与平均池化层组合，构建PW-Pool降维模块，减少模型参数量，对特征图的通道特征向量进行积分，得到最终的诊断结果。最后，选取包含轴承常见故障的两个数据集对模型进行验证，实验结果显示，在小样本轴承故障诊断（bearing fault diagnosis,BFD）任务中，本文模型与现有主流的故障诊断框架相比在轻量性和鲁棒性等方面表现更加优异，可满足实际轴承故障检测需求。

关键词: 变工况故障诊断, 卷积神经网络, 注意力机制, 深度学习

Abstract: In engineering practice, the performance of fault diagnosis models is affected by factors such as strong noise interference, limited sample sizes, and high model complexity, which poses challenges to the application of existing data-driven intelligent models for equipment diagnosis. To address these issues, this paper proposes a lightweight model, PCSA-Net, based on a parallel optimized convolutional block attention module (CBAM). First, a multi-scale signal feature extractor (SFE) is used to convert the input sensor signal into a feature map. Then, the traditional CBAM is optimized through the development of a collaborative attention block, the design of a learnable layer scaling strategy, and the parallelization of perceptual data features. Additionally, a PW-Pool dimension reduction module is introduced by combining point convolution with average pooling layers to reduce the number of model parameters. The channel feature vector of the feature map is then integrated to obtain the final diagnosis result. Finally, the proposed model is validated using two datasets containing common bearing faults. Experimental results show that in the small sample bearing fault diagnosis (BFD) task, the proposed model outperforms the existing mainstream fault diagnosis framework in terms of lightness and robustness, and meets the practical needs of bearing fault detection in real-world applications.

Key words: variable operating condition fault diagnosis, convolutional neural network, attention mechanism, deep learning

中图分类号:

TH17
TH133.3

贾志洋, 许兆, 冷艳梅, 闻新, 龚浩宇. 基于并行优化CBAM的轻量级故障诊断模型[J]. 应用科学学报, 2025, 43(1): 94-109.

JIA Zhiyang, XU Zhao, LENG Yanmei, WEN Xin, GONG Haoyu. Lightweight Fault Diagnosis Model Based on Parallel Optimized CBAM[J]. Journal of Applied Sciences, 2025, 43(1): 94-109.

参考文献

[1] Kitcher P. A priori knowledge [J]. The Philosophical Review, 1980, 89(1): 3-23.
[2] Dai X W, Gao Z W. From model, signal to knowledge: a data-driven perspective of fault detection and diagnosis [J]. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2226-2238.
[3] Hong Y Y, Pula R A. Methods of photovoltaic fault detection and classification: a review [J]. Energy Reports, 2022, 8: 5898-5929.
[4] Zhu Y, Li G P, Tang S N, et al. Acoustic signal-based fault detection of hydraulic piston pump using a particle swarm optimization enhancement CNN [J]. Applied Acoustics, 2022, 192: 108718.
[5] Dao F, Zeng Y, Qian J. Fault diagnosis of hydro-turbine via the incorporation of Bayesian algorithm optimized CNN-LSTM neural network [J]. Energy, 2024, 290: 130326.
[6] Wang M H, Lu S D, Hsieh C C, et al. Fault detection of wind turbine blades using multichannel CNN [J]. Sustainability, 2022, 14(3): 1781.
[7] Thomas J B, Chaudhari S G, Shihabudheen K V, et al. CNN-based transformer model for fault detection in power system networks [J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 2504210.
[8] Jia L, Chow T W S, Yuan Y. GTFE-Net: a Gramian time frequency enhancement CNN for bearing fault diagnosis [J]. Engineering Applications of Artificial Intelligence, 2023, 119: 105794.
[9] Anurag C, Kumar M R, Shahab F, et al. Multi-input CNN based vibro-acoustic fusion for accurate fault diagnosis of induction motor [J]. Engineering Applications of Artificial Intelligence, 2023, 120: 105872.
[10] Zheng L, Yi H. Circulation pump bearing fault diagnosis research based on BAM-CNN model and CWT processing time-frequency map [C]//2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), 2023: 1-7.
[11] Gana M, Achour H, Laghrouche M. Enhanced motor fault detection system based on a dual-signature image classification method using CNN [J]. Engineering Research Express, 2023, 5(1): 015009.
[12] Gong B, An A M, Shi Y K, et al. Fast fault detection method for photovoltaic arrays with adaptive deep multiscale feature enhancement [J]. Applied Energy, 2024, 353: 122071.
[13] Guo M F, Liu W L, Gao J H, et al. A data-enhanced high impedance fault detection method under imbalanced sample scenarios in distribution networks [J]. IEEE Transactions on Industry Applications, 2023, 59(4): 4720-4733.
[14] Fang X Y, Qu J F, Chai Y, et al. Adaptive multiscale and dual subnet convolutional autoencoder for intermittent fault detection of analog circuits in noise environment [J]. ISA Transactions, 2023, 136: 428-441.
[15] Zhou K, Tong Y F, Li X T, et al. Exploring global attention mechanism on fault detection and diagnosis for complex engineering processes [J]. Process Safety and Environmental Protection, 2023, 170: 660-669.
[16] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [J]. Advances in Neural Information Processing Systems, 2017, 30.
[17] Chengh B, Misra I, Schwing A G, et al. Masked-attention mask transformer for universal image segmentation [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 1280-1289.
[18] Nie X, Duan M Y, Ding H X, et al. Attention mask R-CNN for ship detection and segmentation from remote sensing images [J]. IEEE Access, 2020, 8: 9325-9334.
[19] Fan Z H, Gong Y Y, Liu D, et al. Mask attention networks: rethinking and strengthen transformer [DB/OL]. 2021[2024-07-10]. http://arxiv.org/abs/2103.13597.
[20] Harley A W, Derpanis K G, Derpanis I. Segmentation-aware convolutional networks using local attention masks [C]//IEEE International Conference on Computer Vision, 2017: 5048- 5057.
[21] Hu J, Shen L, Sun G. Squeeze-and-excitation networks [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[22] Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 11531-11539.
[23] Li X, Wang W, Hu X, et al. Selective kernel networks [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 510-519.
[24] Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module [C]//European Conference on Computer Vision, 2018: 3-19.
[25] Kang Y, Ku E J, Jung I G, et al. Dexamethasone and post-adenotonsillectomy pain in children [J]. Medicine, 2021, 100(2): e24122.
[26] Wang J, Shao H D, Yan S, et al. C-ECAFormer: a new lightweight fault diagnosis framework towards heavy noise and small samples [J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107031.
[27] Li J, Liu Y B, Li Q J. Intelligent fault diagnosis of rolling bearings under imbalanced data conditions using attention-based deep learning method [J]. Measurement, 2022, 189: 110500.
[28] Targ S, Almeida D, Lyman K. ResNet in ResNet: generalizing residual architectures [EB/OL]. (2016-03-25) [2024-07-10]. http://arxiv.org/abs/1603.08029.
[29] Duan R F, Chen Z Y, Meng W, et al. HDCGD-CBAM: satellite interference recognition algorithm based on improved CLDNN and CBAM [J]. China Communications, 2024, 21(12): 257-274.
[30] Luo Y, Wang Z. An improved ResNet algorithm based on CBAM [C]//2021 International Conference on Computer Network, Electronic and Automation, 2021: 121-125.
[31] Lin L, Zhang J, Gao X, et al. Power fingerprint identification based on the improved VI trajectory with color encoding and transferred CBAM-ResNet [J]. Plos One, 2023, 18(2): e0281482.
[32] Chen X, Zhang B K, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model [J]. Journal of Intelligent Manufacturing, 2021, 32(4): 971-987.
[33] Ben Ali J, Fnaiech N, Saidi L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals [J]. Applied Acoustics, 2015, 89: 16-27.
[34] Zhou J Y, Zhang X F, Jiang H, et al. Cross-domain transfer fault diagnosis by classimbalanced deep subdomain adaptive network [J]. Measurement, 2025, 242: 115901.
[35] Chen J, Zhang L, Li Y, et al. A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems [J]. Renewable and Sustainable Energy Reviews, 2022, 161: 112395.
[36] Cheng F, Niu B, Xu N, et al. Fault detection and performance recovery design with deferred actuator replacement via a low-computation method [J]. IEEE Transactions on Automation Science and Engineering, 2024, 21(3): 4646-4656.
[37] Chen H T, Li L L, Shang C, et al. Fault detection for nonlinear dynamic systems with consideration of modeling errors: a data-driven approach [J]. IEEE Transactions on Cybernetics, 2023, 53(7): 4259-4269.
[38] Plakias S, Boutalis Y S. A novel information processing method based on an ensemble of auto-encoders for unsupervised fault detection [J]. Computers in Industry, 2022, 142: 103743.
[39] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study [J]. Mechanical Systems and Signal Processing, 2015, 64: 100-131.
[40] Fang H R, Deng J, Bai Y X, et al. CLFormer: a lightweight transformer based on convolutional embedding and linear self-attention with strong robustness for bearing fault diagnosis under limited sample conditions [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3504608.
[41] Mehta S, Rastegari M. MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer [DB/OL]. 2021[2024-07-10]. http://arxiv.org/abs/2110.02178.