滚动轴承是旋转机械系统中常见的重要组成部分，广泛应用于航空、航天和智能制造等多个领域。它承担着支撑和降低磨损等关键功能，因此被称为“工业关节”。有效监测滚动轴承的健康状况，对于确保机械设备安全、稳定运行具有重要意义。传统的故障诊断技术受限于信号非平稳特性和故障机理研究，同时在特征提取方面存在主观性，难以满足不断增长的诊断需求。近年来，深度学习在机械故障诊断领域得到广泛应用，具备出色的非线性表征能力和模式分类性能。然而，在设备运行工况和数据属性方面仍有待加强。针对上述问题，本文基于深度学习理论，分别从深度网络模型的复杂多分支结构、关键特征提取不足、较大图结构数据和高参数量四大问题开展了相关研究，并通过多个实验平台进行了实际应用的验证。主要内容与创新点如下：

(1) 针对现有深度学习模型结构复杂和推理速度慢的问题，提出了一种基于结构重参数化VGG网络的滚动轴承故障诊断模型。首先，通过短时傅里叶变换和伪彩色处理技术将一维振动信号转换成三通道彩色时频图像。然后，将这些图像输入到结构重参数化VGG模型中以学习聚类分类的特征信息。该模型在训练阶段采用多分支卷积结构，推理阶段将多分支结构融合为单路3×3卷积，提高网络的训练和推理速度。最后使用凯斯西储大学滚动轴承实验数据集验证了所述方法的可行性及有效性。

(2) 针对结构重参数化VGG网络特征提取不足的问题，提出了一种基于双重注意力机制的结构重参数化VGG网络的滚动轴承故障诊断方法。该方法通过融合双重注意力机制，一方面，在卷积层内部通过通道注意力机制加强对重要特征的提取；另一方面，在不同卷积层之间引入空间注意力机制，以动态调整特征图的权重。这种综合运用注意力机制的方法能够更有效地提取滚动轴承振动信号中的关键特征。采用自主搭建的滚动轴承试验平台验证了所述方法的可行性和有效性。

(3) 针对图神经网络在处理较大图结构数据和聚合高阶邻域信息不足的问题，提出了一种基于自适应小型图结构-高阶多头图注意力嵌入的滚动轴承故障诊断方法。首先，通过堆叠一维卷积神经网络构成的自适应预处理层，对一维时域信号进行自适应滤波与压缩处理，其次，采用类启发式图结构数据生成方法，将处理后的特征样本转换为更小、更易处理的自适应小型拓扑规则图结构，以减少计算复杂度和存储需求。然后，引入高阶多头图注意力嵌入网络，该网络可以同时考虑多个节点的高阶邻域信息，能够对每个节点的不同邻域部分进行加权处理，并将这些信息有效地聚合起来，从而更全面地提取图结构中的复杂关系和特征。最后采用凯斯西储大学和自建的轴承数据集验证了所述方法的可行性及有效性。

(4) 针对现有深度网络中存在高参数量的问题，提出了一种基于倒残差结构和残差多层感知机的轻量化移位窗口Transformer的滚动轴承故障诊断方法。该方法首先运用补丁嵌入方法对数据增强后的一维振动信号进行向量序列化。其次，将倒残差结构和残差多层感知机有序融合到移位窗口Transformer中，具体而言，倒残差结构在每个层级中负责减少参数量，以保持模型的轻量化特性；而残差多层感知机则在此基础上进行特征的进一步提取和增强，从而提高模型的准确性。这样的设计在保证模型准确性的同时，有效地减少了模型的参数量，从而实现模型的轻量化设计。最后采用帕德伯恩大学滚动轴承实验数据集和自建滚动轴承数据集验证了所述方法的可行性和有效性。

Rolling bearings, as common components in rotating mechanical systems, are widely used in various fields such as aviation, aerospace, and smart manufacturing. They bear key functions such as supporting and reducing wear, and is therefore known as the "industrial joints." Additionally, they exhibit strong subjectivity in feature extraction, which makes it challenging to meet the growing diagnostic demands. In recent years, deep learning has been extensively applied in mechanical fault diagnosis due to its outstanding capability in nonlinear representation and pattern classification performance, gradually becoming a research hotspot. However, existing deep learning fault diagnosis methods still lack sufficient consideration for equipment operating conditions and data attributes, thereby limiting their practical effectiveness. To address these issues, this paper takes deep learning as the theoretical basis and conducts research on four major problems: the complex multi-branch structure of deep network models, inadequate extraction of key features, large-scale graph-structured data, and high parameterization. Through validation on multiple experimental platforms, the main research content and innovations are as follows:

(1) To address the issues of complex structure and slow inference speed in existing deep learning models, a rolling bearing fault diagnosis model based on structure-reparameterized VGG network is proposed. Initially, one-dimensional vibration signals are transformed into three-channel color images through short-time Fourier transform and pseudo-color processing techniques. Subsequently, these images are inputted into the structure-reparameterized VGG model to learn clustering classification features. During the training phase, a multi-branch convolutional structure is employed, while during the inference phase, the multi-branch structure is merged into a single 3×3 convolution to enhance the speed of both training and inference. The effectiveness of the proposed method is validated using the Case Western Reserve University rolling bearing experimental dataset.

(2) A rolling bearing fault diagnosis method based on a dual attention mechanism is proposed to address the issue of insufficient feature extraction in the structure reparameterized VGG network. In this method, a dual attention mechanism is integrated, wherein the channel attention mechanism enhances the extraction of important features within convolutional layers, and the spatial attention mechanism between different convolutional layers dynamically adjusts the weights of feature maps. This comprehensive utilization of attention mechanisms effectively extracts key features from rolling bearing vibration signals. The proposed method's effectiveness was confirmed through testing on a self-constructed rolling bearing experimental platform.

(3) To tackle the issues of handling large graph-structured data and aggregating high-order neighborhood information in graph neural networks, a rolling bearing fault diagnosis method based on adaptive small graph structure and high-order multi-head graph attention embedding is proposed. Firstly, the signal is filtered and compressed by a stacked one-dimensional convolutional neural network layer, Secondly, a heuristic method generates smaller, easier-to-process graph structures from the feature samples, reducing computational complexity and storage needs. In the end, a high-order multi-head graph attention embedding network is introduced, which simultaneously considers high-order neighborhood information of multiple nodes, weighting different neighborhood parts of each node, and effectively aggregating this information to comprehensively extract complex relationships and features within the graph structure. The effectiveness of the proposed method was validated using both the Case Western Reserve University rolling bearing experimental dataset and a self-constructed bearing dataset.

(4) To solve the issue of high parameterization in existing deep networks, a lightweight rolling bearing fault diagnosis method based on inverted residual structure and residual multilayer perceptron in shift window transformer is proposed. Initially, the method utilizes patch embedding to vectorize augmented one-dimensional vibration signals. Then, the inverted residual structure and residual multilayer perceptron are sequentially fused into the shift window transformer. Specifically, the inverted residual structure reduces the parameter count in each layer to maintain the model's lightweight characteristics, while the residual multilayer perceptron further extracts and enhances features to improve the model's accuracy. This design effectively reduces the model's parameter count while ensuring accuracy. The proposed method was substantiated with datasets from Padreborn University and self-built rolling bearing datasets.

[1] 钟秉林, 黄仁. 机械故障诊断学[M]. 北京: 机械工业出版社, 2006.

[2] 何正嘉, 陈进, 王太勇, 等. 机械故障诊断理论及应用[M]. 北京: 高等教育出版社, 2010.

[3] 王国彪, 何正嘉, 陈雪峰, 等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报, 2013, 49(01):63-72.

[4] Shao H, Lin J, Zhang L, et al. A novel approach of multisensory fusion to collaborative fault diagnosis in maintenance[J]. Information Fusion, 2021, 74:65-76.

[5] 王代超. 基于多源数据融合的旋转机械故障诊断方法研究[D]. 山东大学, 2022.

[6] Cunha B Z, Droz C, Zine A M, et al. A review of machine learning methods applied to structural dynamics and vibroacoustic[J]. Mechanical Systems and Signal Processing, 2023, 200:110535.

[7] 蒲削锟. 标签噪声下的故障诊断算法研究[D]. 浙江大学, 2023.

[8] 孟静. 基于稀疏表示理论的轴承复合故障诊断方法研究[D]. 东南大学, 2021.

[9] 金桐彤. 考虑域影响的旋转机械故障诊断方法研究[D]. 吉林大学, 2022.

[10] 陈进. 机械设备振动监测与故障诊断[M]. 上海: 上海交通大学出版社, 1999.

[11] 鄢小安. 基于数学形态学的滚动轴承故障诊断方法研究[D]. 东南大学, 2019.

[12] Sun Y, Li H, Sun L, et al. Failure analysis of floating offshore wind turbines with correlated failures[J]. Reliability Engineering & System Safety, 2023, 238:109485.

[13] 邵思羽. 基于深度学习的旋转机械故障诊断方法研究[D]. 东南大学, 2019.

[14] Gawde S, Patil S, Kumar S, et al. A scoping review on multi-fault diagnosis of industrial rotating machines using multi-sensor data fusion[J]. Artificial Intelligence Review, 2023, 56(5):4711-4764.

[15] Sun Y J, Wang J, Wang X. Fault diagnosis of mechanical equipment in high energy consumption industries in China: A review[J]. Mechanical Systems and Signal Processing, 2023, 186:109833.

[16] 俞啸. 数据驱动的滚动轴承故障特征分析与诊断方法研究[D]. 中国矿业大学, 2017.

[17] 廖奕校. 基于多源域知识迁移的旋转机械智能故障诊断方法研究[D]. 华南理工大学, 2022.

[18] 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.

[19] Tama B A, Vania M, LEE S, et al. Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals[J]. Artificial Intelligence Review, 2023, 56(5):4667-4709.

[20] Perez-Sanjines F, Peeters C, Verstraeten T, et al. Fleet-based early fault detection of wind turbine gearboxes using physics-informed deep learning based on cyclic spectral coherence[J]. Mechanical Systems and Signal Processing, 2023, 185:109760.

[21] Zhu L, Chen C, Wang H, et al. Machine Learning in Urban Rail Transit Systems: A Survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2023:1-26.

[22] Tong J, Tang S, Wu Y, et al. A fault diagnosis method of rolling bearing based on improved deep residual shrinkage networks[J]. Measurement, 2023, 206:112282.

[23] He C, Shi H, Si J, et al. Physics-informed interpretable wavelet weight initialization and balanced dynamic adaptive threshold for intelligent fault diagnosis of rolling bearings[J]. Journal of Manufacturing Systems, 2023, 70:579-592.

[24] Pu H, Zhang K, An Y. Restricted Sparse Networks for Rolling Bearing Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2023, 19(11):11139-11149.

[25] Zhu Z, Lei Y, Qi G, et al. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery[J]. Measurement, 2023, 206:112346.

[26] Jie Y, Kimmig A, Dongkun W, et al. A systematic review of data-driven approaches to fault diagnosis and early warning[J]. Journal of Intelligent Manufacturing, 2023, 34(8):3277-3304.

[27] Zheng Z, Wang F, Gong G, et al. Intelligent technologies for construction machinery using data-driven methods[J]. Automation in Construction, 2023, 147:104711.

[28] Atoui M A, Cohen A. Coupling data-driven and model-based methods to improve fault diagnosis[J]. Computers in Industry, 2021, 128:103401.

[29] Zhu Z, Lei Y, Qi G, et al. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery[J]. Measurement, 2023, 206:112346.

[30] Zhang S, Lei S U, Jiefei G U, et al. Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey[J]. Chinese Journal of Aeronautics, 2023, 36(1):45-74.

[31] Li Y, Han M, Shahidehpour M, et al. Data-driven distributionally robust scheduling of community integrated energy systems with uncertain renewable generations considering integrated demand response[J]. Applied Energy, 2023, 335:120749.

[32] Qian Q, Qin Y, Luo J, et al. Deep discriminative transfer learning network for cross-machine fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 186:109884.

[33] Yang G, Tao H, Yu T, et al. Online Fault Diagnosis of Harmonic Drives Using Semi-supervised Contrastive Graph Generative Network via Multimodal data[J]. IEEE Transactions on Industrial Electronics, 2023, 71(3):3055-3063.

[34] Chen J, Huang R, Chen Z, et al. Transfer learning algorithms for bearing remaining useful life prediction: A comprehensive review from an industrial application perspective[J]. Mechanical Systems and Signal Processing, 2023, 193:110239.

[35] Deng Y, Lv J, Huang D, et al. Combining the theoretical bound and deep adversarial network for machinery open-set diagnosis transfer[J]. Neurocomputing, 2023, 548:126391.

[36] Lu B, Zhang Y, Liu Z, et al. A novel sample selection approach based universal unsupervised domain adaptation for fault diagnosis of rotating machinery[J]. Reliability Engineering & System Safety, 2023, 240:109618.

[37] Jia S, Li Y, Wang X, et al. Deep causal factorization network: A novel domain generalization method for cross-machine bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 192:110228.

[38] Wang Y, Wu J, Yu Z, et al. A structurally re-parameterized convolution neural network-based method for gearbox fault diagnosis in edge computing scenarios[J]. Engineering Applications of Artificial Intelligence, 2023, 126:107091.

[39] Yu X, Tang B, Deng L. Fault diagnosis of rotating machinery based on graph weighted reinforcement networks under small samples and strong noise[J]. Mechanical Systems and Signal Processing, 2023, 186:109848.

[40] Zhang Y, Ji J, Ren Z, et al. Multi-sensor open-set cross-domain intelligent diagnostics for rotating machinery under variable operating conditions[J]. Mechanical Systems and Signal Processing, 2023, 191:110172.

[41] Liu Y, Ramin P, Flores-Alsina X, et al. Transforming data into actionable knowledge for fault detection, diagnosis and prognosis in urban wastewater systems with AI techniques: A mini-review[J]. Process Safety and Environmental Protection, 2023, 172:501-512.

[42] Sahin S, Tolun M R, Hassanpour R. Hybrid expert systems: A survey of current approaches and applications[J]. Expert systems with applications, 2012, 39(4):4609-4617.

[43] Surucu O, Gadsden S A, Yawney J. Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances[J]. Expert Systems with Applications, 2023, 221:119738.

[44] Krishnamurthi M, Phillips D T. An expert system framework for machine fault diagnosis[J]. Computers & industrial engineering, 1992, 22(1):67-84.

[45] Gelgele H L, Wang K. An expert system for engine fault diagnosis: development and application[J]. Journal of Intelligent Manufacturing, 1998, 9:539-545.

[46] Angeli C. An online expert system for fault diagnosis in hydraulic systems[J]. Expert systems, 1999, 16(2):115-120.

[47] Ebersbach S, Peng Z. Expert system development for vibration analysis in machine condition monitoring[J]. Expert systems with applications, 2008, 34(1):291-299.

[48] Gu X, Han J, Shen Q, et al. Autonomous learning for fuzzy systems: a review[J]. Artificial Intelligence Review, 2023, 56(8):7549-7595.

[49] Varshney A K, Torra V. Literature Review of the Recent Trends and Applications in Various Fuzzy Rule-Based Systems[J]. International Journal of Fuzzy Systems, 2023, 25(6):2163-2186.

[50] Ameid T, Ammar A, Talhaoui H, et al. An automatic rotor bar fault diagnosis using fuzzy logic and DWT-energy for backstepping control driven induction motor in low-speed operation[J]. Soft Computing, 2023, 27(15):10411-10426.

[51] Mousavi M, Mostafavi A, Moradi M, et al. Robust Fault Isolation of Gas Turbines via Nonlinear Intelligent Observer and Takagi Sugeno Fuzzy Inference System[J]. IEEE Sensors Journal, 2023, 23(20):25075-25085.

[52] Zemali Z, Cherroun L, Hadroug N, et al. Robust intelligent fault diagnosis strategy using Kalman observers and neuro-fuzzy systems for a wind turbine benchmark[J]. Renewable Energy, 2023, 205:873-898.

[53] Pérez-Pérez E J, Puig V, López-Estrada F R, et al. Robust fault diagnosis of wind turbines based on MANFIS and zonotopic observers[J]. Expert Systems with Applications, 2024, 235:121095.

[54] Berredjem T, Benidir M. Bearing faults diagnosis using fuzzy expert system relying on an improved range overlaps and similarity method[J]. Expert Systems with Applications, 2018, 108:134-142.

[55] 王进花, 岳亮辉, 曹洁, 等. 基于随机变分推理贝叶斯神经网络的发电机轴承故障诊断[J]. 控制与决策, 2023, 38(04): 1015-1021.

[56] Qiao J, Sun Z, Meng X. Interval type-2 fuzzy neural network based on active semi-supervised learning for non-stationary industrial processes[J]. IEEE Transactions on Automation Science and Engineering, 2023, 21(2):1151-1162.

[57] Xu X, Cao D, Zhou Y, et al. Application of neural network algorithm in fault diagnosis of mechanical intelligence[J]. Mechanical Systems and Signal Processing, 2020, 141:106625.

[58] Najaran M H T. An evolutionary ensemble convolutional neural network for fault diagnosis problem[J]. Expert Systems with Applications, 2023, 233:120678.

[59] Chen M, Qu R, Fang W. Case-based reasoning system for fault diagnosis of aero-engines[J]. Expert Systems with Applications, 2022, 202:117350.

[60] 李长伟, 雷文平, 董辛旻, 等. GA-CFS结合案例推理的轴承故障诊断[J]. 机械设计与制造, 2023, (01):26-29.

[61] Qian W, Li S, Lu J. Adaptive nearest neighbor reconstruction with deep contractive sparse filtering for fault diagnosis of roller bearings[J]. Engineering Applications of Artificial Intelligence, 2022, 111:104749.

[62] Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical Systems and Signal Processing, 2020, 138:106587.

[63] Geng H, Peng Y, Ye L, et al. Generalized broadband mode decomposition method and its application in fault diagnosis of variable speed spherical roller bearing[J]. Measurement, 2023, 208:112450.

[64] Xiao M, Wang Z, Zhao Y, et al. A new fault feature extraction method of rolling bearings based on the improved self-selection ICEEMDAN-permutation entropy[J]. ISA transactions, 2023, 143:536-547.

[65] Xu C, Yang J, Zhang T, et al. Adaptive Parameter Selection Variational Mode Decomposition Based on a Novel Hybrid Entropy and Its Applications in Locomotive Bearing Diagnosis[J]. Measurement, 2023, 217:113110.

[66] Chen B, Zhang W, Gu J, et al. Product envelope spectrum optimization-gram: An enhanced envelope analysis for rolling bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 193:110270.

[67] Chen Z, Yang Y, He C, et al. Feature extraction based on hierarchical improved envelope spectrum entropy for rolling bearing fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72:3518912.

[68] 刘若晨, 顾双双, 孙见忠, 等. 基于短时傅里叶变换及其倒频谱的滚动轴承静电监测[J]. 航空动力学报, 2023, 1-9.

[69] 胡爱军, 严家祥, 白泽瑞. 基于MOMEDA和增强倒频谱的风电机组齿轮箱多故障诊断方法[J]. 振动与冲击, 2021, 40(07):268-273.

[70] Randall R B, Smith W A, Borghesani P, et al. A new angle-domain cepstral method for generalised gear diagnostics under constant and variable speed operation[J]. Mechanical Systems and Signal Processing, 2022, 178:109313.

[71] Zheng J, Ying W, Pan H, et al. Holo-hilbert square spectral analysis: A new fault diagnosis tool for rotating machinery health management[J]. Mechanical Systems and Signal Processing, 2023, 189:110069.

[72] Ni Q, Ji J, Halkon B, et al. Physics-Informed Residual Network (PIResNet) for rolling element bearing fault diagnostics[J]. Mechanical Systems and Signal Processing, 2023, 200:110544.

[73] 王冉, 黄裕春, 张军武, 等. 基于低秩和稀疏分解的滚动轴承故障特征提取方法对比研究[J]. 振动与冲击, 2023, 42(21):182-191.

[74] 包文杰, 涂晓彤, 李富才, 等. 参数化的短时傅里叶变换及齿轮箱故障诊断[J]. 振动.测试与诊断, 2020, 40(02):272-277.

[75] Jiang Z, Zhang K, Zhang X, et al. A Tacholess Order Tracking Method Based on Spectral Amplitude Modulation for Variable Speed Bearing Fault Diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72:3518708.

[76] Yan Z, Xu Y, Zhang K, et al. Adaptive synchroextracting transform and its application in bearing fault diagnosis[J]. ISA transactions, 2023, 137:574-589.

[77] Miaofen L, Youmin L, Tianyang W, et al. Adaptive synchronous demodulation transform with application to analyzing multicomponent signals for machinery fault diagnostics[J]. Mechanical Systems and Signal Processing, 2023, 191:110208.

[78] Aziz S, Khan M U, Faraz M, et al. Intelligent bearing faults diagnosis featuring Automated Relative Energy based Empirical Mode Decomposition and novel Cepstral Autoregressive features[J]. Measurement, 2023, 216:112871.

[79] Kumar A, Berrouche Y, Zimroz R, et al. Non-parametric Ensemble Empirical Mode Decomposition for extracting weak features to identify bearing defects[J]. Measurement, 2023, 211:112615.

[80] Zhang Q, Yuan R, Lv Y, et al. Multivariate dynamic mode decomposition and its application to bearing fault diagnosis[J]. IEEE Sensors Journal, 2023, 23(7):7514-7524.

[81] Ma P, Zhang H, Wang C. Adaptive dynamic mode decomposition and its application in rolling bearing compound fault diagnosis[J]. Structural Health Monitoring, 2023, 22(1):398-416.

[82] 李华. 基于频带熵改进理论的轴承故障诊断算法研究[D]. 昆明理工大学, 2020.

[83] Zhou N, Cheng Y, Wang Z, et al. CFFsgram: A candidate fault frequencies-based optimal demodulation band selection method for axle-box bearing fault diagnosis[J]. Measurement, 2023, 207:112368.

[84] Goyal D, Choudhary A, Pabla B S, et al. Support vector machines based non-contact fault diagnosis system for bearings[J]. Journal of Intelligent Manufacturing, 2020, 31:1275-1289.

[85] Wang Z, Yao L, Cai Y. Rolling bearing fault diagnosis using generalized refined composite multiscale sample entropy and optimized support vector machine[J]. Measurement, 2020, 156:107574.

[86] Zhang J, Zhang Q, Qin X, et al. A two-stage fault diagnosis methodology for rotating machinery combining optimized support vector data description and optimized support vector machine[J]. Measurement, 2022, 200:111651.

[87] 蔡志鑫, 党章, 吕勇, 等. 自适应动模式分解和GA-SVM在行星轴承故障分类中的应用[J]. 工程科学学报, 2023, 45(09):1559-1568.

[88] 于广伟, 闫莉. 基于多尺度迁移符号动力学熵和支持向量机的轴承诊断方法研究[J]. 西北工业大学学报, 2023, 41(02):344-353.

[89] Tang Y, Chang Y, Li K. Applications of K-nearest neighbor algorithm in intelligent diagnosis of wind turbine blades damage[J]. Renewable Energy, 2023, 212:855-864.

[90] 彭成, 贺婧, 唐朝晖，等. 基于双维度EKNN的滚动轴承早期故障分类算法[J]. 计算机集成制造系统, 2021, 27(01):90-101.

[91] 赵聪聪, 刘玉梅, 赵颖慧, 等. 基于MMFE和可拓k-medoids聚类的轴承性能退化评估[J]. 振动与冲击, 2022, 41(17):123-130.

[92] 李海浪, 邹益胜, 曾大懿, 等. 一种基于特征聚类和评价的轴承寿命预测新方法[J]. 振动与冲击, 2022, 41(05):141-150.

[93] 于军, 刘立飞, 邓立为, 等. 基于流向图和非朴素贝叶斯推理的滚柱轴承故障程度识别[J]. 计算机集成制造系统, 2020, 26(05):1202-1210.

[94] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786):504-507.

[95] Li P, Pei Y, Li J. A comprehensive survey on design and application of autoencoder in deep learning[J]. Applied Soft Computing, 2023, 138:110176.

[96] Bengio Y, Lamblin P, Popovici D, et al. Greedy layer-wise training of deep networks[J]. Advances in neural information processing systems, 2006, 19.

[97] Sermanet P, Chintala S, LeCun Y. Convolutional neural networks applied to house numbers digit classification[C]. Proceedings of the 21st international conference on pattern recognition (ICPR2012). IEEE, 2012: 3288-3291.

[98] Funahashi K, Nakamura Y. Approximation of dynamical systems by continuous time recurrent neural networks[J]. Neural networks, 1993, 6(6):801-806.

[99] Joulin A, Cissé M, Grangier D, et al. Efficient softmax approximation for GPUs[C]. International conference on machine learning. PMLR, 2017:1302-1310.

[100] Qian J, Jiang L, Song Z. Locally linear back-propagation based contribution for nonlinear process fault diagnosis[J]. IEEE/CAA Journal of Automatica Sinica, 2020, 7(3):764-775.

[101] Liu S, He J, Chen Z, et al. Discriminative Stacked Auto-encoder: Feature-Integration Boosting for Bearing Fault Diagnosis[J]. IEEE Sensors Journal, 2023, 23(22):27549-27558.

[102] Chen L, Ma Y, Hu H, et al. An effective fault diagnosis approach for bearing using stacked de-noising auto-encoder with structure adaptive adjustment[J]. Measurement, 2023, 214:112774.

[103] Pang S. Stacked maximum independence autoencoders: A domain generalization approach for fault diagnosis under various working conditions[J]. Mechanical Systems and Signal Processing, 2024, 208:111035.

[104] 张彬桥, 舒勇, 江雨. 基于改进变分模态分解和优化堆叠降噪自编码器的轴承故障诊断[J]. 计算机集成制造系统, 2023, 1-20.

[105] 张西宁, 向宙, 夏心锐, 等. 堆叠自编码网络性能优化及其在滚动轴承故障诊断中的应用[J]. 西安交通大学学报, 2018, 52(10):49-56.

[106] 杜先君, 贾亮亮. 基于优化堆叠降噪自编码器的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(12):2827-2838.

[107] 马航宇, 周笛, 卫宇杰, 等. 变工况下基于自适应深度置信网络的轴承智能故障诊断[J]. 上海交通大学学报, 2022, 56(10):1368-1378.

[108] 李益兵, 王磊, 江丽. 基于PSO改进深度置信网络的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(05):89-96.

[109] Yu Y, Shi P, Tian J, et al. Rolling mill health states diagnosing method based on multi-sensor information fusion and improved DBNs under limited datasets[J]. ISA transactions, 2023, 134:529-547.

[110] Pan Y, Cheng D, Wei T, et al. Rolling bearing performance degradation assessment based on deep belief network and improved support vector data description[J]. Mechanical Systems and Signal Processing, 2022, 181:109458.

[111] Tang J, Wu J, Hu B, et al. Towards a fault diagnosis method for rolling bearing with Bi-directional deep belief network[J]. Applied Acoustics, 2022,192:108727.

[112] Oh H, Jung J, Jeon B C, et al. Scalable and unsupervised feature engineering using vibration-imaging and deep learning for rotor system diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017, 65(4):3539-3549.

[113] 陶唐飞, 周文洁, 况佳臣, 等. 融合多小波分解的深度卷积神经网络轴承故障诊断方法[J]. 西安交通大学学报, 2024, (05):1-10.

[114] 唐伯宇, 邵星, 王翠香, 等. 基于双通道CNN与SSA-SVM的滚动轴承故障诊断[J]. 控制理论与应用, 2023,1-10.

[115] 郭盼盼, 张文斌, 崔奔, 等. 基于增强深度卷积神经网络的滚动轴承多工况故障诊断方法[J]. 振动工程学报, 2023,1-14.

[116] Ruan D, Wang J, Yan J, et al. CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis[J]. Advanced Engineering Informatics, 2023, 55:101877.

[117] Wang H, Liu Z, Peng D, et al. Interpretable convolutional neural network with multilayer wavelet for Noise-Robust Machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 195:110314.

[118] Wang X, Mao D, Li X. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network[J]. Measurement, 2021, 173:108518.

[119] Xu Y, Feng K, Yan X, et al. CFCNN: A novel convolutional fusion framework for collaborative fault identification of rotating machinery[J]. Information Fusion, 2023,95:1-16.

[120] Sinitsin V, Ibryaeva O, Sakovskaya V, et al. Intelligent bearing fault diagnosis method combining mixed input and hybrid CNN-MLP model[J]. Mechanical Systems and Signal Processing, 2022, 180:109454.

[121] 宫文峰, 张美玲, 陈辉. 基于深度学习的旋转机械大数据智能故障诊断方法[J]. 计算机集成制造系统, 2023,1-21.

[122] Chen X, Zhang B, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021,32:971-987.

[123] Gao D, Zhu Y, Ren Z, et al. A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity[J]. Knowledge-Based Systems, 2021, 231:107413.

[124] Buchaiah S, Shakya P. Bearing fault diagnosis and prognosis using data fusion based feature extraction and feature selection[J]. Measurement, 2022, 188:110506.

[125] Xu Z, Mei X, Wang X, et al. Fault diagnosis of wind turbine bearing using a multi-scale convolutional neural network with bidirectional long short term memory and weighted majority voting for multi-sensors[J]. Renewable Energy, 2022, 182:615-626.

[126] 陈超, 郭婧, 屈华伟, 等. 基于多尺度卷积神经网络和GRU的滚动轴承故障诊断[J]. 轴承, 2023,1-11.

[127] 徐鹏, 皋军, 邵星. 基于AMCNN-BiGRU的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2023, 42(18):71-80.

[128] An Z, Li S, Wang J, et al. A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network[J]. ISA transactions, 2020, 100:155-170.

[129] Barros C D T, Mendonça M R F, Vieira A B, et al. A survey on embedding dynamic graphs[J]. ACM Computing Surveys (CSUR), 2021, 55(1):1-37.

[130] Xu M. Understanding graph embedding methods and their applications[J]. SIAM Review, 2021, 63(4):825-853.

[131] Febrinanto F G, Xia F, Moore K, et al. Graph lifelong learning: A survey[J]. IEEE Computational Intelligence Magazine, 2023, 18(1):32-51.

[132] Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE transactions on neural networks, 2008, 20(1):61-80.

[133] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv:1609.02907, 2016.

[134] Ruiz L, Gama F, Ribeiro A. Gated graph recurrent neural networks[J]. IEEE Transactions on Signal Processing, 2020, 68:6303-6318.

[135] Veličković P, Cucurull G, Casanova A, et al. Cucurull Guillem, Casanova Arantxa, et al. Graph attention networks[J]. arXiv preprint arXiv:1710.10903, 2017.

[136] Rennard V, Nikolentzos G, Vazirgiannis M. Graph Auto-Encoders for Learning Edge Representations[C]. Complex Networks & Their Applications IX: Volume 2, Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020. Springer International Publishing, 2021: 117-129.

[137] Li T, Sun C, Li S, et al. Explainable graph wavelet denoising network for intelligent fault diagnosis[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022. 1-14

[138] Yu Z, Zhang C, Deng C. An improved GNN using dynamic graph embedding mechanism: A novel end-to-end framework for rolling bearing fault diagnosis under variable working conditions[J]. Mechanical Systems and Signal Processing, 2023, 200:110534.

[139] 谢锋云, 王玲岚, 宋明桦, 等. 基于GCN的多源变工况滚动轴承故障诊断[J]. 铁道科学与工程学报, 2023,1-12.

[140] Zhang D, Stewart E, Entezami M, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network[J]. Measurement, 2020, 156:107585.

[141] Yang C, Zhou K, Liu J. SuperGraph: Spatial-temporal graph-based feature extraction for rotating machinery diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 69(4):4167-4176.

[142] Zhou K, Yang C, Liu J, et al. Dynamic graph-based feature learning with few edges considering noisy samples for rotating machinery fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 69(10):10595-10604.

[143] Jiang Y, Zheng L, Tang C, et al. LSTM-based Node-Gated Graph Neural Network for Cross-condition Few-shot Bearing Fault Diagnosis[J]. IEEE Sensors Journal, 2024, 24(3):3445-3456.

[144] Wei Y, Wu D, Terpenny J. Bearing remaining useful life prediction using self-adaptive graph convolutional networks with self-attention mechanism[J]. Mechanical Systems and Signal Processing, 2023, 188:110010.

[145] 雷春丽, 薛林林, 夏奔锋, 等. 采用马尔科夫转移场和图注意力网络的滚动轴承故障诊断方法[J]. 振动工程学报, 2023,1-10.

[146] 曹洁, 陈泽阳, 王进花. Multi-GAT:基于多度量衡构建图的故障诊断方法[J]. 控制理论与应用, 2023,1-10.

[147] Xie Z, Chen J, Feng Y, et al. Semi-supervised multi-scale attention-aware graph convolution network for intelligent fault diagnosis of machine under extremely-limited labeled samples[J]. Journal of Manufacturing Systems, 2022, 64:561-577.

[148] 邵海东, 颜深, 肖一鸣, 等. 时变转速下基于改进图注意力网络的轴承半监督故障诊断[J]. 电子与信息学报, 2023, 45(05):1550-1558.

[149] Meng Z, Zhu J, Cao S, et al. Bearing Fault Diagnosis under Multi-sensor Fusion Based on Modal Analysis and Graph Attention Network[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72:3526510.

[150] Abudurexiti Y, Han G J, Liu L, et al. Graph-guided Higher-Order Attention Network for Industrial Rotating Machinery Intelligent Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2023, 20(2):1113-1123.

[151] Wen H, Guo W, Li X. A novel deep clustering network using multi-representation autoencoder and adversarial learning for large cross-domain fault diagnosis of rolling bearings[J]. Expert Systems with Applications, 2023, 225:120066.

[152] Liu J, Zhou K, Yang C, et al. Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning[J]. Frontiers of Mechanical Engineering, 2021, 16(4):829-839.

[153] Sun Z, Wang Y, Sun G, et al. Neighborhood graph embedding interpretable fault diagnosis network based on local and non-local information balanced under imbalanced samples[J]. Structural Health Monitoring, 2023, 22(3):1721-1744.

[154] Zhao X, Jia M, Liu Z. Semisupervised deep sparse auto-encoder with local and nonlocal information for intelligent fault diagnosis of rotating machinery[J]. IEEE Transactions on Instrumentation and Measurement, 2020,701-13.

[155] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[156] Bao G, Zhang Y, Teng Z, et al. G-Transformer for Document-Level Machine Translation[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, 2021.

[157] Wu C, Wu F, Qi T, et al. Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 2021: 848-853.

[158] Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]. European conference on computer vision. Cham: Springer International Publishing, 2020: 213-229.

[159] Wang L, Li R, Zhang C, et al. UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 190:196-214.

[160] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[C]//International Conference on Learning Representations. 2020.

[161] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows. 2021:10012-10022.

[162] 刘俊锋, 俞翔, 万海波, 等. 基于MFMD和Transformer-CNN的滚动轴承故障诊断方法[J]. 航空动力学报, 2023, 38(06):1446-1456.

[163] Ding Y, Jia M, Miao Q, et al. A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings[J]. Mechanical Systems and Signal Processing, 2022, 168:108616.

[164] 赵志宏, 李春秀, 李乐豪, 等. 一种机械设备故障诊断的FD-Transformer方法[J]. 振动与冲击, 2023, 42(08):326-333.

[165] Jin Y, Hou L, Chen Y. A time series transformer based method for the rotating machinery fault diagnosis[J]. Neurocomputing, 2022, 494:379-395.

[166] Lin T, Zhu Y, Ren Z, et al. CCFT: The Convolution and Cross-Fusion Transformer for Fault Diagnosis of Bearings[J]. IEEE/ASME Transactions on Mechatronics, 2023, 1-12.

[167] 赵洪山, 林诗雨, 孙承妍, 等. 考虑多时间尺度信息的风力发电机滚动轴承故障预测[J]. 中国电机工程学报, 2023,1-14.

[168] Tang J, Zheng G, Wei C, et al. Signal-transformer: A robust and interpretable method for rotating machinery intelligent fault diagnosis under variable operating conditions[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-11.

[169] Du X, Jia L, Haq I. Fault diagnosis based on SPBO-SDAE and transformer neural network for rotating machinery[J]. Measurement, 2022, 188:110545.

[170] Wang G, Liu D, Cui L. Auto-Embedding Transformer for Interpretable Few-Shot Fault Diagnosis of Rolling Bearings[J]. IEEE Transactions on Reliability, 2023, 1-10.

[171] Hou Y, Wang J, Chen Z, et al. Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved Transformer[J]. Engineering Applications of Artificial Intelligence, 2023, 124:106507.

[172] An Y, Zhang K, Chai Y, et al. Gaussian Mixture Variational Based Transformer Domain Adaptation Fault Diagnosis Method and Its Application in Bearing Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2023, 20(1):615-625.

[173] Li J, Bao Y, Liu W, et al. Twins transformer: Cross-attention based two-branch transformer network for rotating bearing fault diagnosis[J]. Measurement, 2023, 223:113687.

[174] Xiao Y, Shao H, Wang J, et al. Bayesian variational transformer: A generalizable model for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 207:110936.

[175] Vu M H, Nguyen V Q, Tran T T, et al. Few-Shot Bearing Fault Diagnosis via Ensembling Transformer-based Model with Mahalanobis Distance Metric Learning from Multiscale Features[J]. IEEE Transactions on Instrumentation and Measurement, 2024. 73:25136

[176] Chang S, Wang L, Shi M, et al. Extended attention signal transformer with adaptive class imbalance loss for Long-tailed intelligent fault diagnosis of rotating machinery[J]. Advanced Engineering Informatics, 2024, 60:102436.

[177] Liang P, Yu Z, Wang B, et al. Fault transfer diagnosis of rolling bearings across multiple working conditions via subdomain adaptation and improved vision transformer network[J]. Advanced Engineering Informatics, 2023, 57:102075.

[178] Li X, Su H, Xiang L, et al. Transformer-based meta learning method for bearing fault identification under multiple small sample conditions[J]. Mechanical Systems and Signal Processing, 2024, 208:110967.

[179] Fu Z, Liu Z, Ping S, et al. TRA-ACGAN: A motor bearing fault diagnosis model based on an auxiliary classifier generative adversarial network and Transformer network[J]. ISA transactions, 2024.

[180] Li S, Ji J C, Xu Y, et al. Dconformer: A denoising convolutional transformer with joint learning strategy for intelligent diagnosis of bearing faults[J]. Mechanical Systems and Signal Processing, 2024, 210: 111142.

[181] Wu X, Peng H, Cui X, et al. Multi-Channel vibration signals fusion based on rolling bearings and MRST-Transformer fault diagnosis model[J]. IEEE Sensors Journal, 2024.

[182] Liu H, Xu Q, Han X, et al. Attention on the key modes: Machinery fault diagnosis transformers through variational mode decomposition[J]. Knowledge-Based Systems, 2024: 289:111479.

[183] 刘杰, 谭玉涛, 谷艳玲, 等. 不均衡样本下轴承故障的LSGAN-Swin Transformer诊断方法[J]. 振动工程学报, 2023,1-13.

[184] Chen J, Lin C, Lu Q, et al. A Decision Fusion SWT-RF Method for Rolling Bearing Enhanced Diagnosis under Low-quality Data[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73:3509511.

[185] Chen J, Chen J, Chen Z, et al. Hybrid augmented network with balance domain window for few-shot fault diagnosis under sharp speed variation[J]. Mechanical Systems and Signal Processing, 2024, 207:110944.

[186] Chen Z, Chen J, Liu S, et al. Multi-channel Calibrated Transformer with Shifted Windows for few-shot fault diagnosis under sharp speed variation[J]. ISA transactions, 2022, 131:501-515.

[187] 王奉涛, 苏文胜著. 滚动轴承故障诊断与寿命预测[M]. 北京: 科学出版社, 2018.

[188] 邵凡. 基于迁移学习的轴承故障诊断研究[D]. 南京信息工程大学, 2022.

[189] Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.

[190] Tieleman T. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude[J]. COURSERA: Neural networks for machine learning, 2012, 4(2):26.

[191] 杨东华, 何涛, 王宏志, 等. 面向知识图谱的图嵌入学习研究进展[J]. 软件学报, 2022, 33(09):3370-3390.

[192] Su X, Liu H, Tao L, et al. An end-to-end framework for remaining useful life prediction of rolling bearing based on feature pre-extraction mechanism and deep adaptive transformer model[J]. Computers & Industrial Engineering, 2021, 161:107531.

[193] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[194] Zhang J Q, Yi S, Liang G, et al. A new bearing fault diagnosis method based on modified convolutional neural networks[J]. Chinese Journal of Aeronautics, 2020, 33(2):439-447.

[195] Liu T, Li L, Noman K, et al. Local maximum instantaneous extraction transform based on extended autocorrelation function for bearing fault diagnosis[J]. Advanced Engineering Informatics, 2024, 61: 102487.

[196] Ma L, Jiang B, Lu N, et al. Angular contact ball bearing skidding mechanism analysis and diagnosis considering flexible rotor characteristics[J]. Mechanical Systems and Signal Processing, 2024, 207: 110942.

[197] 刘飞, 陈仁文, 邢凯玲, 等. 基于迁移学习与深度残差网络的滚动轴承快速故障诊断算法[J]. 振动与冲击, 2022, 41(03):154-164.

[198] Ding X, Zhang X, Ma N, et al. Repvgg: Making vgg-style convnets great again[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 13733-13742.

[199] Su H, Xiang L, Hu A, et al. A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions[J]. Mechanical Systems and Signal Processing, 2022, 169:108765.

[200] Chaleshtori A E, Aghaie A. A novel bearing fault diagnosis approach using the Gaussian mixture model and the weighted principal component analysis[J]. Reliability Engineering & System Safety, 2024, 242:109720.

[201] Jiang W, Xu Y, Chen Z, et al. Fault diagnosis for rolling bearing using a hybrid hierarchical method based on scale-variable dispersion entropy and parametric t-SNE algorithm[J]. Measurement, 2022, 191:110843.

[202] Selvaraju R R, Cogswell M, Das A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization[C]. Proceedings of the IEEE international conference on computer vision. 2017: 618-626.

[203] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.

[204] Zhang W, Li C, Peng G, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical systems and signal processing, 2018, 100:439-453.

[205] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv:1609.02907, 2016.

[206] Morris C, Ritzert M, Fey M, et al. Weisfeiler and leman go neural: Higher-order graph neural networks. 2019: 4602-4609.

[207] Zhou H, Luo F, Zhuang H P, et al. Attention multi-hop graph and multi-scale convolutional fusion network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:5508614.

[208] Liu X, Lu J, Li Z. Multi-Scale Fusion Attention Convolutional Neural Network for Fault Diagnosis of Aero-Engine Rolling Bearing[J]. IEEE Sensors Journal, 2023, 23(17):19918-19934.

[209] Zhang Z, Cui P, Zhu W. Deep learning on graphs: A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(1):249-270.

[210] Cong W, Ramezani M, Mahdavi M. On provable benefits of depth in training graph convolutional networks[J]. Advances in Neural Information Processing Systems, 2021, 34:9936-9949.

[211] Li T, Zhao Z B, Sun C, et al. Multireceptive Field Graph Convolutional Networks for Machine Fault Diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 68(12):12739-12749.

[212] Brody S, Alon U, Yahav E. How Attentive are Graph Attention Networks?[C]//International Conference on Learning Representations. 2021.

[213] Hamilton W, Ying Z T, Leskovec J. Inductive representation learning on large graphs[J]. Advances in neural information processing systems, 2017, 30.

[214] Defferrard M E L, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering[J]. Advances in neural information processing systems, 2016, 29.

[215] Xu Y, Yan X, Sun B, et al. Global contextual residual convolutional neural networks for motor fault diagnosis under variable-speed conditions[J]. Reliability Engineering & System Safety, 2022, 225:108618.

[216] Xu Y, Ji J, Ni Q, et al. A graph-guided collaborative convolutional neural network for fault diagnosis of electromechanical systems[J]. Mechanical Systems and Signal Processing, 2023, 200:110609.

[217] Tang X, Xu Z, Wang Z. A novel fault diagnosis method of rolling bearing based on integrated vision transformer model[J]. Sensors, 2022, 22(10):3878.

[218] Jiao Z, Pan L, Fan W, et al. Partly interpretable transformer through binary arborescent filter for intelligent bearing fault diagnosis[J]. Measurement, 2022, 203:111950.

[219] Li Z, Zhang Z, Zhao H, et al. Text compression-aided transformer encoding[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(7):3840-3857.

[220] Jiang Y, Sharma B, Madhavi M, et al. Knowledge distillation from bert transformer to speech transformer for intent classification[J]. arXiv preprint arXiv:2108.02598, 2021.

[221] Ding M, Lian X, Yang L, et al. Hr-nas: Searching efficient high-resolution neural architectures with lightweight transformers[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 2982-2992.

[222] Igor Farka V S, Masulli Paolo, Otte Sebastian, et al. Artificial Neural Networks and Machine Learning-ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14-17, 2021, Proceedings, Part I[M]. Springer Nature, 2021.

[223] Touvron H, Bojanowski P, Caron M, et al. Resmlp: Feedforward networks for image classification with data-efficient training[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(4):5314-5321.

[224] Hendrycks D, Gimpel K. Gaussian error linear units (gelus)[J]. arXiv preprint arXiv:1606.08415, 2016.

[225] Tang T, Qiu C, Yang T, et al. A novel lightweight relation network for cross-domain few-shot fault diagnosis[J]. Measurement, 2023, 213:112697.

[226] Lessmeier C, Kimotho J K, Zimmer D, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification[C]. PHM Society European Conference. 2016, 3(1).

[227] Sandler M, Howard A, Zhu M L, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.

[228] Zhang X, Zhou X, Lin M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.

[229] Ma N, Zhang X, Zheng H, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]. Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.

[230] Fang H, Deng J, Bai Y, 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, 2021, 71:1-8.

[231] Peng D, Wang H, Liu Z L, et al. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7):4949-4960.