一種面向旋轉(zhuǎn)機械多傳感器故障診斷的模態(tài)融合深度聚類方法

伍章俊; 許仁禮; 方剛; 邵海東

doi:10.11999/JEIT240648

一種面向旋轉(zhuǎn)機械多傳感器故障診斷的模態(tài)融合深度聚類方法

doi: 10.11999/JEIT240648

伍章俊^{1, 2},
許仁禮^{1, 3},
方剛^{1, 3},
邵海東^4, ,

1.
合肥工業(yè)大學(xué)管理學(xué)院合肥 230009
2.
過程優(yōu)化與智能決策教育部重點實驗室合肥 230009
3.
智能決策與信息系統(tǒng)技術(shù)教育部工程研究中心合肥 230009
4.
湖南大學(xué)機械與運載工程學(xué)院長沙 410082

基金項目: 國家自然科學(xué)基金(52275104)，湖南省創(chuàng)新平臺與人才計劃(2023RC3097)

詳細(xì)信息

作者簡介:
伍章?。耗校┦?，副教授，碩士生導(dǎo)師，研究方向為機器學(xué)習(xí)與預(yù)防性維護

許仁禮：男，碩士生，研究方向為故障診斷與無監(jiān)督學(xué)習(xí)

方剛：男，碩士生，研究方向為圖神經(jīng)網(wǎng)絡(luò)與半監(jiān)督學(xué)習(xí)

邵海東：男，博士，副教授，博士生導(dǎo)師，研究方向為故障診斷與智能運維、數(shù)據(jù)挖掘與信息融合

通訊作者:
邵海東　hdshao@hnu.edu.cn

中圖分類號: TN911.7; TH133; TP183
計量
- 文章訪問數(shù): 334
- HTML全文瀏覽量: 85
- PDF下載量: 62
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-07-25
- 修回日期: 2024-12-02
- 網(wǎng)絡(luò)出版日期: 2024-12-06
- 刊出日期: 2025-01-31

A Modal Fusion Deep Clustering Method for Multi-sensor Fault Diagnosis of Rotating Machinery

WU Zhangjun^{1, 2},
XU Renli^{1, 3},
FANG Gang^{1, 3},
SHAO Haidong^{4
, ,}

1.
School of Management, Hefei University of Technology, Hefei 230009, China
2.
Key Laboratory of Process Optimization and Intelligent Decision-making, Ministry of Education, Hefei 230009, China
3.
Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies, Hefei 230009, China
4.
College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China

Funds: The National Natural Science Foundation of China (52275104), Hunan Province Innovation Platform and Talent Plan Project (2023RC3097)

摘要

摘要: 針對單傳感器和單模態(tài)信號特征信息不足的問題，該文提出一種基于多模態(tài)融合的端到端深度聚類旋轉(zhuǎn)機械多傳感器故障診斷方法(EDCM-MFF)。首先，利用門控遞歸單元自編碼模塊提取多傳感器故障信號的深度時序特征。然后，應(yīng)用短時傅里葉變換(STFT)將故障信號轉(zhuǎn)換為時頻圖像，并通過卷積自編碼器提取這些圖像的深度空間特征。接著，設(shè)計了一種模態(tài)融合注意力機制，通過計算不同模態(tài)深度特征之間的親和矩陣，實現(xiàn)模態(tài)特征的融合。最后，采用Kullback-Leibler(KL)散度聚類，以端到端方式實現(xiàn)故障類型的識別。實驗結(jié)果顯示，該方法在東南大學(xué)齒輪箱和軸承數(shù)據(jù)集上的識別準(zhǔn)確率分別為99.16%和98.63%。與現(xiàn)有的無監(jiān)督學(xué)習(xí)方法相比，所提方法能夠更有效地實現(xiàn)多傳感器和多模態(tài)的旋轉(zhuǎn)機械故障診斷。
- 旋轉(zhuǎn)機械 /
- 故障診斷 /
- 多模態(tài)融合 /
- 深度聚類
Abstract: Objective Rotating machinery is essential across various industrial sectors, including energy, aerospace, and manufacturing. However, these machines operate under complex and variable conditions, making timely and accurate fault detection a significant challenge. Traditional diagnostic methods, which use a single sensor and modality, often miss critical features, particularly subtle fault signatures. This can result in reduced reliability, increased downtime, and higher maintenance costs. To address these issues, this study proposes a novel modal fusion deep clustering approach for multi-sensor fault diagnosis in rotating machinery. The main objectives are to: (1) improve feature extraction through time-frequency transformations that reveal important temporal-spectral patterns, (2) implement an attention-based modality fusion strategy that integrates complementary information from various sensors, and (3) use a deep clustering framework to identify fault types without needing labeled training data. Methods The proposed approach utilizes a multi-stage pipeline for thorough feature extraction and analysis. First, raw multi-sensor signals, such as vibration data collected under different load and speed conditions, are preprocessed and transformed with the Short-Time Fourier Transform (STFT). This converts time-domain signals into time-frequency representations, highlighting distinct frequency components related to various fault conditions. Next, Gated Recurrent Units (GRUs) model temporal dependencies and capture long-range correlations, while Convolutional AutoEncoders (CAEs) learn hierarchical spatial features from the transformed data. By combining GRUs and CAEs, the framework encodes both temporal and structural patterns, creating richer and more robust representations than traditional methods that rely solely on either technique or handcrafted features. A key innovation is the modality fusion attention mechanism. In multi-sensor environments, individual sensors typically capture complementary aspects of system behavior. Simply concatenating their outputs can lead to suboptimal results due to noise and irrelevant information. The proposed attention-based fusion calculates modality-specific affinity matrices to assess the relationship and importance of each sensor modality. With learnable attention weights, the framework prioritizes the most informative modalities while diminishing the impact of less relevant ones. This ensures the fused representation captures complementary information, resulting in improved discriminative power. Finally, an unsupervised clustering module is integrated into the deep learning pipeline. Rather than depending on labeled data, the model assigns samples to clusters by refining cluster assignments iteratively using a Kullback-Leibler (KL) divergence-based objective. Initially, a soft cluster distribution is created from the learned features. A target distribution is then computed to sharpen and define cluster boundaries. By continuously minimizing the KL divergence between these distributions, the model self-optimizes over time, producing well-separated clusters corresponding to distinct fault types without supervision. Results and Discussions The proposed approach’s effectiveness is illustrated using multi-sensor bearing and gearbox datasets. Compared to conventional unsupervised methods—like traditional clustering algorithms or single-domain feature extraction techniques—this framework significantly enhances clustering accuracy and fault recognition rates. Experimental results show recognition accuracies of approximately 99.16% on gearbox data and 98.63% on bearing data, representing a notable advancement over existing state-of-the-art techniques. These impressive results stem from the synergistic effects of advanced feature extraction, modality fusion, and iterative clustering refinement. By extracting time-frequency features through STFT, the method captures a richer representation than relying solely on raw time-domain signals. The use of GRUs incorporates temporal information, enabling the capture of dynamic signal changes that may indicate evolving fault patterns. Additionally, CAEs reveal meaningful spatial structures from time-frequency data, resulting in low-dimensional yet highly informative embeddings. The modality fusion attention mechanism further enhances these benefits by emphasizing relevant modalities, such as vibration data from various sensor placements or distinct physical principles, thus leveraging their complementary strengths. Through the iterative minimization of KL divergence, the clustering process becomes more discriminative. Initially broad and overlapping cluster boundaries are progressively refined, allowing the model to converge toward stable and well-defined fault groupings. This unsupervised approach is particularly valuable in practical scenarios, where obtaining labeled data is costly and time-consuming. The model’s ability to learn directly from unlabeled signals enables continuous monitoring and adaptation, facilitating timely interventions and reducing the risk of unexpected machine failures. The discussion emphasizes the adaptability of the proposed method. Industrial systems continuously evolve, and fault patterns can change over time due to aging, maintenance, or shifts in operational conditions. The unsupervised method can be periodically retrained or updated with new unlabeled data. This allows it to monitor changes in machinery health and quickly detect new fault conditions without the need for manual annotation. Additionally, the attention-based modality fusion is flexible enough to support the inclusion of new sensor types or measurement channels, potentially enhancing diagnostic performance as richer data sources become available. Conclusions This study presents a modal fusion deep clustering framework designed for the multi-sensor fault diagnosis of rotating machinery. By combining time-frequency transformations with GRU- and CAE-based deep feature encoders, attention-driven modality fusion, and KL divergence-based unsupervised clustering, this approach outperforms traditional methods in accuracy, robustness, and scalability. Key contributions include a comprehensive multi-domain feature extraction pipeline, an adaptive modality fusion strategy for heterogeneous sensor data integration, and a refined deep clustering mechanism that achieves high diagnostic accuracy without relying on labeled training samples. Looking ahead, there are several promising directions. Adding more modalities—like acoustic emissions, temperature signals, or electrical measurements—could lead to richer feature sets. Exploring semi-supervised or few-shot extensions may further enhance performance by utilizing minimal labeled guidance when available. Implementing the proposed model in an industrial setting, potentially for real-time use, would also validate its practical benefits for maintenance decision-making, helping to reduce operational costs and extend equipment life.
- Rotating machinery /
- Fault diagnosis /
- Multimodal fusion /
- Deep clustering

HTML全文

圖 1 EDCM-MFF方法框架圖

下載: 全尺寸圖片幻燈片

圖 2 時序特征提取模塊結(jié)構(gòu)圖

下載: 全尺寸圖片幻燈片

圖 3 空間特征提取模塊結(jié)構(gòu)圖

下載: 全尺寸圖片幻燈片

圖 4 多模態(tài)特征融合模塊結(jié)構(gòu)圖

下載: 全尺寸圖片幻燈片

圖 5 不同模態(tài)的ACC, NMI和ARI

下載: 全尺寸圖片幻燈片

圖 6 MFF 中不同時間步的權(quán)重可視化結(jié)果

下載: 全尺寸圖片幻燈片

圖 7 MFF中不同傳感器的權(quán)重可視化結(jié)果

下載: 全尺寸圖片幻燈片

圖 8 基于不同深度特征維度的ACC, NMI和ARI

下載: 全尺寸圖片幻燈片

圖 9 基于不同聚類損失權(quán)重系數(shù)的ACC, NMI和ARI

下載: 全尺寸圖片幻燈片

圖 10 EDCM-MFF消融實驗的ACC, NMI和ARI

下載: 全尺寸圖片幻燈片

圖 11 融合特征可視化結(jié)果

下載: 全尺寸圖片幻燈片

1 EDCM-MFF的算法流程

輸入：多傳感器信號數(shù)據(jù)$ {{\boldsymbol{X}}^{\rm S}} $；
多傳感器時頻圖像數(shù)據(jù)$ {{\boldsymbol{X}}^{\rm{I}}} $；
聚類質(zhì)心數(shù)目$K$；
聚類損失的權(quán)重系數(shù)$\lambda $。
預(yù)訓(xùn)練：
根據(jù)式(10)和式(15)對特征提取模塊的GRU-AE和CAE進行　　　預(yù)訓(xùn)練；
根據(jù)式(16)–式(18)計算${{\boldsymbol{Z}}^{\mathrm{F}}}$；
使用K-Means初始化聚類質(zhì)心$ {\boldsymbol{{\mu}} _j}(j = 1,2,\cdots,K) $。
微調(diào)：
For iter = 1, 2, ···, MAXITER do
根據(jù)式(16)–式(18)計算${{\boldsymbol{Z}}^{\mathrm{F}}}$；
根據(jù)式(19)計算${{\boldsymbol{Q}}^{\mathrm{F}}}$；
根據(jù)式(20)計算${{\boldsymbol{P}}^{\mathrm{F}}}$；
根據(jù)式(23)更新整個網(wǎng)絡(luò)參數(shù)。
End for
For iter = 1, 2, ···, N do //N為樣本數(shù)
根據(jù)式(22)計算第$i$個多傳感器數(shù)據(jù)樣本的聚類分配。
End for
輸出：聚類分配$ y \in {\mathbb{R}^N} $。

下載: 導(dǎo)出CSV

表 1 齒輪箱和軸承數(shù)據(jù)集

數(shù)據(jù)集	樣本數(shù)量	狀態(tài)類型描述
G_data	5×1022×2	健康、齒面磨損、根部裂紋、斷齒、缺損
B_data	5×1022×2	健康、外圈故障、內(nèi)圈故障、復(fù)合故障、滾珠故障

下載: 導(dǎo)出CSV

表 2 實驗參數(shù)設(shè)置說明表

方法	參數(shù)
K-Means	迭代次數(shù)：20；簇的數(shù)目：5
AE+K-Means	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10
DEC	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10
IDEC	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10；聚類損失權(quán)重系數(shù)$\lambda $：0.1
DCN	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10；聚類損失權(quán)重系數(shù)$\lambda $：0.1
DSC-Nets	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10；聚類損失權(quán)重系數(shù)${\lambda _1}$：1.0；正則化損失權(quán)重系數(shù)${\lambda _2}$：0.01
MvDSCN	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10；聚類損失權(quán)重系數(shù)${\lambda _1}$：0.01；lp范數(shù)正則化損失權(quán)重系數(shù)${\lambda _2}$：1.0；共同性正則化損失權(quán)重系數(shù)${\lambda _3}$：0.1；差異性正則化損失權(quán)重系數(shù)${\lambda _4}$：0.1
AMVDSN	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；深度特征維度：10；聚類損失權(quán)重系數(shù)${\lambda _1}$：0.1；重構(gòu)損失權(quán)重系數(shù)${\lambda _2}$：0.1；正則化損失權(quán)重系數(shù)${\lambda _3}$：0.01
EDCM-MFF	編碼器網(wǎng)絡(luò)層數(shù)：3；解碼器網(wǎng)絡(luò)層數(shù)：3；卷積核大小(2維)：7×7, 5×5, 3×3；時間步數(shù)目：32；深度特征維度：{10, 20, 40, 80, 160}；聚類損失權(quán)重系數(shù)$\lambda $：{0.01, 0.1, 1, 10, 100, 1000}

下載: 導(dǎo)出CSV

表 3 在G_data和B_data上的ACC, NMI和ARI(%)

方法	G_data			B_data
方法	ACC	NMI	ARI	ACC	NMI	ARI
K-Means	79.04	85.47	75.89	76.92	85.02	73.70
AE+K-Means	95.42	88.87	90.15	96.33	90.82	91.70
DEC	97.56	94.14	94.86	97.59	94.41	95.05
IDEC	97.82	94.63	95.57	97.70	94.32	95.03
DCN	97.86	94.81	95.26	97.89	94.87	95.62
DSC-Nets	97.80	94.55	95.53	97.56	94.17	94.73
MvDSCN	98.64	96.80	96.87	98.15	95.23	95.86
AMVDSN	99.08	97.05	97.71	98.53	96.06	96.43
EDCM-MFF	99.16	97.98	98.40	98.63	96.64	97.12

下載: 導(dǎo)出CSV

參考文獻(28)

[1]	王玉靜, 康守強, 張云, 等. 基于集合經(jīng)驗?zāi)B(tài)分解敏感固有模態(tài)函數(shù)選擇算法的滾動軸承狀態(tài)識別方法[J]. 電子與信息學(xué)報, 2014, 36(3): 595–600. doi: 10.3724/SP.J.1146.2013.00434. WANG Yujing, KANG Shouqiang, ZHANG Yun, et al. Condition recognition method of rolling bearing based on ensemble empirical mode decomposition sensitive intrinsic mode function selection algorithm[J]. Journal of Electronics & Information Technology, 2014, 36(3): 595–600. doi: 10.3724/SP.J.1146.2013.00434.
[2]	文成林, 呂菲亞. 基于深度學(xué)習(xí)的故障診斷方法綜述[J]. 電子與信息學(xué)報, 2020, 42(1): 234–248. doi: 10.11999/JEIT190715. WEN Chenglin and Lü Feiya. Review on deep learning based fault diagnosis[J]. Journal of Electronics & Information Technology, 2020, 42(1): 234–248. doi: 10.11999/JEIT190715.
[3]	邵海東, 肖一鳴, 鄧乾旺, 等. 基于不確定性感知網(wǎng)絡(luò)的可信機械故障診斷[J]. 機械工程學(xué)報, 2024, 60(12): 194–206. doi: 10.3901/JME.2024.12.194. SHAO Haidong, XIAO Yiming, DENG Qianwang, et al. Trustworthy mechanical fault diagnosis using uncertainty-aware network[J]. Journal of Mechanical Engineering, 2024, 60(12): 194–206. doi: 10.3901/JME.2024.12.194.
[4]	康守強, 楊佳軒, 王玉靜, 等. 基于改進寬度模型遷移學(xué)習(xí)的不同負(fù)載下滾動軸承狀態(tài)快速分類方法[J]. 電子與信息學(xué)報, 2023, 45(5): 1824–1832. doi: 10.11999/JEIT220401. KANG Shouqiang, YANG Jiaxuan, WANG Yujing, et al. A fast classification method of rolling bearing state under different loads based on improved broad model transfer learning[J]. Journal of Electronics & Information Technology, 2023, 45(5): 1824–1832. doi: 10.11999/JEIT220401.
[5]	邵海東, 顏深, 肖一鳴, 等. 時變轉(zhuǎn)速下基于改進圖注意力網(wǎng)絡(luò)的軸承半監(jiān)督故障診斷[J]. 電子與信息學(xué)報, 2023, 45(5): 1550–1558. doi: 10.11999/JEIT220303. SHAO Haidong, YAN Shen, XIAO Yiming, et al. Semi-supervised bearing fault diagnosis using improved graph attention network under time-varying speeds[J]. Journal of Electronics & Information Technology, 2023, 45(5): 1550–1558. doi: 10.11999/JEIT220303.
[6]	孫瑾鈴, 張偉濤, 樓順天. 基于等變化自適應(yīng)源分離算法的滾動軸承故障信號自適應(yīng)盲提取[J]. 電子與信息學(xué)報, 2020, 42(10): 2471–2477. doi: 10.11999/JEJT190722. SUN Jinling, ZHANG Weitao, and LOU Shuntian. Adaptive blind extraction of rolling bearing fault signal based on equivariant adaptive separation via independence[J]. Journal of Electronics & Information Technology, 2020, 42(10): 2471–2477. doi: 10.11999/JEJT190722.
[7]	邵海東, 林健, 閔志閃, 等. 分布外樣本干擾下基于改進半監(jiān)督原型網(wǎng)絡(luò)的齒輪箱跨域故障診斷[J]. 機械工程學(xué)報, 2024, 60(4): 212–221. doi: 10.3901/JME.2024.04.212. SHAO Haidong, LIN Jian, MIN Zhishan, et al. Improved semi-supervised prototype network for cross-domain fault diagnosis of gearbox under out-of-distribution interference samples[J]. Journal of Mechanical Engineering, 2024, 60(4): 212–221. doi: 10.3901/JME.2024.04.212.
[8]	XIAO Yiming, SHAO Haidong, HAN Songyu, et al. Novel joint transfer network for unsupervised bearing fault diagnosis from simulation domain to experimental domain[J]. IEEE/ASME Transactions on Mechatronics, 2022, 27(6): 5254–5263. doi: 10.1109/TMECH.2022.3177174.
[9]	解騫, 徐浩嵐, 王彤, 等. 基于自主認(rèn)知深度時間聚類表示的隔離開關(guān)故障診斷方法[J]. 電氣工程學(xué)報, 2024, 19(1): 281–289. doi: 10.11985/2024.01.030. XIE Qian, XU Haolan, WANG Tong, et al. Disconnector fault diagnosis method based on autonomous-cognition deep temporal clustering representation[J]. Journal of Electrical Engineering, 2024, 19(1): 281–289. doi: 10.11985/2024.01.030.
[10]	LI Xiang, LI Xu, and MA Hui. Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery[J]. Mechanical Systems and Signal Processing, 2020, 143: 106825. doi: 10.1016/j.ymssp.2020.106825.
[11]	LIU Yongjie, DING Kun, ZHANG Jingwei, et al. Fault diagnosis approach for photovoltaic array based on the stacked auto-encoder and clustering with I-V curves[J]. Energy Conversion and Management, 2021, 245: 114603. doi: 10.1016/j.enconman.2021.114603.
[12]	YU Jianbo and YAN Xuefeng. Multiscale intelligent fault detection system based on agglomerative hierarchical clustering using stacked denoising autoencoder with temporal information[J]. Applied Soft Computing, 2020, 95: 106525. doi: 10.1016/j.asoc.2020.106525.
[13]	ZHAO Bo, ZHANG Xianmin, WU Qiqiang, et al. A novel unsupervised directed hierarchical graph network with clustering representation for intelligent fault diagnosis of machines[J]. Mechanical Systems and Signal Processing, 2023, 183: 109615. doi: 10.1016/j.ymssp.2022.109615.
[14]	REN Yazhou, PU Jingyu, YANG Zhimeng, et al. Deep clustering: A comprehensive survey[EB/OL]. https://arxiv.org/abs/2210.04142, 2022.
[15]	IKOTUN A M, EZUGWU A E, ABUALIGAH L, et al. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data[J]. Information Sciences, 2023, 622: 178–210. doi: 10.1016/j.ins.2022.11.139.
[16]	XIE Junyuan, GIRSHICK R, and FARHADI A. Unsupervised deep embedding for clustering analysis[C]. The 33rd International Conference on Machine Learning, New York City, USA, 2016: 478–487.
[17]	GUO Xifeng, GAO Long, LIU Xingwang, et al. Improved deep embedded clustering with local structure preservation[C]. The Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia, 2017: 1753–1759. doi: 10.24963/ijcai.2017/243.
[18]	WU Zhangjun, FANG Gang, WANG Yifei, et al. An end-to-end deep clustering method with consistency and complementarity attention mechanism for multisensor fault diagnosis[J]. Applied Soft Computing, 2024, 158: 111594. doi: 10.1016/j.asoc.2024.111594.
[19]	WANG Kejun, WANG Wenqing, ZHAO Yabo, et al. Multisensor fault diagnosis via Markov chain and evidence theory[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106851. doi: 10.1016/j.engappai.2023.106851.
[20]	MAN Jie, DONG Honghui, JIA Limin, et al. AttGGCN model: A novel multi-sensor fault diagnosis method for high-speed train bogie[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19511–19522. doi: 10.1109/TITS.2022.3156281.
[21]	TONG Jinyu, LIU Cang, ZHENG Jinde, et al. Multi-sensor information fusion and coordinate attention-based fault diagnosis method and its interpretability research[J]. Engineering Applications of Artificial Intelligence, 2023, 124: 106614. doi: 10.1016/j.engappai.2023.106614.
[22]	CUI Jian, XIE Ping, WANG Xiao, et al. M2FN: An end-to-end multi-task and multi-sensor fusion network for intelligent fault diagnosis[J]. Measurement, 2022, 204: 112085. doi: 10.1016/j.measurement.2022.112085.
[23]	XU Yadong, FENG Ke, YAN Xiaoan, et al. CFCNN: A novel convolutional fusion framework for collaborative fault identification of rotating machinery[J]. Information Fusion, 2023, 95: 1–16. doi: 10.1016/j.inffus.2023.02.012.
[24]	YANG Chaoying, LIU Jie, ZHOU Kaibo, et al. Semisupervised machine fault diagnosis fusing unsupervised graph contrastive learning[J]. IEEE Transactions on Industrial Informatics, 2023, 19(8): 8644–8653. doi: 10.1109/TII.2022.3220847.
[25]	WANG Daichao, LI Yibin, JIA Lei, et al. Novel three-stage feature fusion method of multimodal data for bearing fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3514710. doi: 10.1109/TIM.2021.3071232.
[26]	MA Meng, SUN Chuang, and CHEN Xuefeng. Deep coupling autoencoder for fault diagnosis with multimodal sensory data[J]. IEEE Transactions on Industrial Informatics, 2018, 14(3): 1137–1145. doi: 10.1109/TII.2018.2793246.
[27]	CHE Changchang, WANG Huawei, NI Xiaomei, et al. Hybrid multimodal fusion with deep learning for rolling bearing fault diagnosis[J]. Measurement, 2021, 173: 108655. doi: 10.1016/j.measurement.2020.108655.
[28]	HU Zhanxuan, WANG Yichen, NING Hailong, et al. Mutual-taught deep clustering[J]. Knowledge-Based Systems, 2023, 282: 111100. doi: 10.1016/j.knosys.2023.111100.