基于故障语义生成和广义零样本学习的复合故障诊断模型

董靖川 ,  李佳明 ,  王太勇 ,  赵锡博 ,  张正日 ,  陈楷文

天津大学学报(自然科学与工程技术版) ›› 2026, Vol. 59 ›› Issue (11) : 1127 -1137.

PDF (2460KB)
天津大学学报(自然科学与工程技术版) ›› 2026, Vol. 59 ›› Issue (11) : 1127 -1137. DOI: 10.11784/tdxbz202508018

基于故障语义生成和广义零样本学习的复合故障诊断模型

作者信息 +

Compound Fault Diagnosis Model Based on Fault Semantics Generation and Generalized Zero-Shot Learning

Author information +
文章历史 +
PDF (2518K)

摘要

滚动轴承复合故障诊断是故障诊断领域的一大挑战,主要是由于复合故障具有复杂的耦合特性,且在实际工业环境中难以获取和标记复合故障数据.现有的零样本复合故障诊断方法普遍缺乏同时识别单一故障和复合故障的能力.针对这一问题,提出了一种基于故障语义生成和广义零样本学习的复合故障诊断(FSG-GZSL)模型,以实现不同工作条件下的滚动轴承单一故障与复合故障的识别.该模型主要由复合故障预诊断模块、语义生成模块和复合故障诊断模块组成.首先,构建双通道域对抗神经网络作为复合故障预诊断模块,将时频图作为模块的输入,通过设定阈值条件来实现单一故障的识别并分离出复合故障.其次,设计了一种基于时频域统计特征的故障语义构建方法,用以提取样本的故障语义特征,并构建变分自编码器-生成式对抗网络(VAE-GAN)模型作为语义生成模块,通过学习单故障语义特征及其之间的耦合关系,生成伪复合故障语义.最后,利用 K-means 聚类模型作为复合故障诊断模块,先将伪复合故障语义输入形成聚类中心,通过比较样本故障语义与聚类中心的距离来实现复合故障的分类.本文在两个真实轴承故障数据集上进行了实验验证,分别达到了 96.02%和 97.41%的准确率,结果表明该方法在诊断效果上优于其他对比方法,且展现出较强的鲁棒性.

Abstract

Diagnosing compound faults of rolling bearings remains a major challenge in fault diagnosis. This is mainly due to the complex coupling characteristics of compound faults and the difficulty in collecting and labeling compound fault data under real industrial conditions. Existing zero-shot compound fault diagnosis methods generally lack the ability to identify single and compound fault categories. To address this issue,a compound fault diagnosis model based on fault semantics generation and generalized zero-shot learning(FSG-GZSL) was proposed. This model aimed to recognize single and compound rolling bearing faults under various working conditions. The proposed model consisted of three modules:a pre-diagnosis module,a semantics generation module,and a compound fault diagnosis module. First,a dual-channel domain-adversarial neural network was developed as the pre-diagnosis module. It takes time-frequency images as input and identifies single faults by applying a threshold while separating compound faults. Next,a fault semantics construction method based on time-frequency statistical features was designed to extract semantic features from samples. A variational autoencoder-generative adversarial network(VAE-GAN) model was built as the semantics generation module,which would learn the semantic features of single faults and their coupling relationships to generate pseudo compound fault semantics. Finally,a K-means clustering model was employed as the diagnosis module. Pseudo compound fault semantics were used to form cluster centers,and compound faults were classified by comparing distances between the sample semantics and cluster centers. Experiments were conducted on two real-world bearing fault datasets and achieved accuracies of 96.02% and 97.41%,respectively. These results demonstrate that the proposed method outperforms other competing approaches in diagnostic accuracy and exhibits strong robustness.

关键词

广义零样本学习 / 变分自编码器-生成式对抗网络 / 域对抗神经网络 / 复合故障诊断

Key words

generalized zero-shot learning / variational autoencoder-generative adversarial network / domain adversarial neural network / compound fault diagnosis

引用本文

引用格式 ▾
董靖川,李佳明,王太勇,赵锡博,张正日,陈楷文. 基于故障语义生成和广义零样本学习的复合故障诊断模型[J]. 天津大学学报(自然科学与工程技术版), 2026, 59(11): 1127-1137 DOI:10.11784/tdxbz202508018

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

王太勇, 王廷虎, 王 鹏, 等. 基于注意力机制 BiLSTM 的设备智能故障诊断方法[J]. 天津大学学报(自然科学与工程技术版), 2020, 53(6): 601-608.

[2]

Wang Taiyong, Wang Tinghu, Wang Peng, et al. An intelligent fault diagnosis method based on attention—based bidirectional LSTM network[J]. Journal of Tianjin University(Science and Technology), 2020, 53(6): 601-608(in Chinese).

[3]

王国锋, 张旭东, 汪 菲, 等. 基于优化 EFD 算法的风电行星齿轮箱故障诊断研究[J]. 天津大学学报(自然科学与工程技术版), 2023, 56(4): 355-360.

[4]

Wang Guofeng, Zhang Xudong, Wang Fei, et al. Wind power planetary gearbox fault diagnosis based on optimized EFD algorithm [J]. Journal of Tianjin University(Science and Technology), 2023, 56(4): 355-360(in Chinese).

[5]

林诗麒, 陈智丽, 李宇鹏, 等. 基于深度学习和多域决策融合的轴承故障智能诊断技术[J]. 计算机集成制造系统, 2024, 30(10): 3708-3718.

[6]

Lin Shiqi, Chen Zhili, Li Yupeng, et al. Intelligent bearing fault diagnosis technology based on deep learning and multi—domain decision fusion[J]. Computer Integrated Manufacturing Systems, 2024, 30(10) : 3708-3718(in Chinese).

[7]

Song B Y, Liu Y Y, Fang J Z, et al. An optimized CNN—BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples[J]. Neurocomputing, 2024, 574: 127284.

[8]

程建刚, 毕凤荣, 张立鹏, 等. 基于 MACNN 的柴油机故障诊断方法研究[J]. 振动与冲击, 2022, 41(10): 8-15.

[9]

Cheng Jiangang, Bi Fengrong, Zhang Lipeng, et al. Fault diagnosis method for diesel engines based on MACNN[J]. Journal of Vibration and Shock, 2022, 41(10): 8-15(in Chinese).

[10]

周 旷, 覃文博, 孙天宇. 基于可信多源领域自适应的跨域滚动轴承故障诊断[J]. 控制与决策, 2025, 40(7): 2251-2260.

[11]

Zhou Kuang, Qin Wenbo, Sun Tianyu. Cross—domain fault diagnosis of rolling bearings based on trusted multi—source domain adaptation[J]. Control and Decision, 2025, 40(7): 2251-2260(in Chinese).

[12]

Gao T Y, Yang J L, Tang Q. A multi—source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions[J]. Information Fusion, 2024, 106: 102278.

[13]

王 鹏, 李丹青, 王 恒. 基于改进交替迁移学习的滚动轴承故障诊断算法[J]. 振动与冲击, 2024, 43(5): 239-249.

[14]

Wang Peng, Li Danqing, Wang Heng. Rolling bearing fault diagnosis algorithm based on improved alternating transfer learning[J]. Journal of Vibration and Shock, 2024, 43(5): 239-249(in Chinese).

[15]

魏文军, 张轩铭, 杨立本. 基于模糊聚类和改进 Densenet 网络的小样本轴承故障诊断[J]. 哈尔滨工业大学学报, 2024, 56(3): 154-163.

[16]

Wei Wenjun, Zhang Xuanming, Yang Liben. Fault diagnosis of small sample bearings based on fuzzy clustering and improved Densenet network[J]. Journal of Harbin Institute of Technology, 2024, 56(3): 154-163(in Chinese).

[17]

刘 臻, 彭珍瑞, 王圣杰. 小样本下 SE—ResNet 与元迁移学习的变工况轴承故障诊断[J]. 振动工程学报, 2025, 38(6): 1199-1211.

[18]

Liu Zhen, Peng Zhenrui, Wang Shengjie. Bearing fault diagnosis under few—shot and variable working conditions using SE—ResNet and Meta—Transfer learning[J]. Journal of Vibration Engineering, 2025, 38(6): 1199-1211(in Chinese).

[19]

邹 松, 董绍江, 夏宗佑, 等. 基于特征解纠缠和联合域对齐的滚动轴承多源域迁移诊断方法[J]. 振动与冲击, 2025, 44(1): 113—120, 133.

[20]

Zou Song, Dong Shaojiang, Xia Zongyou, et al. Multi—source domain transfer diagnosis method for rolling bearings based on features disentanglement and joint domain alignment[J]. Journal of Vibration and Shock, 2025, 44(1): 113—120, 133(in Chinese).

[21]

Chen H H, Hong J, Cheng C, et al. Zero—shot compound fault diagnosis method using semantic construction and embedding[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 3535013.

[22]

李耀华, 赵 佳, 张鑫杰. 基于语义融合零样本学习的轴承复合故障诊断模型[J]. 振动与冲击, 2025, 44(10): 278-286.

[23]

Li Yaohua, Zhao Jia, Zhang Xinjie. Bearing compound fault diagnosis model based on semantic fusion zero sample learning[J]. Journal of Vibration and Shock, 2025, 44(10): 278-286(in Chinese).

[24]

Xu J, Zhou L, Zhao W H, et al. Zero—shot learning for compound fault diagnosis of bearings[J]. Expert Systems with Applications, 2022, 190: 116197.

[25]

Cen J, Zhao B C, Liu X, et al. An intelligent compound fault diagnosis method using generalized zero—shot model of bearing[J]. Measurement Science and Technology, 2024, 35(9): 096134.

[26]

Xu J, Kong H, Li K, et al. Generative zero—shot compound fault diagnosis based on semantic alignment[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 3508713.

[27]

Thuan N D, Hong H S. HUST bearing:A practical dataset for ball bearing fault diagnosis[J]. BMC Research Notes, 2023, 16(1): 138.

[28]

Huang R, Li J, Liao Y, et al. Deep adversarial capsule network for compound fault diagnosis of machinery toward multidomain generalization task[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3506311.

[29]

Dibaj A, Ettefagh M M, Hassannejad R, et al. A hybrid fine—tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal—severity faults[J]. Expert Systems with Applications, 2021, 167: 114094.

[30]

Xing S B, Lei Y G, Wang S H, et al. A label description space embedded model for zero—shot intelligent diagnosis of mechanical compound faults[J]. Mechanical Systems and Signal Processing, 2022, 162: 108036.

[31]

Wang J, Xu Z W, Niu F Z, et al. Adaptively weighted semantic autoencoder for zero—shot compound fault diagnosis[J]. IEEE Sensors Journal, 2024, 24(22): 37472-37481.

基金资助

国家重点研发计划资助项目(2022YFB3303601)

天津市科学技术局资助项目(23YDPYGX00210)

AI Summary AI Mindmap
PDF (2460KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉