基于精细复合缩放多尺度加权排列熵的跨域故障诊断方法

doi:10.3901/JME.2025.16.028

摘要/Abstract

摘要： 离心压缩机、蒸汽轮机、烟气轮机等大型旋转机械是石油化工企业的核心动力设备，实现设备常见典型故障的智能诊断对于开展智能运维至关重要。针对旋转机械跨域迁移诊断中存在早期微弱故障提取难、抗噪声干扰性能弱、不同故障状态信号特征易混淆以及跨工况数据共性特征学习性能低的难题，研究构建一种有效获取全频带范围微小振荡模式的精细复合缩放多尺度加权排列熵指标，并提出一种旋转机械跨域故障迁移诊断方法。首先，对多源典型故障数据库中原始振动信号分解、筛选和重构并提取其敏感共性特征；其次，采用多核孪生集成特征学习策略不断迭代提升模型对转子不平衡、轴系不对中、动静碰摩、油膜涡动和喘振五类源域故障特征的学习分类性能；然后，利用半监督流形特征迁移策略缩小目标域和源域特征分布差异，并通过强分类器映射匹配故障类别标签；最后，基于真实工程故障案例数据验证了该方法的有效性，并与文献公开的五类熵特征和六种故障诊断方法进行对比，表明所提方法对不同设备多工况条件下的跨域故障具有更优越的诊断性能。

关键词: 精细复合缩放多尺度加权排列熵, 旋转机械, 跨域故障诊断, 多核孪生集成特征学习, 半监督流形特征迁移

Abstract: Centrifugal compressors, steam turbines, and flue gas turbines, among other large rotating machinery, are core power equipment in the petrochemical enterprises. Intelligent diagnosis of common typical equipment faults is crucial for carrying out intelligent operation and maintenance. To address challenges such as the difficulty in extracting early-stage weak faults, poor noise interference resistance, confusion of signal features across different fault states, and low learning performance of common features in cross-condition data, the refined composite zoom multi-scale weighted permutation entropy index has been constructed, which is effective for capturing subtle oscillation patterns across the full frequency band. A method for cross-domain fault transfer diagnosis in rotating machinery is also proposed. Firstly, the method is initiated with the decomposition, filtering, and reconstruction of raw vibration signals from a multi-source typical fault database to extract their sensitive common features. Subsequently, the multi-kernel twin ensemble feature learning strategy is employed to iteratively enhance the model's feature classification performance for five types of source domain faults: rotor unbalance, shaft misalignment, static and dynamic rubbing, oil film whirl, and surge. Then, the semi-supervised manifold feature transfer strategy is used to minimize the differences in feature distributions between the target and source domains, with the strong classifier mapping and matching fault category labels. Finally, the effectiveness of the proposed method is validated using real engineering fault case data and compared against five published entropy features and six fault diagnosis methods from the references, demonstrating superior diagnostic performance of the proposed method under multiple operating conditions for different equipment.

Key words: refined composite zoom multiscale weighted permutation entropy, rotating machinery, cross-domain fault diagnosis, multi-kernel twin ensemble feature learning, semi-supervised manifold feature transfer

中图分类号:

TH17

肖扬, 王华庆, 李华, 王庆锋. 基于精细复合缩放多尺度加权排列熵的跨域故障诊断方法[J]. 机械工程学报, 2025, 61(16): 28-39.

XIAO Yang, WANG Huaqing, LI Hua, WANG Qingfeng. Cross-domain Fault Diagnosis Method Based on Refined Composite Zoom Multi-scale Weighted Permutation Entropy[J]. Journal of Mechanical Engineering, 2025, 61(16): 28-39.

参考文献

[1] GANGSAR P , PANDEY R K , CHOUKSEY M. Unbalance detection in rotating machinery based on support vector machine using time and frequency domain vibration features[J]. Noise & Vibration Worldwide, 2021, 52(4-5): 75-85.
[2] SAJID S, HALEEM A, BAHL S, et al. Data science applications for predictive maintenance and materials science in context to Industry 4.0[J]. Materials Today: Proceedings, 2021, 45(6): 4898-4905.
[3] OCHELLA S, SHAFIEE M, DINMOHAMMADI F. Artificial intelligence in prognostics and health management of engineering systems[J]. Engineering Applications of Artificial Intelligence, 2022, 108: 104552.
[4] 程哲,韦磊,程军圣,等. 基于演员-评论家结构的深度强化学习齿轮箱智能故障诊断方法[J]. 失效分析与预防, 2023, 18(3): 141-148, 200. CHENG Zhe, WEI Lei, CHENG Junsheng, et al. Deep reinforcement learning gearbox intelligent fault diagnosis method based on actor-critic structure[J]. Failure Analysis and Prevention, 2023, 18(3): 141-148, 200.
[5] 邓飞跃. 基于自适应谐波小波和能量熵的转子系统故障诊断研究[J]. 中国测试, 2016, 42(8): 103-107. DENG Feiyue. Fault diagnosis of rotor system based on adaptive harmonic wavelet and energy entropy[J]. China Measurement & Test, 2016, 42(8): 103-107.
[6] 刘仁伟,岳林. 基于双谱熵和聚类分析的转子系统故障诊断[J]. 振动、测试与诊断, 2023, 43(1): 188-193, 205. LIU Renwei, YUE Lin. Rotor system fault diagnosis based on bispectrum entropy and clustering analysis[J]. Journal of Vibration, Measurement & Diagnosis, 2023, 43(1): 188-193, 205.
[7] 高玉才,付忠广,谢玉存,等. 改进型 LeNet-5 方法在转子系统故障诊断中的应用研究[J]. 汽轮机技术, 2021, 63(6): 445-447, 454. GAO Yucai, FU Zhongguang, XIE Yucun, et al. Research on the application of improved LeNet-5 method in rotor system fault diagnosis[J]. Turbine Technology, 2021, 63(6): 445-447, 454.
[8] LIU Shucong, WANG Hongjun, TANG Jingpeng, et al. Research on fault diagnosis of gas turbine rotor based on adversarial discriminative domain adaption transfer learning[J]. Measurement, 2022, 196: 111174.
[9] HE Zhiyi, SHAO Haidong, ZHONG Xiang, et al. An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE[J]. Advanced Engineering Informatics, 2020, 46: 101150.
[10] JIGYASU R, SHRIVASTAVA V, SINGH S, et al. Transfer learning based bearing and rotor fault diagnosis of induction motor[C]// 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), April 28-29, 2022, Noida. India: IEEE, 2022: 2628-2632.
[11] 贾思祥,孙丁一,毛刚,等. 基于对抗熵的转子系统跨工况故障诊断方法[J]. 机械工程学报, 2023, 59(15): 110-120. JIA Sixiang, SUN Dingyi, MAO Gang, et al. Adversarial entropy based fault diagnosis method for rotor system across different working conditions[J]. Journal of Mechanical Engineering, 2023, 59(15): 110-120.
[12] XIAO Yang, WANG Qingfeng, WANG Shuai, et al. Research on a multisource domain improved fault diagnosis method of the rotor system[J]. IEEE Access, 2022, 10: 85399-85415.
[13] JIA Feng, LEI Yaguo, LU Na, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing, 2018, 110: 349-367.
[14] 邵海东,林健,闵志闪,等. 分布外样本干扰下基于改进半监督原型网络的齿轮箱跨域故障诊断[J]. 机械工程学报, 2024, 60(4): 212-221. 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.
[15] MA Chenyang, LI Yongbo, WANG Xianzhi, et al. Early fault diagnosis of rotating machinery based on composite zoom permutation entropy[J]. Reliability Engineering and System Safety, 2023, 230: 108967.
[16] KE Yun, SONG Enzhe, CHEN Yanzhen, et al. Multiscale bidirectional diversity entropy for diesel injector fault-type diagnosis and fault degree diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 6503410.
[17] HU Qin, SI Xiaosheng, QIN Aisong, et al. Balanced adaptation regularization based transfer learning for unsupervised cross-domain fault diagnosis[J]. IEEE Sensors Journal, 2022, 22(12): 12139-12151.
[18] 候双珊,郑近德,潘海洋,等. 基于复合多尺度交叉模糊熵的行星齿轮箱故障诊断[J]. 振动与冲击, 2023, 42(20): 130-135, 171. HOU Shuangshan, ZHENG Jinde, PAN Haiyang, et al. Flanetary gearbox fault diagnosis based on composite multi-scale cross fuzzy entropy[J]. Journal of Vibration and Shock, 2023, 42(20): 130-135, 171.
[19] WANG Shun, LI Yongbo, NOMAN K, et al. Cumulative spectrum distribution entropy for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 206: 110905.
[20] 赵柄锡,冀大伟,袁奇,等. 采用时域与时频域联合特征空间的转子系统碰磨故障诊断[J]. 西安交通大学学报, 2020, 54(1): 75-84. ZHAO Bingxi, JI Dawei, YUAN Qi, et al. Rubbing fault diagnosis of rotor system based on combined feature space in time and time-frequency domains[J]. Journal of Xi’an Jiaotong University, 2020, 54(1): 75-84.
[21] 石明宽,赵荣珍. 基于局部边缘判别投影的机械故障诊断方法[J]. 振动、测试与诊断, 2021, 41(1): 126-132, 204. SHI Mingkuan, ZHAO Rongzhen. A method of mechanical fault diagnosis based on locality margin discriminant projection[J]. Journal of Vibration , Measurement & Diagnosis, 2021, 41(1): 126-132, 204.
[22] 邵海东,李伟,刘翊,等. 时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断[J]. 机械工程学报, 2023, 59(12): 215-224. SHAO Haidong, LI Wei, LIU Yi, et al. Fault diagnosis of rotor-bearing system under time-varying speeds by using dual-threshold attention-embedded GAN and small samples[J]. Journal of Mechanical Engineering, 2023, 59(12): 215-224.
[23] 伍济钢,文港,杨康. 改进注意力机制的航空发动机试验转子系统智能故障诊断[J]. 振动与冲击, 2024, 43(4): 261-269. WU Jigang , WEN Gang , YANG Kang. Improved attention mechanism for intelligent fault diagnosis of experimental rotor systems in aero engines[J]. Journal of Vibration and Shock, 2024, 43(4): 261-269.
[24] LIAO Yixiao, HUANG Ruyi, LI Jipu, et al. Dynamic distribution adaptation based transfer network for cross domain bearing fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2021, 34: 52.
[25] LIANG Ruijun, RAN Wenfeng, CHEN Yao, et al. Fault diagnosis method for rotating machinery based on multi-scale features[J]. Chinese Journal of Mechanical Engineering, 2023, 36: 141.