面向旋转机械健康监测和早期故障检测的Diffusion-Ramanujan数字孪生架构

doi:10.3901/JME.260488

摘要/Abstract

摘要： 旋转机械的健康监测与早期故障检测对保障设备安全运行至关重要。传统故障特征提取方法多依赖预设参数，限制了实际应用效果。Ramanujan周期变换虽能通过正交子空间有效分离信号周期成分，但其性能高度依赖高保真故障仿真模型，而模型构建通常需要先验故障特征信息，难以在缺乏故障样本的场景中推广。为解决此问题，提出一种融合条件扩散模型与Ramanujan周期变换的数字孪生架构(Diffusion-Ramanujan)。该方法采用无分类器引导机制构建条件扩散模型，将未知类型故障样本转化为健康样本，通过对比转化前后样本包络谱的分布差异，自动挖掘潜在故障特征；进而基于所提取特征构建唯象仿真模型作为数字孪生体，驱动Ramanujan周期变换实现无参数依赖的故障特征分离，并构建健康因子评估设备状态。IMS轴承数据集实验结果表明，所提方法能在缺乏故障先验知识的情况下有效识别早期故障，较提升包络谱、Anomaly-Transformer等基线模型具有更早故障检测时间和更高监测准确性，为旋转机械健康管理提供了不依赖预设参数与先验知识的有效路径。

关键词: 旋转机械, 早期故障检测, 扩散模型, Ramanujan周期变换, 数字孪生

Abstract: Health monitoring and early fault detection of rotating machinery are crucial for ensuring equipment operational safety. Traditional fault feature extraction methods often rely on preset parameters, limiting their effectiveness in practical applications. Although the Ramanujan Periodic Transform can effectively separate periodic components in signals by constructing orthogonal subspaces, its performance heavily depends on high-fidelity fault simulation models, which typically require prior knowledge of fault features, making it difficult to generalize in scenarios lacking fault samples. To address this issue, a digital twin architecture integrating conditional diffusion models and the Ramanujan Periodic Transform (Diffusion-Ramanujan) is proposed. This method employs a classifier-free guided conditional diffusion model to transform unknown-type fault samples into healthy samples. By comparing the distribution differences in the envelope spectra before and after transformation, potential fault features are automatically mined. Based on the extracted features, a phenomenological simulation model is constructed as a digital twin to drive the Ramanujan Periodic Transform, enabling parameter-independent fault feature separation from monitoring data and the establishment of health indicators for equipment health monitoring. Experimental results on the IMS bearing dataset demonstrate that the proposed method can effectively identify early faults without prior fault knowledge, achieving earlier fault detection time and higher monitoring accuracy compared to baseline models such as Improved Envelope Spectrum and Anomaly-Transformer. This provides an effective pathway for rotating machinery health management that does not rely on preset parameters or prior knowledge.

Key words: rotating machinery, early fault detection, diffusion model, Ramanujan periodic transform, digital twin

中图分类号:

TG156

胡文扬, 李奇, 林起鉴, 王天杨, 阎绍泽, 褚福磊. 面向旋转机械健康监测和早期故障检测的Diffusion-Ramanujan数字孪生架构[J]. 机械工程学报, 2026, 62(12): 77-86.

HU Wenyang, LI Qi, LIN Qijian, WANG Tianyang, YAN Shaoze, CHU Fulei. Diffusion-Ramanujan Digital Twin Architecture for Rotating Machinery Health Monitoring and Early Fault Detection[J]. Journal of Mechanical Engineering, 2026, 62(12): 77-86.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260488

http://www.cjmenet.com.cn/CN/Y2026/V62/I12/77

参考文献

[1] LEI Yaguo，YANG Bin，JIANG Xinwei，et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical systems and signal processing，2020，138:106587.
[2] WANG Tianyang，HAN Qinkai，CHU Fulei，et al. Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox:A review[J]. Mechanical Systems and Signal Processing，2019，126:662-685.
[3] SUN Shilin，WANG Tianyang，CHU Fulei. In-situ condition monitoring of wind turbine blades:A critical and systematic review of techniques，challenges，and futures[J]. Renewable and Sustainable Energy Reviews，2022，160:112326.
[4] LI Hua，WU Xing，LIU Tao，et al. Composite fault diagnosis for rolling bearing based on parameter-optimized VMD[J]. Measurement，2022，201:111637.
[5] LU Guoliang，WEN Xin，HE Guangshuo，et al. Early fault warning and identification in condition monitoring of bearing via wavelet packet decomposition coupled with graph[J]. IEEE/ASME Transactions on Mechatronics，2021，27(5):3155-3164.
[6] NASSEF M G A，HUSSEIN T M，MOKHIAMAR O. An adaptive variational mode decomposition based on sailfish optimization algorithm and Gini index for fault identification in rolling bearings[J]. Measurement，2021，173:108514.
[7] HU Wenyang，WANG Tianyang，CHU Fulei. A novel Ramanujan digital twin for periodic fault feature extraction of rotating machines[C]//International conference on the Efficiency and Performance Engineering Network. Cham:Springer Nature Switzerland，2023:751-760.
[8] TAO Fei，ZHANG He，LIU Ang，et al. Digital twin in industry:State-of-the-art[J]. IEEE Transactions on industrial informatics，2018，15(4):2405-2415.
[9] HU Chunhua，FAN Weicun，ZENG Elan，et al. Digital twin-assisted real-time traffic data prediction method for 5G-enabled internet of vehicles[J]. IEEE Transactions on Industrial Informatics，2021，18(4):2811-2819.
[10] WEI Yongli，HU Tianliang，ZHOU Tingting，et al. Consistency retention method for CNC machine tool digital twin model[J]. Journal of Manufacturing Systems，2021，58:313-322.
[11] KAPTEYN M G，PRETORIUS J V R，WILLCOX K E. A probabilistic graphical model foundation for enabling predictive digital twins at scale[J]. Nature Computational Science，2021，1(5):337-347.
[12] HU Wenyang，WANG Tianyang，CHU Fulei. A Wasserstein generative digital twin model in health monitoring of rotating machines[J]. Computers in Industry，2023，145:103807.
[13] HU Wenyang，WANG Tianyang，CHU Fulei. Novel Ramanujan digital twin for motor periodic fault monitoring and detection[J]. IEEE Transactions on Industrial Informatics，2023，19(12):11564-11572.
[14] HU Wenyang，WANG Tianyang，CHU Fulei. A faulty simulation model guided Ramanujan digital twin architecture for rotating machine health monitoring[J]. ISA Transactions，2025，157:408-418.
[15] 胡文扬，王天杨，张飞斌，等. 仿真驱动下基于Ramanujan周期变换的轴承早期故障特征提取[J]. 机械工程学报，2023，59(13):148-156. HU Wenyang，WANG Tianyang，ZHANG Feibin，et al. Extraction of early fault features of bearings based on Ramanujan period transform method driven by simulation[J]. Journal of Mechanical Engineering，59(13):148-156.
[16] VAIDYANATHAN P P. Ramanujan sums in the context of signal processing—Part I:Fundamentals[J]. IEEE Transactions on Signal Processing，2014，62(16):4145-4157.
[17] VAIDYANATHAN P P. Ramanujan sums in the context of signal processing—Part II:FIR representations and applications[J]. IEEE Transactions on Signal Processing，2014，62(16):4158-4172.
[18] VAIDYANATHAN P P，TENNETI S. Srinivasa Ramanujan and signal-processing problems[J]. Philosophical Transactions of the Royal Society A，2020，378(2163):20180446.
[19] HO J，JAIN A，ABBEEL P. Denoising diffusion probabilistic models[J]. Advances in Neural Information Processing Systems，2020，33:6840-6851.
[20] DHARIWAL P，NICHOL A. Diffusion models beat gans on image synthesis[J]. Advances in Neural Information Processing Systems，2021，34:8780-8794.
[21] HO J，SALIMANS T. Classifier-free diffusion guidance[J]. arXiv preprint arXiv:2207.12598，2022.
[22] QIU Hai，LEE J，LIN Jing，et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration，2006，289(4-5):1066-1090.
[23] ABBOUD D，ELBADAOUI M，SMITH W A，et al. Advanced bearing diagnostics:A comparative study of two powerful approaches[J]. Mechanical Systems and Signal Processing，2019，114:604-627.
[24] HU Wenyang，FRUSQUE G，WANG Tianyang，et al. Classifier-free diffusion-based weakly-supervised approach for health indicator derivation in rotating machines:Advancing early fault detection and condition monitoring[J]. arXiv preprint arXiv:2409.01676，2024.
[25] XU Jiehui，WU Haixu，WANG Jianmin，et al. Anomaly transformer:Time series anomaly detection with association discrepancy[J]. arXiv preprint arXiv:2110.02642，2021.
[26] SAID E M，LE-KHAC N A，DEV S，et al. Network anomaly detection using LSTM based autoencoder[C]// Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks. 2020:37-45.
[27] ZHAN Jun，WANG Siqi，MA Xiandong，et al. Stgat-mad:Spatial-temporal graph attention network for multivariate time series anomaly detection[C]//ICASSP 2022-2022 IEEE International Conference on Acoustics，Speech and Signal Processing (ICASSP). IEEE，2022:3568-3572.