针对旋转机械设备故障诊断中特征提取不充分、特征融合机制欠缺以及复杂工况下模型诊断能力不足等问题,提出一种基于双域特征融合的FFT-CNN-Informer故障诊断方法。该方法构建了并行的时域-频域特征提取架构,利用快速傅里叶变换（FFT）获取频域特征信息,设计多尺度卷积神经网络（CNN）提取局部时域特征,并引入概率稀疏自注意力机制捕获长程依赖关系,实现了对振动信号的多维度特征提取。同时,引入残差学习和自适应特征融合机制,增强了模型对不同工况下故障特征的提取能力。在凯斯西储大学轴承数据集上的实验结果表明了该方法的优越性。在风电机组轴承数据集上进行实验,诊断准确率相较于基础的Transformer、LSTM模型分别提高了6.73和9.77个百分点,消融实验进一步证实了双域特征提取架构和自适应特征融合机制的必要性,验证了该方法在实际风电场应用中的有效性和鲁棒性。
Abstract
To address the challenges of insufficient feature extraction, inadequate feature fusion mechanisms, and limited diagnostic capability under complex operating conditions in rotating machinery fault diagnosis, a novel FFT-CNN-Informer fault diagnosis method based on dual-domain feature fusion is proposed. A parallel time-frequency domain feature extraction architecture is constructed. Specifically, Fast Fourier Transform （FFT） is employed to extract frequency-domain features, a multi-scale Convolutional Neural Network （CNN） is designed to capture local temporal features, and a Probabilistic Sparse Self-Attention mechanism is introduced to capture long-range dependencies, enabling multi-dimensional feature extraction of vibration signals. Furthermore, residual learning and an adaptive feature fusion mechanism are incorporated to enhance the ability to extract fault features under varying operating conditions. Experimental results on the Case Western Reserve University bearing dataset demonstrate the superiority of the proposed method. On wind turbine bearing datasets, the proposed method outperforms baseline Transformer and LSTM models by 6.73% and 9.77% in diagnostic accuracy, respectively. Ablation studies further validate the necessity of the dual-domain feature extraction architecture and the adaptive feature fusion mechanism, confirming the effectiveness and robustness of the method in practical wind farm applications.
关键词
风电机组 /
故障诊断 /
深度学习 /
频域分析 /
轴承 /
数据融合
Key words
wind turbines /
fault diagnosis /
deep learning /
frequency domain analysis fusion /
bearing /
data fusion
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李俊卿, 胡晓东, 王罗, 等. 考虑数据不足和基于合作博弈模型融合的风电机组轴承故障诊断方法[J]. 太阳能学报, 2024, 45(1): 234-241.
LI J Q, HU X D, WANG L, et al.Bearing fault diagnosis method for wind turbine considering insufficient data and based on cooperative game model fusion[J]. Acta energiae solaris sinica, 2024, 45(1): 234-241.
[2] JARAMILLO F, GUTIÉRREZ J M, ORCHARD M, et al. A Bayesian approach for fatigue damage diagnosis and prognosis of wind turbine blades[J]. Mechanical systems and signal processing, 2022, 174: 109067.
[3] PICHIKA S V V S N, MEGANAA G, GEETHA RAJASEKHARAN S, et al. Multi-component fault classification of a wind turbine gearbox using integrated condition monitoring and hybrid ensemble method approach[J]. Applied acoustics, 2022, 195: 108814.
[4] ANTONIADOU I, MANSON G, STASZEWSKI W J, et al. A time-frequency analysis approach for condition monitoring of a wind turbine gearbox under varying load conditions[J]. Mechanical systems and signal processing, 2015, 64/65: 188-216.
[5] ZHOU F N, YANG S, HE Y F, et al.Fault diagnosis based on deep learning by extracting inherent common feature of multi-source heterogeneous data[J]. Proceedings of the Institution of Mechanical engineers, part I: journal of systems and control engineering, 2021, 235(10): 1858-1872.
[6] 李俊, 刘永葆, 余又红. 卷积神经网络和峭度在轴承故障诊断中的应用[J]. 航空动力学报, 2019, 34(11): 2423-2431.
LI J, LIU Y B, YU Y H.Application of convolutional neural network and kurtosis in fault diagnosis of rolling bearing[J]. Journal of aerospace power, 2019, 34(11): 2423-2431.
[7] 刘洋, 程强, 史曜炜, 等. 基于注意力模块及1D-CNN的滚动轴承故障诊断[J]. 太阳能学报, 2022, 43(3): 462-468.
LIU Y, CHENG Q, SHI Y W, et al.Fault diagnosis of rolling bearings based on attention module and 1D-CNN[J]. Acta energiae solaris sinica, 2022, 43(3): 462-468.
[8] 邵海东, 陈星恺, 曹鸿儒, 等. 内对抗指导无监督多域适配网络的轴承协同故障诊断[J]. 中国科学(技术科学), 2023, 53(7): 1229-1240.
SHAO H D, CHEN X K, CAO H R, et al.Internal adversarial guided unsupervised multi-domain adaptation network for collaborative fault diagnosis of bearing[J]. Scientia sinica (technologica), 2023, 53(7): 1229-1240.
[9] PENG B S, XIA H, LYU X Z, et al.An intelligent fault diagnosis method for rotating machinery based on data fusion and deep residual neural network[J]. Applied intelligence, 2022, 52(3): 3051-3065.
[10] 赵敬娇, 赵志宏, 杨绍普. 基于残差连接和1D-CNN的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(10): 1-6.
ZHAO J J, ZHAO Z H, YANG S P.Rolling bearing fault diagnosis based on residual connection and 1D-CNN[J]. Journal of vibration and shock, 2021, 40(10): 1-6.
[11] ZHAO K Y, SUN R T, LI L, et al.An improved evidence fusion algorithm in multi-sensor systems[J]. Applied intelligence, 2021, 51(11): 7614-7624.
[12] HAN K, WANG Y H, CHEN H T, et al.A survey on vision transformer[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(1): 87-110.
[13] XIAO Y M, SHAO H D, FENG M J, et al.Towards trustworthy rotating machinery fault diagnosis via attention uncertainty in transformer[J]. Journal of manufacturing systems, 2023, 70: 186-201.
[14] DING Y F, JIA M P, MIAO Q H, 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.
[15] HAN S Y, SHAO H D, CHENG J S, et al.Convformer-NSE: a novel end-to-end gearbox fault diagnosis framework under heavy noise using joint global and local information[J]. IEEE/ASME transactions on mechatronics, 2023, 28(1): 340-349.
[16] WANG R, ZHANG S J, LIU S Q, et al.A bearing fault diagnosis method for high-noise and unbalanced dataset[J]. Smart and resilient transportation, 2023, 5(1): 28-45.
[17] ZHOU H Y, ZHANG S H, PENG J Q, et al.Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(12): 11106-11115.
[18] 赵小强, 张亚洲. 利用改进卷积神经网络的滚动轴承变工况故障诊断方法[J]. 西安交通大学学报, 2021, 55(12): 108-118.
ZHAO X Q, ZHANG Y Z.Improved CNN-based fault diagnosis method for rolling bearings under variable working conditions[J]. Journal of Xi’an Jiaotong University, 2021, 55(12): 108-118.
[19] Case Western Reserve University Bearing Data Center. Seeded fault test data[EB/OL].http://csegroups.case.edu/bearingdatacenter.
[20] MOSHREFZADEH A.Condition monitoring and intelligent diagnosis of rolling element bearings under constant/variable load and speed conditions[J]. Mechanical systems and signal processing, 2021, 149: 107153.
[21] SAIDI L, BEN ALI J, BECHHOEFER E, et al.Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR[J]. Applied acoustics, 2017, 120: 1-8.
[22] 李振恩, 张新燕, 胡威, 等. 基于健康指数的风电机组高速轴轴承状态评估与预测[J]. 太阳能学报, 2021, 42(10): 290-297.
LI Z E, ZHANG X Y, HU W, et al.State accessment and prediction of wind turbine high speed shaft bearing based on health index[J]. Acta energiae solaris sinica, 2021, 42(10): 290-297.
基金
辽宁省教育厅面上项目（LJ212410142026）
PDF(3814 KB)
