VMD-HT-ResNet-BASED VIBRATION CONDITION MONITORING AND EARLY WARNING FOR WIND TURBINE TOWER

Hu Yang; Li Bo; Hu Yaozong; Fu Daoyi; Hu Haopeng

doi:10.19912/j.0254-0096.tynxb.2023-1342

PDF(3694 KB)

Acta Energiae Solaris Sinica ›› 2024, Vol. 45 ›› Issue (12) : 388-396. DOI: 10.19912/j.0254-0096.tynxb.2023-1342

VMD-HT-ResNet-BASED VIBRATION CONDITION MONITORING AND EARLY WARNING FOR WIND TURBINE TOWER

Hu Yang¹, Li Bo¹, Hu Yaozong¹, Fu Daoyi², Hu Haopeng²

Author information +

History +

Abstract

Aiming at the problem that it is difficult to reliably monitor and warn the multimodal vibration of large wind turbine tower, a multi-input and multi-output（MIMO） nonlinear dynamic modelling method combining variational modal decomposition（VMD）-Hilbert transform（HT）-residual network（RestNet） is proposed to model the nonlinear dynamic characteristics of tower vibration of wind turbines. The inherent modal vibration of the tower is decomposed and extracted, and the differential dynamic regression vectors that accurately characterize the vibration characteristics of the tower are defined, and balanced sampling and MIMO modelling are carried out for the whole working conditions. Then, an exponential moving average （EWMA） index is established to evaluate the health of the tower, which is used for its condition monitoring and early warning. Simulation results show that the proposed method achieves high-precision monitoring and early warning of the tower vibration characteristics of wind turbines under all operating conditions, which provides a guarantee for the high safety operation of the turbines.

Key words

wind turbines / tower / variational mode decomposition / differential dynamic modelling / residual neural / healthiness evaluation

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Hu Yang, Li Bo, Hu Yaozong, Fu Daoyi, Hu Haopeng. VMD-HT-ResNet-BASED VIBRATION CONDITION MONITORING AND EARLY WARNING FOR WIND TURBINE TOWER[J]. Acta Energiae Solaris Sinica. 2024, 45(12): 388-396 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1342

References

[1] 魏煜锋, 何维令, 蒋祥增, 等. 高柔塔风电机组塔筒振源特性分析[J]. 振动与冲击, 2023, 42(2): 189-196.
WEI Y F, HE W L, JIANG X Z, et al.Vibration source characteristics of a high-soft tower wind turbine[J]. Journal of vibration and shock, 2023, 42(2): 189-196.
[2] 苗风麟, 施洪生, 张小青. 风力发电机组多领域耦合模型及动态响应分析[J]. 中国电机工程学报, 2015, 35(7): 1704-1712.
MIAO F L, SHI H S, ZHANG X Q.Modelling of wind turbines coupled in multi-domain and dynamic response analysis[J]. Proceedings of the CSEE, 2015, 35(7): 1704-1712.
[3] CHEN Y M, JIN X, CHENG P, et al.Combining CFD and artificial neural network techniques to predict vortex-induced vibration mechanism for wind turbine tower hoisting[J]. Communications in nonlinear science and numerical simulation, 2022, 114: 106688.
[4] 苗风麟, 施洪生, 张小青. 风电机组耦合振动特性分析[J]. 中国电机工程学报, 2016, 36(1): 187-195.
MIAO F L, SHI H S, ZHANG X Q.Coupled vibration analysis of wind turbine[J]. Proceedings of the CSEE, 2016, 36(1): 187-195.
[5] 陈修高, 宋羽佳, 孙晓彦, 等. 数据-知识驱动的变工况运行风电机组塔筒振动状态预测[J]. 热力发电, 2023, 52(3): 58-66.
CHEN X G, SONG Y J, SUN X Y, et al.Data-knowledge driven prediction of tower vibration state of wind turbines operating under variable operating conditions[J]. Thermal power generation, 2023, 52(3): 58-66.
[6] 孙志伟, 史立, 胡雄, 等. 振动信号小波分解系数压缩编码方法[J]. 济南大学学报(自然科学版), 2019, 33(5): 396-402.
SUN Z W, SHI L, HU X, et al.Vibration signal wavelet decomposition coefficient compression coding method[J]. Journal of University of Ji'nan (science and technology), 2019, 33(5): 396-402.
[7] 黄华, 薛文虎, 姚嘉靖, 等. 基于图论诊断法与小波包变换的数控机床进给系统故障诊断研究[J]. 振动与冲击, 2022, 41(15): 130-137, 185.
HUANG H, XUE W H, YAO J J, et al.Fault diagnosis of NC machine tool feed system based on graph theory diagnosis method and wavelet packet transform[J]. Journal of vibration and shock, 2022, 41(15): 130-137, 185.
[8] 卢绪祥, 苏一鸣, 吴家腾, 等. 基于EMD及灰色关联度的滑动轴承润滑状态故障诊断研究[J]. 动力工程学报, 2016, 36(1): 42-47.
LU X X, SU Y M, WU J T, et al.Fault diagnosis on lubrication state of journal bearings based on EMD and grey relational degree[J]. Journal of Chinese Society of Power Engineering, 2016, 36(1): 42-47.
[9] 费鸿禄, 刘梦, 曲广建, 等. 基于集合经验模态分解-小波阈值方法的爆破振动信号降噪方法[J]. 爆炸与冲击, 2018, 38(1): 112-118.
FEI H L, LIU M, QU G J, et al.A method for blasting vibration signal denoising based on ensemble empirical mode decomposition-wavelet threshold[J]. Explosion and shock waves, 2018, 38(1): 112-118.
[10] HU Y J, OUYANG Y, WANG Z L, et al.Vibration signal denoising method based on CEEMDAN and its application in brake disc unbalance detection[J]. Mechanical systems and signal processing, 2023, 187: 109972.
[11] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[12] XING Z K, HE Y G.Multi-modal multi-step wind power forecasting based on stacking deep learning model[J]. Renewable energy, 2023, 215: 118991.
[13] 毕贵红, 赵鑫, 李璐, 等. 双模式分解CNN-LSTM集成的短期风速预测模型[J]. 太阳能学报, 2023, 44(3): 191-197.
BI G H, ZHAO X, LI L, et al.Dual-mode decomposition CNN-LSTM integrated short-term wind speed forecasting model[J]. Acta energiae solaris sinica, 2023, 44(3): 191-197.
[14] CHEN W H, ZHOU H T, CHENG L S, et al.Condition monitoring of wind turbine using novel deep learning method and dynamic kernel principal components Mahalanobis distance[J]. Engineering applications of artificial intelligence, 2023, 125: 106757.
[15] 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.
[16] 向玲, 王朋鹤, 李京蓄. 基于CNN-LSTM的风电机组异常状态检测[J]. 振动与冲击, 2021, 40(22): 11-17.
XIANG L, WANG P H, LI J X.Abnormal state detection of wind turbines based on CNN-LSTM[J]. Journal of vibration and shock, 2021, 40(22): 11-17.
[17] ABOU HOURAN M, SALMAN BUKHARI S M, ZAFAR M H, et al. COA-CNN-LSTM: coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications[J]. Applied energy, 2023, 349: 121638.
[18] 张小刚, 丁华, 王晓波, 等. 深度残差网络在滚动轴承故障诊断中的研究[J]. 机械设计与制造, 2022(1): 77-80.
ZHANG X G, DING H, WANG X B, et al.Study on fault diagnosis of rolling bearing by deep residual network[J]. Machinery design & manufacture, 2022(1): 77-80.
[19] 陶涛, 龙凯, 白欣鉴, 等. 风电机组高柔塔二阶涡激振动特性研究[J]. 太阳能学报, 2022, 43(2): 498-503.
TAO T, LONG K, BAI X J, et al.Study on second-order vortex-induced vibration characteristics of high-flexible towers of wind turbines[J]. Acta energiae solaris sinica, 2022, 43(2): 498-503.
[20] HU A J, ZHAO J, XIANG L.Output-only modal analysis of wind turbine tower based on vibration response under emergency stop[J]. ISA transactions, 2018, 80: 411-426.
[21] 胡阳, 简睿妮, 房方. 基于FDD-HSM方法的复杂拓扑供热管道动态等值建模[J]. 控制理论与应用, 2022, 39(3): 509-518.
HU Y, JIAN R N, FANG F.Dynamic equivalent modelling of complex topological heating pipeline based on finite difference domain-hybrid semi-mechanism method[J]. Control theory & applications, 2022, 39(3): 509-518.
[22] 胡阳, 王蔚然, 房方, 等. 风电机组运行动态数字孪生建模及半物理仿真[J]. 系统仿真学报, 2024, 36(3): 636-648.
HU Y, WANG W R, FANG F, et al.Dynamic digital twin modelling and Semi-Physical simulation of wind turbine operation[J]. Journal of system simulation, 2024, 36(3): 636-648.
[23] 徐卓飞, 武丽花, 黄卿, 等. 基于深度残差网络的滚动轴承故障诊断方法[J]. 机械设计与研究, 2021, 37(3): 78-83.
XU Z F, WU L H, HUANG Q, et al.Research on the method of fault diagnosis for rolling bearings based on the deep residual network[J]. Machine design & research, 2021, 37(3): 78-83.
[24] 杨爱萍, 李磊磊, 张兵, 等. 基于轻量化渐进式残差网络的图像快速去模糊[J]. 电子与信息学报, 2022, 44(5): 1674-1682.
YANG A P, LI L L, ZHANG B, et al.Fast image deblurring based on the lightweight progressive residual network[J]. Journal of electronics & information technology, 2022, 44(5): 1674-1682.
[25] BAI H, SHI L J, AOUES Y, et al.Estimation of probability distribution of long-term fatigue damage on wind turbine tower using residual neural network[J]. Mechanical systems and signal processing, 2023, 190: 110101.