多传感器数据融合的风电齿轮箱性能衰退评估
|
摘要
针对风电齿轮箱传动结构复杂、所处工况恶劣,难以提取有效振动信号特征进行性能衰退分析的问题,提出多传感器数据融合的风电齿轮箱性能衰退评估方法。该方法将自适应完全集合经验模态分解(CEEM-DAN)、核主分量分析(KPCA)和Hotelling T2统计量相结合,先对风电齿轮箱全寿命的非线性、非平稳振动信号进行CEEMDAN-KPCA降噪处理,再利用KPCA对降噪后的多组振动信号进行融合分析,提取连续的T2值(C-T2)及其时域特征作为评估指标,建立风电齿轮箱性能衰退模型。实验结果表明,该方法对风电齿轮箱振动信号降噪效果显著,C-T2特征有效解决了多组振动信号特征维数膨胀问题,且C-T2时域特征模型比振动信号时域特征模型能更准确地评估风电齿轮箱性能的衰退过程。
Aiming at the problem that wind turbine generator gearbox was difficult to extract the effective features of vibration signals for performance degradation analysis caused by the complex power driving structure and terrible working conditions,a method based on multi-sensor information fusion was proposed.Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),Kernel Principal Component Analysis(KPCA)and Hotelling's T-squared statistic(T2)were used to achieve the assessment of performance degradation.A CEEMDAN-KPCA based method was applied to denoise and reconstruct the nonlinear and unstable vibration signals of the life cycle;the reconstructed signals were fused with KPCA,and then continuous T2(C-T2)and related time domain features were extracted to establish the performance degradation models.Experimental results showed that the proposed method had a remarkable effect on denoising the vibration signals,and C-T2 was effective to solve the expansion of feature dimension caused by multiple sets of vibration signals.As well as,models of related time domain features by C-T2 could evaluate the performance degradation more accurate than the time-domain features of vibration signal.
Aiming at the problem that wind turbine generator gearbox was difficult to extract the effective features of vibration signals for performance degradation analysis caused by the complex power driving structure and terrible working conditions,a method based on multi-sensor information fusion was proposed.Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),Kernel Principal Component Analysis(KPCA)and Hotelling's T-squared statistic(T2)were used to achieve the assessment of performance degradation.A CEEMDAN-KPCA based method was applied to denoise and reconstruct the nonlinear and unstable vibration signals of the life cycle;the reconstructed signals were fused with KPCA,and then continuous T2(C-T2)and related time domain features were extracted to establish the performance degradation models.Experimental results showed that the proposed method had a remarkable effect on denoising the vibration signals,and C-T2 was effective to solve the expansion of feature dimension caused by multiple sets of vibration signals.As well as,models of related time domain features by C-T2 could evaluate the performance degradation more accurate than the time-domain features of vibration signal.
引文
[1]WANG Hui,LI Xiaolong,WANG Gang,et al.Research on failure of wind turbine gearbox and recent development of its design and manufacturing technologies[J].China Mechanical Engineering,2013,24(11):1542-1549(in Chinese).[王辉,李晓龙,王罡,等.大型风电齿轮箱的失效问题及其设计制造技术的国内外现状分析[J].中国机械工程,2013,24(11):1542-1549.]
[2]LEI Yaguo,LIN Jing,HE Zhengjia,et al.A method based on multi-sensor data fusion for fault detection of planetary gearboxes[J].Sensors,2012,12(2):2005-2017.
[3]JING L,WANG T,ZHAO M,et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox[J].Sensors,2017,17(2):414-428.
[4]FENG Zhipeng,LIANG Ming,ZHANG Yi,et al.Fault diagnosis for wind turbine planetary gearboxes via demodulation analysis based on ensemble empirical mode decomposition and energy separation[J].Renewable Energy,2012,47:112-126.
[5]YANG Jie,CHEN Jie,HONG Rongjing,et al.Research of slew bearing signal de-noising based on multi-scale principal component analysis and EEMD[J].Journal of Central South University:Science and Technology,2016,47(4):1173-1180(in Chinese).[杨杰,陈捷,洪荣晶,等.基于EEMD-多尺度主元分析的回转支承信号降噪方法研究[J].中南大学学报:自然科学版,2016,47(4):1173-1180.]
[6]FENG Yang,HUANG Xiaodiao,HONG Rongjing,et al.Amulti-dimensional data-driven method for large-size slewing bearings performance degradation assessment[J].Journal of Central South University:Science and Technology,2017,48(3):684-693(in Chinese).[封杨,黄筱调,洪荣晶,等.基于数据驱动的回转支承性能退化评估方法[J].中南大学学报:自然科学版,2017,48(3):684-693.]
[7]YEH J R,SHIEH J S,HUANG N E.Complementary ensemble empirical mode decomposition:a novel noise enhanced data analysis method[J].Advances in Adaptive Data Analysis,2010,2(2):135-156.
[8]NGUYEN V H,GOLINVAL J C.Fault detection based on kernel principal component analysis[J].Engineering Structures,2010,32(11):3683-3691.
[9]LIU Zhiwen,GUO Wei,TANG Zhangchun,et al.Multi-sensor data fusion using a relevance vector machine based on an ant colony for gearbox fault detection[J].Sensors,2015,15(9):21857-21875.
[10]YANG Zhiling,YAO Zhiye,WANG Ruiming.Study on fault diagnosis of gearbox based on HMM[J].Acta Energiae Solaris Sinica,2017,38(9):2574-2581(in Chinese).[杨志凌,姚治业,王瑞明.基于HMM的风电机组齿轮箱故障诊断研究[J].太阳能学报,2017,38(9):2574-2581.]
[11]MARQUEZ F P G,TOBIAS A M,PEREZ J M P,et al.Condition monitoring of wind turbines:techniques and methods[J].Renewable Energy,2012,46(5):169-178.
[12]KEOGH E,MUEEN A.Curse of dimensionality[M]//Encyclopedia of Machine Learning.Berlin,Germany:SpringerVerlag,2011:257-258.
[13]SHE Bo,TIAN Fuqing,TANG Jian,et al.Fault diagnosis of rolling bearing based on adaptive LTSA algorithm[J].Journal of Huazhong University of Science and Technology:Natural Science Edition,2017,45(1):91-96(in Chinese).[佘博,田福庆,汤健,等.基于自适应LTSA算法的滚动轴承故障诊断[J].华中科技大学学报:自然科学版,2017,45(1):91-96.]
[14]TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//Proceedings of 2011IEEE International Conference on Acoustics,Speech and Signal Processing.Washington,D.C.,USA:IEEE,2011:4144-4147.
[15]GAO Zingyong,LIANG Yinlin,GAO Jianmin,et al.State monitoring of complex electormechanical system based on integrated entropy of KPCA[J].Computer Integrated Manufacturing Systems,2015,21(5):1327-1333(in Chinese).[高智勇,梁银林,高建民,等.基于集成熵KPCA的复杂机电系统状态监测方法[J].计算机集成制造系统,2015,21(5):1327-1333.]
[16]SHAO R,HU W,WANG Y,et al.The fault feature extraction and classification of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform[J].Measurement,2014,54(6):118-132.
[17]WANG Yuanhang,DENG Chao,HU Xianghong,et al.Failure time estimation for mechanical device based on performance degradation[J].Computer Integrated Manufacturing Systems,2015,21(8):2147-2157(in Chinese).[王远航,邓超,胡湘洪,等.基于性能退化的机械设备寿命预测[J].计算机集成制造系统,2015,21(8):2147-2157.]
[18]Standardization Administration of the People's Republic of China.GB/T 19073-2008.Gearbox of wind turbine generator system[S].Beijing:Standards Press of China,2008(in Chinese).[中国国家标准化管理委员会.GB/T 19073-2008.风力发电机组齿轮箱[S].北京:中国标准出版社,2008.]
[19]LLOYD G.Rules and guidelines industrial services part 4-guideline for the certification of condition monitoring systems for wind turbines[EB/OL].[2017-07-12].https://www.dnvgl.com/rules-standards/gl-rules-guidelines.html,2013.
[2]LEI Yaguo,LIN Jing,HE Zhengjia,et al.A method based on multi-sensor data fusion for fault detection of planetary gearboxes[J].Sensors,2012,12(2):2005-2017.
[3]JING L,WANG T,ZHAO M,et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox[J].Sensors,2017,17(2):414-428.
[4]FENG Zhipeng,LIANG Ming,ZHANG Yi,et al.Fault diagnosis for wind turbine planetary gearboxes via demodulation analysis based on ensemble empirical mode decomposition and energy separation[J].Renewable Energy,2012,47:112-126.
[5]YANG Jie,CHEN Jie,HONG Rongjing,et al.Research of slew bearing signal de-noising based on multi-scale principal component analysis and EEMD[J].Journal of Central South University:Science and Technology,2016,47(4):1173-1180(in Chinese).[杨杰,陈捷,洪荣晶,等.基于EEMD-多尺度主元分析的回转支承信号降噪方法研究[J].中南大学学报:自然科学版,2016,47(4):1173-1180.]
[6]FENG Yang,HUANG Xiaodiao,HONG Rongjing,et al.Amulti-dimensional data-driven method for large-size slewing bearings performance degradation assessment[J].Journal of Central South University:Science and Technology,2017,48(3):684-693(in Chinese).[封杨,黄筱调,洪荣晶,等.基于数据驱动的回转支承性能退化评估方法[J].中南大学学报:自然科学版,2017,48(3):684-693.]
[7]YEH J R,SHIEH J S,HUANG N E.Complementary ensemble empirical mode decomposition:a novel noise enhanced data analysis method[J].Advances in Adaptive Data Analysis,2010,2(2):135-156.
[8]NGUYEN V H,GOLINVAL J C.Fault detection based on kernel principal component analysis[J].Engineering Structures,2010,32(11):3683-3691.
[9]LIU Zhiwen,GUO Wei,TANG Zhangchun,et al.Multi-sensor data fusion using a relevance vector machine based on an ant colony for gearbox fault detection[J].Sensors,2015,15(9):21857-21875.
[10]YANG Zhiling,YAO Zhiye,WANG Ruiming.Study on fault diagnosis of gearbox based on HMM[J].Acta Energiae Solaris Sinica,2017,38(9):2574-2581(in Chinese).[杨志凌,姚治业,王瑞明.基于HMM的风电机组齿轮箱故障诊断研究[J].太阳能学报,2017,38(9):2574-2581.]
[11]MARQUEZ F P G,TOBIAS A M,PEREZ J M P,et al.Condition monitoring of wind turbines:techniques and methods[J].Renewable Energy,2012,46(5):169-178.
[12]KEOGH E,MUEEN A.Curse of dimensionality[M]//Encyclopedia of Machine Learning.Berlin,Germany:SpringerVerlag,2011:257-258.
[13]SHE Bo,TIAN Fuqing,TANG Jian,et al.Fault diagnosis of rolling bearing based on adaptive LTSA algorithm[J].Journal of Huazhong University of Science and Technology:Natural Science Edition,2017,45(1):91-96(in Chinese).[佘博,田福庆,汤健,等.基于自适应LTSA算法的滚动轴承故障诊断[J].华中科技大学学报:自然科学版,2017,45(1):91-96.]
[14]TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//Proceedings of 2011IEEE International Conference on Acoustics,Speech and Signal Processing.Washington,D.C.,USA:IEEE,2011:4144-4147.
[15]GAO Zingyong,LIANG Yinlin,GAO Jianmin,et al.State monitoring of complex electormechanical system based on integrated entropy of KPCA[J].Computer Integrated Manufacturing Systems,2015,21(5):1327-1333(in Chinese).[高智勇,梁银林,高建民,等.基于集成熵KPCA的复杂机电系统状态监测方法[J].计算机集成制造系统,2015,21(5):1327-1333.]
[16]SHAO R,HU W,WANG Y,et al.The fault feature extraction and classification of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform[J].Measurement,2014,54(6):118-132.
[17]WANG Yuanhang,DENG Chao,HU Xianghong,et al.Failure time estimation for mechanical device based on performance degradation[J].Computer Integrated Manufacturing Systems,2015,21(8):2147-2157(in Chinese).[王远航,邓超,胡湘洪,等.基于性能退化的机械设备寿命预测[J].计算机集成制造系统,2015,21(8):2147-2157.]
[18]Standardization Administration of the People's Republic of China.GB/T 19073-2008.Gearbox of wind turbine generator system[S].Beijing:Standards Press of China,2008(in Chinese).[中国国家标准化管理委员会.GB/T 19073-2008.风力发电机组齿轮箱[S].北京:中国标准出版社,2008.]
[19]LLOYD G.Rules and guidelines industrial services part 4-guideline for the certification of condition monitoring systems for wind turbines[EB/OL].[2017-07-12].https://www.dnvgl.com/rules-standards/gl-rules-guidelines.html,2013.