基于分形和概率神经网络的水电机组故障诊断
|
摘要
水电机组振动信号属于非线性、非平稳信号,在不同尺度下呈现一定的相似性,是典型的分形信号。本文运用多重分形方法分析机组振动信号,提取信号的广义维数谱特征,并应用人工鱼群算法优化的概率神经网络进行故障诊断。诊断实例表明,多重分形和概率神经网络结合,能够准确辨别故障类型。与BP和RBF网络相比,该方法诊断识别率更高,速度更快,为机组运行维护人员提供更为可靠的参考依据。
Vibration signals from a hydropower unit are non-linear and non-stationary, but they are similar in different scales and typical of fractal features. This paper reports a multi-fractal method of fault diagnosis for hydropower units, analyzing the vibration signals, extracting their generalized dimensional spectral features, and diagnosing the fault with a probabilistic neural network optimized by the artificial fish swarm algorithm. A case study shows that this method, through combination of multi-fractal and probabilistic neural network, can accurately distinguish fault types. Compared with a BP or RBF network,it achieves a higher diagnostic recognition rate and faster speed, thus providing a more reliable tool for unit operation and maintenance personnel.
Vibration signals from a hydropower unit are non-linear and non-stationary, but they are similar in different scales and typical of fractal features. This paper reports a multi-fractal method of fault diagnosis for hydropower units, analyzing the vibration signals, extracting their generalized dimensional spectral features, and diagnosing the fault with a probabilistic neural network optimized by the artificial fish swarm algorithm. A case study shows that this method, through combination of multi-fractal and probabilistic neural network, can accurately distinguish fault types. Compared with a BP or RBF network,it achieves a higher diagnostic recognition rate and faster speed, thus providing a more reliable tool for unit operation and maintenance personnel.
引文
[1]郭庆丰,王成栋,刘佩森.时域指标和峭度分析法在滚动轴承故障诊断中的应用[J].机械传动,2016,40(11):172-175.GUO Qingfeng,WANG Chengdong,LIU Peisen.Application of time domain index and kurtosis analysis method in the fault diagnosis of rolling bearing[J].Journal of Mechanical Transmission,2016,40(11):172-175.(in Chinese)
[2]陈子建,王振涛,许杰彬.基于幅值域参数的船舶液压系统故障诊断研究[J].船舶工程,2016,38(S2):101-104.CHEN Zijian,WANG Zhentao,XU Jielin.Study on fault diagnosis of ship hydraulic system based on amplitude domain parameters[J].Ship Engineering,2016,38(S2):101-104.(in Chinese)
[3]陈东华,张凤雏.基于傅里叶变换的同步交流发电机旋转整流器故障诊断[J].机械制造与自动化,2017,46(4):205-208.CHEN Donghua,ZHANG Fengchu.Fault diagnosis of synchronous AC generator rotating rectifier based on Fourier transform[J].Machine Building&Automation,2017,46(4):205-208.(in Chinese)
[4]胡振邦,许睦旬,姜歌东,等.基于小波降噪和短时傅里叶变换的主轴突加不平衡非平稳信号分析[J].振动与冲击,2014,33(5):20-23.HU Zhenbang,XU Muxun,JIANG Gedong,et al.Analysis of non-stationary signal of a sudden unbalanced spindle based on wavelet noise reduction and short-time Fourier transformation[J].Journal of Vibration and Shock,2014,33(5):20-23.(in Chinese)
[5]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究[J].中国电机工程学报,2006,26(24):164-168.PENG Wenji,LUO Xingqi.Research on vibrant fault diagnosis of hydro-turbine generating unit based on wavelet packet analysis and support vector machine[J].Proceedings of the CSEE,2006,26(24):164-168.(in Chinese)
[6]安周鹏,肖志怀,陈宇凡,等.小波包能量谱和功率谱分析在水电机组故障诊断中的应用[J].水力发电学报,2015,34(6):182-190.AN Zhoupeng,XIAO Zhihuai,CHEN Yufan,et al.Analysis of wavelet packet energy spectrum and power spectrum and its application to fault diagnosis of hydropower units[J].Journal of Hydroelectric Engineering,2015,34(6):182-190.(in Chinese)
[7]李辉,王瀚,白亮,等.改进希尔伯特-黄变换方法提取水轮机动态特征信息[J].中国电机工程学报,2011,31(2):78-84.LI Hui,WANG Han,BAI Liang,et al.Dynamic characteristic information extraction of hydro turbine based on improved hilbert-huang transform method[J].Proceedings of the CSEE,2011,31(2):78-84.(in Chinese)
[8]徐玉秀,钟建军,刘薇,等.基于广义分形的旋转机械故障诊断识别与分类[J].辽宁工程技术大学学报,2005,24(4):591-594.XU Yuxiu,ZHONG Jianjun,LIU Wei,et al.Application of multifactal theory to coupling fault diagnosis[J].Journal of Liaoning Technical University,2005,24(4):591-594.(in Chinese)
[9]褚青青,肖涵,吕勇,等.基于多重分形理论与神经网络的齿轮故障诊断[J].振动与冲击,2015,34(21):15-18.CHU Qingqing,XIAO Han,LV Yong,et al.Gear fault diagnosis based on multifractal theory and neural network[J].Journal of Vibration and Shock,2015,34(21):15-18.(in Chinese)
[10]郭鹏程,孙龙刚,李辉,等.基于多重分形谱和改进BP神经网络的水电机组振动故障诊断研究[J].水力发电学报,2014,33(3):299-305.GUO Pengcheng,SUN Longgang,LI Hui,et al.Vibration fault diagnosis of hydropower unit based on multi-fractal spectrum and improved BP neural network[J].Journal of Hydroelectric Engineering,2014,33(3):299-305.(in Chinese)
[11]YU Y,LI B L,SHANG J S,et al.The application of vibration signal multi-fractal in fault diagnosis[C]//Second International Conference on Future Networks.Sanya:IEEE Computer Society,2010:164-167.
[12]LI M,MA W X,LUI X J.Investigation of rolling bearing fault diagnosis based on multi-fractal and general fractal dimension[C]//Second Intelligent Computation Technology and Automation.Zhangjiajie:IEEE Computer Society,2009:545-548.
[13]唐静远,师奕兵,周龙甫,等.非线性模拟电路故障诊断的小波领袖多重分形分析方法[J].控制与决策,2010,25(4):605-609.TANG Jingyuan,SHI Yibing,ZHOU Longfu,et al.Nonlinear analog circuit fault diagnosis using wavelet leaders multi-fractal analysis method[J].Control and Decision,2010,25(4):605-609.(in Chinese)
[14]贾勇,何正友,赵静.基于小波熵和概率神经网络的配电网电压暂降源识别方法[J].电网技术,2009,33(16):63-69.JIA Yong,HE Zhengyou,ZHAO Jing.A method to identify voltage sag sources in distribution network based on wavelet entropy and probability neural network[J].Power System Technology,2009,33(16):63-69.(in Chinese)
[15]苑津莎,尚海昆.基于主成分分析和概率神经网络的变压器局部放电模式识别[J].电力自动化设备,2013,33(6):27-31.YUAN Jinsha,SHANG Haikun.Pattern recognition based on principal component analysis and probabilistic neural networks for partial discharge of power transformer[J].Electric Power Automation Equipment,2013,33(6):27-31.(in Chinese)
[16]XU C M,ZHANG H,HUANG C H,et al.Study of fault diagnosis based on probabilistic neural network for turbine generator unit[C]//2010 International Conference on Artificial Intelligence and Computational Intelligence.Sanya:IEEE Computer Society,2010:275-279.
[17]LI S,LI X Y,WANG W X,et al.Fault diagnosis of transformer based on probabilistic neural network[C]//2011 Fourth International Conference on Intelligent Computation Technology and Automation.Washington,DC,USA:IEEE Computer Society,2011:128-131.
[18]MANDELBROT B B.Fractals:form,chance,and dimension[M].W.H.Freeman,1977.
[19]GRASSBERGER P.Generalized dimensions of strange attractors[J].Physics Letters A,1983,97(6):227-230.
[20]PEYRIèRE J.Multifractal measures[M]//Probabilistic and Stochastic Methods in Analysis,with Applications.Springer Netherlands,1992.
[21]SPECHT D F.Probabilistic neural networks[J].Neural Networks,1990,3(1):109-118.
[22]杨凌霄,朱亚丽.基于概率神经网络的高压断路器故障诊断[J].电力系统保护与控制,2015,43(10):62-67.YANG Lingxiao,ZHU Yali.High voltage circuit breaker fault diagnosis of probabilistic neural network[J].Power System Protection and Control,2015,43(10):62-67.(in Chinese)
[23]李晓磊,钱积新.人工鱼群算法:自下而上的寻优模式[C]//过程系统工程2001年会论文集,2001.LI Xiaolei,QIAN Jixin.Artificial fish swarm algorithm:bottom-up optimization model[C]//Proceedings of the2001 Annual Conference on Process Systems Engineering,2001.(in Chinese)
[24]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践,2002,22(11):32-38.LI Xiaolei,SHAO Zhijiang,QIAN Jixin.An optimizing method based on autonomous animates:fish-swarm algorithm[J].System Engineering Theory and Practice,2002,22(11):32-38.(in Chinese)
[25]李晓磊.一种新型的智能优化方法:人工鱼群算法[D].杭州:浙江大学,2003.LI Xiaolei.A new intelligent optimization method:Artificial fish school algorithm[D].Hangzhou:Zhejiang University,2003.(in Chinese)
[2]陈子建,王振涛,许杰彬.基于幅值域参数的船舶液压系统故障诊断研究[J].船舶工程,2016,38(S2):101-104.CHEN Zijian,WANG Zhentao,XU Jielin.Study on fault diagnosis of ship hydraulic system based on amplitude domain parameters[J].Ship Engineering,2016,38(S2):101-104.(in Chinese)
[3]陈东华,张凤雏.基于傅里叶变换的同步交流发电机旋转整流器故障诊断[J].机械制造与自动化,2017,46(4):205-208.CHEN Donghua,ZHANG Fengchu.Fault diagnosis of synchronous AC generator rotating rectifier based on Fourier transform[J].Machine Building&Automation,2017,46(4):205-208.(in Chinese)
[4]胡振邦,许睦旬,姜歌东,等.基于小波降噪和短时傅里叶变换的主轴突加不平衡非平稳信号分析[J].振动与冲击,2014,33(5):20-23.HU Zhenbang,XU Muxun,JIANG Gedong,et al.Analysis of non-stationary signal of a sudden unbalanced spindle based on wavelet noise reduction and short-time Fourier transformation[J].Journal of Vibration and Shock,2014,33(5):20-23.(in Chinese)
[5]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究[J].中国电机工程学报,2006,26(24):164-168.PENG Wenji,LUO Xingqi.Research on vibrant fault diagnosis of hydro-turbine generating unit based on wavelet packet analysis and support vector machine[J].Proceedings of the CSEE,2006,26(24):164-168.(in Chinese)
[6]安周鹏,肖志怀,陈宇凡,等.小波包能量谱和功率谱分析在水电机组故障诊断中的应用[J].水力发电学报,2015,34(6):182-190.AN Zhoupeng,XIAO Zhihuai,CHEN Yufan,et al.Analysis of wavelet packet energy spectrum and power spectrum and its application to fault diagnosis of hydropower units[J].Journal of Hydroelectric Engineering,2015,34(6):182-190.(in Chinese)
[7]李辉,王瀚,白亮,等.改进希尔伯特-黄变换方法提取水轮机动态特征信息[J].中国电机工程学报,2011,31(2):78-84.LI Hui,WANG Han,BAI Liang,et al.Dynamic characteristic information extraction of hydro turbine based on improved hilbert-huang transform method[J].Proceedings of the CSEE,2011,31(2):78-84.(in Chinese)
[8]徐玉秀,钟建军,刘薇,等.基于广义分形的旋转机械故障诊断识别与分类[J].辽宁工程技术大学学报,2005,24(4):591-594.XU Yuxiu,ZHONG Jianjun,LIU Wei,et al.Application of multifactal theory to coupling fault diagnosis[J].Journal of Liaoning Technical University,2005,24(4):591-594.(in Chinese)
[9]褚青青,肖涵,吕勇,等.基于多重分形理论与神经网络的齿轮故障诊断[J].振动与冲击,2015,34(21):15-18.CHU Qingqing,XIAO Han,LV Yong,et al.Gear fault diagnosis based on multifractal theory and neural network[J].Journal of Vibration and Shock,2015,34(21):15-18.(in Chinese)
[10]郭鹏程,孙龙刚,李辉,等.基于多重分形谱和改进BP神经网络的水电机组振动故障诊断研究[J].水力发电学报,2014,33(3):299-305.GUO Pengcheng,SUN Longgang,LI Hui,et al.Vibration fault diagnosis of hydropower unit based on multi-fractal spectrum and improved BP neural network[J].Journal of Hydroelectric Engineering,2014,33(3):299-305.(in Chinese)
[11]YU Y,LI B L,SHANG J S,et al.The application of vibration signal multi-fractal in fault diagnosis[C]//Second International Conference on Future Networks.Sanya:IEEE Computer Society,2010:164-167.
[12]LI M,MA W X,LUI X J.Investigation of rolling bearing fault diagnosis based on multi-fractal and general fractal dimension[C]//Second Intelligent Computation Technology and Automation.Zhangjiajie:IEEE Computer Society,2009:545-548.
[13]唐静远,师奕兵,周龙甫,等.非线性模拟电路故障诊断的小波领袖多重分形分析方法[J].控制与决策,2010,25(4):605-609.TANG Jingyuan,SHI Yibing,ZHOU Longfu,et al.Nonlinear analog circuit fault diagnosis using wavelet leaders multi-fractal analysis method[J].Control and Decision,2010,25(4):605-609.(in Chinese)
[14]贾勇,何正友,赵静.基于小波熵和概率神经网络的配电网电压暂降源识别方法[J].电网技术,2009,33(16):63-69.JIA Yong,HE Zhengyou,ZHAO Jing.A method to identify voltage sag sources in distribution network based on wavelet entropy and probability neural network[J].Power System Technology,2009,33(16):63-69.(in Chinese)
[15]苑津莎,尚海昆.基于主成分分析和概率神经网络的变压器局部放电模式识别[J].电力自动化设备,2013,33(6):27-31.YUAN Jinsha,SHANG Haikun.Pattern recognition based on principal component analysis and probabilistic neural networks for partial discharge of power transformer[J].Electric Power Automation Equipment,2013,33(6):27-31.(in Chinese)
[16]XU C M,ZHANG H,HUANG C H,et al.Study of fault diagnosis based on probabilistic neural network for turbine generator unit[C]//2010 International Conference on Artificial Intelligence and Computational Intelligence.Sanya:IEEE Computer Society,2010:275-279.
[17]LI S,LI X Y,WANG W X,et al.Fault diagnosis of transformer based on probabilistic neural network[C]//2011 Fourth International Conference on Intelligent Computation Technology and Automation.Washington,DC,USA:IEEE Computer Society,2011:128-131.
[18]MANDELBROT B B.Fractals:form,chance,and dimension[M].W.H.Freeman,1977.
[19]GRASSBERGER P.Generalized dimensions of strange attractors[J].Physics Letters A,1983,97(6):227-230.
[20]PEYRIèRE J.Multifractal measures[M]//Probabilistic and Stochastic Methods in Analysis,with Applications.Springer Netherlands,1992.
[21]SPECHT D F.Probabilistic neural networks[J].Neural Networks,1990,3(1):109-118.
[22]杨凌霄,朱亚丽.基于概率神经网络的高压断路器故障诊断[J].电力系统保护与控制,2015,43(10):62-67.YANG Lingxiao,ZHU Yali.High voltage circuit breaker fault diagnosis of probabilistic neural network[J].Power System Protection and Control,2015,43(10):62-67.(in Chinese)
[23]李晓磊,钱积新.人工鱼群算法:自下而上的寻优模式[C]//过程系统工程2001年会论文集,2001.LI Xiaolei,QIAN Jixin.Artificial fish swarm algorithm:bottom-up optimization model[C]//Proceedings of the2001 Annual Conference on Process Systems Engineering,2001.(in Chinese)
[24]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践,2002,22(11):32-38.LI Xiaolei,SHAO Zhijiang,QIAN Jixin.An optimizing method based on autonomous animates:fish-swarm algorithm[J].System Engineering Theory and Practice,2002,22(11):32-38.(in Chinese)
[25]李晓磊.一种新型的智能优化方法:人工鱼群算法[D].杭州:浙江大学,2003.LI Xiaolei.A new intelligent optimization method:Artificial fish school algorithm[D].Hangzhou:Zhejiang University,2003.(in Chinese)