Abstract：To diagnose faults in of a hydro-turbine unit accurately and precisely, a fault diagnosis model for vibration signal of hydropower units is built based on the EMD, multi-fractal spectrum and improved BP neural network in this paper. A series of vibration signals under various conditions, such as normal rotor system, oil film whirl in bearings, rotor imbalance, and rotor misalignment etc. are acquired from a hydro-turbine unit. At first, the EMD components of these vibration signals are obtained through empirical mode decomposition. Then the waveform samples are extracted by using EMD coefficients according to the signal waveform tendency curves. Thirdly, the eigenvalues alpha(q)and f(q), are extracted from the waveform samples by means of multifractal spectrum algorithm. Finally, the eigenvectors are input into a BP network for classification and recognition. The trained neural network is applied to all the samples and the test accuracy is 100%. The results show that the multi-fractal spectrum not only is feasible for fault diagnosis of hydropower unit but also can improve the precision of diagnosis and enhance human-computer interaction.
薛延刚. 基于EMD和Multi-fractal spectrum的BP水机故障诊断[J]. 排灌机械工程学报, 2016, 34(5): 455-460.
XUE Yan′gang. An investigation into fault diagnosis of hydro-turbine unit based on EMD multifractal spectrum. Journal of Drainage and Irrigation Machinery Engin, 2016, 34(5): 455-460.
[1]郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版),2013,34(1):49-53. HAO Yong,SUN Xudong,WANG Hao.Spectral quantitative model optimization by modified successive projection algorithm[J]. Journal of Jiangsu University(natural science edition),2013,34(1): 49-53.(in Chinese)[2]刘昌领,陈建义,李清平,等.基于ANSYS的六缸压缩机曲轴模态分析及谐响应分析[J].流体机械,2012,40(8):17-21. LIU Changling,CHEN Jianyi,LI Qingping,et al. Modal and harmonic response analysis of crankshaft of a six cylinders compressor by ANSYS[J].Fluid machinery,2012,40(8):17-21.(in Chinese)[3]钟明寿,龙源,谢全民,等.基于分形盒维数和多重分形的爆破地震波信号分析[J].振动与冲击,2010,29(1):7-11. ZHONG Mingshou,LONG Yuan,XIE Quanmin,et al. Signal analysis for blasting seismic wave based on fractal box-dimension and multi-fractal[J].Journal of vibration and shock,2010,29(1):7-11.(in Chinese)[4]WANG Yukui, LI Hongru, YE Peng. Fault feature extraction of hydraulic pump based on CNC de-noising and HHT[J]. Journal of failure analysis and prevention, 2015, 15(1):139-151.[5]薛延刚,王瀚.基于HHT的水轮机空化信号研究 [J].水力发电学报,2015,34(5):147-151. XUE Yangang,WANG Han. Investigation on turbine cavitation signals analysis based on Hilbert-Huang transform[J].Journal of hydroelectric engineering,2015,34(5):147-151.(in Chinese)[6]ZHU Xiaojun, HU Jingxian,MA Xiao. Coherence research of audio-visual cross-modal based on HHT[J]. Journal of multimedia, 2014,9(2):230-237.[7]ARTHUR H, GEISTHOFF U, GOSSAGE J R. Executive summary of the 11th HHT international scientific conference[J]. Angiogenesis, 2015,18(4):511-524.[8]RAJA J E, KIONG L C, SOONG L W. Hilbert-Huang transform-based emitted sound signal analysis for tool flank wear monitoring[J]. Arabian journal for science & engineering, 2013, 38(8):2219-2226.[9]LYUBUSHIN A A, KALÁB Z, LEDNICKÁ M, et al. Discrimination of earthquakes and explosions using multi-fractal singularity spectrums properties[J]. Journal of seismology, 2013, 17(3):975-983.[10]GAO Lihao,FU Zuntao.Multi-fractal behaviors of relative humidity over China[J].Atmospheric and oceanic science letters,2015, 6(2):74-78.[11]LYUBUSHIN A. How soon would the next mega-earthquake occur in Japan?[J]. Natural Science, 2013, 5(8A):1-7.[12]DONG Yufeng, JIN Guodong. A multifractal model for linking Lagrangian and Eulerian velocity structure functions[J]. Acta mechanica sinica,2014, 30(4):480-484.[13]李辉,白亮,罗兴锜,等.基于模糊聚类的水电机组轴心轨迹多重分形特征识别[J],水力发电学报,2012,31(4):238-242. LI Hui,BAI Liang,LUO Xingqi,et al. Multi-fractal feature recognition for shaft centerline orbit of hydropower units based on fuzzy clustering[J]. Journal of hydroelectric engineering, 2012,31(4):238-242.(in Chinese)[14]郭鹏程,罗兴锜,王勇劲,等.基于粒子群算法与改进BP神经网络的水电机组轴心轨迹识别[J].中国电机工程学报,2011,31(8):93-97. GUO Pengcheng, LUO Xingqi,WANG Yongjing, et al. Identification of shaft centerline orbit for hydropower units based on particle swarm optimization and improved BP neural network[J]. Proceedings of the CSEE,2011, 31(8):93-97.(in Chinese)[15]周磊.基于改进神经网络的SRM转子位置预测[J].信息技术,2015(9):151-154. ZHOU Lei. The improved RBF-BP neural network based on Adaboost algorithm for rotor position prediction of switched relutance motor[J]. Information technology,2015(9):151-154.(in Chinese)[16]WOZNIAK M, ONOFRI F R A, BARBOSA S, et al. Comparison of methods to derive morphological parameters of multi-fractal samples of particle aggregates from TEM images[J]. Journal of aerosol science, 2012, 47(3):12-26.
