改进变分模态分解在柴油机故障诊断中的应用
|
摘要
为实现柴油机故障的快速诊断,针对变分模态分解(VMD)的不足,提出一种改进的VMD方法,利用改进自适应遗传算法(IAGA)对VMD的参数进行优化。对IAGA的交叉和变异算子进行改进,将VMD分解结果中的局部极小排列熵值作为整个进化过程中的适应度值,对VMD的模态数K与惩罚因子α进行迭代寻优,得到最优参数组合。利用优化后的VMD对曲轴轴承故障模拟实验振动信号进行分解,根据排列熵值大小选择故障分量并提取能量,利用支持向量机(SVM)对故障模式进行识别。仿真分析和曲轴轴承故障模拟实验验证该方法有效。
To quickly diagnose the faults of a diesel engine, the paper applies the improved adaptive genetic algorithm(IAGA), which has a changed crossover and mutation rates, to optimize the parameters of variational mode decomposition(VMD). With the local minimal entropy decomposed by VMD as the fitness function of IAGA, the new method obtains the optimal parameter combination after an iteration of the modal number and penalty factor, applies the optimized VMD to decompose the simulated vibration signals of crankshaft bearing faults, of which the components rank by the value of permutation entropy, and makes a pattern recognition of fault mode with support vector method(SVM). The simulation analysis and simulated experiment validate this method's effectiveness.
To quickly diagnose the faults of a diesel engine, the paper applies the improved adaptive genetic algorithm(IAGA), which has a changed crossover and mutation rates, to optimize the parameters of variational mode decomposition(VMD). With the local minimal entropy decomposed by VMD as the fitness function of IAGA, the new method obtains the optimal parameter combination after an iteration of the modal number and penalty factor, applies the optimized VMD to decompose the simulated vibration signals of crankshaft bearing faults, of which the components rank by the value of permutation entropy, and makes a pattern recognition of fault mode with support vector method(SVM). The simulation analysis and simulated experiment validate this method's effectiveness.
引文
[1]马新娜,杨绍普.滚动轴承复合故障诊断的自适应方法研究[J].振动与冲击,2016,35(10):145-150.
[2]牟伟杰,石林锁,蔡艳平,等.基于EMD-WVD与LNMF的内燃机故障诊断[J].振动与冲击,2016,35(23):191-196.
[3]贾继德.汽车故障诊断中的信号处理方法[M].北京:化学工业出版社,2015:45-66.
[4]程军圣,杨怡,杨宇.局部特征尺度分解方法及其在齿轮故障诊断中的应用[J].机械工程学报,2012,48(9):64-71.
[5] HUANG N E,SHEN Z,LONG S R. A new view of nonlinear water waves:the Hilbert spectrum[J]. Annu. Rev. Fluid Mech.,1999,31:417-457.
[6] RAI V K,MOHANTY A R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform[J].Mechanical Systems and Signal Processing, 2007,21(6):2607-2615.
[7] WU Z H, HUANG N E. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009(1):1-41.
[8] SMITH J S. The local mean decomposition and its application to EEG percept ion data[J]. Journal of the Royal Society Interface,2005,2(5):443-454.
[9]程军圣,郑近德,杨宇.一种新的非平稳信号分析方法—局部特征尺度分解法[J].振动工程学报,2012,25(2):215-220.
[10]周义,李鸿光.快速自适应经验模态分解方法的基本原理及其性能评估[J].振动与冲击,2016,35(3):14-19.
[11] FREI M G,OSORIO I. Intrinsic time-scale decomposition:time-frequency-energy analysis and real-time filtering of nonstationary signals[J]. Proc. Royal Soc. A,2007,463:321-342.
[12] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing,2013,62(3):531-544.
[13]唐贵基,王晓龙.变分模态分解方法在滚动轴承早期故障诊断中的应用[J].振动工程学报,2016,29(4):638-648.
[14] SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems Man&Cybernetics,2002,24(4):656-667.
[15] SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems Man&Cybernetics,2002,24(4):656-667.
[16] BANDT C, POMPE B. Permutation entropy:a natural complexity measure for time series.[J]. Physical Review Letters,2002,88(17):174102.
[17]冯辅周,饶国强,司爱威,等.排列熵算法研究及其在振动信号突变检测中的应用[J].振动工程学报,2012,25(2):221-224.
[18]贾继德,吴春志,贾翔宇,等.一种适用于发动机振动信号的时频分析方法[J].汽车工程,2017,39(1):97-101.
[2]牟伟杰,石林锁,蔡艳平,等.基于EMD-WVD与LNMF的内燃机故障诊断[J].振动与冲击,2016,35(23):191-196.
[3]贾继德.汽车故障诊断中的信号处理方法[M].北京:化学工业出版社,2015:45-66.
[4]程军圣,杨怡,杨宇.局部特征尺度分解方法及其在齿轮故障诊断中的应用[J].机械工程学报,2012,48(9):64-71.
[5] HUANG N E,SHEN Z,LONG S R. A new view of nonlinear water waves:the Hilbert spectrum[J]. Annu. Rev. Fluid Mech.,1999,31:417-457.
[6] RAI V K,MOHANTY A R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform[J].Mechanical Systems and Signal Processing, 2007,21(6):2607-2615.
[7] WU Z H, HUANG N E. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009(1):1-41.
[8] SMITH J S. The local mean decomposition and its application to EEG percept ion data[J]. Journal of the Royal Society Interface,2005,2(5):443-454.
[9]程军圣,郑近德,杨宇.一种新的非平稳信号分析方法—局部特征尺度分解法[J].振动工程学报,2012,25(2):215-220.
[10]周义,李鸿光.快速自适应经验模态分解方法的基本原理及其性能评估[J].振动与冲击,2016,35(3):14-19.
[11] FREI M G,OSORIO I. Intrinsic time-scale decomposition:time-frequency-energy analysis and real-time filtering of nonstationary signals[J]. Proc. Royal Soc. A,2007,463:321-342.
[12] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing,2013,62(3):531-544.
[13]唐贵基,王晓龙.变分模态分解方法在滚动轴承早期故障诊断中的应用[J].振动工程学报,2016,29(4):638-648.
[14] SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems Man&Cybernetics,2002,24(4):656-667.
[15] SRINIVAS M, PATNAIK L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Transactions on Systems Man&Cybernetics,2002,24(4):656-667.
[16] BANDT C, POMPE B. Permutation entropy:a natural complexity measure for time series.[J]. Physical Review Letters,2002,88(17):174102.
[17]冯辅周,饶国强,司爱威,等.排列熵算法研究及其在振动信号突变检测中的应用[J].振动工程学报,2012,25(2):221-224.
[18]贾继德,吴春志,贾翔宇,等.一种适用于发动机振动信号的时频分析方法[J].汽车工程,2017,39(1):97-101.