一种带变异算子的粒子群优化粒子滤波降噪算法
|
摘要
提出一种面向机械故障诊断非线性振动信号特征提取及实时滤波降噪的新型粒子群优化粒子滤波(NPSO-PF)算法,是基于带变异算子的粒子群优化粒子滤波算法。应用变异控制函数和操作算子,通过改善粒子滤波(PF)算法粒子贫乏、利用率不高等问题,加速粒子集收敛,减少整个算法运行的时间。仿真结果通过与PF算法和PSO-PF算法相比,论证了提出的NPSO-PF算法具有更低的均方根误差、更短的运行时间、更高的信噪比和更稳定的滤波性能。
A novel particle swarm optimization particle filter(NPSO-PF)algorithm was proposed for the realtime filtering noise reduction of nonlinear vibration signals and feature extraction in fault diagnosis of mechanical system. The particle filter(PF)algorithm was optimized by the particle swarm with the mutation operator,by use of the mutation control function and operator to improve the problems of particle poverty and low utilization rate. The convergence of the particle sets is accelerated,and the running time of the proposed algorithm was reduced. By the comparisons of PF,PSO-PF and NPSO-PF algorithms,the simulation results show that the proposed NPSO-PF algorithm has the advantages of being less root mean square errors,shorter running time,higher signal/noise ratio and with more stable filtering performance.
A novel particle swarm optimization particle filter(NPSO-PF)algorithm was proposed for the realtime filtering noise reduction of nonlinear vibration signals and feature extraction in fault diagnosis of mechanical system. The particle filter(PF)algorithm was optimized by the particle swarm with the mutation operator,by use of the mutation control function and operator to improve the problems of particle poverty and low utilization rate. The convergence of the particle sets is accelerated,and the running time of the proposed algorithm was reduced. By the comparisons of PF,PSO-PF and NPSO-PF algorithms,the simulation results show that the proposed NPSO-PF algorithm has the advantages of being less root mean square errors,shorter running time,higher signal/noise ratio and with more stable filtering performance.
引文
[1]刘天宇,吴金斌,周世健.附加斜率绝对值法的模态相关EMD-ICA滤波降噪算法及GPS应用研究[J].江西科学,2017(4):509-515.
[2]黄名钿,高伟.粒子群优化改进小波阈值函数的去噪研究[J].软件,2017(9):182-186.
[3]ANANTH C,VIVEK T,SELVAKUMAR S,et al.Impulse noise removal using improved particle swarm optimization[J].Social Science Electronic Publishing,2017(3):366-370.
[4]张荣光,胡晓辉,宗永胜,等.禁忌离散粒子群优化的粗糙集属性约简算法[J].小型微型计算机系统,2017(8):1840-1844.
[5]MALLICK S,KAK R,MANDAL D,et al.Optimal sizing of CMOS analog circuits using gravitational search algorithm with particle swarm optimization[J].International Journal of Machine Learning and Cybernetics,2017(8):309-331.
[6]张威虎,郭明香,贺元恺,等.一种改进的蝴蝶算法优化粒子滤波算法[J].西安科技大学学报,2019(1):119-123.
[7]陆湛.基于变分贝叶斯学习的粒子滤波研究[D].广州:华南理工大学,2017.
[8]HAVSNGI R.Joint parameter and state estimation based on marginal particle filter and particle swarm optimization[J].Circuits,Systems,and Signal Processing,2018(37):3558-3575.
[9]王尔申,庞涛,曲萍萍,等.基于混沌的改进粒子群优化粒子滤波算法[J].北京航空航天大学学报,2016,42(5):885-890.
[10]TANG G,WEI B,WU D,et al.The optimal wavelengths for light absorption spectroscopy measurements based on genetic algorithm-particle swarm optimization[J].Journal of Applied Spectroscopy,2018,85(1):109-118.
[11]韩雪,程奇峰,赵婷婷,等.基于粒子滤波重采样与变异操作的改进粒子群算法[J].计算机应用,2016,36(4):1008-1014.
[12]杨柳.基于RBF-PF和粒子群优化小波神经网络在齿轮箱故障诊断中的研究[D].武汉:武汉工程大学,2016.
[13]袁开宇,储珺,冷四军,等.基于特征融合的粒子群优化粒子滤波跟踪方法[J].南昌航空大学学报(自然科学版),2015(1):33-41.
[14]LIU Z,LI H,ZHU P.Diversity enhanced particle swarm optimization algorithm and its application in vehicle lightweight design[J].Journal of Mechanical Science and Technology,2019,33(2):695-709.
[15]余仁波,赵修平,孟凡磊.一种带变异算子的PSO算法[J].舰船电子工程,2016,36(10):26-29.
[2]黄名钿,高伟.粒子群优化改进小波阈值函数的去噪研究[J].软件,2017(9):182-186.
[3]ANANTH C,VIVEK T,SELVAKUMAR S,et al.Impulse noise removal using improved particle swarm optimization[J].Social Science Electronic Publishing,2017(3):366-370.
[4]张荣光,胡晓辉,宗永胜,等.禁忌离散粒子群优化的粗糙集属性约简算法[J].小型微型计算机系统,2017(8):1840-1844.
[5]MALLICK S,KAK R,MANDAL D,et al.Optimal sizing of CMOS analog circuits using gravitational search algorithm with particle swarm optimization[J].International Journal of Machine Learning and Cybernetics,2017(8):309-331.
[6]张威虎,郭明香,贺元恺,等.一种改进的蝴蝶算法优化粒子滤波算法[J].西安科技大学学报,2019(1):119-123.
[7]陆湛.基于变分贝叶斯学习的粒子滤波研究[D].广州:华南理工大学,2017.
[8]HAVSNGI R.Joint parameter and state estimation based on marginal particle filter and particle swarm optimization[J].Circuits,Systems,and Signal Processing,2018(37):3558-3575.
[9]王尔申,庞涛,曲萍萍,等.基于混沌的改进粒子群优化粒子滤波算法[J].北京航空航天大学学报,2016,42(5):885-890.
[10]TANG G,WEI B,WU D,et al.The optimal wavelengths for light absorption spectroscopy measurements based on genetic algorithm-particle swarm optimization[J].Journal of Applied Spectroscopy,2018,85(1):109-118.
[11]韩雪,程奇峰,赵婷婷,等.基于粒子滤波重采样与变异操作的改进粒子群算法[J].计算机应用,2016,36(4):1008-1014.
[12]杨柳.基于RBF-PF和粒子群优化小波神经网络在齿轮箱故障诊断中的研究[D].武汉:武汉工程大学,2016.
[13]袁开宇,储珺,冷四军,等.基于特征融合的粒子群优化粒子滤波跟踪方法[J].南昌航空大学学报(自然科学版),2015(1):33-41.
[14]LIU Z,LI H,ZHU P.Diversity enhanced particle swarm optimization algorithm and its application in vehicle lightweight design[J].Journal of Mechanical Science and Technology,2019,33(2):695-709.
[15]余仁波,赵修平,孟凡磊.一种带变异算子的PSO算法[J].舰船电子工程,2016,36(10):26-29.