基于MPSO-BP神经网络的PSD误差补偿
|
摘要
针对光电位置传感器(PSD)测试系统的输出非严格线性的标定问题,提出了改进的粒子群优化BP神经网络的非线性补偿方法。采用自适应调整学习因子构造MPSO-BP神经网络分类器,建立一个2×35×2的BP神经网络。利用标定数据训练网络,将训练好的网络应用到输出信号。实验结果表明,相比于BP神经网络0.297%的相对误差,PSO-BP神经网络的相对误差减小到0.052%,准确度提高5倍以上,提高了PSD传感器的可靠性和测量精度。
In order to solve the problem of output nonlinearity of position sensitive detector(PSD) testing system,an improved nonlinear compensation method of BP neural network based on particle swarm optimization was proposed.The MPSO-BP neural network classifier was constructed using self-adaptively adjusted learning factors to establish a 2×35×2 BP neural network.Train the network with calibration data and apply the trained network to the output signal.The results show that compared to the relative error of 0.297% in BP neural network,the relative error of PSO-BP neural network is reduced to 0.052%.The accuracy is improved by more than 5 times,and the reliability and measurement accuracy of PSD sensor are improved.
In order to solve the problem of output nonlinearity of position sensitive detector(PSD) testing system,an improved nonlinear compensation method of BP neural network based on particle swarm optimization was proposed.The MPSO-BP neural network classifier was constructed using self-adaptively adjusted learning factors to establish a 2×35×2 BP neural network.Train the network with calibration data and apply the trained network to the output signal.The results show that compared to the relative error of 0.297% in BP neural network,the relative error of PSO-BP neural network is reduced to 0.052%.The accuracy is improved by more than 5 times,and the reliability and measurement accuracy of PSD sensor are improved.
引文
[1] CAREY W,YEE S.Calibation of nonlinear solid-state sensor arrays using multivariate regression techniques [J].Sensors and Actuators B:Chemical,1992(2):113-122.
[2] 孙淑光,王天游,程鹏,等.MEMS惯性传感器随机误差分析与去噪研究 [J].计算机测量与控制,2016(3):291-295.
[3] SAHA A,DAS S,SURESH M,et al.FPGA based self-vibration compensated two dimensional non-contact vibration measurement using 2D position sensitive detector with remote monitoring [J].Measurement,2017:271-278.
[4] REGNIER S,HALIYO S,VITARD J,et al.Calibration and nonlinearity compensation for force application in AFM based nanomanipulation [J].IEEE/RSJ International Conference on Intelligen,2014:4024-4029.
[5] 陈盛,赵东标,陆永华,等.螺纹参数测量中工件定位误差分析和补偿 [J].中国机械工程,2013(14):1956-1960.
[6] 呼静静,李国勇,张彦龙.基于差分进化算法的摩擦力建模与前馈补偿 [J].工程设计学报,2016(5):431-436.
[7] SUN Z,SONG Q,LIU C Q,et al.A new method based on position sensitive detectors to measure spatial angle of large-scale gyroidal [J].Applied Mechanics and Materials,2013:1352-1356.
[8] WEN L.The Evaluation of BP-ISP strategy alignment degree with PSO-based ANN [J].International Symposium on Neural Networks:Adv,2007,4493:284-291.
[9] CHEN Y,LI L,XIAO J,et al.Particle swarm optimizer with crossover operation [J].Engineering Applications of Artificial Intelligence,2018:159-169.
[10] LING S H,IU H,LEUNG F H F,et al.Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packaging [J].Industrial Electronics,IEEE Transactions on,2008(9):3447-3460.
[11] 赵佳鑫,高岳林.一种改进的自适应粒子群算法[J].宁夏大学学报(自然科学版),2016(2):125-130;134.
[12] 行鸿彦,郭敏,张兰,等.基于改进SPSO-BP神经网络的温度传感器湿度补偿[J].传感技术学报,2018(3):380-385.
[2] 孙淑光,王天游,程鹏,等.MEMS惯性传感器随机误差分析与去噪研究 [J].计算机测量与控制,2016(3):291-295.
[3] SAHA A,DAS S,SURESH M,et al.FPGA based self-vibration compensated two dimensional non-contact vibration measurement using 2D position sensitive detector with remote monitoring [J].Measurement,2017:271-278.
[4] REGNIER S,HALIYO S,VITARD J,et al.Calibration and nonlinearity compensation for force application in AFM based nanomanipulation [J].IEEE/RSJ International Conference on Intelligen,2014:4024-4029.
[5] 陈盛,赵东标,陆永华,等.螺纹参数测量中工件定位误差分析和补偿 [J].中国机械工程,2013(14):1956-1960.
[6] 呼静静,李国勇,张彦龙.基于差分进化算法的摩擦力建模与前馈补偿 [J].工程设计学报,2016(5):431-436.
[7] SUN Z,SONG Q,LIU C Q,et al.A new method based on position sensitive detectors to measure spatial angle of large-scale gyroidal [J].Applied Mechanics and Materials,2013:1352-1356.
[8] WEN L.The Evaluation of BP-ISP strategy alignment degree with PSO-based ANN [J].International Symposium on Neural Networks:Adv,2007,4493:284-291.
[9] CHEN Y,LI L,XIAO J,et al.Particle swarm optimizer with crossover operation [J].Engineering Applications of Artificial Intelligence,2018:159-169.
[10] LING S H,IU H,LEUNG F H F,et al.Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packaging [J].Industrial Electronics,IEEE Transactions on,2008(9):3447-3460.
[11] 赵佳鑫,高岳林.一种改进的自适应粒子群算法[J].宁夏大学学报(自然科学版),2016(2):125-130;134.
[12] 行鸿彦,郭敏,张兰,等.基于改进SPSO-BP神经网络的温度传感器湿度补偿[J].传感技术学报,2018(3):380-385.