基于GA-BP神经网络的光纤位移传感器光强补偿研究
|
摘要
为了实现光纤位移传感器的光强补偿和减小测量误差,提出了一种基于遗传算法(GA)优化BP神经网络的光强补偿及校正模型。首先通过对光纤位移传感器做标定实验,获得传感器测量的原始数据,然后采用GA-BP神经网络进行建模,通过对遗传算法的适应度函数、编码方式和参数进行研究,利用遗传算法的全局寻优能力对传统BP神经网络的权值、阈值进行优化,改善了其容易陷入局部极值的问题。最后利用实测数据对GA-BP网络和传统BP网络进行训练,实验结果表明,GA-BP网络比BP网络的预测误差小很多,提高了补偿精度,从而实现了光纤位移传感器的光强补偿。
In order to achieve light intensity compensation and reduce measurement error of fiber displacement sensor, a model of light intensity compensation and correction was proposed based on BP neural network optimized by Genetic Algorithm( GA). First, through the calibration experiment to the optical fiber displacement sensor, the original data was obtained. Then, the GA-BP neural network was used for modeling. Through the study on the encoding method, fitness function and parameters of GA, the global optimization capability of GA was used to optimize the weights and thresholds of traditional BP neural network, which made it less easier to fall into local extreme. Finally, the measured data was used to train the GA-BP network and the traditional BP network. The experimental results show that: compared with BP network, the GA-BP network has much smaller prediction error and higher compensation accuracy, and thus can realize the intensity compensation of the optical fiber displacement sensor.
In order to achieve light intensity compensation and reduce measurement error of fiber displacement sensor, a model of light intensity compensation and correction was proposed based on BP neural network optimized by Genetic Algorithm( GA). First, through the calibration experiment to the optical fiber displacement sensor, the original data was obtained. Then, the GA-BP neural network was used for modeling. Through the study on the encoding method, fitness function and parameters of GA, the global optimization capability of GA was used to optimize the weights and thresholds of traditional BP neural network, which made it less easier to fall into local extreme. Finally, the measured data was used to train the GA-BP network and the traditional BP network. The experimental results show that: compared with BP network, the GA-BP network has much smaller prediction error and higher compensation accuracy, and thus can realize the intensity compensation of the optical fiber displacement sensor.
引文
[1]狄海廷.锯齿型曲率光纤传感器特性及相关技术研究[D].哈尔滨:哈尔滨工业大学,2011.
[2]GUO Y,WANG Y T,JIN M.Improvement of measurement range of optical fiber displacement sensor based on neutral network[J].Optik,2014,125(1):126-129.
[3]胡新宁,崔春艳,刘建华,等.应用光纤位移传感器在液氦温度下测量超导体微位移[J].稀有金属材料与工程,2008,37(s):472-475.
[4]张朝龙,江巨浪,李彦梅,等.基于云粒子群-最小二乘法支持向量机的传感器温度补偿[J].传感技术学报,2012,25(4):472-477.
[5]王灵刚,张蕾,普杰信,等.改进BP神经网络在物体识别中的应用[J].电光与控制,2012,19(4):68-71.
[6]刘浩然,赵翠香,李轩,等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报,2016,37(7):1574-1579.
[7]彭基伟,吕文华,行鸿彦,等.基于改进GA-BP神经网络的湿度传感器的温度补偿[J].仪器仪表学报,2013,34(1):153-160.
[8]蔡斌军.基于GA+BP网络速度辨识的直接转矩控制[J].控制工程,2012,19(4):733-736.
[9]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器学报,2015,29(8):1157-1163.
[10]王俊,周树道,叶松,等.融合遗传算法与BP神经网络的气象威胁度建模与评估[J].电光与控制,2012,19(3):74-77.
[11]DING S F,SU C Y,YU J Z.An optimizing BP neural network algorithm based on genetic algorithm[J].Artificial Intelligence Review,2011,36(2):153-162.
[2]GUO Y,WANG Y T,JIN M.Improvement of measurement range of optical fiber displacement sensor based on neutral network[J].Optik,2014,125(1):126-129.
[3]胡新宁,崔春艳,刘建华,等.应用光纤位移传感器在液氦温度下测量超导体微位移[J].稀有金属材料与工程,2008,37(s):472-475.
[4]张朝龙,江巨浪,李彦梅,等.基于云粒子群-最小二乘法支持向量机的传感器温度补偿[J].传感技术学报,2012,25(4):472-477.
[5]王灵刚,张蕾,普杰信,等.改进BP神经网络在物体识别中的应用[J].电光与控制,2012,19(4):68-71.
[6]刘浩然,赵翠香,李轩,等.一种基于改进遗传算法的神经网络优化算法研究[J].仪器仪表学报,2016,37(7):1574-1579.
[7]彭基伟,吕文华,行鸿彦,等.基于改进GA-BP神经网络的湿度传感器的温度补偿[J].仪器仪表学报,2013,34(1):153-160.
[8]蔡斌军.基于GA+BP网络速度辨识的直接转矩控制[J].控制工程,2012,19(4):733-736.
[9]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器学报,2015,29(8):1157-1163.
[10]王俊,周树道,叶松,等.融合遗传算法与BP神经网络的气象威胁度建模与评估[J].电光与控制,2012,19(3):74-77.
[11]DING S F,SU C Y,YU J Z.An optimizing BP neural network algorithm based on genetic algorithm[J].Artificial Intelligence Review,2011,36(2):153-162.