首页 | 本学科首页   官方微博 | 高级检索  
     

L-M贝叶斯正则化BP神经网络在红外CO_2传感器的应用
引用本文:赵久强,王震洲. L-M贝叶斯正则化BP神经网络在红外CO_2传感器的应用[J]. 河北工业科技, 2018, 35(4): 273-277
作者姓名:赵久强  王震洲
作者单位:河北科技大学信息科学与工程学院
基金项目:河北省科技支撑计划项目(16273705D)
摘    要:针对温度会影响红外CO_2传感器的输出电压,造成对CO_2的浓度检测误差较大的问题,提出了一种基于L-M贝叶斯正则化BP神经网络的温度补偿方法。实验中将传感器输出电压比和温度作为神经网络的输入,CO_2浓度作为神经网络的输出,并通过L-M算法和贝叶斯正则化对神经网络进行优化。经过实验仿真证明,在温度补偿后红外CO_2传感器测量输出的浓度值最大相对误差为4.557 8%,具有较高的精确度。因此L-M贝叶斯正则化BP神经网络能对红外CO_2传感器进行有效的温度补偿,可为相关红外传感器仪器的改进提供参考。

关 键 词:计算机神经网络;红外CO2传感器;BP神经网络;L-M算法;贝叶斯正则化;温度补偿
收稿时间:2018-04-09
修稿时间:2018-05-07

Application of BP neural network with L-M Bayesian regularization in infrared CO2 sensor
ZHAO Jiuqiang and WANG Zhenzhou. Application of BP neural network with L-M Bayesian regularization in infrared CO2 sensor[J]. Hebei Journal of Industrial Science & Technology, 2018, 35(4): 273-277
Authors:ZHAO Jiuqiang and WANG Zhenzhou
Abstract:Aiming at the influence of temperature on the output voltage of infrared CO2 sensor and the detection error of CO2 concentration, a temperature compensation method based on L-M Bayes regularization BP neural network is proposed. The output voltage ratio of the infrared CO2 sensor and temperature are taken as input of neural network, CO2 concentration is used as output of neural network, and neural network is optimized by L-M algorithm. The experimental simulation shows that the maximum relative error of the measured output is 4.557 8% after temperature compensation, which has high accuracy. Therefore, the L-M Bayesian regularization BP neural network can effectively compensate the temperature of the infrared CO2 sensor, which provides a reference for the improvement of related infrared sensor instruments.
Keywords:computer neural network   infrared CO2 sensor   BP neural network   L-M algorithm   Bayesian regularization   temperature compensation
本文献已被 CNKI 等数据库收录!
点击此处可从《河北工业科技》浏览原始摘要信息
点击此处可从《河北工业科技》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号