针对温度会影响红外CO2传感器的输出电压,造成对CO2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,CO2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CO2传感器测量输出的浓度值最大相对误差为4.5578％,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CO2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.%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 out-put 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 4.5578％ after temperature compensation,which has high accuracy.There-fore,the L-M Bayesian regularization BP neural network can effectively compensate the temperature of the infrared CO2 sen-sor,which provides a reference for the improvement of related infrared sensor instruments.
展开▼
