基于GA-BP神经网络的温度传感器校准系统

Title Temperature Sensor Calibration System Based on GA-BP Neural Network

鉴于制药厂对温度的严格要求,对温度传感器DS18B20在10℃-30℃(制药厂要求温度范围)内进行校准。经BP神经网络校准后,最大误差从0.5℃降至0.24℃。BP神经网络随机生成初始参数易造成局部最优和收敛速度慢,故利用遗传算法对其进行优化。优化后收敛轮数从25降为13,最大误差从0.24℃降为0.21℃,精度在原BP神经网络基础上提升了12.5%。实验结果表明,利用遗传算法优化BP神经网络可加快训练收敛速度,提升校准结果精度。此外,采用以Cortex-M3为内核的STM32F103系列MCU开发温度传感器校准系统,将训练好的神经网络搭载到相应的校准模块。经调试,此系统校准精度与Matlab测试结果一致。

In view of the strict requirements of the pharmaceutical factory for temperature,the temperature sensor DS18 B20 is calibrated in the range of 10℃-30℃(the temperature range required by the pharmaceutical factory).After calibration by BP neural network,the maximum error is reduced from 0.5℃ to 0.24℃.BP neural network generates initial parameters randomly,which is easy to cause local optimization and slow convergence speed,so genetic algorithm is used to optimize it.After optimization,the number of convergence rounds is reduced from 25 to 13,and the maximum error is reduced from 0.24℃ to 0.21℃.The accuracy is improved by 12.5% based on the original BP neural network.The experimental results show that the BP neural network optimized by genetic algorithm can speed up the training convergence speed and improve the accuracy of calibration results.In addition,STM32 F103 MCU based on Cortex-M3 is used to develop the temperature sensor calibration system,and the trained neural network is carried to the corresponding calibration module.After debugging,the calibration accuracy of this system is consistent with that of MATLAB.