论文部分内容阅读
针对环境温湿度对矿用红外甲烷传感器测量精度的影响问题,以人工神经网络为基础,通过遗传优化对传统误差反向传播(back propagation)神经网络算法进行改进,有效改善了BP神经网络收敛速度慢,易陷入局部极小值等缺点。将改进后的算法写入基于MSP430单片机的矿用红外甲烷传感器,在实时甲烷浓度测量中精度提高了4%。
In view of the influence of temperature and humidity on the measurement accuracy of mine infrared methane sensor, based on artificial neural network, the traditional back propagation neural network algorithm is improved by genetic optimization, which effectively improves the convergence speed of BP neural network Slow, easy to fall into the local minimum and other shortcomings. The improved algorithm is written into the MSP430-based mining infrared methane sensor, which improves the accuracy of real-time methane concentration by 4%.