摘要
采用遗传学习算法和误差反向传播(BP)算法相结合的混合算法来训练前馈人工神经网络,从而提高神经网络的收敛质量和收敛速度,并将此算法运用到电子舌对黄酒的检测上。与经典BP网络及附加动量项BP网络的训练与预测进行了比较。结果显示:遗传优化BP算法具有预测精度高、收敛速度快及运行时间短的优点,是一种快速、可靠的方法。
The combination of genetic algorithm and back propagation algorithm for training the neural network is described. It can improve the search efficiency and realize global optimization, and this GA-BP algorithm is employed to detect the rice wine by electronic tongue. Compared with the standard back propagation algorithm and its improved method, the result shows the GA-BP algorithm has better prediction precision, higher convergent speed and less running time, and it is a fast and credible method.
出处
《电子技术应用》
北大核心
2009年第7期91-94,共4页
Application of Electronic Technique
关键词
黄酒
电子舌
BP神经网络
遗传算法
rice wine
electronic tongue
BP neural network
genetic algorithm
