【摘要】 针对高炉煤粉喷吹系统 ,建立一种基于遗传算法的神经网络流量测量模型 ,考虑BP算法训练神经网络测量模型时收敛速度慢、动态特性不够理想等不足 ,用改进的遗传算法来优化神经网络测量模型的参数 ,以提高测量系统的精度·现场实验表明 ,最大满量程误差小于 3 .8%,具有工程应用价值·更多还原

【Abstract】 For pulverized coal injection systems of blast furnaces, a neural network (NN) flowrate measurement model based on Genetic Algorithms (GA) is presented. In order to overcome the disadvantages such as slow convergent speed and unsatisfied dynamic characteristic as backpropagation (BP) was used to train the neural network measurement model,the GA method was applied to optimize parameters of NN thus to improve the performance of the measurement model. Spot experiments show that the model can reduce the errors of measurement down to less than 3 8% ,which means the great engineering application worthiness.更多还原