论文部分内容阅读
基于BP人工神经网络原理,利用MATLAB神经网络工具箱,以试验得到的243组数据作为样本,建立一个以提升管风速、鼓泡床风速、鼓泡床物料静床高、床料平均粒径为输入变量,以颗粒循环流率为输出变量,用于预测中心提升管内循环流化床颗粒循环流率的BP神经网络模型。对模型的隐含层层数和隐含层节点数对预测结果的影响进行分析,发现在隐含层层数为1,隐含层节点数为15时,模型预测结果误诊率最小,预测相对误差在±8%以内,总体平均偏离度为3.09%,网络性能最优,从而为中心提升管内循环流化床装置的设计和运行提供指导。
Based on the principle of BP artificial neural network and using the MATLAB neural network toolbox, the 243 sets of data obtained from the experiment were used as a sample to establish a method to increase the tube velocity, bubble column velocity, bubbling bed material static bed height, Input variables, the particle circulation flow rate as the output variable, used to predict the center of the circulating fluidized bed to enhance the circulating particle flow rate of the BP neural network model. The influence of the number of hidden layers and the number of hidden layers on the prediction results is analyzed. It is found that the number of hidden layers is 1, the number of hidden layers is 15, the misdiagnosis rate of model prediction is the smallest, and the prediction is relative The error is within ± 8%, the overall average deviation is 3.09%, and the network performance is the best, which will provide guidance for the center to enhance the design and operation of the circulating fluidized bed device in the pipe.