论文部分内容阅读
通过采集和测定35个矿区煤样品的化学组成、结构参数和润湿接触角,构建了以13个影响因子为输入参数和以接触角为输出目标的3层BP人工神经网络,并利用该模型估算煤尘润湿接触角。结果表明,隐含层节点数为19时,接触角估算值与实测值的决定系数R2=0.957,平均相对误差为4.59%,表明基于BP神经网络建立的煤尘润湿接触角估算模型具有很高的精度。
By collecting and measuring the chemical composition, structural parameters and wetting contact angles of coal samples from 35 coal mines, a 3-layer BP artificial neural network with 13 influencing factors as input parameters and contact angles as output targets was constructed. By using this model Estimate the wet dust contact angle. The results show that when the number of hidden layer nodes is 19, the determination coefficient of contact angle and the measured value are R2 = 0.957 and the average relative error is 4.59%, which shows that the estimation model of wetting contact angle of coal dust based on BP neural network has very good High precision.