采用BP神经网络模型预测油田废水混凝处理效果

Predication of the Efficiency of Coagulating Treatment for Oil Field Sewage by BP Neural Network

采用均匀设计方法选择神经网络的训练样本,并建立了基于BP人工神经网络的油田废水混凝处理系统的数学模型。利用该模型对实验数据进行预测,结果表明模型的预测值与实测值的平均绝对误差仅为0.74%。可见这种方法预测精度高,具有一定的实际应用价值。

A mathematic model based on BP artificial neural network was established for the coagulating treatment of oil fieldsewage,and uniform design was used to choose samples for training the neural network. With this model,the average absolute error be-tween the predicted data and experimental data was only 0.74%,indicating that the model has high predicting accuracy and is worth ofpractical application.