Method for predicting coke oven gas generation amount of iron and steel enterprises

The invention discloses an iron and steel enterprise coke oven gas generation amount prediction method, and belongs to the technical field of artificial intelligence. The coke oven gas generation amount of the iron and steel enterprise is predicted through the three steps of pretreatment, model prediction and result prediction. According to the method, abnormal value detection is carried out by using the isolated forest algorithm, the processed coke oven gas data is input into the BP neural network for training and learning, the coke oven gas flow at the future moment is predicted, and a reliable basis is provided for gas optimization scheduling of enterprises. 本发明公开了一种钢铁企业焦炉煤气发生量预测方法，属于人工智能技术领域。本发明通过预处理、预测模型和预测结果这三个步骤来实现钢铁企业焦炉煤气发生量预测。本发明使用孤立森林算法进行异常值检测，本发明将处理后的焦炉煤气数据输入到BP神经网络中进行训练学习，预测出未来时刻的焦炉煤气流量，为企业的煤气优化调度提供可靠的依据。