基于加权极限学习机的连铸漏钢预报系统

Prediction System of Continuous Casting Breakout Steel Based on Weighted Extreme Learning Machine

为了能够及时准确地预测连铸漏钢,提出了一种基于改进人工蜂群算法(IABC)优化加权极限学习机(WELM)参数的连铸漏钢预测模型,有效地提高了漏钢预测模型的寻优速度和预测精度,并结合钢厂连铸现场的历史数据,对所提出的连铸漏钢预测系统进行了离线测试。结果表明新的IABC-WELM模型具有良好的泛化能力,其连铸漏钢预报准确率可达98%。

A continuous casting leakage prediction model based on improved artificial bee colony algorithm(IABC)optimized weighted extreme learning machine(WELM)parameters is proposed in this paper,which effectively improved the steel leakage prediction.The optimization speed and prediction accuracy of the model were combined with the historical data of continuous casting of a steel mill to test the proposed continuous casting leakage prediction system.