为提高热连轧产品质量和性能,对粗轧入口温度建模预测研究.建立一种基于机器学习的粗轧入口板坯温度预测模型,首先对传感器采集的粗轧入口板坯温度值进行预处理;其次采用智能粒子群优化算法(particle swarm optimization,PSO),对最小二乘支持向量机(least squares support vector machine,LSSVM)预测模型进行寻优;最后建立一种PSO-LSSVM粗轧入口板坯温度预测模型.通过大量数据训练优化仿真,结果表明,此模型预测精度高,拟合效果好.
Temperature Prediction of Roughing Inlet Slab based on Machine Learning
In order to improve the quality and performance of hot continuous rolling products,the modeling and prediction of roughing inlet temperature were studied.A prediction model of roughing inlet slab temperature based on machine learning was established.Firstly,the temperature of roughing inlet slab collected by sensor was preprocessed.Secondly,the intelligent particle swarm optimization(PSO)algorithm was used to optimize the least squares support vector machine(LSSVM)prediction model.Finally,a PSO-LSSVM inlet slab temperature prediction model was established.Through a large number of data training and optimization simulation,the results show that the model has high prediction accuracy and good fitting effect.
temperature forecastingparticle swarm optimizationprediction modeldata
万方数据
维普
