| 支持向量机与神经网络相结合的板带凸度预测 |
| |
| 引用本文： | 刘明华,张强.支持向量机与神经网络相结合的板带凸度预测[J].智能系统学报,2022,17(3):506-514. |
| |
| 作者姓名： | 刘明华 张强 |
| |
| 作者单位： | 西安建筑科技大学 冶金工程学院, 陕西 西安 710055 |
| |
| 摘 要： | 为提高热轧生产过程中板带凸度的预测精度，提出了一种将粒子群优化算法(particle swarm optimization, PSO)、支持向量回归(support vector regression, SVR)和BP神经网络(back propagation neural network, BPNN)相结合的板带凸度预测模型。采用PSO算法优化SVR模型的参数，建立了PSO-SVR板带凸度预测模型，提出采用BPNN建立板带凸度偏差模型与PSO-SVR板带凸度模型相结合的方法对板带凸度进行预测。采用现场数据对模型的预测精度进行验证，并采用统计指标评价模型的综合性能。仿真结果表明，与PSO-SVR、SVR、BPNN和GA-SVR模型进行比较，PSO-SVR+BPNN模型具有较高的学习能力和泛化能力，并且比GA-SVR模型运算时间短。
|
| 关 键 词： | 支持向量回归 神经网络 板带凸度 粒子群优化算法 热轧板带过程 机器学习 预测 大数据 |
Prediction of strip crown based on support vector machine and neural network |
| |
| LIU Minghua,ZHANG Qiang.Prediction of strip crown based on support vector machine and neural network[J].CAAL Transactions on Intelligent Systems,2022,17(3):506-514. |
| |
| Authors: | LIU Minghua ZHANG Qiang |
| |
| Affiliation: | School of Metallurgical Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China |
| |
| Abstract: | To improve the prediction accuracy of strip crown in a hot-rolled production process, a modeling method combining particle swarm optimization (PSO) algorithm, support vector regression (SVR), and BP neural network (BPNN) is proposed. The PSO algorithm was employed to optimize the parameters of the SVR model, and the PSO–SVR strip crown prediction model was established. A method combining the BPNN strip crown deviation model with the PSO–SVR strip crown model is also proposed to predict the strip crown. The prediction accuracy of the model was validated with field experimental data, and the comprehensive performance of the model was evaluated using statistical indicators. The simulation results show that in contrast to the PSO–SVR, SVR, BPNN, and GA-SVR models, the PSO–SVR+BPNN model exhibits a greater learning capacity and generalization ability. The computing time of the PSO–SVR+BPNN model is also less than that of the GA-SVR model. |
| |
| Keywords: | support vector regression neural network strip crown particle swarm optimization algorithm hot strip rolling process machine learning prediction big data |
|
| 点击此处可从《智能系统学报》浏览原始摘要信息 |
|
点击此处可从《智能系统学报》下载全文 |
|
