深度神经网络轧制力建模及其并行优化研究

控制工程 ›› 2022, Vol. 29 ›› Issue (8) : 1379-1386.

深度神经网络轧制力建模及其并行优化研究

作者信息 +

Research on Rolling Force Modeling and Parallel Optimization of Deep Neural Network

Author information +

文章历史 +

摘要

冷连轧过程控制的轧制力模型是整个轧制过程计算机控制的基础。为提高 5 机架2030 冷连轧系统轧制力模型的精度和适用性，提出了多输入多输出深度神经网络轧制力模型的数据预处理、建模和并行优化方法。对含有不同隐含层数和节点数的神经网络，采用不同训练算法（SCG 算法和 L-M 算法）与不同优化方法（多线程 CPU、单 GPU 和多线程 CPU+GPU），研究了神经网络结构、训练算法和优化方法对神经网络轧制力模型的性能、训练时长、线性相关系数的影响。研究结果表明：含有 2 个隐含层、采用 L-M 算法和多线程 CPU 优化方法可获得综合性能最优的神经网络轧制力模型；神经网络轧制力模型的计算误差远小于在线使用的 Siemens 轧制力模型的计算误差。

Abstract

The rolling force model of cold continuous rolling process control is the basis of computer control for the entire rolling process. In order to improve the accuracy and applicability of rolling force model of 5-stand 2030 cold continuous rolling system, methods for data preprocessing, modeling and parallel optimization of rolling force model of deep neural network with multi-input and multi-output are proposed. For neural networks with different numbers of hidden layers and nodes, different training algorithms (SCG algorithm and L-M algorithm) and different optimization methods (multi-threaded CPU, single-GPU and multi-threaded CPU+GPU) are used to study the effects of the neural network structure, training algorithm and optimization method on performance, training duration, linear correlation coefficient of the neural network model. The results show that the rolling force model of neural network with two hidden layers, trained by L-M algorithm and optimized by multi-thread CPU, can obtain the best comprehensive performance. The calculation error of the rolling force model of neural network is much smaller than that of Siemens rolling force model used online.

导出引用

刘翰培, 汪宇轩, 王亚琴, 罗小川. 深度神经网络轧制力建模及其并行优化研究[J]. 控制工程, 2022, 29(8): 1379-1386

LIU han-pei, WANG Yu-xuan, WANG Ya-qin, LUO Xiao-chuan. Research on Rolling Force Modeling and Parallel Optimization of Deep Neural Network[J]. Control Engineering of China, 2022, 29(8): 1379-1386