高速高精度带钢表面检测系统的设计与实现  

Research and Implementation for High-speed and High-precision Strip Surface Detection System

作　　者：张培培 吕震宇 赵爽 吴红霞 

机构地区：[1]华北理工大学管理学院,河北唐山063000

出　　处：《哈尔滨理工大学学报》2016年第6期44-49,共6页Journal of Harbin University of Science and Technology

基　　金：河北省科技厅计划项目(16454901D);唐山市科技局计划项目(15210339;13130228Z)

摘　　要：针对带钢表面缺陷检测系统的速度滞后,精度偏低等问题,在分析成像理论和图像检测理论的基础上,设计并实现了一种带钢表面缺陷高速高精度在线检测系统.该系统首先采用大功率半导体均匀发光激光器技术、高速线扫描成像技术和基于图形处理器的Gabor纹理滤波技术实现了高速高分辨率的图像采集和处理,然后采用基于嵌套循环的K-折交叉验证、信息增益率和BP神经网络方法构建了高准确率的分类器,以达到对带钢表面缺陷高速高精度在线检测.实验结果表明,该系统满足了现有带钢生产速度的要求,具有较高的精度和准确率.Aiming at the fact that strip detection system has the problem of velocity lag and low precision,based on the analysis of imaging and image detection algorithm,we proposed and realized a new high-speed and high-precision strip surface online detection system.This system,using high-power semiconductor uniform luminescence laser technology,high-speed line scan imaging technology,Gabor texture filtering technique based on Graphic Processing Unit（GPU） realized a high-speed and high-precision image acquisition and processing,and using the nested loop based methods of K-fold cross validation,information gain rate and BP neural network,realized a classifier with high accuracy.The results show that the system meets the requirements of the existing strip production speed,and the system has the advantage of high precision and high accuracy.

关 键 词：图像采集和处理 图像检测 Gabor纹理滤波 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.4[自动化与计算机技术—控制科学与工程]