基于深度学习的太阳能电池片表面缺陷检测方法  

Solar Cells Surface Defects Detection Based on Deep Learning

作　　者：王宪保[1,2] 李洁[1] 姚明海[1] 何文秀[1] 钱沄涛[2] 

机构地区：[1]浙江工业大学信息工程学院,杭州310023 [2]浙江大学计算机科学与技术学院,杭州310027

出　　处：《模式识别与人工智能》2014年第6期517-523,共7页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.61070113);浙江省自然科学基金项目(No.LY14F030009)资助

摘　　要：目前对太阳能电池片的缺陷检测仍依赖人工完成,很难通过传统的CCD成像系统自动识别.作为一种多层神经网络学习算法,深度学习因对输入样本数据强大的特征提取能力而受到广泛关注.文中提出一种基于深度学习的太阳能电池片表面缺陷检测方法,该方法首先根据样本特征建立深度置信网络(DBN),并训练获取网络的初始权值;然后通过BP算法微调网络参数,取得训练样本到无缺陷模板之间的映射关系;最后利用重构图像与缺陷图像之间的对比关系,实现测试样本的缺陷检测.实验表明DBN能较好地建立上述映射关系,且准确、快速地进行缺陷检测.Defects of solar cells are detected mainly by manual operation, and they are difficult to be detected automatically by traditional charge-coupled device （CCD） imaging system. As a training multi-layer neural network, deep learning draws great attention due to its strong ability to extract features from input sample data. A method for solar cells surface defects detection based on deep learning is proposed. Firstly, deep belief networks （DBN） are established and trained according to the sample features to obtain the initial weights of the networks. Then, the traditional BP algorithm is conducted to fine-tune the network parameters to get the mapping relationship between the training samples and the defect-free template. Finally, the defects of testing samples are detected by the contrast between the reconstruction image and the defect image. Experimental results show that DBN perfectly establishes the mappingrelationship, and it can quickly detect defects with a high accuracy.

关 键 词：深度学习 缺陷检测 限制玻尔兹曼机(RBM) 深度置信网络(DBN) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]