Photovoltaic cell appearance defect classification method based on multi-channel residual neural network

Abstract

The invention relates to a photovoltaic cell appearance defect classification method based on a multi-channel residual neural network. The method classifies the photovoltaic cell appearance defects based on a depth learning algorithm of a multi-channel input residual neural network. Firstly, the acquired photovoltaic cell sheet appearance image is preprocessed. 20% of that target image are randomly selected as a t sample set, the remaining target images are manually sorted, label are added, the size of the target images is quantized and multi-channel information in the target images is extracted, so that the training sample sets with fixed scales are obtained respectively, and the sample sets are verified. The training set is inputted into the residual neural network, and the multidimensional output eigenvalue matrix of the image is obtained. According to the extracted multi-dimensional eigenvalue matrix, the verification set image features are loaded into softmax classifier for classification, and the classification results are compared with the labels, and the test data and multi-dimensional eigenvalue matrix are loaded into the classifier to obtain the final classification. Thisapplication has high accuracy and high speed.

Description

Technical field [0001] The invention relates to the technical field of visual inspection for classification of appearance defects of photovoltaic cells, in particular to a method for classification of appearance defects of photovoltaic cells based on a multi-channel residual neural network. Background technique [0002] The quality of silicon wafers directly determines the efficiency of photovoltaic cells. During the cell production process, coating and wet etching may cause appearance defects, including dirty films, chromatic aberration, scratches, thick lines, broken grids, slurry leakage, chipped corners, chipped edges, etc., which affect the efficiency of the cell . At this stage, there are mainly the following methods for the inspection and classification of appearance defects at home and abroad: manual visual inspection method, CCD inspection method, etc. Some large foreign companies, such as Belgium ICOS, have launched professional CCD camera-based solar vision inspectio...

AI Technical Summary

Problems solved by technology

However, most domestic small and medium-sized enterprises cannot afford imported hardware equipment and expensive software authorization

At present, Li Qiao (Li Qiao. Research on the appearance detection technology of solar cells based on machine vision [D]. Suzhou University, 2016.) proposed a detection algorithm combining local adaptive threshold processing method and region growing method to detect inverted corners, edge defects and surface stains and other defects, but such methods have poor real-time performance and are not suitable for polysilicon cells; Wang Xianbao (Wang Xianbao, Li Jie, Yao Minghai, He Wenxiu, Qian Yuntao. Based on deep learning [J]. Pattern Recognition and Artificial Intelligence, 2014, 27 (06): 517-523.) A deep belief network (DBN) deep learning algorithm is proposed to detect cracks, scratches and missing corners. For Invisible defects, such as thick lines, leakage, etc., cannot be detected

Images