Solar cell defect detection method based on convolutional neural network multi-feature fusion

Abstract

The invention discloses a solar cell defect detection method based on convolutional neural network multi-feature fusion. The invention belongs to the technical field of solar cell surface defect detection, solving the technical problem of adaptability of a network to various defect types on the surface of a solar cell panel. The solar cell defect detection method introduces the idea of cross-layerconnection on the basis of a Faster R-CNN convolutional neural network structure, so as to learn shallow layer information while learning deep layer characteristic information, thus reducing the error rate effectively, extracts the target candidate box in a multi-scale mode, and selects the proper box as the candidate box through fusion in a certain proportion, so that the omission ratio is reduced to a certain degree, and the multi-scale feature fusion layer is additionally arranged so that the method can be effectively suitable for detecting the surface defects of the solar cell panel. Aiming at the long, narrow and fine characteristics of the surface defects of the solar cell panel, various aspect ratios and scales are used, so that the solar cell panel is more suitable for defect types, and the accuracy of a prediction box can be improved, and the target detection accuracy and defect position detection can be effectively improved, and a higher confidence coefficient value is achieved.

Description

technical field [0001] The invention belongs to the technical field of solar cell surface defect detection, and in particular relates to a solar cell panel defect detection method based on convolutional neural network multi-feature fusion. Background technique [0002] In recent years, human activities have become more and more dependent on energy, and the environmental problems caused by the excessive use and massive consumption of non-renewable energy such as petroleum have intensified. Solar photovoltaic power generation technology is a typical representative of new energy technology. The wide application of this technology can well alleviate the current energy problems. Therefore, the exploitation and effective utilization of solar energy has become an important development trend in the future. Solar energy comes from sunlight, which is a green energy that is safe, reliable, clean, free from geographical restrictions, does not require fuel consumption, and has high energ...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the existing technology and solve the technical problem of network adaptability to various types of defects on the surface of solar panels, the present invention provides a solar cell defect detection method based on convolutional neural network multi-feature fusion

Images