Data training method of deep stack type hybrid self-encoding network

Abstract

The invention discloses a data training method of a deep stack type hybrid self-encoding network. The method comprises the following steps: carrying out image preprocessing on an acquired photovoltaic infrared image to obtain a small sample hot spot image data set; firstly, pre-training DAE by utilizing a small sample hot spot image data set without a label, and when the reconstruction error of input and output is minimum, indicating that training is completed; and taking image features extracted by a DAE hidden layer as the input of SAE, making the pre-trained DAE, SAE and AE cascaded, and adding a deep stack type hybrid auto-encoder to perform training identification on the small sample hot spot image data set. The method has strong feature extraction and expression capabilities, and can overcome an over-fitting phenomenon caused by insufficient sample size so as to improve the hot spot recognition and positioning accuracy of the model.

Description

technical field [0001] The invention relates to the technical field of small-sample photovoltaic hot spot recognition, in particular to a data training method for a deep stacked hybrid autoencoder network. Background technique [0002] There are mainly the following problems in the field of hot spot recognition of photovoltaic infrared images: (1) the lack of original samples makes it impossible to directly use the traditional data-driven classification neural network; (2) because the number of cells with hot spots is relatively small compared with other states, Therefore, there is an unbalanced sample set, which leads to the prediction result of the model focusing on the category with a large number of samples, or even giving up the prediction of a small number of samples. (3) Due to the small sample size, over-fitting phenomenon will occur in the training of the network model, resulting in a low accuracy rate of hot spot recognition. Therefore, we improve this and propose...

AI Technical Summary

Problems solved by technology

[0002] There are mainly the following problems in the field of hot spot recognition of photovoltaic infrared images: (1) the lack of original samples makes it impossible to directly use the traditional data-driven classification neural network; (2) because the number of cells with hot spots is relatively small compared with other states, Therefore, there is an unbalanced sample set, which leads to the prediction result of the model focusing on the category with a large number of samples, or even giving up the prediction of a small number of samples.

(3) Due to the small sample size, over-fitting phenomenon will occur in the training of the network model, resulting in low accuracy of hot spot recognition

Images