Quality estimation method and quality estimation device
AssigneeHitachi, Ltd.
InventorsToru KOUNO, Jun TSUNODA
Life of this patent
Estimating the term…
Abstract
In a quality estimation method according to an aspect of the present invention, a relationship between luminance of an EL image and quality of a solar cell module is learned in advance by a learning device, quality classification of the solar cell module is acquired from an output layer of the learning device, and detailed classification of the quality of the solar cell module is acquired from an intermediate layer of the learning device.
Claims10
A quality estimation method of estimating quality of a solar cell module, the method comprising:
- acquiring an image obtained by capturing light emission generated by recombination of electrons and holes of a pn junction included in the solar cell module;
- dividing the image into a plurality of regions and calculating luminance of each of the regions;
- and
- acquiring a result of estimating the quality of the solar cell module from a learning device by inputting the calculated luminance to the learning device that has learned a relationship between the luminance of each of the regions and the quality of the solar cell module by machine learning,
- wherein
- the learning device includes an input layer, an intermediate layer, and an output layer,
- the learning device performs the machine learning in advance to classify the quality of the solar cell module in accordance with an output from the output layer,
- the learning device performs the machine learning in advance to more finely classify the quality based on the output from the output layer in accordance with an output from the intermediate layer, and
- in the acquiring of the quality, the classification of the quality of the solar cell module based on at least the output from the output layer is acquired by inputting the calculated luminance to the learning device.
A quality estimation device estimating quality of a solar cell module, the device comprising:
- a calculation unit configured to estimate the quality,
- wherein
- the calculation unit performs:
- acquiring an image obtained by capturing light emission generated by recombination of electrons and holes of a pn junction included in the solar cell module,
- dividing the image into a plurality of regions and calculating luminance of each of the regions, and
- acquiring a result of estimating the quality of the solar cell module from a learning device by inputting the calculated luminance to the learning device that has learned a relationship between the luminance of each of the regions and the quality of the solar cell module by machine learning,
- the learning device includes an input layer, an intermediate layer, and an output layer,
- the learning device performs the machine learning in advance to classify the quality of the solar cell module in accordance with an output from the output layer,
- the learning device performs the machine learning in advance to more finely classify the quality based on the output from the output layer in accordance with an output from the intermediate layer, and
- in the acquiring of the quality, the classification of the quality of the solar cell module based on at least the output from the output layer is acquired by inputting the calculated luminance to the learning device.
Dependencies are inferred from the claim text.