Solar Panel Inspection Employs Drone, AI, Automatic Reporting (2)
Mosaic abnormalities caused by lightning can be detected
In analyzing thermal distribution images shot by drones from the sky in the post-process, AI is not used to identify positions of images and to match them against the solar panel layout drawing of the solar power plant.
Positions of solar panels with abnormal thermal distribution on the layout drawing are identified by using the panel layout drawing of the site obtained in advance from the customer, that is, the power producer or the O&M company, and matching the data on the automatic flight route against positional information of thermal distribution images. This process was automated.
AI is used after this process. Phenomena of abnormal thermal distribution in solar panels are classified into four types and the degrees of urgency for measures are also classified into three levels.
Thermal distribution abnormalities are categorized into "partial overheating/heating (hot spot)," "cluster abnormality," "overheating of entire solar panel" and "overheating of entire string."
"Partial overheating/heating" is caused by microcracks in cells, staining of solar panels or shades on solar panels in many cases. "Cluster abnormality" is caused by disconnection of interconnectors, defective soldering or short circuiting of bypass diodes in many cases (Fig. 2).
"Cluster abnormality" means the stopping of power generation by a cluster (a series circuit of multiple cells that are divided into three one-third sections) due to activation of the bypass diode following an output drop from cells (power generation elements) caused by problems.
"Overheating of entire solar panel" is caused by cracking of cover glass or abnormality in the back sheet in many cases. "Overheating of entire string" is caused by damage to connectors, damage to cables or opening of junction boxes in many cases.
"RAPID machine learning technology," one of the AI technology groups of NEC, is used for automatic analysis.
"RAPID machine learning technology" was developed by incorporating so-called deep learning technology used to teach computers to perform actions similar to human actions including sound recognition, image identification and estimation. Discrimination of normal thermal distribution from abnormal thermal distribution and identification of abnormality trends, which are needed to analyze thermal distribution images shot by drones from the sky, are learned automatically by AI to realize classification of data and detection of abnormalities with high accuracy, according to the company (Fig. 3).
The data needed for automatic learning is called the "teaching data." Normal thermal distribution images and images containing abnormal thermal distribution were collected respectively for solar cells, clusters consisting of cells, solar panels and strings to use as the "teaching data." Teaching of AI was performed using the data to establish a model for automatic analysis by AI.
The analysis accuracy of solar panel thermal distribution images is estimated at 95% in manual analysis for general services. The company made efforts to improve the analysis accuracy by AI to the same or higher level and decided to offer the services because the goal was achieved.
Damage due to reverse current caused by lightning strike also detectable
According to actual analyses, abnormalities that are rarely detected by drone inspection were discovered in the validation test stage. They are problems where mosaic thermal distribution abnormalities appear on solar panels (Fig. 4).
It is believed that the abnormalities were caused by a reverse current flowing to solar panels, which is generated by a lightning strike or failure of an anti-backflow diode. Cells are damaged by backflow of current to panels, resulting in thermal distribution abnormalities with contrasting density similar to mosaic patterns depending on the degree of the damage, according to estimations. The cells were overheated to 100°C or higher and needed to be replaced immediately.
Abnormalities detected by NESIC services are evaluated for urgency by three levels in the reports. Overheating of 80°C or more is classified as the top urgency level. Therefore, the level 100°C or higher due to mosaic abnormality mentioned above was the top urgency level.
The company shoots still images. Many companies shoot moving images in their services, but still images are more advantageous for reporting urgency levels because information on absolute temperatures is recorded in all pixels, according to the company. Absolute temperatures are not recorded in moving images, which leads to significant limitations in mapping on layout drawings.
At the power plant where mosaic abnormalities were discovered in panels, which seem to have been caused by a lightning strike, the actual power generation amount was much less than the amount estimated at the time of working out the business plan for three consecutive years, but the situation was left unchecked.
For the hardware side, the speed of the analysis engine was increased and its weight was reduced by using special technology developed by NEC Laboratories America Inc to improve the analysis environment. Following this improvement, only a single server is required for analysis, without the need for a large-scale hardware environment, according to the company.
The company uses infrared cameras manufactured by a US company for mounting on the drones although infrared cameras for mounting on drones are also manufactured by Nippon Avionics Co Ltd of the NEC Group (See related article).
Products of the US manufacturer, which are widely used, were incorporated because infrared camera modules manufactured by Nippon Avionics have yet to satisfy the requirements of NESIC in terms of downsizing and weight reduction.
Going forward, the company plans to offer the solar panel inspection services using drones to many power plants, not limiting the targets to solar power plants from which the company is entrusted with EPC and O&M services. The company emphasized that it can diagnose solar panels based on a wide variety of experiences because it handles a wide range of EPC and O&M services and has abundant knowledge on panel abnormalities.