Solar cell panel fault analysis method and device based on machine learning

• Main Authors: JIANG BIAORONG, ZHOU SHUANGQUAN, PEI LIUSHENG, WANG HAIFENG, LI GUANGHUI, YANG JIANHUI, YANG XIANCHUAN, LIU YONG
• Format: Patent
• Language: Chinese; English
• Published: 31.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a solar cell panel fault analysis method and device based on machine learning. The method comprises: obtaining the flight path of an unmanned aerial vehicle and multiple images shot in the flight process of the unmanned aerial vehicle; acquiring shooting position information of each image in the plurality of images according to the flight path; identifying each image, and identifying each solar cell panel in the image; identifying the image corresponding to each solar cell panel to determine whether the solar cell panel fails or not; and, under the condition that the solar cell panel breaks down, sending alarm information, wherein the alarm information comprises the image and the position of the solar cell panel which breaks down. According to the invention, the problem that whether the surface of the solar cell panel has low influence on the power generation efficiency needs to be manually inspected in the prior art is solved, so that the inspection efficiency is improved, and the aff