Training and recognition method and device for visible light fault model of photovoltaic module

Abstract

The invention discloses a training and recognition method and device for a visible light fault model of a photovoltaic module. The method comprises the steps of in response to an obtained to-be-detected image, cutting the to-be-detected image; marking pixel coordinates of each piece of image data in the to-be-detected image; in response to the acquired multiple pieces of image data, outputting target object image data in the multiple pieces of image data by a Faster-RCNN training model; judging whether the pixel coordinates of the image data of a certain obstacle are within the range of the pixel coordinates of all photovoltaic module image data or not; and if the pixel coordinates of the image data of a certain obstacle are within the range of the pixel coordinates of all photovoltaic module image data , outputting the pixel coordinates of the image data of the obstacle. By extracting the image features of the photovoltaic module and the bird droppings, the coordinate range of the photovoltaic module and the coordinates of the bird droppings in the detected image are identified, and the overlapped part of the coordinate range and the coordinates of the bird droppings is marked asthe bird droppings covering fault point of the photovoltaic module, so that the identification of the bird droppings shielding fault point of the photovoltaic module is realized.

Description

technical field [0001] The invention belongs to the technical field of photovoltaic component fault detection, and in particular relates to a method and device for training and identifying a visible light fault model of a photovoltaic component. Background technique [0002] The faults of photovoltaic modules can be divided into: one is caused by environmental factors, such as shadows caused by buildings, trees, clouds, dust, bird excrement, etc.; the other is the aging of photovoltaic modules due to long-term operation. The faults such as component short circuit, open circuit and mismatch of photovoltaic components are caused. These faults can be divided into soft faults and hard faults. Soft faults refer to faults that change with time, such as clouds passing by or shadows of buildings. This fault does not need to be eliminated. Hard faults refer to faults that do not change with time, such as dust, bird excrement, and short-circuit and open-circuit faults, so they need t...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method and device for training and identifying fault models of photovoltaic modules, which are used to solve the problem that manual inspections in the prior art are affected by terrain and cannot reach some areas, resulting in inspection blind spots and manual inspections that cost a lot Technical issues of time and human cost

Images