Mountain photovoltaic module construction management method and system based on Yolov8-OBB convolutional neural network, and medium
By adopting a construction management method based on Yolov8-OBB convolutional neural networks, the problems of data dispersion and manual dependence in the construction management of mountain photovoltaic modules were solved. The method achieved automated collection of construction progress and real-time data updates, improved management efficiency and resource allocation response speed, and accumulated reusable digital assets.
CN120913100APending Publication Date: 2025-11-07WUHAN SURVEYING GEOTECHN RES INST OF MCC
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202510883747.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-29
- Publication Date
- 2025-11-07
Smart Images

Figure CN120913100A_ABST
Abstract
The invention relates to a mountain photovoltaic module construction management method and system based on a Yov8-OBB convolutional neural network and a storage medium, and the method comprises the steps: collecting a photovoltaic module image of a mountain at a fixed point; preprocessing the image data of the photovoltaic module of the mountainous region; importing a volume neural network model based on Yolov8-OBB, and carrying out photovoltaic module image recognition; marking parameters are set, and model training is carried out on the Yov8-OBB; generating a result report; the information is uploaded to an enterprise digital intelligent construction cloud platform, classified, collected and stored; through screening and verification of data of different dimensions, completion data is formed; and uploading various data to an enterprise digital intelligent construction cloud platform to realize accumulation of enterprise engineering digital asset management information. According to the invention, intelligent management and control of construction process management can be effectively realized through deep learning and cloud cooperation. The method has remarkable advantages in the aspects of efficiency, cost and safety, and a reproducible technical path is provided for new energy engineering construction under complex terrains.
Need to check novelty before this filing date? Find Prior Art