Infrastructure quality common fault prediction method and system based on artificial intelligence image recognition

The invention provides an infrastructure quality common fault prediction method and system based on artificial intelligence image recognition, and belongs to the technical field of infrastructure quality detection. The method comprises the following steps: establishing a sample database containing capital construction quality common fault models; establishing a current three-dimensional model of the current overhead line according to the capital construction data of the current overhead line and the image data of the current overhead line; taking the capital construction data and the environmental parameters as comparison attributes, and selecting capital construction quality common fault models with the similarity higher than a first percentage to be added into a first contrast set; by taking the defect characteristic data as comparison attributes, screening out an infrastructure quality common fault model with the similarity higher than a second percentage, and adding the infrastructure quality common fault