Building quality prediction method, device and storage medium based on deep learning

Abstract

The present invention provides a building quality prediction method, device and storage medium based on deep learning, including: acquiring quality data of multiple dimensions, and the quality data of each dimension respectively includes corresponding quality evaluation scores, dimension information and building type information; The dimension weight values ​​of different dimension information are determined based on the building type information, and the quality data of multiple dimensions of the same building have the same building type information; the variable values ​​in the first deep learning model are filtered according to the multiple dimension information to obtain the second a deep learning model, where variables in the second deep learning model correspond to quality data of multiple dimensions; and a third deep learning model is obtained by adjusting variable weights of variable values ​​in the second deep learning model based on the quality data of multiple dimensions; A plurality of quality evaluation scores and dimension weight values ​​are input into the third deep learning model to obtain building quality prediction results, accuracy prediction results and comprehensive results.

Description

technical field [0001] The present invention relates to the technical field of building quality, in particular to a deep learning-based building quality prediction method, device and storage medium. Background technique [0002] Construction project quality inspection refers to the activities of testing the materials, components, equipment, and project entity quality and use functions of construction projects to determine their quality characteristics in accordance with relevant national laws, regulations, mandatory standards for project construction and design documents. . [0003] In the process of building quality inspection, inspections of various dimensions and levels are included. For example, foundation engineering inspection, main structure engineering on-site inspection and building curtain wall engineering inspection, etc. Among them, foundation engineering testing includes foundation and composite foundation bearing capacity static load testing, pile bearing cap...

AI Technical Summary

Problems solved by technology

[0004] In the existing inspection process, most of the output is an absolute value of qualified and unqualified, which will cause many developers and builders to construct according to the minimum standard

It is impossible for the developer and the purchaser to have a quantitative concept of the quality of the qualified building project

Images