Bridge deck pavement crack propagation sensitivity analysis method and device based on GA-BP neural network and storage medium

• Main Authors: QIAN ZHENDONG, REN HAISHENG, CAO HAIBO, CHEN TUANJIE, LIU YANG, HUANG WEI
• Format: Patent
• Language: Chinese; English
• Published: 07.06.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to a bridge deck pavement crack propagation sensitivity analysis method and device based on a GA-BP neural network and a storage medium, and the method comprises the steps: S1, obtaining a plurality of groups of test data which comprise the value of each sensitivity parameter and the value of the corresponding maximum crack volume; s2, on the basis of the obtained test data, a fracture volume prediction model is trained, and the fracture volume prediction model is a GA-BP neural network; s3, selecting a sensitive parameter; s4, controlling the selected sensitivity parameters to change in a corresponding pre-configured range, and keeping other sensitivity parameters unchanged to obtain a plurality of target prediction data groups, inputting each obtained target prediction data group into a trained fracture volume prediction model to obtain a predicted value of the maximum fracture volume corresponding to each target prediction data group; s5, judging whether traversal of all the sensitive