Building post-earthquake damage grade classification method based on deep learning

Abstract

The invention provides a building post-earthquake damage grade evaluation method based on deep learning, relates to the field of earthquake engineering, and is characterized in that damaged and damaged house images in an earthquake area are acquired, marked and a data set is established, and the buildings in the images are subjected to earthquake damage classification based on deep learning. According to the method, accurate damage classification can be quickly and efficiently performed on the building in the earthquake-bearing area, the calculation capability and the quick decision-making capability of the deep neural network can be utilized to replace on-site manual evaluation, time and energy consumption is greatly reduced, and under the condition that the accuracy is ensured, the damage condition of the building in a large-range earthquake-bearing area is efficiently judged.

Description

technical field [0001] The invention relates to a method for classifying post-earthquake damage levels of buildings based on deep learning, and belongs to the technical field of earthquake engineering. Background technique [0002] In the post-earthquake damage assessment of buildings, it is necessary to quickly assess the damage of buildings in the disaster area after the earthquake, so as to obtain the number and degree of damage of buildings after the earthquake in a timely manner, which is convenient for later auxiliary decision-making and emergency rescue. In order to accurately classify the damage levels of buildings in the earthquake-damaged area, it is necessary to promptly investigate the distribution and quantity of disasters after the earthquake and conduct a rapid assessment. [0003] In the earthquake emergency phase, fast, timely and accurate building safety appraisal is an effective way to properly resettle the victims; it can prevent secondary disasters cause...

AI Technical Summary

Problems solved by technology

The manual detection method is not only time-consuming, but also requires a lot of manpower, material and financial resources, and has the characteristics of low detection accuracy and large influence of human factors

Apart from this, in many cases it is not possible to detect the crack visually due to the inaccessibility of the area or the microscopic size of the crack

Such hidden cracks can reduce the strength of the structure, leading to ductile or brittle failure, which poses a serious safety hazard

Images