Device and method for monitoring structural health degree of structural body based on deep learning

Abstract

The invention relates to a deep learning-based structural health degree monitoring device for a structural body and a monitoring method adopting the deep learning-based structural health degree monitoring device. The health degree monitoring equipment works in a passive monitoring mode or an active monitoring mode, and comprises a vibration generation unit; a sensing unit; and a monitoring degree monitoring device. The defect that traditional subjective judgment of structural health conditions by people is inaccurate is overcome, and more scientific and quantitative accurate information is provided. According to the method, a fine-tuned VGGish network model is used for classifying and recognizing vibration signals collected by monitoring equipment, and the structural health degree is obtained. According to the method, the deep learning technology is applied to structural health monitoring, the tedious task of researching and representing traditional features of a structural damage state is avoided, and a deep learning network model is used for automatically learning the features to realize classification and recognition.

Description

technical field [0001] The invention relates to a structural health monitoring device and a monitoring method using the device, in particular to a structure health monitoring device based on deep learning and a monitoring method using the device. Background technique [0002] Modern society is inseparable from structural and mechanical engineering, such as space shuttles, bridges, power generation systems, rotating machinery, offshore oil platforms, housing construction and defense systems. Many existing projects are approaching their design life, which may cause safety problems or cause significant economic losses at any time. Therefore, pre-judging the damage-aware structure status has become an urgent problem to be solved. [0003] The term structural health monitoring generally refers to the process of applying damage diagnosis in infrastructure such as aerospace, civil and mechanical engineering. Since the 1990s, my country has installed bridge structural health monit...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: the structural health monitoring method based on single feature extraction is easily affected by environmental noise, resulting in unstable performance of structural health quantitative analysis

Images