Structure damage detection system and method based on voiceprint recognition

Abstract

The invention discloses a structural damage detection system and method based on voiceprint recognition. An on-site knocking detection module is used for detecting an on-site structure and obtaining continuous sound signals; a primary audio anomaly detection module is used for receiving input of continuous sound signals and outputting feature vectors formed by various voiceprint features to the damage feature classification detection module; a damage feature classification detection module outputs an undetermined damage category of the internal damage through a machine learning classification algorithm; a damage feature re-checking module feeds back an undetermined damage category to the field knocking detection module, and a field knocking detection module adjusts the knocking detection frequency and intensity according to preset damage voiceprint features and outputs the re-checked damage category to an alarm module; the alarm module records the damage type and the damage occurrence position. According to the system, dependence on experience and technology of detection personnel is reduced, operation is more visual, and the result is more accurate.

Description

technical field [0001] The invention relates to the technical field of structural damage detection, in particular to a structural damage detection system and method based on voiceprint recognition. Background technique [0002] Nondestructive testing methods such as ultrasonic rebound, acoustic emission testing, X-ray projection, and infrared scanning are commonly used in engineering applications in order to achieve the purpose of detecting structural damage. However, the current status of engineering applications in developed countries such as the United States and Japan shows that the current nondestructive testing technology is far from meeting the requirements of practical engineering applications. At the same time, it is necessary to quickly judge the damage type, location, and degree after collecting signals on site. The main reason is that due to the high price of testing equipment and different working principles and performances, especially for the rapid detection ...

AI Technical Summary

Problems solved by technology

However, this kind of automatic rapid detection technology is mainly based on optical image detection technology, which can only detect the damage on the surface of the structure. In order to further understand the damage inside the structure, it is necessary to develop an automatic rapid detection method for the internal damage of the structure.

Images