Concrete structure defect detection method based on elastic wave and machine learning

Abstract

The invention discloses a concrete structure defect detection method based on elastic wave and machine learning, which adopts an impact elastic wave as a detection medium, utilizes picked-up signal characteristics and combines machine learning to obtain an analysis model, thereby detecting concrete structure defects. Signal features mainly use the spectral characteristics and spectral cumulative deviation rate, and establish attributes for machine learning; the benchmark parameters reflecting the mechanical properties of concrete are obtained by acquiring the information of the sound part of concrete structure. By testing the sound concrete structure and defective concrete structure under various structural thicknesses and working conditions, the signal characteristic attribute is analyzed, and the training set is built for machine learning and the analysis model is obtained; the test data of concrete structure in unknown state are analyzed by using the analysis model, and the analysisresults are verified. The data and validation results are added to the training set as examples, and the above steps are repeated to optimize the analysis model and improve the accuracy.

Description

technical field [0001] The invention relates to a detection method, in particular to a detection method for concrete structure defects based on elastic waves and machine learning. Background technique [0002] Concrete structure is the most widely used and most important building and civil structure today. Its large-area concrete structure like tunnel lining acts as a supporting superstructure in engineering, which directly affects the safety of the tunnel construction process and operation stage. However, during the construction process, there will still be defects in the concrete structure due to reasons such as cutting corners, backward construction technology, wrong construction steps or human negligence. [0003] Corresponding to the concrete structure of concealed engineering, there are many detection methods for non-destructive testing of concrete structure defects under the premise of no damage, such as shock elastic wave, geological radar, ultrasonic, etc. The two ...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the problem of low precision and accuracy in the detection of concrete structure defects. The present invention provides a method for detecting defects in concrete structures based on elastic waves and machine learning that solves the above problems

Images