Underground karst cave detection method based on pile hammer shock excitation and k-nearest neighbor algorithm

Abstract

The invention discloses an underground karst cave detection method based on pile hammer shock excitation and a k nearest neighbor algorithm. The method comprises the following steps: firstly buildinga model library comprising different karst cave sizes and positions, and enabling the positions and sizes of karst caves in a model to be labels; secondly, conducting finite element calculation on themodel base, and obtaining acceleration responses of specific positions of the earth surface under different karst cave working conditions under pile hammer shock excitation; thirdly, conducting feature extraction on the acceleration response data, combining extracted features and labels into a database, randomly dividing a training set and a test set, inputting the training set into a k-nearest neighbor algorithm for machine learning, and obtaining a preliminary karst cave detection model based on the k-nearest neighbor algorithm; and finally, adjusting model parameters according to the prediction precision to obtain an optimal karst cave detection model based on a k-nearest neighbor algorithm. The method can effectively realize accurate recognition of the position and the geometric dimension of the underground karst cave, and has the advantages of lower cost and higher efficiency compared with the existing karst cave detection technology.

Description

technical field [0001] The invention relates to the technical field of karst cave detection, in particular to an underground karst cave detection method based on pile hammer shock and k-nearest neighbor algorithm. Background technique [0002] Karst caves refer to the space formed by soluble rocks under the action of karst, which widely exist in various provinces and cities in my country, especially in the southwest region. Underground karst caves pose a serious threat to the safety of foundation engineering construction. Under the action of slight disturbance of the soil layer, collapse may occur, and accidents such as grout leakage and hole collapse are also prone to occur during concrete pouring, resulting in economic losses and even threats to construction personnel. life safety. Therefore, the development of efficient karst cave detection technology can provide reliable technical support for the evaluation of the geological conditions of the soil layer in the early sta...

AI Technical Summary

Problems solved by technology

In addition, the response data obtained by sensors at different locations and at different times in the construction site is not only huge in quantity, but also complex and changeable due to external environmental interference data.

Images