An Intelligent Recognition Method of Abnormal Body Boundary in Electrical Imaging Results

Abstract

The present invention proposes a clustering algorithm using unsupervised machine learning, especially in the prior art because the excitation field sources are electromagnetic waves or electric fields, there is a natural diffusion effect, and the imaging results generally show resistivity, conductivity, polarization, etc. In the form of contour diagrams of rate and field strength equivalents, there is often a gradual and smooth transition between the anomaly body and the background value, and there is no obvious difference. It is difficult and inefficient to manually determine the exact boundary of the anomaly body. The data processing method of the invention intelligently recognizes the boundary of the abnormal body in the imaging result, and can accurately divide the abnormal and background regions in real time.

Description

technical field [0001] The invention belongs to the technical field of geophysical surveying, and relates to a data processing method capable of quickly and intelligently identifying the boundary of an abnormal body in an electromagnetic imaging result. Background technique [0002] Electromagnetic methods in geophysical surveys have a natural diffusion effect because the excitation field sources are all electromagnetic waves or electric fields. There is often a gradual and smooth transition between the abnormal body and the background value. The existing inversion models are all smooth models to ensure calculation accuracy and speed. However, in reality, there is no clear difference, and it is difficult and inefficient to manually determine the accurate boundaries of abnormal bodies. [0003] In recent years, my country's coal mine major accidents have generally shown a downward trend, but the number of major and major flood accidents and the number of deaths have increase...

AI Technical Summary

Problems solved by technology

[0005] The data processing of borehole transient electromagnetic generally adopts the resistivity inversion imaging method. Considering the multi-solution of the inversion, in order to improve the accuracy in the inversion fitting process, a smoother model is often selected to fit the measured data, so that The final inversion result is an imaging model with continuous, smooth, and gradual changes in resistivity. The contrast and changes at the boundaries of geological bodies are relatively vague, and it is difficult to clearly reflect the difference between geological anomalies and background values. Interpretation work often requires human intervention by experienced experts, which is not conducive to accurate guidance of geophysical prospecting work in production and subsequent drilling and tunneling work

Images