Intelligent identification method for abnormal body boundary in electrical imaging result

Abstract

The invention provides a clustering algorithm in unsupervised machine learning, and particularly aims to solve the problems that in the prior art, due to the fact that excitation field sources are electromagnetic waves or electric fields, diffusion effects naturally exist, imaging results are generally represented as contour map forms of resistivity, conductivity, polarizability, field intensity and the like, anomalous bodies and background values are always gradually changed and are in smooth transition, and the imaging quality is poor. There is no distinct difference, and manual determination of the accurate boundary of the anomalous body is difficult and low in efficiency. According to the data processing method for intelligently identifying the abnormal body boundary in the imaging result, the abnormal area and the background area can be accurately divided 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 boundaries of abnormal bodies in electromagnetic imaging results. Background technique [0002] Electromagnetic methods in geophysical surveying have a natural diffusion effect because the excitation field sources are electromagnetic waves or electric fields, and the imaging results are generally in the form of thermal maps of resistivity, conductivity, polarizability, and field strength. There is often a gradual and smooth transition between the abnormal body and the background value. The existing inversion models are all smooth models, which guarantee the calculation accuracy and speed. But in reality, there is no obvious difference, and it is difficult and inefficient to manually determine the exact boundary of the abnormal body. [0003] In recent years, my country's major coal mine acc...

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