Microseism P-wave first arrival pickup method and system based on capsule neural network

Abstract

The invention relates to the technical field of microseism data processing, in particular to a microseism P-wave first arrival pickup method and system based on a capsule neural network. The method comprises the steps of preparing an original data set, making a data training set, selecting first arrival points of a part of sample signals of the original data set, labeling the first arrival pointsto serve as a labeled part, and taking the other part of sample signals as a label-free part, inputting the data training set into a combined training model, and predicting and evaluating the characteristics of the microseism signals, carrying out target detection on the microseism signal characteristics to obtain a first arrival point of the microseism signal. The system comprises a data acquisition module, a data training set making module, a data training module and an output module. According to the embodiment of the invention, the capsule neural network and the semi-supervised learning are combined, and the RPN network is used for detecting the microseism signal, thereby achieving the pickup of the first arrival point of the microseism signal, and improving the feature extraction accuracy of the microseism signal and the accurate pickup of the P-wave first arrival point.

Description

technical field [0001] The invention relates to the technical field of microseismic data processing, in particular to a method and system for picking up microseismic P wave first arrival based on a capsule neural network. Background technique [0002] The effective detection of microseismic signals is of great significance to the stable and high production of oilfield development. Usually the microseismic effective signal energy is weak, the signal-to-noise ratio is low, and even completely submerged in the noise. Although there are many conventional seismic data processing methods, if they are directly applied to microseismic data, they often cannot obtain satisfactory results, which will directly affect the quality and accuracy of microseismic monitoring. Therefore, finding a suitable method to identify weak effective signals in microseismic data is the key to microseismic data processing and interpretation. [0003] In 2018, in the paper "Method of Microseismic P-wave A...

AI Technical Summary

Problems solved by technology

[0004] The disadvantage of the existing technology is that although this method can improve the signal recognition rate to a certain extent, the accuracy rate of extracting microseismic signal features is not high, resulting in only 73.5% of the accuracy rate of P wave first arrival point picking

Images