Method for automatically separating data in each stage of shield tunneling process and computer readable medium

Abstract

The invention relates to a method for automatically separating data in each stage of a shield tunneling process and a computer readable medium. The method comprises the following steps: acquiring tunneling parameter data; extracting tunneling state data; judging whether the time nodes of adjacent data are continuous or not, and dividing each initial tunneling circulation section; smoothing the data; calculating a minimum peak point for each tunneling stage of the data, and segmenting the data to form single tunneling circulation sections; calculating a maximum peak point of the single tunneling circulation section, and segmenting the data into a rising section data segmentation point and a stable tunneling section data segmentation point according to the first maximum peak point; performing piecewise linear fitting on the data to calculate the slope, and taking positive and negative change points of the slope as segmentation points of a stable tunneling section and a descending section, so that separation of the stable section and the descending section is achieved; and obtaining the separated data of the ascending section, the stable tunneling section and the descending section. Compared with the prior art, the invention has the advantages that misjudgment can be effectively avoided, and data identification is complete.

Description

technical field [0001] The invention relates to the technical field of unmanned shield tunneling construction, in particular to a method for automatically separating data at each stage of a shield tunneling process and a computer-readable medium. Background technique [0002] Shield construction is developing towards intelligence from manual control to unmanned driving, in which the independent decision-making of tunneling parameters is an extremely important part. For this reason, a large number of scholars have used machine learning algorithms to carry out model training on the collected data and tried to Realize independent recommendation of tunneling parameters. Among them, the data used for machine learning model training is based on the data in the stable phase of the shield machine, so the separation and extraction of data in the ascending segment, stable segment, and descending segment is extremely important. [0003] In the prior art, research on the separation of ...

AI Technical Summary

Problems solved by technology

[0004] The above methods are all based on the time continuity of the excavation state or the continuous slope based on the separation of the rising segment data and the stable segment data. However, due to the fluctuation of the data and the multiple adjustments of the rising segment, it is difficult to ensure that the slope of the rising segment data is always constant. is positive, so these methods often can only identify part of the rising segment, and cannot accurately identify all the rising segment data

Images