XGBoost-based underground comprehensive pipe gallery safety condition evaluation method

Abstract

The invention relates to an XGBoost-based underground comprehensive pipe gallery safety condition evaluation method in the field of underground comprehensive pipe gallery safety. The method comprisesthe steps of S1, obtaining an original data sample of an underground pipe gallery; s2, preprocessing the original data sample; s3, performing feature construction on the preprocessed data to obtain adata set after feature construction; s4, performing feature selection on the data set after feature construction to obtain a data sample set; and S5, inputting the data sample set into an XGBoost algorithm model for model training to obtain a safety condition evaluation model, and determining the safety state of the underground pipe gallery according to an output result. According to the method, the collected data are preprocessed according to the characteristics of the underground pipe gallery, and a machine learning method is adopted, so that the judgment of the safety condition of the dataunderground comprehensive pipe gallery is more accurate and intelligent, the management efficiency is improved, and the management cost is reduced.

Description

technical field [0001] The invention relates to the safety field of an underground comprehensive utility gallery, in particular to an XGBoost-based method for evaluating the safety status of an underground comprehensive utility gallery. Background technique [0002] As the lifeline of the city, the underground comprehensive utility corridor is a collection of various pipeline facilities. The system is huge and complex, and there are many potential safety risks. question. A large amount of data generated during the operation of the underground utility tunnel is currently not being utilized, resulting in a waste of management resources. [0003] The safety status of the underground utility tunnel is very important, and it is related to the environment inside the utility tunnel (CO 2 Concentration, temperature, humidity, CH 4 Concentration), the operation and maintenance status of the pipe gallery (equipment service life, equipment maintenance times, equipment purchase time)...

AI Technical Summary

Problems solved by technology

[0005] (1) Traditional distributed monitoring mostly adopts manual management mode, the operation and management cost is high, and the management level and quality cannot be effectively guaranteed;

[0006] (2) The monitoring and processing system has a large demand for data collection capabilities, which is likely to cause congestion in the information and data transmission process, and poor ability to analyze and judge disaster situations;

[0007] (3) There are various types of management monitoring video and monitoring data, and there is a problem of information islands between systems, which brings difficulties to the decision-making of relevant departments

Images