Data driving algorithm for spontaneous combustion coal-mine fire big data platform

Abstract

The invention provides a data driving algorithm for a spontaneous combustion coal-mine fire big data platform, and relates to a probability estimation method for the spontaneous combustion coal-mine fire mark gas occurrence rate. The method comprises the following steps that 1, coal-mine mark gas concentration data is collected; 2, data is pre-processed; 3, the probability distribution type to which the mark gas growth rate belongs is judged through hypothesis test; 4, parameters of probability distribution are calculated through all mark gas occurrence rate data by means of a Maximum Likelihood Estimation method; 5, by means of the obtained parameters of the probability distribution, real probability distribution of the mark gas change rate is simulated through a large amount of data points by means of a Monte Carlo Simulation method; 6, by means of the real mark gas change rate distribution obtained in the last step, mark gas concentration distribution in future prediction time is obtained by multiplying time wanting to predict; 7 a mark gas concentration alarm limit is set, and the probability of occurrence is obtained.

Description

technical field [0001] The invention relates to the technical field of natural fire detection, in particular to a data-driven algorithm for a coal mine spontaneous combustion fire big data platform. Background technique [0002] my country's coal mines have a mining history of more than 100 years. With the increase of mine mining life, mining depth and mining scope, coal spontaneous combustion disasters are becoming more and more serious. Coalfield fires not only lost hundreds of millions of tons of coal, but also caused problems such as geological environment, ecological environment, and atmospheric environment, which will bring immeasurable harm to the sustainable development of my country's economy in the future. The coal dust and gas explosions caused by mine fires will lead to serious coal mine accidents, freeze a large amount of coal resources and production equipment, and cause huge economic losses and casualties. Therefore, the prevention of spontaneous coal fire ac...

AI Technical Summary

Problems solved by technology

This type of method mainly has two kinds of deficiencies: (1) because downhole conditions are complex and changeable

Environmental factors and human factors, such as ventilation, gas content, temperature, construction plan, working face advancement speed and other conditions are many and complex, which will have a great impact on the prediction of fire development trend, while traditional theoretical models and other deterministic prediction methods However, all variable conditions cannot be considered, and the fire development trend can only be fitted mechanically, and the prediction accuracy is often very low; (2) There are a lot of uncertainties in the underground environment and human factors

Due to the changeable environment and human factors, many variables are random and uncertain, and the prediction of traditional theoretical models cannot reflect the influence of these randomness, which seriously affects the credibility of the prediction results of traditional methods. The security guidance of the lack of practical significance

Images