Research on early identification of burning status in a fire area in Xinjiang based on data-driven

Abstract

The early combustion stage in coalfield fire areas (CFA) is the initial phase of coal fire development and spread, making the effective identification of the combustion state crucial. To effectively identify the early combustion state of CFA, this study investigates the CFA in Xinjiang, China. Based on the abnormal characteristics of shallow soil and surface space, a data-driven evaluation method for identifying early combustion states of CFA is proposed. Construct a soil-gas dual-layer early combustion state assessment model of CFA. The evaluation model was applied and validated in the coal fire areas of Xinjiang, China.The results show that there are obvious differences in the spatial distribution of auto-ignition gas, temperature, humidity, surface vegetation coverage and other indicators in the shallow soil and surface space of the coal fire area. The early combustion states of coal fires in areas A, B, and C in the survey area are all in the combustion stage, the combustion state in area D is in the oxidation stage. The accuracy of the evaluation method is bidirectionally verified by the radon measurement method and the infrared thermal imaging detection method. It provides a theoretical basis for controlling the development and spread of coalfield fire areas.

Keywords

• Coalfield fire areas
• Data driven
• Triangular fuzzy analytic hierarchy process
• GIS
• Assessment method