Dynamic Coal-Rock Interface Identification Based on Infrared Thermal Image Characteristics

In this study, a new method was proposed to identify the coal-rock interface based on infrared thermal image characteristics during cutting process, which overcomes the problem of low identification accuracy. The cutting signals change significantly with the coal-rock proportion, thus, seven coal-rock mixture test specimens with different proportions were poured. Then, the infrared thermal images of peak were tested while cutting coal-rock specimens with different proportions. Furthermore, by analyzing the flash temperature characteristics of picks, a temperature characteristic database of peaks while cutting different coal-rock specimens was built. Finally, a dynamic recognition model for coal-rock interface identification was established based on minimum fuzzy entropy. The experimental results show that, the total recognition error was merely 3.24%, which proved that the proposed method improved the identification accuracy effectively and provided the theoretical foundation and technical premise to realize automatic and intelligent mining.