Failure precursors recognition method for loading coal and rock using the fracture texture features of infrared thermal images.

• The Contrast Texture Feature Values (CTFV) is proposed to extract subtle changes in the thermal image caused by crack evolution based on the Gray Level Co-occurrence Matrix (GLCM). • The cumulative Crack Texture Thermal Image (CTTI) is reconstructed using CTFV, which can reflect the spatial evolution process of loading coal and rock cracks. • The CTFV can provide readily identifiable precursor information for the coal and rock failure, and the precursor can be divided into high risk, medium risk, and low risk levels based on different gray levels. • An anomaly detection method for CTFV was proposed based on sliding window probability density estimation to achieve real-time and adaptive recognition of rock failure precursors. Early warning of the catastrophic failure of rocks is a challenging rock mechanics problem. This article proposed a failure precursor recognition method based on infrared thermal image texture features for coal and rock. Based on spatiotemporal background noise correction for infrared thermal images, a new thermal image parameter of loading coal and rock, Contrast Texture Feature Values (CTFV), is proposed to extract subtle changes in the thermal image caused by crack evolution based on the Gray Level Co-occurrence Matrix (GLCM). The cumulative Crack Texture Thermal Image (CTTI) is reconstructed using CTFV, which can accurately reflect the spatial evolution process of loading coal and rock cracks. The CTFV remains at 0 in the early stage of loading and gradually increases with stress increase at the unstable crack propagation stage, which can serve as a reference for precursor warning of coal and rock failure. For shale, sandstone, and limestone, the precursor of CTFV at grayscale levels of 7, 8, and 9, can be classified into high failure risk, medium failure risk, and low failure risk, respectively. For coal samples, the CTFV is only applicable for the critical warning of high failure risk when the grayscale level is 7. Then, an adaptive identification method for failure precursors based on the sliding window probability density estimation method is proposed. The research results can enhance the reliability of IR monitoring technology for rock failure and instability early warning and can provide support for the prevention and control of rock engineering and geological disasters. [ABSTRACT FROM AUTHOR]