Thermal image recognition of high-temperature brick wall in coking chamber

Diagnostic technology for coke-making plants under operation for many decades is a pressing concern in the domestic steel industry. This paper describes a new approach for monitoring carbon deposition on high-temperature coking chamber walls. Texture analysis based on gray-level co-occurrence matrices and other texture features was applied to thermal images. As a result, brick surface, solid carbon and patchy carbon could be distinguished with practicable accuracy.