Real-time coal classification in thermal power plants

Continuous variations in coal quality have a strong influence on operation of thermal power plants. However, in absence of real-time measurements of quality, the operators remain partially blind to the actual coal being consumed, leading to sub-optimal operation. A two-stage solution is proposed for real-time soft sensing of coal type. First, a novel semi-supervised cascaded clustering algorithm (SSCC) is utilized to extract coal classes from the historical sensor data of the plant and create a coal class library. The online stage includes a coal change detection algorithm to detect transition of coal and a SSCC-based coal classifier that enables real-time classification of coal using only the live sensor data. The algorithms are tested and verified with a set of synthetically generated industrial scale coal mill operation data. The real-time classification of coal can facilitate continuous optimum operation of plant vis-a-vis the emissions, efficiency and maintenance.

Automated summary

Continuous variations in coal quality have a significant impact on the operation of thermal power plants. This study proposes a two-stage solution for real-time soft sensing of coal type in order to improve the optimization of plant operation. By utilizing a semi-supervised cascaded clustering algorithm (SSCC) and online coal change detection algorithm, real-time classification of coal can be achieved using only live sensor data. The developed algorithms were tested and verified using synthetically generated industrial scale coal mill operation data. Real-time coal classification enables continuous optimum operation in terms of emissions, efficiency, and maintenance.