Multisegment pulverised coal mill model and online implementation for condition monitoring

This paper presents a new multisegment coal mill mathematical model, which covers the whole milling process from mill start-up to shutdown. This model is initially derived through analysing energy transfer, heat exchange and mass flow balances of a coal mill. Evolutionary computational techniques are then adopted to identify the unknown system parameters. After the model was tested offline, it was converted into a discrete-time form for the purpose of online implementation. A shared-memory technique is employed to accommodate the measurement data dynamically in realtime, which provides a generic platform to communicate with different software environments used by different mill plants. A user-friendly interface is designed to satisfy the requirement specified by the plant engineers. The model can be used to improve the combustion process control and fault diagnosis.