The Development of a Monitoring and Control System for Pulverised Coal Flames Using Artificial Intelligence Techniques

This paper discusses the application of low cost sensors for monitoring pulverised coal flames. A series of burner diagnostics tests using Infra-red (IR), Microphone and Acoustic Emission (AE) sensors were conducted on a 150 kW pulverised fuel (pf) burner rig based at Casella CRE Ltd. in the United Kingdom. These experiments systematically varied the burner swirl number and the secondary airflow rate over a significant range for two different coals so that both satisfactory and ‘poor’ combustion conditions were obtained. The infra-red radiation from the flame, the combustion noise and the acoustic emission generated in the burner body were measured, as were the fuel and airflow rates and pollutant emissions. The signals from the sensors were analysed by using signal processing techniques to reveal a number of features. These in turn were compared with the three major combustion gases such as Nitrogen Oxides (NOx), Carbon monoxide (CO) and Oxygen (O₂) followed by correlation coefficient analysis (CCA). It is envisaged that these sensors can be used for predicting gaseous emissions and will be particularly attractive for multiple burner installations where the pollutant emissions are often discharged through a common manifold, so that the individual burner performance is often not known and cannot be optimised.