This paper describes the development of an intelligent Flame Diagnostic System which is able to monitor the combustion characteristics of individual burners based on direct measurement and analysis of the flame radiation signals. A series of experiments were conducted on a 500 kW pilot-scale furnace fitted with both a single burner and also two burners firing in a regenerative manner. The experiments covered a wide range of burner operating conditions including variations in the burner firing-rate and excess air level. A fibre-optic based optical instrument, incorporating broad ultraviolet, visible and infrared photo diodes was developed and used to acquire the dynamic flame signals through a data acquisition system. These flame signals were then analysed off-line, using simple signal processing methods, to yield a set of flame features. Correlation of these flame features with respect to the excess air level and NOx emissions were made using neural network models. The present work indicates that the measurement of flame radiation characteristics, coupled with advanced data modelling techniques such as neural networks, provides a promising means of monitoring and optimising burner performance.