Optimisation of sinter plant operating conditions and BF burden material resources using advanced multivariate statistics

The project has demonstrated that it is possible to differentiate between the effects of sinter bled, plant, process operations and their resultant effects on quality and productivity. This has enabled an improved window for process operation and blend optimisation to be defined. Developments related to blast furnace requirements having established the effects that sinter of different physical, mineralogy and chemistry and coke have on its operation. Defining the sinter and coke requirements for the blast furnace operating regime sinter quality, coke quality and productivity have been optimised as a function of cost and energy usage. The classification of sintering ores demonstrated by use of data clustering techniques gives the ability and confidence to assess new ores without undertaking pilot or plant based assessments. Tools developed and deployed for improved monitoring of sinter plant and blast furnace operation give permanent monitoring and provide a facility to identify deviations in performance. The tools meet the need of providing complex analysis and model development to plant technologists without having to have extensive knowledge of the underlying principles. Techniques applied including genetic algorithms, fuzzy systems, have been linked to traditional statistical techniques to refine the accuracy of the models. Reverse engineering of models has been developed to enable predict of the inputs, to achieve a required process output. The methods employed are transferable to other production facilities, or similar design and capacity. Where plant configurations are different, data associated with normal plant operations will have to be used to tune the models.