A control scheme for a furnace can use real-time and historical data to model performance and determine relationships between different data and performance parameters for use in correcting suboptimal performance of the furnace in real-time. Operational parameters can be logged throughout the cycle for all cycles for a period of time in order to establish a baseline. This data can then be used to calculate the performance of the process. A regression analysis can be carried out in order to determine which parameters affect different aspects of performance. These relationships can then be used to predict performance during a single cycle in real-time and provide closed or open loop feedback to control furnace operation to result in enhanced performance.