Furnace operation optimization with hybrid model based on mechanism and data analytics

The operation optimization problem of furnace process (OOPFP) is to obtain an optimal setting of furnace temperatures to make the reheated slabs have suitable temperature distribution with minimum energy consumption and oxide loss. Since the furnace process is complex, dynamic, and nonlinear, it is difficult to establish a precise process model for the OOPFP. In this paper, firstly, a novel hybrid modeling method combining temperature mechanism with data analytics is proposed to map the relationship of the temperature variables in the furnace process more accurately. The main idea of the hybrid modeling is to compensate for the deviation of original temperature mechanism model through the least squares support vector machine. Then, an improved differential evolution (DE) with feasible region dynamic adjustment strategy and population size gradual shrinking strategy is proposed to solve the OOPFP under hybrid model. Finally, extensive numerical experiments are carried out to demonstrate the effectiveness and accuracy of the hybrid model, and evaluate the performance of the improved DE on solving OOPFP. Experimental results show that the hybrid model is more precise than the original mechanism one, and the proposed DE outperforms other representative algorithms, respectively.