This paper constructs the framework of the reproducing kernel Hilbert space for multiple kernel learning, which provides clear insights into the reason that multiple kernel support vector machines (SVM) outperform single kernel SVM. These results can serve as a fundamental guide to account for the superiority of multiple kernel to single kernel learning. Subsequently, the constructed multiple kernel learning algorithms are applied to model a nonlinear blast furnace system only based on its input-output signals. The experimental results not only confirm the superiority of multiple kernel learning algorithms, but also indicate that multiple kernel SVM is a kind of highly competitive data-driven modeling method for the blast furnace system and can provide reliable indication for blast furnace operators to take control actions.
Note to Practitioners-This paper is motivated by the problem of predicting the silicon content in blast furnace hot metal, whichis an open problem for realizing blast furnace automation. Here, based on the single kernel and multiple kernel SVM, we pay special attention to the silicon trend prediction since it can provide more direct guideline for taking control action in the blast furnace operation. Theoretically, we have given the detailed reasons that multiple kernel SVM is superior to single kernel SVM, which can improve the transparency of multiple kernel learning algorithm. The experimental results, not only confirm the superiority of multiple kernel learning algorithms, but also indicate that multiple kernel SVM is a kind of highly competitive data-driven modeling method for the blast furnace system and can provide reliable indication for blast furnace operators to take control actions.Index Terms-Data-driven, multiple kernel support vector machines (SVM), nonlinear blast furnace system, quadratically constrained quadratic programming, reproducing kernel Hilbert space.