Empirical Formula Index Soft Sensing of Raw Material Burnability Based on PSO-LSSVM

The burnability of cement raw materials is crucial for cement production. Currently, the burnability index of raw materials cannot be obtained in real time. In order to enable this index to be obtained online, this paper establishes a PSO-LSSVM soft sensing model for raw material burnability index. The model uses particle swarm optimization (PSO) algorithm to optimize the RBF kernel function parameter <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\sigma^{2}$</tex> and penalty coefficient <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$c$</tex> in the least squares support vector machine LSSVM model, improving the prediction accuracy of the model and verifying the feasibility of the scheme. It provides a solution to the difficulty of obtaining the burnability index variable online and helps with online control of the cement production process.