RUL Prediction of the Injection Lance in Copper Top-Blown Smelting Using KPCA and TSO-Optimized LSSVM

As the core component of the copper top-blown smelting, the service life of the injection lance critically affects production stability. To monitor the operating condition of the injection lance, a data-driven model is proposed to predict the Remaining Useful Life (RUL) or service life, namely, the DKT-LSSVM model. Firstly, to reduce noise interference, the Daubechies wavelet with four vanishing moments (DB4) denoising is used to process the raw data. Then, the Kernel Principal Component Analysis (KPCA) method is utilized to extract the principal components from the denoised data, which retains at least 90% information content (18 principal components are obtained). These principal components are used as inputs to a Least Square Support Vector Machine (LSSVM) model to predict the RUL of the injection lance, and a Tuna Swarm Optimization (TSO) algorithm is proposed to optimize the hyperparameters of the LSSVM. The results show that the proposed algorithm performs well in RUL prediction of the injection lance, with RMSE=1.2274 (day), MAE=0.6623 (day) and R$^2$=0.9308. Therefore, the proposed algorithm can provide effective RUL prediction for the injection lance, reduce its operational risks, and improve the stability and reliability of the copper top-blown smelting system.