Prediction of Aluminum Electrolysis Superheat Based on Improved Relative Density Noise Filter SMO
Yunsheng Liu, Shuyin Xia, Hong Qi Yu, Yueguo Luo, Baiyun Chen, Kang Liu, Guoyin Wang · 2018
Adjusting superheat is very important in the production of aluminum electrolysis. However, due to the influence of the detection equipment and environment, there usually exist noise data which might have effects on the superheat adjustment. CNSMO(Class Noise based Sequential Minimal Optimization) [1] has a good performance in processing the data containing noise and prediction of superheat, which contains a large number of noise samples such that the generalizability of conventional SVMs deteriorates. The main reason is that the kernel mapping of the noise samples is likely to lead to overfitting in conventional SVMs [2]-[4]. However, ineffectiveness of CNSMO appears in asymmetric data. To deal with the problem, we optimize the relative density threshold and propose the IRDNF-SMO (Improved Relative Density Noise Filter based SMO algorithm). In the IRDNF-SMO, not only the relative density model is used for class noise detection, but the threshold of the relative density is optimized instead of setting to the fixed value such that the ineffectiveness is alleviated in asymmetric data. The experimental results on industry data sets and benchmark data sets demonstrated that the proposed algorithm has higher prediction accuracy in the data sets.