Soft Sensing Based on Hilbert-Huang Transform and Wavelet Support Vector Machine

At present, much more soft sensing have been widely used in industrial process control to improve the quality of product and assure safety in production. A novel method using Hilbert-Huang transform (HHT) combined with wavelet support vector machine (WSVM) is put forward. Firstly the method analyzes the intrinsic mode function (IMF) obtained after the empirical mode decomposition (EMD), then extracts IMF energy feature as the input feature vectors of the wavelet support vector machine. Based on the wavelet analysis and conditions of the support vector kernel function, a novel multi-dimension admissible support vector wavelet kernel function is presented, which is a multidimensional wavelet kernel, thus enhancing the generalization ability of the SVM. The proposed method is used to build soft sensing of diesel oil solidifying point. Compared with other two models, the result shows that HHT-WSVM approach has a better prediction and generalization.