Gaussian process multi-model modeling method based on AR model
基于AR模型思想的高斯过程多模型建模方法

The value of K is difficult to be exactly determined in K-nearest neighbor algorithm. This paper proposed a Gaussian process multi-model modeling method based on the idea of AR model. The method introduced the model output value of previous moments into the input set of the current moment, calculated the mean minimum distance of the training samples to get a search radius. And it determined the value of K according to the radius and calculated the weights of the output according to the K neighbor samples. Finally it took the weighted output mode to get the output of combinational model. The method was used for the soft-sensor model to estimate the content of phenol at the outlet of a reaction vessel in a Bisphenol A production process. The simulation results show that the method has a higher accuracy and better model generalization ability.