Structure control classification and optimization model of hollow carbon nanosphere core polymer particle based on improved differential evolution support vector machine

The structure of core polymer particle is an important index of efficiency in hollow carbon nanosphere. How to control and optimize the structure of core polymer particle has been investigated using pattern recognition method in this research. A novel method of pattern recognition material design based on differential evolution support vector machine was proposed. The control model was established and software was adopted to carry out a digital simulation for the model. Using the model, we found the control criteria and optimized conditions for pore structure of composite polymer. Then, the results are compared to other classification methodologies. Experimental results show this model has higher classification accuracy in most of data sets. Experimental and dynamics results show that the properties of hollow carbon nanosphere have been greatly improved.