A soft-sensor model of VCM rectification concentration based on an improved WOA-RBFNN

Abstract

Abstract Due to the complex nonlinear relationship among many variables in the rectification process of vinyl chloride monomer (VCM), there is a problem that its concentration is difficult to measure in real time. A method based on the tabu whale optimization algorithm for optimizing the radial basis function neural network (RBFNN) to model the concentration of the VCM rectification process is proposed. Firstly, the t-distributed stochastic neighbor embedding algorithm is used to compress high-dimensional data into low-dimensional space to obtain new data, the input of the soft-sensor model, and to maximize the retention of information about the input data to minimize the impact on the data redundancy model. Secondly, since the whale optimization algorithm (WOA) is prone to produce local optimality, a tabu search algorithm is introduced to help it jump out of the local optimality. Finally, the improved WOA is used to optimize the parameters of the RBFNN model, and the model is applied to the comparison experiment in the process of vinyl chloride rectification. According to the simulation results, the method improves the prediction accuracy of the model and has better practicability.