Prediction of CO₂ Solubility in Polymers by Radial Basis Function Artificial Neural Network Based on Chaotic Self‐adaptive Particle Swarm Optimization and Fuzzy Clustering Method

Abstract

To replace costly and time-consuming experimentation in laboratory, a novel solubility prediction model based on chaos theory, self-adaptive particle swarm optimization (PSO), fuzzy c-means clustering method, and radial basis function artificial neural network (RBF ANN) is proposed to predict CO 2 solubility in polymers, hereafter called CSPSO-FC RBF ANN. The premature convergence problem is overcome by modifying the conventional PSO using chaos theory and self-adaptive inertia weight factor. Fuzzy c-means clustering method is used to tune the hidden centers and radial basis function spreads. The modified PSO algorithm is employed to optimize the RBF ANN connection weights. Then, the proposed CSPSO-FC RBF ANN is used to investigate solubility of CO 2 in polystyrene (PS), polypropylene (PP), poly(butylene succinate) (PBS) and poly(butylene succinate-co-adipate) (PBSA), respectively. Results indicate that CSPSO-FC RBF ANN is an effective method for gas solubility in polymers. In addition, compared with conventional RBF ANN and PSO ANN, CSPSO-FC RBF ANN shows better performance. The values of average relative deviation (ARD), squared correlation coefficient (R 2 ) and standard deviation (SD) are 0.1071, 0.9973 and 0.0108, respectively. Statistical data demonstrate that CSPSO-FC RBF ANN has excellent prediction capability and high-accuracy, and the correlation between prediction values and experimental data is good.

Synthesis of carbon nanotube‐based nanocomposite and application for wastewater treatment by ultrasonicated adsorption process

“…The main key to a successful implementation of RBFNN is to find three important parameters: the hidden centres, the radius (spread) of each RBF function in each dimension and the number of neurons …”

Prediction of the stress relaxation property of diene rubber composites by artificial neural network approaches

“…25,29 Differing from universal approximation neural networks, such as a multilayer perceptron, RBF employs specic radial basis functions in hidden layer nodes to realize nonlinear mapping. 25,29 Differing from universal approximation neural networks, such as a multilayer perceptron, RBF employs specic radial basis functions in hidden layer nodes to realize nonlinear mapping.…”

“…where w ik is the ith-row kth-column element in the matrix W. Previous studies 25,29,30,33,35 indicated that empirical formula and heuristics were generally adopted to optimize and determine the number of hidden layer nodes. Therefore, a batch operation parameter training method was used to train the RBF in this study.…”

A double-population chaotic self-adaptive evolutionary dynamics model for the prediction of supercritical carbon dioxide solubility in polymers

“…In recent years, dissolution calculation models have been widely considered and mainly include traditional models based on mathematical theory and computational models based on information technology [12,[16][17][18][19][20][21][22]. Mathematical models mainly include thermodynamic equation of state models and empirical/semi-empirical models.…”