¹ School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China, 510640
² School of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China, 518060
³ Shenzhen Key laboratory of mould advanced manufacture, Shenzhen, China, 518060

---

Abstract—Temperature forecasting of hydrogen-producing reactor is a complicated problem due to its nonlinearity and the small quantity of training data. Support vector machine (SVM) has been successfully employed to solve regression problem of nonlinearity and small sample. The determination for hyper-parameters including kernel parameters and the regularization is important to the performance of SVM. Particle Swarm Optimization (PSO) is a method for finding a solution of stochastic global optimizer based on swarm intelligence. Using the interaction of particles, PSO searches the solution space intelligently and finds out the best one. Thus, the proposed forecasting model based on the global optimization of PSO and local accurate searching of SVM is applied to forecast hydrogenproducing reactor temperature in this paper. Practical example results indicate that the application of the PSOSVM method to temperature forecasting of hydrogenproducing reactor is feasible and effective. And to prove the effectiveness of the model, other existing methods are used to compare with the result of SVM. The results show that the model is effective and highly accurate in the forecasting of hydrogen-producing reactor temperature.

Index Terms—Support vector machine, Particle swarm optimization, parameter selection, prediction

[PDF]

Cite: Minqiang Pan, Dehuai Zeng, and Gang Xu, " Temperature Prediction of Hydrogen Producing Reactor Using SVM Regression with PSO," Journal of Computers vol. 5, no. 3, pp. 388-393, 2010.