基于模糊核聚类的乙烯裂解深度DE-LSSVM多模型建模

Multiple DE-LSSVM modeling of ethylene cracking severity based on fuzzy kernel clustering

乙烯裂解深度的建模与控制对于裂解炉的实时优化具有重要意义。针对石脑油原料组分复杂、油品特性波动大等状况,采用模糊核聚类对石脑油数据库进行最优划分,建立最小二乘支持向量机的多模型,对于最小二乘支持向量机中模型的参数选取,利用差分进化算法进行参数寻优,提高了模型的精度和泛化能力。通过对现场数据的建模实验,结果表明:基于模糊核聚类的乙烯裂解深度最小二乘支持向量机多模型跟踪性能良好,预测精度较高。

Modeling and control of ethylene cracking severity is very important to the real-time optimization of cracking furnace.To address the problem with the complexity and volatility of naphtha feedstock components,fuzzy kernel clustering method was developed to divide the naphtha database optimally.After establishing multiple models of least squares support vector machine（LSSVM）,in order to improve the model accuracy and generalization ability,differential evolution algorithm was used to determine the proper parameters of the LSSVM model.We established each sub-model based on the sub-condition in ethylene cracking process,also the switching strategy was based on weighted value.The simulation results on the real industrial data showed that DE-LSSVM multiple models of ethylene cracking severity based on fuzzy kernel clustering got good tracking performance and high accuracy.