欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对氧化铝生产蒸发过程铝酸钠溶液浓度难以在线检测问题,提出一种基于灰色关联分析和核主元分析相结合的支持向量机蒸发过程建模方法.该方法采用灰色关联分析和核主元分析过程可测参数确定出软测量模型的输入输出变量,再用混沌粒子群优化算法的最小二乘支持向量机构建软测量模型.通过灰关联和核主元分析,既可以全面广泛的筛选出输入变量,增强了模型的适应能力;又可以消除样本共线性,大大降低样本维数.以蒸发过程生产数据进行实验验证的结果表明,与KPCA-LSSVM和LSSVM相比,新模型收敛速度快、鲁棒性较强、精度较高、泛化性更好,能有效的实现蒸发过程铝酸钠溶液浓度的在线检测.
英文摘要：
Aiming at online testing problem of concentration of sodium aluminate solution in evaporation process of alumina production,a support vector machine modeling method based on gray relational analysis and kernel principal component analysis in evaporation process was proposed.The input and output variables of the prediction models were determined by analyzing process parameters based on principal components analysis and grey relational analysis.and then the LSSVM model was made based on chaotic PSO.The experimental results of industrial production data of evaporation process showed that,by grey relational analysis,the new model can filter out and deal with mass input variables without special subjective selection,enhance the adaptability of new model,eliminate redundancy and reduce dimension of the samples.Compared with KPCA-LSSVM and LSSVM model,the new model can provide a better convergence rate and also get good robustness,high accuracy,and better generalization.It can online measure concentration of sodium aluminate solution in evaporation process effectively.
同期刊论文项目
同项目期刊论文
Nonparametric density estimation of froth colour texture distribution for monitoring sulphur flotati
Kinetic Modeling and Parameter Estimation for Competing Reactions in Copper Removal Process from Zin
Operational patterns recognition using multi-class cost-sensitive learning for alumina evaporation p
Recognition of the operational statuses of reagent addition using dynamic bubble size distribution i
期刊信息
位置：