Prediction of Alumina Density Based on LSSVM

doi:10.16182/j.issn1004731x.joss.201805029

Abstract

Abstract: The prediction model of alumina density based on the PSO algorithm with swarm activity to optimize LSSVM method is built. According to the production process characteristics of aluminum electrolysis and historical data, the input variables of the model is determined. It can solve these problems that Particle Swarm Optimization (PSO) algorithm is with the risk of premature convergence and least square support vector machine is time consuming with parameter selection. The method uses swarm activity as diversity index. When swarm activity is quickened to descend, evolution operation is added to modify the positions or velocities of particles to improve standard PSO algorithm. Study shows that, the improved PSO-LSSVM prediction method has better estimating performance and less computational time than the traditional LSSVM method.

Key words: aluminum electrolysis, alumina density, least squares support vector machine, particle swarm optimization

CLC Number:

TP391.9

Cui Guimei, Yang Haijin, Liu Piliang, Yu Kai. Prediction of Alumina Density Based on LSSVM[J]. Journal of System Simulation, 2018, 30(5): 1844-1849.

References

[1] 林景栋, 吕函坷, 朱斌泉. 基于正交预测的铝电解槽氧化铝浓度判定[J]. 控制工程, 2012(5): 873-876.
Lin Jingdong, Lü Hanke, Zhu Binquan.Determination of alumina density based on orthogonal prediction[J]. Control Engineering Of China, 2012(5): 873-876.
[2] 郭俊, 桂卫华. 铝电解生产过程的多目标优化[J]. 中南大学学报(自然科学版), 2012, 43(2): 548-553.
Guo Jun, Gui Weihua.Multi-objective optimization for aluminum electrolysis production process[J]. Journal of Central South University(Natural Science), 2012, 43(2): 548-553.
[3] 张愉. 氧化铝浓度的RBF神经网络软测量模型研究[J]. 计算机测量与控制, 2010(11): 242-247.
Zhang Yu.Study on RBF Neural Network Soft Sensing Model of Alumina Concentration[J]. Computer Measurement & Control, 2010(11): 242-247.
[4] 李家界, 马驰, 郭宏伟, 等. 基于铝电解过程的神经网络模型预测控制的应用研究[J]. 轻金属, 2007(3): 25-28.
Li Jiajie, Ma Chi, Guo Hongwei, et al.The Research and application Of Neural Network model predictive control based on aluminum electrolysis process[J]. Light Metals, 2007(3): 25-28.
[5] 蒋少华, 桂卫华, 阳春华. 基于RS与LSSVM多分类法的障诊断方法及应用[J]. 中南大学学报(自然科学版), 2009, 40(2): 447-451.
Jiang Shaohua, Gui Weihua, Yang Chunhua.Fault diagnosis method and application based on RS and LSSVM multi classification method[J]. Journal of Central South University(Natural Science), 2009, 40(2): 447-451.
[6] 孙斌, 姚海涛. 基于PSO优化lssvm的短期风速预测[J]. 电力系统保护与控制, 2012, 40(5): 85-89.
Sun Bin, Yao Haitao.The short-term wind speed forecast analysis based on the PSO-LSSVM predict model[J]. Power System Protection and Control, 2012, 40(5): 85-89.
[7] 左旭坤, 苏守宝. 一种群活性反馈粒子群优化算法[J]. 计算机工程, 2012, 38(13): 182-184.
Zuo Xukun, Su Shoubao.Particle Swarm Optimization Algorithm with Swarm Activity Feedback[J]. Computer Engineering, 2012, 38(13): 182-184.
[8] 刘华董, 林玉娥, 张君施. 基于混沌搜索解决早熟收敛的混合粒子群算法[J]. 计算机工程与应用, 2006, 42(13): 77-79.
Liu Huadong, Lin Yue, Zhang Junshi.A Hybrid Particle Swarm Optimization Based on Chaos Strategy to Handle Local Convergence[J].Computer Engineering and Application, 2006, 42(13): 77-79.
[9] Xi Yugeng, Geng Xiaojun, Chen Hong.Progress of predictive control performance study[J]. Control theory and applications (S1000-8152), 2012, 17(4): 74-75.
[10] 刘雅锋, 廖贤安. 铝电解槽内衬的应力分析与结构设计[J]. 轻金属, 2013(6): 27-29.
Liu Yafeng, Liao Xian’an.Lining stress analysis and structure design of aluminum electrolysis pots[J]. Light Metals, 2013(6): 27-29.
[11] 周乃军, 童道辉, 张家奇, 等. 导流式铝电解槽电一热平衡计算建模与应用[J]. 中南大学学报(自然科学),2011, 42(12): 3888-3893.
Zhou Naijun, Tong Daohui, Zhang Jiaqi, et al.Modeling and application of electric heat balance calculation for diversion aluminum reduction cell[J].Journal of Central South University(Natural Science), 2011, 42(12): 3888-3893.
[12] 邓胜祥, 马和平, 谢青松, 等. 预焙铝电解槽在线仿真槽况诊断专家系统研究[J]. 计算机测量与控制, 2011, 19(8): 1850-1852.
Deng Shengxiang, Ma Heping, Xie Qingsong, et al.A Study of On-line Simulation and Cell Condition Diagnosis Expert System of Prebaked Cell for Aluminum-reduction[J]. Computer Measurement & Control, 2011, 19(8): 1850-1852.
[13] Li J, Wang J.Research of temperature predictive control based on LSSVM optimized by improved PSO for thick steel plate roller hearth normalizing furnace[J]. Intelligent Control & Automation (S2153-0653), 2010: 3717-3721.
[14] Zhou Tianpei.Study of alumina density control based on intelligent characteristic model[J]. Trans Tech Publications (S1142-9021), 2011(3): 27-29.
[15] 崔喜风, 张红亮, 邹忠, 等. 铝电解槽电热场计算精度与网格密度的关系[J]. 中南大学学报(自然科学版), 2011, 42(3): 574-578.
Cui Xifeng, Zhang Hongliang, Zou Zhong, et al.Relationship between thermal-electrical calculation accuracy of aluminum reduction cells and mesh density[J]. Journal of Central South University (Natural Science)2011, 42(3): 574-578.
[16] 张红亮, 张翩辉, 李劫, 等. 160 kA预焙铝电解槽电流强化后热平衡的数值计算[J]. 轻金属, 2011(11): 33-36.
Zhang Hongliang, Zhang Pianhui, Li jie, et al. Numerical calculation of heat balance adjustment of 160kA pre- baked aluminium reduction pot after current strengthen[J]. Light Metals, 2011(11): 33-36.
[17] 乔宗良, 张蕾, 周建新, 等. 一种改进的CPSO- LSSVM软测量模型及其应用[J]. 仪器仪表学报, 2014(1): 234-240.
Qiao Zongliang, Zhang Lei, Zhou Jianxin, et al.Soft sensor modeling method based on improved CPSO-LSSVM and its applications[J]. Chinese Journal of Scientific Instrument, 2014(1): 234-240.
[18] Cao Danyang, Zeng Shuiping, Li Jinhong.Variable universe fuzzy expert system for aluminum electrolysis[J]. Ransactions of Nonferrous Metals Society of China (S1003-6326), 2011, 21(2): 429-435.
[19] 郭俊, 桂卫华. 基于网格聚类LS-SVM的铝电解生产过程极距软测量[J]. 控制与决策, 2012, 27(8): 1261-1264.
Guo Jun, Gui Weihua.Soft-sensing of polar distance for aluminum electrolysis production process based on grid-based clustering LS-SVM[J]. Control and Decision, 2012, 27(8): 1261-1264.
[20] 穆朝絮, 张瑞民, 孙长银. 基于粒子群优化的非线性系统最小二乘支持向量机预测控制方法[J]. 控制理论与应用, 2010, 27(2): 164-168.
Mu Chaoxu, Zhang Ruimin, Sun Changyin.Least squares support vector machine predictive control for nonlinear systems based on particle swarm optimization[J]. Control Theory and Application, 2010, 27(2): 164-168.
[21] Jun Yi.Integration of fuzzy information granulation and support vector machine for prediction alumina density Cognitive Informatics & Cognitive Computer[C]// 2012 IEEE 11th International Conference on, 2012, 22(6): 21-23.