| 基于SVM增量学习的氯甲烷含水量预测控制 |
| |
| 引用本文： | 朱小萍,夏陆岳,孙小方,蔡亦军,周猛飞,潘海天.基于SVM增量学习的氯甲烷含水量预测控制[J].科技通报,2012(1):133-136. |
| |
| 作者姓名： | 朱小萍 夏陆岳 孙小方 蔡亦军 周猛飞 潘海天 |
| |
| 作者单位： | 浙江工业大学化学工程与材料学院 |
| |
| 基金项目： | 浙江省科技厅科研计划项目(2009C32078);浙江省自然科学基金(Z4100743) |
| |
| 摘 要： | 由于氯甲烷回收过程具有工艺过程复杂、非线性、时变性等特点,导致氯甲烷含水量难以预测。提出了ISVM软测量建模方法,鉴于新增训练样本中如果存在违反KKT条件的样本,则这些样本中肯定存在新的支持向量,必然会使支持向量集发生变化,原分类支持向量集中的非支持向量也有可能转化为支持向量,进一步提出了改进ISVM氯甲烷含水量预测模型。研究结果表明:通过与普通ISVM预测模型比较,采用改进ISVM预测模型的预测结果具有更佳的预测精度,为氯甲烷含水量的控制提供了更精确的条件。
|
| 关 键 词： | 支持向量机 增量学习 氯甲烷 含水量 预测 控制 |
Prediction and Control of Water Content in Chloromethane base on Support Vector Machine Incremental Learning |
| |
| Zhu Xiaoping,XIA Luyue,SUN Xiaofang,CAI Yijun,ZHOU Mengfei,PAN Haitian.Prediction and Control of Water Content in Chloromethane base on Support Vector Machine Incremental Learning[J].Bulletin of Science and Technology,2012(1):133-136. |
| |
| Authors: | Zhu Xiaoping XIA Luyue SUN Xiaofang CAI Yijun ZHOU Mengfei PAN Haitian |
| |
| Institution: | (College of Chemical Engineering and Materials Science,Zhejiang University of Technology,Hangzhou 310032,China) |
| |
| Abstract: | Water content is one of the most important index of chloromethane quality,however the process of chloromethane recovery is complex,that measuring water content is very diffcult.For solving this problem,support vector machine incremental learning is used for modeling the water content of chloromethane.Because the sample of violating the KKT in the incremental sample will change the initial support vector sample,and the initial not support vector sample will translate into support vector sample,a improving model based on support vector machine incremental learning is established.The prediction result shows that using improved incremental learning greatly increases precision of the model. |
| |
| Keywords: | support vector machine incremental learning chloromethane water content prediction control |
| 本文献已被 CNKI 等数据库收录！ |
|
