基于支持向量回归机算法的海水富营养化过程中藻类繁殖状态软测量研究

Study on soft sensing for status of algae reproduction in the process of seawater eutrophication based on Support Vector Regression algorithm

提出了利用支持向量回归机算法(SVR)建立海水叶绿素-a浓度的软测量方法,采用灰色关联分析法获取叶绿素-a软测量模型的主要辅助测量变量。将基于支持向量回归机的叶绿素-a软测量结果与BP神经网络和T-S模糊神经网络方法进行了对比,结果表明,这种基于支持向量回归机的软测量方法能够有效测量海水叶绿素-a的浓度。

A soft sensing method of measuring the concentration of chlorophyll-a in seawater based on Support Vector Regression （SVR） is proposed.The method of Grey Correlation Analysis is used for obtaining the key secondary variables of soft sensing model of chlorophyll-a.The result of soft sensing based on SVR has been compared with the result from BP neural network and T-S fuzzy neural network.The testing result indicates that this soft sensing method based on SVR can effectively estimate the concentration of chlorophyll-a in seawater.