基于软传感器技术的海水富营养化监测

On Monitoring of Seawater Eutrophication Based on Soft Sensor Technology

藻类的繁殖生长状态很难用一种传感器在线、实时地直接测量出来。影响藻类生长的环境理化因子众多,这些环境因子之间又相互作用,海洋生态环境是一个高度复杂的非线性系统,很难用传统的机理建模方法来描述。文中用T-S模糊神经网络描述这种复杂的非线性系统,通过构造软传感器来测量藻类的繁殖生长状况。将叶绿素a的含量作为描述藻类生长状态的直接指标,并作为系统的输出变量,通过相关性分析,将影响藻类繁殖生长的主要环境因子作为系统的输入变量,通过对样本的学习训练,构造基于T-S模糊神经网络的软传感器模型。实验结果表明,这种软传感器模型能较好地描述可测环境因子与海水叶绿素a含量之间的非线性映射关系,验证了这种软传感器在监测海水水质异常变化时的有效性。

The state of algae growth is difficult to be measured by some kind of sensor directly. There are many environmental factors to affect the growth of algae, these factors have more internal functions affected each other, so the system is a complex nonlinear system, and it is difficult to be represented by mechanism model. In this paper, T-S fuzzy neural network is adopted to describe this kind of complex system. The state of algae growth can be measured by constructing the soft sensor. Content of chlorophyll-a can indicate the state of algae reproduction as the direct index, and it can be regarded as the output of the model system, some key environmental factors can be chosen as the input variables of the model system after correlation analysis. Soft sensor model based on T-S fuzzy neural network can be constructed by sample training. Experiment result illustrates that this kind of soft sensor model can well describe this nonlinear mapping relationship between the measurable environmental factors and the content of chlorophyll-a, and it can be effectively proved in early warning for the quality of seawater changing remarkably by this soft sensor.