Soft sensor based on T-S fuzzy neural network applied in state monitoring of algae growth in seawater

The state of algae growth in seawater has great effect to marine environment, but it is difficult to find a kind of sensor to measure it on line and with real-time. In this paper, a kind of soft sensor built by T-S fuzzy neural network is applied to monitor the reproduction state of algae growth. The content of chlorophyll-a in seawater is regarded as the token factor to describe the state of algae growth, and it also can be regarded as the output variable of the system. By the analysis of correlation, some key chemical-physical environmental factors effecting the content of chlorophyll-a should be chosen as the input variables of the model system. 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 chemical-physical factors and the content of chlorophyll-a, and this kind of soft sensor can be effectively validated by monitoring the state of algae growth in practice.