Zhou Chunshan, Zhang Chao, Tian Di, Wang Ke, Huang Mingzhi, Liu Yanbiao
a School of Geography and Planning, Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Sun Yat-sen University , Guangzhou , PR China.
b Environmental Research Institute, South China Normal University , Guangzhou , PR China.
J Environ Sci Health A Tox Hazard Subst Environ Eng. 2018 Jan 2;53(1):91-98. doi: 10.1080/10934529.2017.1369815. Epub 2017 Oct 30.
In order to manage water resources, a software sensor model was designed to estimate water quality using a hybrid fuzzy neural network (FNN) in Guangzhou section of Pearl River, China. The software sensor system was composed of data storage module, fuzzy decision-making module, neural network module and fuzzy reasoning generator module. Fuzzy subtractive clustering was employed to capture the character of model, and optimize network architecture for enhancing network performance. The results indicate that, on basis of available on-line measured variables, the software sensor model can accurately predict water quality according to the relationship between chemical oxygen demand (COD) and dissolved oxygen (DO), pH and NH-N. Owing to its ability in recognizing time series patterns and non-linear characteristics, the software sensor-based FNN is obviously superior to the traditional neural network model, and its R (correlation coefficient), MAPE (mean absolute percentage error) and RMSE (root mean square error) are 0.8931, 10.9051 and 0.4634, respectively.
为了管理水资源，设计了一种软件传感器模型，利用混合模糊神经网络（FNN）对中国珠江广州段的水质进行估算。该软件传感器系统由数据存储模块、模糊决策模块、神经网络模块和模糊推理生成器模块组成。采用模糊减法聚类来捕捉模型特征，并优化网络结构以提高网络性能。结果表明，基于现有的在线测量变量，该软件传感器模型能够根据化学需氧量（COD）与溶解氧（DO）、pH值与氨氮（NH-N）之间的关系准确预测水质。由于其具有识别时间序列模式和非线性特征的能力，基于软件传感器的模糊神经网络明显优于传统神经网络模型，其相关系数（R）、平均绝对百分比误差（MAPE）和均方根误差（RMSE）分别为0.8931、10.9051和0.4634。
