An ammonia nitrogen concentration online soft measure method based on the neural network
Ge Zhao, Guang Han, ShiYu Ren, Xiaoyun Sun · 2017
Aiming at the problem that the key water quality parameters in wastewater treatment processing is difficult to detect real-time accurately. An ammonia nitrogen concentration soft measure model based on the artificial neural network(ANN) is proposed in this paper, and utilizing existing data to achieve parameters detection in real-time accurately during the process of wastewater treatment processing. Firstly, parameters which are easily to detect are chosen as instrumental variables, then optimize the network's parameters by gradient descent algorithm. The experimental results show that the fitting results of the effluent ammonia nitrogen in this paper is good when the hidden neurons are 15 and the learning rate is 0.07, which achieves the detection of the effluent ammonia nitrogen in real-time accurately.