%A Hongbin LIU,Liu SONG %T Study on modeling methods of wastewater treatment processes with canonical correlation analysis %0 Journal Article %D 2020 %J Journal of Shandong University(Engineering Science) %R 10.6040/j.issn.1672-3961.0.2018.552 %P 101-108 %V 50 %N 1 %U {http://gxbwk.njournal.sdu.edu.cn/CN/abstract/article_1899.shtml} %8 2020-02-20 %X

With the improvement of public awareness of environmental protection, the discharge of industrial wastewater became a crucial issue in industrial production. The typical water quality models were based on static models which ignored the dynamic information in process variables, resulting in the reduction in the accuracy of model prediction and the generalization ability of the models. Considering the time-varying and dynamic characteristics of process variables, a time difference model embedded into canonical correlation analysis was proposed in this paper. The effect of the order of the time difference model on the prediction accuracy was also analyzed. Compared with the traditional canonical correlation analysis, the root mean square error values of effluent chemical oxygen demand and effluent total nitrogen were reduced from 1.502 8 to 0.564 5 and from 2.344 0 to 1.192 6, respectively. The correlation coefficient values were increased from 0.422 7 to 0.847 0 and from 0.405 9 to 0.793 6, respectively. The results indicated that the prediction accuracy and generalization ability of the model were both improved.