A fuzzy inference system using sensor measurements was developed to estimate the influent COD/N ratio and ammonia load. The sensors measured ORP, DO and pH. The sensor profiles had a close relationship with the influent COD/N ratio and ammonia load. To confirm this operational knowledge for constructing a rule set, a correlation analysis was conducted. The results showed that a rule generation method based only on operational knowledge did not generate a sufficiently accurate relationship between sensor measurements and target variables. To compensate for this defect, a decision tree algorithm was used as a standardized method for rule generation. Given a set of inputs, this algorithm was used to determine the output variables. However, the generated rules could not estimate the continuous influent COD/N ratio and ammonia load. Fuzzified rules and the fuzzy inference system were developed to overcome this problem. The fuzzy inference system estimated the influent COD/N ratio and ammonia load quite well. When these results were compared to the results from a predictive polynomial neural network model, the fuzzy inference system was more stable.
Rule-based fuzzy inference system for estimating the influent COD/N ratio and ammonia load to a sequencing batch reactor
Y.J. Kim, H. Bae, J.H. Ko, K.M. Poo, S. Kim, C.W. Kim, H.J. Woo; Rule-based fuzzy inference system for estimating the influent COD/N ratio and ammonia load to a sequencing batch reactor. Water Sci Technol 1 January 2006; 53 (1): 199–207. doi: https://doi.org/10.2166/wst.2006.022
Download citation file:
Impact Factor 1.915
CiteScore 3.3 • Q2
13 days from submission to first decision on average