Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Water quality parameters like temperature, pH, total dissolved solids (TDS), total suspended solids (TSS), dissolved oxygen (DO), oil and grease, etc., are calculated from the field while parameters like biological oxygen demand (BOD) and chemical oxygen demand (COD) are interpreted through the laboratory tests. On one hand parameters like temperature, pH, DO, etc., can be accurately measured with the exceeding simplicity, whereas on the other hand calculation of BOD and COD is not only cumbersome but also inaccurate many times. A number of previous researchers have tried to use different empirical methods to predict BOD and COD but these empirical methods have their limitations due to their less versatile application. In this paper, an attempt has been made to calculate BOD and COD from simple field parameters like temperature, pH, DO, TSS, etc., using Artificial Neural Network (ANN) method. Datasets have been obtained from analysis of mine water discharge of one of the mines in Jharia coalfield, Jharkhand, India. 73 data sets were used to establish ANN architecture out of which 58 datasets were used to train the network while 15 datasets for testing the network. The results show encouraging similarity between experimental and predicted values. The RMSE values obtained for the BOD and COD are 0.114 and 0.983 %, respectively.