Estimation of chemical oxygen demand by ultraviolet spectroscopic profiling and artificial neural networks

摘要: A simple method based on the mathematical treatment of spectral absorbance profiles in conjunction with artificial neural networks (ANNs) is demonstrated for rapidly estimating chemical oxygen demand (COD) values wastewater samples. In order to improve spectroscopic analysis and ANN training time as well reduce storage space trained algorithm, it necessary decrease input vector size by extracting unique characteristics from raw pattern. Key features pattern were therefore selected obtain profile, reducing 160 10 inputs. The results indicate that COD obtained agreed those entire profile technique was also compared estimated a multiple linear regression (MLR) model validate whether ANNs better more robust models rapid analysis. It found predicted closer standard than MLR model.