Outlet water BOD online soft measurement method based on self-organizing RBFNN

Abstract

The invention discloses an effluent BOD (biochemical oxygen demand) online soft measurement method based on a self-organizing RBF (radial basis function) neural network, which is directly applied to the field of sewage treatment. The invention provides an effluent BOD prediction method based on self-organizing RBF (Radial Basis Function) nerves in order to solve the problems that the effluent BOD concentration in the current sewage treatment process is long in test period and relatively large in hysteresis, and cannot reflect the change of BOD in a water body in time, and the like. A compact network structure is obtained, an on-line small-batch gradient learning algorithm is provided for on-line learning of network parameters, rapid and stable convergence performance is obtained, accurate prediction of the effluent BOD concentration is finally achieved, and the problem that the BOD concentration is difficult to measure in the sewage treatment process is solved.

Description

technical field [0001] The invention relates to the field of artificial intelligence and is directly applied to the field of sewage treatment. Background technique [0002] The sewage treatment process has many reactions and is very complicated, which makes it very difficult to measure important parameters in the sewage. Biochemical Oxygen Demand (BOD) refers to the amount of oxygen consumed by microorganisms in the water body to convert organic matter into inorganic matter. It can directly reflect the degree of water pollution and is a very important water quality detection index in the process of sewage treatment. At present, methods for predicting BOD concentration in effluent include dilution and inoculation method, artificial timing sampling, etc. However, the dilution and inoculation method has problems such as long test period, large lag, and inability to reflect changes in BOD in water in time. The method of using an instrument to detect the BOD in the effluent in t...

AI Technical Summary

Problems solved by technology

This method uses the Gaussian membership degree as the similarity measure standard, designs the online structure self-organization mechanism of the network, and proposes an online small-batch gradient learning algorithm to learn the network parameters online, realizes the online real-time prediction of the concentration of BOD in the effluent, and solves the problem of BOD in the process of sewage treatment. Difficult problems with concentration measurement

Images