Design And Implementation Of SBR Sewage Treatment Control System Based On Soft Sensing

Eutrophication will lead to a over-reproduction of algae in water,a decrease of the dissolved oxygen in water,the stinking of water,and further affecting the water quality.The main reason for this phenomenon is that the total phosphorus in the water has not been effectively removed by the sewage treatment plant.Sequencing Batch Reactor(SBR)water treatment process is a common phosphorus removal process.In the process of phosphorus removal,as the on-line phosphorus meters is quite expensive while the process is greatly lagged behind,it is impossible to detect the total phosphorus content in real time,and also an effective control system could not be established,while it is not allowed to discharge the total phosphorus exceeding the relevant standard.So,as a result,the phosphorus removal agent is added excessively,causing toxicity to activated sludge and increasing the cost.As the soft sensing technology could realize real-time prediction of total phosphorus value,a feedback system of phosphorus removal process is established so as to reduce the dosage of phosphorus removal agent.Therefore,it is of great significance and practical application value to study SBR sewage treatment control system based on soft sensing.The SBR sewage treatment control system is modified and a soft-sensing based SBR sewage treatment control system is proposed in this paper.The auxiliary variables related to the phosphorus removal process are analyzed.Based on the soft-sensing model,the real-time total phosphorus content is predicted.OPC communication technology is adopted to connect the software and hardware of the system,and the predicted total phosphorus value is taken as the system feedback value to realize the closed-loop control of the dosage of phosphorus removal agent.This system also includes a data acquisition system,which is combined with chemical analysis experiments to establish a soft measurement data set.In the establishment of the soft measurement model,the genetic algorithm is used to optimize the BP neural network,and the weights and thresholds of the BP neural network is adjusted so as to reduce the prediction error.While through the modification of the genetic algorithm parameters,the optimal soft sensing model is found in this paper.Experiments have shown that the BP neural network optimized with GA model parameters could accurately predict the real-time total phosphorus content in SBR process operation.Compared with the traditional control system,the proposed SBR.sewage treatment control system based on soft sensing could reduce the dosage of phosphorus removal agents,thus the harmful impacts caused by excessive dosage of phosphorus removal agents are greatly eliminated,which will make SBR process run stably.It is of sound engineering application value.