Membrane pollution multi-index identification method based on cascade neural network

Abstract

The invention provides a cascading neural network-based membrane pollution multi-index identification method, which is characterized in that the method considers the interference of irrelevant input variables on output indexes, can avoid the influence of the irrelevant variables on output based on a cascading structure, and adjusts the parameters of a cascading neural network through a hierarchical learning algorithm. The membrane pollution multi-index prediction is realized, the problem that the membrane pollution multi-index prediction precision cannot meet the requirement is solved, and the method has relatively high prediction precision and identification effect.

Description

technical field [0001] Based on the operating characteristics of the sewage treatment process of the membrane bioreactor, the invention designs a multi-indicator identification method for membrane pollution by using the cascaded neural network based on the hierarchical learning algorithm, and realizes the multi-index identification method related to the membrane pollution in the sewage treatment process of the membrane bioreactor. The prediction of each index; the multiple indexes related to membrane fouling refer to membrane water permeability, membrane pore radius and membrane life in the process of membrane bioreactor sewage treatment. These indexes are to measure whether membrane fouling occurs, the severity of membrane fouling and Significant signs of features. The multi-index identification method of membrane fouling based on cascaded neural network can improve the accuracy of the multi-index identification model, obtain accurate prediction results, and comprehensively c...

AI Technical Summary

Problems solved by technology

[0004] The invention proposes a multi-indicator identification model of membrane pollution based on cascaded neural network. The model considers the interference of irrelevant input variables on output indicators, and can avoid the influence of irrelevant variables on output based on the cascade structure, and through layering The learning algorithm adjusts the parameters of the cascaded neural network to realize the prediction of multiple indicators of membrane pollution, which solves the problem that the prediction accuracy of multiple indicators of membrane pollution cannot meet the requirements, and has high prediction accuracy and identification effect

Images