Sludge expansion intelligent identification method based on type II fuzzy neural network

Abstract

The invention provides a sludge expansion intelligent identification method based on a self-organizing type II fuzzy neural network, and belongs to the technical field of intelligent detection. The sludge volume index (SVI) concentration of the sewage treatment plant is an important index to measure the sludge bulking phenomenon in the activated sludge process. As the sludge volume index (SVI) cannot be monitored online and the sludge expansion frequent fault type is difficult to judge, the soft measuring model of the sludge volume index (SVI) is established based on the self-organizing type II fuzzy neural network to complete real-time detection of the sludge volume index (SVI) concentration and determine the sludge expansion fault type through combination with the target correlation identification algorithm. The results show that the intelligent identification method can quickly obtain the sludge volume index (SVI) concentration, accurately identify the sludge expansion fault type, improve the quality and the efficiency of sewage treatment and ensure the stable and safe operation of the sewage treatment process.

Description

technical field [0001] Based on the operating characteristics of the sewage treatment process, the present invention designs an intelligent identification method for sludge bulking by using the type II fuzzy neural network, and realizes the real-time measurement of the sludge volume index SVI in the sewage treatment process and the identification of the sludge bulking fault category; sewage treatment The plant sludge volume index SVI concentration is an index to measure the coagulation, settlement and concentration performance of activated sludge. The prediction of sludge volume index SVI in the sewage treatment process and the identification of sludge bulking fault analogy are of great significance to the monitoring and control of the sewage treatment process; the application of intelligent identification methods to the sewage treatment system has a great impact on the energy saving and stability of sewage treatment. Safe operation has an important impact and is an important ...

AI Technical Summary

Problems solved by technology

[0003] At present, a large number of researches on the identification of sludge bulking phenomenon have been carried out, but the realization effect is not optimistic

On the one hand, due to the complex mechanism characteristics of sludge bulking, the sludge bulking diagnosis method based on the mechanism model cannot cover the growth mechanism of all microorganisms, and it is difficult to meet the stability and accuracy requirements

At the same time, the method based on the mechanism model often judges sludge bulking through the morphological characteristics such as the length and abundance of microorganisms, which has the characteristics of complex operation and strong time lag, and is difficult to apply to the actual sewage treatment process

On the other hand, although some modeling methods have achieved certain results in the diagnosis of sludge bulking, the dynamic nonlinearity of the sewage treatment process makes it difficult for the traditional sludge bulking prediction model to adapt to strong dynamic changes in working conditions, and cannot accurately identify sludge bulking. Effect of Mud Bulking Diagnosis on Fault Categories

Images