Sludge expansion fault identification method based on recursive RBF (radial basis function) neural network

A neural network and sludge bulking technology, applied in the field of water treatment, can solve problems such as control measures, no sludge bulking, process failure of sewage treatment process, etc.

Active Publication Date: 2017-08-08
BEIJING UNIV OF TECH
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the problem of sludge bulking has always been a thorny problem in the activated sludge process. Due to the abnormal separation of sludge and water, the sewage treatment process fails
It can be seen that sludge bulking is a common problem faced by sewage treatment plants at home and abroad. Scholars from various countries have done a lot of research on the prevention and control of sludge bulking. Although some progress has been made, so far, there is no research on sludge bulking. effective control measures; the point is that once sludge bulking occurs, the reason is not easy to explore, and it takes a long time to deal with the failure of the process

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sludge expansion fault identification method based on recursive RBF (radial basis function) neural network
  • Sludge expansion fault identification method based on recursive RBF (radial basis function) neural network
  • Sludge expansion fault identification method based on recursive RBF (radial basis function) neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] The present invention selects the characteristic variables of the sludge volume index SVI as the mixed suspended matter concentration MLSS, temperature T, dissolved oxygen concentration DO, chemical oxygen demand COD and total nitrogen TN, and the above units are mg / liter;

[0089] The experimental data comes from the 2014 water quality analysis daily report of a sewage treatment plant; after removing the abnormal experimental samples, there are 100 sets of available data, of which 60 sets are used as training data, and the remaining 40 sets are used as test data; the present invention adopts the following technical scheme and realization step:

[0090] The specific steps of sludge bulking fault identification algorithm based on recursive RBF neural network are as follows:

[0091] 1. A sludge bulking fault identification method based on a recursive RBF neural network, characterized in that it obtains the eigenvalue of the sludge volume index SVI through feature analysi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a sludge expansion fault identification method based on a recursive RBF (radial basis function) neural network, belongs to the field of control and water treatment and aims to solve the problems that sludge expansion in the sewage treatment process is difficult to accurately detect and reasons causing sludge expansion are difficult to identify. The sludge expansion fault identification method based on the recursive RBF neural network is designed, a soft measurement model of an SVI (sludge volume index) is established on the basis of the recursive RBF neural network, real-time prediction of the SVI concentration is completed. Once sludge expansion is detected, the fault variables causing sludge expansion are accurately identified with a fault variable identification (CVI) algorithm. By means of the method, the sewage treatment process can be controlled in advance according to fault variables, and the occurrence rate of sludge expansion is reduced.

Description

technical field [0001] Based on the fact that sludge bulking is easy to occur in the activated sludge process in the sewage treatment process and the cause is not easy to identify, the present invention designs a sludge bulking fault identification method by using the recursive RBF neural network, and realizes the early effective sludge bulking after fault variable identification Adjustment; sewage treatment sludge volume index SVI is an important parameter to characterize sludge bulking, the relationship between sludge volume index SVI and process variables in sewage treatment process is the basic link to realize effective prediction of sludge bulking; and, identification of sludge bulking failure It has an important impact on the stable and safe operation of sewage treatment. It is an important branch of the advanced manufacturing technology field. It belongs to both the control field and the water treatment field. Therefore, identification of sludge bulking faults is of gre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/50G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F30/20G06N3/088C02F2303/12C02F3/12C02F3/006Y02W10/10G06N3/048G06N3/044
Inventor 韩红桂郭亚男乔俊飞
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products