Effluent TP interval prediction method in wastewater treatment

A forecasting method and technology for sewage treatment, applied in forecasting, data processing applications, neural learning methods, etc., can solve the problems of difficult to obtain statistical characteristics, and confidence intervals are not necessarily reliable.

Inactive Publication Date: 2018-11-27
BEIJING UNIV OF TECH
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In practical applications, the statistical characteristics of the error are difficult to obtain. At this time, the confidence interval given by the first method is not necessarily reliable. Therefore, based on the assumption of bounded error, a new soft-sensing method for the TP of the water outlet is given. achieve its guaranteed estimate

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0097] 1. Data acquisition preprocessing stage:

[0098] In this data collection, auxiliary variables such as influent TP, temperature T, and hydrogen ion concentration index pH were measured online. However, because not all the data from the sewage treatment site are helpful for the prediction of effluent TP, it is necessary to carry out the collected auxiliary variables. filter. This time, the partial least squares (PLS) method was used to reduce the dimensionality of the input data, and in R select Under the premise of ≥0.85, the auxiliary variables are finally reduced to 5 dimensions, and the influent TP, temperature T, dissolved oxygen DO, total suspended particles TSS and hydrogen ion concentration index pH are used as inputs to predict the effluent TP.

[0099] 2. Soft sensor modeling stage

[0100] In the soft sensor modeling stage, the method of combining RBF neural network and member identification is mainly used to process the dimensionally reduced data. The proce...

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 relates to an Effluent TP interval prediction method in wastewater treatment. Using an idea combining set membership identification with a neural network, modeling is carried out based on collected data, and an interval estimation of output variable effluent TP is given. The method has two parts: modeling input and output data by a RBF neural network and obtaining set description ofnetwork output weights by a parameter linear set membership identification algorithm. The method comprises: firstly, using approximation ability of the RBF neural network to soft-sensing modeling of effluent total phosphorus in wastewater treatment; secondly, after the center and width of RBF neural network are determined, considering boundedness of modeling error, using the parameter linear set membership identification algorithm to obtain the set description of the network output weights, to obtain reliable interval estimation of effluent total phosphorus. The invention provides a new soft-sensing method, which can calculate the confidence interval of effluent total phosphorus, thereby realizing reliable detection of the water quality indexes.

Description

technical field [0001] The present invention aims to find an effective measurement method for effluent TP, uses the idea of ​​combining member recognition and neural network to model based on collected data, and provides interval estimation of output variable effluent TP. Member identification has been widely used in recent years, and its combination with neural network has been verified in soft sensor technology, signal processing, robust control and fault detection, and has made great progress. Background technique [0002] With the increasingly prominent water environment problems in China, sewage treatment, as an important measure to protect the environment, has attracted more and more attention from the society. The effluent TP reflects the eutrophication of water bodies and is an important indicator for evaluating water quality. Real-time and accurate monitoring of TP content in the process of sewage treatment is particularly important. In addition, the sewage treatme...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06Q10/04
CPCG06N3/08G06Q10/04
Inventor 柴伟郭龙航池彬彬纪镐南
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap