Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chemical oxygen demand soft-sensing method of sewage

A chemical oxygen demand and soft measurement technology, applied in the field of sewage treatment, can solve the problems of cumbersome operation, demanding application conditions, large consumption of silver salt, etc., and achieve the effect of high estimation accuracy and wide application range.

Inactive Publication Date: 2009-10-28
FUDAN UNIV
View PDF0 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) The backflow equipment takes up space, the operation is cumbersome, and it is difficult to measure in batches;
[0007] (2) It is difficult to obtain the required control parameters in real time due to the large time delay of the reaction measurement;
[0008] (3) The consumption of silver salt is large, the analysis cost is high, and the acid waste liquid formed by the silver sulfate and mercury sulfate added in the test process needs to be properly disposed of, otherwise serious secondary pollution will be caused
These problems often cause non-convergence of network training and unprepared parameter estimation.
Therefore, the main problems of the existing sewage COD neural network soft-sensing method are: the application conditions are harsh, and contradictory data are prone to cause the uncertainty of the neural network, and the applicability is poor

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
  • Chemical oxygen demand soft-sensing method of sewage
  • Chemical oxygen demand soft-sensing method of sewage
  • Chemical oxygen demand soft-sensing method of sewage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Example 1 uses the mean value of the COD of the training samples as the basis for classification, and the classification limit is 58 mg / L. Sample 1 is a training data sample with a COD value greater than 58 mg / L, and sample 2 is a training data sample with a COD value less than or equal to 58 mg / L.

[0051] In sample 1, the COD value is large, the decline speed is fast, and the correlation in time is not high, so sample 1 selects BP neural network for training. Use pH, DO and ORP measured online as input layer nodes, COD as output layer nodes, and select five hidden layer nodes to establish a BP network model (such as image 3 ).

[0052] In sample 2, the COD value is small, the reaction time of the processing process is long, and the time correlation is high, so the Elman neural network is selected for training in sample 2. Similarly, with online obtained pH, DO, ORP as the input layer node, COD as the output layer node, select eight hidden layer nodes and eight rece...

Embodiment 2

[0054] Example 2 uses the anaerobic and aerobic states as the basis for classification. In this embodiment, the anaerobic and aerobic states of sewage are judged by the value of dissolved oxygen (DO), and the classification limit is DO=0.7mg / L. Sample 1 is a training data sample with a DO value less than 0.7 mg / L, and sample 2 is a skilled data sample with a DO value greater than 0.7 mg / L.

[0055] Sample 1 selects BP neural network to train, is the same as embodiment 1, uses online measured pH, DO, ORP as input layer node, COD as output layer node, and selects five hidden layer nodes to set up BP network model (such as image 3 ).

[0056] Sample 2 selects the Elman neural network for training. Similarly, the pH, DO, and ORP obtained online are used as input layer nodes, and COD is used as the output layer node. Eight hidden layer nodes and eight successor layer nodes are selected to establish an Elman network model (such as Figure 4 ).

[0057] First use all the training ...

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 a chemical oxygen demand soft-sensing method of sewage, which comprises the steps of: (1) obtaining the water quality parameters of training samples; (2) sorting the training samples; (3) selecting a nerve network and building a nerve network model corresponding to various training samples divided in step (2); (4) training a support vector machine by using various training samples divided in step (2); (5) using various training samples divided in step (2) to train the nerve network model; and (6) estimating the chemical oxygen demand of the sewage. The chemical oxygen demand soft-sensing method of sewage uses the characteristic of better automatic sorting effect of the support vector machine and adopts the support vector machine to sort the training samples, and then respectively estimates the chemical oxygen demand of sewage through the corresponding nerve network. Compared with the prior art, the chemical oxygen demand soft-sensing method of sewage has the beneficial effects of broad range and high estimating range.

Description

technical field [0001] The invention relates to the field of sewage treatment, in particular to a method for soft measurement of chemical oxygen demand in sewage. Background technique [0002] With the development of sewage treatment technology becoming more and more mature, the focus of sewage treatment research has shifted to improving the automatic control level of sewage treatment process, improving the quality of effluent water, and strengthening operation monitoring. These studies are based on real-time, accurate and rapid measurement of wastewater treatment process and effluent water quality parameters. These parameters mainly include: BOD 5 (5-day biochemical oxygen demand), COD (chemical oxygen demand), T-N (total nitrogen), T-P (total phosphorus), etc. [0003] Chemical Oxygen Demand (COD) is the amount of oxidant consumed when various organic substances in water react with an external strong oxidant under certain strict conditions (the result is expressed in mg / ...

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): G01N33/00G06N1/00G06N3/08G06N99/00
Inventor 张杰冯辉雷中方张建秋胡波
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com