Method for predicating COD load of sewage based on vector time sequence model

A technology of time series model and load forecasting, applied in the direction of testing water, measuring devices, instruments, etc., can solve the problems of ignoring the importance of water inflow, strong mutation, uncontrollable water inflow load, etc., and achieve easy understanding and adoption, and easy estimated effect

Active Publication Date: 2017-06-20
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Different from other industrial production processes, the influent load of sewage treatment plants is generally not adjustable, and its mutation is strong and the fluctuation range is large. Especially under the influence of rainfall, it has a strong impac

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
  • Method for predicating COD load of sewage based on vector time sequence model
  • Method for predicating COD load of sewage based on vector time sequence model
  • Method for predicating COD load of sewage based on vector time sequence model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] The present embodiment discloses a method for forecasting a multivariate time series based on a vector autoregressive model (VAR). The method is a method for judging the influence of past trends of interrelated variables on the present and the future, and includes the following steps:

[0066] S1. Variable selection based on data modeling objectives: use the variables collected by the control system to analyze the influent variables of the sewage treatment plant, and the variables include influent water, sewage COD, NH 4 N, PH and inlet water temperature T, through qualitative analysis of the correlation and influence degree between the collected variables and the pollutant load, select the variables that have an impact on the pollutant load;

[0067] This step is based on the data modeling goal of "sewage COD load forecasting" to select variables, use the variables collected by the control system to conduct a preliminary analysis of the influent variables of the sewage ...

Embodiment 2

[0120] like figure 1 , a method for forecasting sewage COD load based on vector time series, including the following modeling and model evaluation steps:

[0121] 1. Through the database of sewage inflow obtained from the control system of a sewage treatment plant, which contains all the data of May and June in the second quarter of 2016, combined with the A2O process of sewage treatment and data variables collected from the database, selected Associated with sewage pollutant load such as influent volume, influent COD, influent NH 4 N, inlet water PH and inlet water temperature T and other variables;

[0122] 2. Follow the data exploration process, first check the quality of the data:

[0123] A. For the selected 5 variables, the first thing that is easy to check is the missing value of the data. Through the preliminary inspection of the data in May and June, it is found that the data in May is seriously missing, so the relatively complete part of June is selected. (June 4,...

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 method for predicating COD load of sewage based on a vector time sequence model. The method comprises the following steps: performing definition of an excavation target in a data mining modeling process; performing data exploration and preprocessing on obtained sewage inlet related data to meet requirements of vector autoregression model modeling; selecting parameters of an maximum likelihood estimation model, selecting information criteria to determine order of the model, and performing model checking through multi-factor blending statics; and further simplifying the model through target parameters, thereby establishing a simple and effective predicating model. The acquired inlet water data determines water inlet amount and inlet water COD, and a sewage COD load attribute is constructed; test data predication is performed through the obtained predicating model, and output of the model is predicated results for a sewage COD load related variable. According to the method disclosed by the invention, the model is simple, multiple variables can be predicated at the same time, predicating precision is relatively high, and needed time is short.

Description

technical field [0001] The invention relates to the technical field of sewage load forecasting for sewage treatment plant inflow, in particular to a method for forecasting sewage COD load based on a vector time series model. Background technique [0002] With the continuous improvement of the degree of industrialization and the growth of population, the discharge of urban sewage is increasing rapidly, which has a huge impact on the environment. Countries all over the world have invested a lot of money in the research of urban sewage treatment technology, and developed many new technologies and new technologies. Technology has played a huge role in improving the water environment. At present, the construction of sewage treatment plants is recognized as an effective way to solve the current situation of water pollution, and all countries are vigorously building them. [0003] However, sewage treatment is an energy-intensive comprehensive technology. With the large-scale const...

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): G01N33/18
CPCG01N33/1806
Inventor 李继庚蔡威满奕曾志强刘焕彬
Owner SOUTH CHINA 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