Intelligent Preprocessing Method of Sewage Measurement Data

A measurement data and preprocessing technology, which is applied in the direction of electrical digital data processing, special data processing applications, digital data information retrieval, etc., can solve difficult problems such as timing problems, and achieve the effect of simplifying complexity

Active Publication Date: 2021-07-23
HUATIAN ENG & TECH CORP MCC +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the measurement of sewage data is based on the same moment, and the sewage treatment system itself has a time lag, it is difficult to analyze the time series of sewage measurement characteristics in the process of intelligent modeling

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
  • Intelligent Preprocessing Method of Sewage Measurement Data
  • Intelligent Preprocessing Method of Sewage Measurement Data
  • Intelligent Preprocessing Method of Sewage Measurement Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solution of the present invention will further explain the actual operation data of a certain sewage treatment plant.

[0027] S101, acquire acquisition data for sewage water quality prediction or control based on time series;

[0028] Specifically, the acquisition data is the detection data during the sewage treatment. This detection data is automatically collected data per two hours, mainly including inlet flow, water COD, water ammonia nitrogen, dissolved oxygen, sludge activity, water temperature, Water flow, water COD and water ammonia nitrogen. Note that all of the following data processing is based on time, so each acquisition record should contain data acquisition time.

[0029] S102, the data is lacking value filled, 3Delta processing, and differential processing;

[0030] Specifically, the current detection data deleted by the sewage treatment plant uses the Lagrang Jian method to replace the 3Delta boundary value, and finally the process after the p...

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 an intelligent preprocessing method for sewage measurement data. The method includes the following steps: 1) preprocessing the time series-based data used for sewage water quality prediction or control; 2) determining the intelligent model, the input feature quantity in the preprocessing data, and the target feature quantity in the preprocessing data ; 3) Group the input feature quantities in the preprocessing data according to the positions of the actual measurement points; 4) Each group of input feature quantities is traversed as a reference to the previous group of input feature quantities, and the traversal unit is one sampling period, and output the combined 5) Utilize the data of the predetermined ratio after combination to carry out intelligent model training; 6) Utilize the remaining data after combination to calculate the mean square error value (MSE) of the smart model; 7) Update the time interval of each group of input feature quantities; 8) If the time interval of each group is less than or equal to the time of the whole sewage process, then return to step 4); 9) output the time interval with the smallest mean square error value in the traversal process, that is, obtain the time difference between each input feature quantity; 10) Recombine the data according to the time interval between each input feature quantity for intelligent model training.

Description

Technical field [0001] The invention belongs to the field of sewage data processing, and more particularly to a method of pretreatment of sewage measurement data when modeling using artificial intelligence technology. Background technique [0002] In my country, most urban sewage treatment plants were treated with active sludge. The sewage treatment process of the active sludge method is a strong coupled multi-input multi-output dynamic system, with a large lag, nonlinear, time-beam, and uncertainties, which brought difficult to modeling. [0003] Traditionally, people can model the actual system using the obtained extensive data knowledge, and widely used in the fields of various controls. However, for complex continuous, time-change, large lags and nonlinear sewage control systems, mathematical modeling methods are severely challenged. In recent years, with the development of artificial intelligence, it can be used to establish a black box mechanism model for sewage measurement...

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 Patents(China)
IPC IPC(8): G06F16/2458
Inventor 韦雪文赵贤林沈存黄丽萍乔瑜张明翔
Owner HUATIAN ENG & TECH CORP MCC
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