Modularized neural network effluent ammonia nitrogen soft measurement method based on EMD algorithm

A neural network and modular technology, which is applied in the soft measurement field of effluent ammonia nitrogen of modular neural network, can solve the problems of high cost and long cycle of effluent ammonia nitrogen measurement, achieve the effects of reducing manual intervention, strong adaptability, and improving prediction accuracy

Pending Publication Date: 2021-05-28
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a modular neural network-based soft-measurement method for effluent ammonia nitrogen, which uses historical data to predict the concentration of effluent ammonia nitrogen at the next moment in the future, and uses the EMD algorithm to decompose the time series of effluent ammonia nitrogen according to the time local characteristics. A simple and independent sub-time series, and establish the corresponding sub-network module (FNN) for training and learning, and finally integrate the results of the sub-network module to realize the prediction of the concentration of ammonia nitrogen in the effluent, and solve the problem of high cost of effluent ammonia nitrogen measurement in the current sewage treatment process. long wait question

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
  • Modularized neural network effluent ammonia nitrogen soft measurement method based on EMD algorithm
  • Modularized neural network effluent ammonia nitrogen soft measurement method based on EMD algorithm
  • Modularized neural network effluent ammonia nitrogen soft measurement method based on EMD algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention provides a modular neural network-based soft sensing method for effluent ammonia nitrogen based on the EMD algorithm. The method utilizes historical data to predict the concentration of effluent ammonia nitrogen at the next moment in the future. The structural topology of the soft sensing method is as follows figure 1 As shown, the flow chart is as figure 2 As shown, the prediction of the concentration of effluent ammonia nitrogen is realized, and the problems of high cost and long cycle of effluent ammonia nitrogen measurement in the current sewage treatment process are solved;

[0060] The experimental data comes from the water quality analysis data of a sewage treatment plant from September 16 to September 22, 2014. There are 1008 effluent ammonia nitrogen concentration samples, 720 data (5 days) as training samples, and the remaining 288 data (2 days) as training samples. test samples;

[0061] A soft sensing method for effluent ammonia nitro...

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 effluent ammonia nitrogen soft measurement method of a modular neural network based on an EMD algorithm, and aims to solve the problems that the effluent ammonia nitrogen concentration is difficult to quickly and accurately detect in real time in a sewage treatment process and the effluent quality is ensured to reach the standard in real-time emission. The method comprises the steps: establishing an effluent ammonia nitrogen prediction model by utilizing the modular neural network based on the EMD algorithm, wherein the model comprises the steps of decomposing an effluent ammonia nitrogen time sequence into a plurality of simple, single-frequency and independent sub-time sequences by using an EMD-based task decomposition algorithm; calculating the complexity and similarity of the sub-time sequences by adopting sample entropy and Euclidean distance, combining the sub-time sequences with low complexity and high similarity, and establishing the corresponding sub-network module for learning. The result shows that the prediction model can automatically adjust the network structure, accurately predicts the effluent ammonia nitrogen concentration in the sewage treatment process, and ensures the stable and safe operation of the sewage treatment process.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, and more specifically, relates to a method for soft sensing of effluent ammonia nitrogen based on a modular neural network of an EMD algorithm. Background technique [0002] Ammonia nitrogen is the main factor causing water environmental pollution and eutrophication of water bodies. The "China Marine Ecological Environment Status Bulletin" published in 2018 shows that some sea areas in my country are in a state of eutrophication. Therefore, in urban sewage treatment plants, ammonia nitrogen in the effluent Concentration is one of the key indicators to evaluate whether the effluent quality in the sewage treatment process is up to standard. The current effluent ammonia nitrogen concentration measurement methods include chemical reaction-based measurement methods and mechanism model-based measurement methods; the chemical reaction-based measurement method is to measure the ammonia nit...

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): G16C20/20G16C20/70G06F30/27G06N3/04G06N3/08G01N33/18G06F119/12
CPCG06F30/27G16C20/70G16C20/20G06N3/049G06N3/08G01N33/182G06F2119/12
Inventor乔俊飞郭鑫李文静刘永雷
OwnerBEIJING UNIV OF TECH