Water quality BOD measurement method based on AQPSO-RBF neural network

A neural network and measurement method technology, applied in the design field of water quality BOD multi-source sensors, can solve the problems of complex operation process, difficult maintenance of equipment, long detection time, etc., and achieve the effect of short time consumption, reduced manpower and convenient operation.

Active Publication Date: 2021-06-29
ZHEJIANG UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] In order to overcome the deficiencies of the prior art such as high price, complex operation process, easy misoperation, long detection time, and extremely difficult maintenance equipment, the present invention provides a water quality BOD measurement method based on AQPSO-RBF neural network, online real-time BOD The measurement method uses the AQPSO-based algorithm to train the RBF neural network in advance. The model training time for 500 sets of training data is within 1 second, and the error in the test data can be controlled within 1. It is a fast and accurate model; the model training is completed Finally, sensors such as temperature, dissolved oxygen, pH, oxidation-reduction potential, and chemical oxygen demand can be used as the input of the AQPSO-RBF neural network, collected by the IoT gateway already running the AQPSO-RBF neural network, and mapped by the neural network. Real-time BOD prediction value can be quickly obtained; real-time, high-precision water quality BOD measurement can be truly realized through the combination of this soft measurement model with sensors and IoT gateways

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
  • Water quality BOD measurement method based on AQPSO-RBF neural network
  • Water quality BOD measurement method based on AQPSO-RBF neural network
  • Water quality BOD measurement method based on AQPSO-RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be further described below in conjunction with the accompanying drawings.

[0075] refer to Figure 1 to Figure 5 , a kind of water quality BOD measuring method based on AQPSO-RBF neural network, comprises the following steps:

[0076] Step 1: Data preprocessing, the process is as follows:

[0077] The invention selects BOD in water quality pollution as a research target, and implements high-precision prediction of BOD through a technical solution of water quality BOD multi-source sensor based on AQPSO-RBF. The data set used in the water quality BOD model of AQPSO-RBF includes sensor data of temperature, dissolved oxygen, pH, oxidation-reduction potential, chemical oxygen demand, and BOD.

[0078] Step 1.1: Use the Raida criterion for data cleaning, delete outliers, and set the entire data set as x1, x2,...,xn. Using ei to represent the residual error of the data, the formula for the standard deviation is:

[0079]

[0080] If the resid...

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 water quality BOD measurement method based on an AQPSO-RBF neural network. The method comprises the following steps: 1, preprocessing data; 2, establishing a model based on an RBF neural network; 3, establishing a model based on the AQPSO-RBF neural network; and 4, predicting a water quality BOD value by the following processes: step 4.1, inputting a training data set into the improved AQPSO-RBF neural network, and then inputting test data into the AQPSO-RBF to dynamically change the network to obtain a final BOD prediction model; and step 4.2, accessing each sensor to the gateway of the Internet of Things, obtaining the value of each sensor through the BOD prediction model of the AQPSO-RBF in the gateway, and outputting the predicted value of the water quality BOD in real time. According to the method, the real-time BOD predicted value can be quickly obtained; and real-time and high-precision water quality BOD measurement can be really realized through combination of the soft measurement model, the sensor and the Internet of Things gateway.

Description

technical field [0001] The invention belongs to the field of water quality BOD measurement, and mainly relates to the design of a water quality BOD multi-source sensor based on AQPSO-RBF, which realizes real-time and high-precision detection of water quality BOD. Oxygen BOD required by organisms in water quality is the most direct index reflecting the pollution degree of water quality, and the measurement process of BOD is very complicated and error-prone, so the present invention has great significance in the measurement of water quality BOD. Background technique [0002] Nowadays, due to factors such as human life and factory discharge, groundwater sources are polluted, which makes limited water resources more tense. In the case of water shortages, we must ensure that water sources are free from pollution, so water quality measurement is an important measure that cannot be ignored. [0003] At present, industries related to water quality testing urgently need a large numb...

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): G06F30/25G06F30/27G06F119/02
CPCG06F30/25G06F30/27G06F2119/02Y02A20/152
Inventor 王涌陆卫左楚涵鲍明月
Owner ZHEJIANG 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