Sewage quality monitoring method based on PLS-PSO-RBF neural network model

A neural network model and quality monitoring technology, applied to biological neural network models, neural learning methods, neural architectures, etc., to achieve the effect of ensuring accuracy

Active Publication Date: 2021-08-06
COLLEGE OF SCI & TECH NINGBO UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the small sample problem is a problem that must be considered in establishing a sewage quality monitoring model

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
  • Sewage quality monitoring method based on PLS-PSO-RBF neural network model
  • Sewage quality monitoring method based on PLS-PSO-RBF neural network model
  • Sewage quality monitoring method based on PLS-PSO-RBF neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0053] Such as figure 1As shown, the present invention discloses a sewage quality monitoring method based on the PLS-PSO-RBF neural network model. The specific implementation of the method of the present invention will be described below in conjunction with a specific application example.

[0054] The flow of the sewage treatment plant in this implementation case is as follows: figure 2 shown. In this implementation case, a total of 212 days of measurement data were continuously collected; among them, the data vectors of the first 112 days were used for model training, and the data vectors of the last 100 days were used as the data vectors sampled in the new day to verify the quality of sewage Monitoring accuracy. It can be seen that there are only 112 samples used for training the model, which is far less than the amount of data required...

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 sewage quality monitoring method based on a PLS-PSO-RBF neural network model, which realizes the establishment of a sewage quality monitoring model meeting the precision requirement by using an RBF neural network on the premise of small samples, thereby realizing the real-time monitoring or soft measurement of the quality of a sewage outlet end. Specifically, according to the method, firstly, a PLS algorithm is used for reducing the dimensionality of input data, then a PSO algorithm is used for optimization to obtain a central point vector of each hidden layer neuron of the RBF neural network, and then real-time monitoring of the quality of the sewage outlet end is carried out in real time based on a PLS-PSO-RBF neural network model. According to the method, through a dimensionality reduction strategy of the PLS algorithm, the negative influence of a small sample problem encountered during sewage quality monitoring modeling relative to input variable dimensionality can be reduced. Meanwhile, the central point vectors of a plurality of hidden layer neurons are searched out through optimization of the PSO algorithm, so that the precision of the RBF neural network model can be ensured to a greater extent.

Description

technical field [0001] The invention relates to a sewage quality soft measurement method, in particular to a sewage quality monitoring method based on a PLS-PSO-RBF neural network model. Background technique [0002] The monitoring of sewage effluent quality by sewage treatment plants can directly affect the natural water environment and public health, because improper sewage treatment will discharge harmful substances into nature, which will spread diseases and affect public life and work. Generally speaking, biochemical oxygen demand (Biochemical Oxygen Demand, abbreviation: BOD), chemical oxygen demand (Chemical Oxygen Demand, abbreviation: COD), total phosphorus concentration (Total Phosphorus, abbreviation: TP), sludge volume Index (Sludge Volume Index, abbreviation: SVI) four indicators play an important role in monitoring the quality of sewage effluent. Therefore, monitoring the quality of sewage is actually monitoring the above four indicators of sewage. [0003] T...

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): G06Q10/06G06N3/04G06N3/08G06Q50/26
CPCG06Q10/06395G06Q50/26G06N3/08G06N3/045
Inventor 陈杨陈勇旗谢一凡
Owner COLLEGE OF SCI & TECH NINGBO UNIV
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