Water quality abnormal event detection method based on spectral statistical characteristics

A technology of abnormal events and statistical characteristics, applied in the direction of color/spectral characteristic measurement, etc., can solve problems such as qualitative anomaly detection

Inactive Publication Date: 2015-07-15
ZHEJIANG UNIV
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The content of the present invention is to solve the problem of qualitative anomaly detection in the case of pollutants injected into water bodies using spectral online detection technology

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 abnormal event detection method based on spectral statistical characteristics
  • Water quality abnormal event detection method based on spectral statistical characteristics
  • Water quality abnormal event detection method based on spectral statistical characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] 1) The flow chart of the detection of the entire water quality abnormal event is attached figure 1 shown.

[0066] 2) Online water quality spectral data collection. First of all, the flow rate of the main pipe needs to be kept relatively constant during the experiment, and the measuring pump also needs to be turned on all the time to measure the flow rate of the main pipe during the experiment. Controlling the flow rate of the main pipeline to be relatively constant can help determine the intensity of the pollution event formed by the pollutant after entering the pipeline network. At the same time, for the tested pollution events, the duration of the event is different, and the pollution degree of the event is also different, so the simulation of the event is more realistic and reliable. The scanning frequency of the spectral sensor is set to scan once every 30s, and the pollutant selected here is phenol.

[0067] The experimental data is based on the experimental da...

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 abnormal event detection method based on spectral statistical characteristics. The water quality abnormal event detection method based on the spectral statistical characteristics comprises the following steps: S1. carrying out water quality online data acquisition; S2. carrying out normalization pre-processing on the original spectral data obtained in the step S1; S3. carrying out a principal component analysis on the normalized spectral data obtained in the step S2, and determining the number of principal components in the principal component analysis; S4. extracting principal component factors in the normalized spectral data on the basis of PPCA calculation for the maximum likelihood estimation; S5. carrying out a multi-dimensional statistical variable online detection control chart analysis, calculating control limit values corresponding to the principal component factors in the step S4 on each time point under a normal-state water quality frame, and marking the spectral data exceeding the value as abnormal; and S6. reporting a water quality abnormal event, and carrying out abnormal event probability analysis on an abnormal time sequence obtained in the step S5 to report the water quality abnormal event. The method combines probability principal component analysis and process statistics with a method for quality control for a monitoring chart, and online water quality abnormal event detection can be realized.

Description

technical field [0001] The invention relates to the field of water quality safety monitoring, in particular to an online water quality abnormal event detection method suitable for ultraviolet-visible light spectroscopy. Background technique [0002] Water resources are the most important resources for human survival, and the quality of urban drinking water is directly related to the quality of life and life safety of the urban population. In daily life, factors that endanger water resources often come from various aspects of life, such as the random disposal of urban domestic and industrial waste, the wanton discharge of untreated domestic and industrial sewage, and the contamination of industrial chemicals during transportation. Leakage and excessive use of pesticides in agricultural production. Nowadays, the environmental protection situation of drinking water in our country is also becoming increasingly severe with the increasingly rapid economic development and the acce...

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): G01N21/31
Inventor 侯迪波黄平捷郭冰冰刘澍张光新张坚文相
Owner ZHEJIANG 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

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