Method for detecting and diagnosing fault in industrial wastewater treatment process based on data model

A technology for industrial wastewater and treatment process, which is applied in water treatment parameter control, biological water/sewage treatment, water/sludge/sewage treatment, etc. And other issues

Inactive Publication Date: 2017-10-27
EAST CHINA UNIV OF SCI & TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, when the water inlet speed is too fast, the reaction in the reaction tank is insufficient, or the oxygen content in the reaction tank is not within the normal range, resulting in insufficient removal of nitrogen and phosphorus. In severe cases, the treated water quality is not up to standard and affects the ecological environment.

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
  • Method for detecting and diagnosing fault in industrial wastewater treatment process based on data model
  • Method for detecting and diagnosing fault in industrial wastewater treatment process based on data model
  • Method for detecting and diagnosing fault in industrial wastewater treatment process based on data model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Below by embodiment the present invention will be further described:

[0056] For the six variables, the dissolved oxygen DO(x 1 , mg / L), suspended matter content in aerobic zone SS(x 2 , mg / L), water inlet flow rate Q in (x 3 ,m 3 / s), outlet flow Q ef (x 4 ,m 3 / s), COD in (x 5 , mg / L), and the content of suspended solids in the outlet SS ef (x 6 ,mg / L), collect a set of 100 samples of historical normal data of the system as training data, and a set of real-time process observation data consisting of 100 samples.

[0057] 1. Preprocessing samples

[0058] Perform normalization processing on the first group of data collected above consisting of 200 samples, using formula (1): x 1 The mean value of is 3.78, and the variance is 1.37; x 2 has a mean of 4.00 and a variance of 1.27; x 3 The mean value of is 3417.48, and the variance is 1290.31; x 4 The mean value of is 4090.31, and the variance is 1274.90; x 5 The mean value of is 24.82, and the variance is ...

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 method for detecting and diagnosing a fault in an industrial wastewater treatment process based on a data model. The method comprises the following steps: taking dissolved oxygen of an intake area, content of suspensoids in an aerobic zone, flow at a water inlet, flow at a water outlet, chemical oxygen demand and the content of the suspensoids at the water outlet as input variables; carrying out normalization processing based on the input variables, carrying out overall modeling on training data by utilizing PCA, selecting a pivot element for each variable according to the produced load vector, and forming a subspace; respectively calculating T2 statistic of each subspace, and constructing an SVDD model; projecting normalized real-time monitoring data to each subspace, and calculating, so that the corresponding T2 statistic is obtained; and calculating distance of the statistic from a circle center in a high dimensional space of an SVDD structure, so that whether the monitoring data at the moment is normal or not is judged.

Description

technical field [0001] The invention belongs to the intersecting field of industrial chemical industry and process control, and relates to a method for timely reflecting the operating state of the system by measuring the amount of data in the process of industrial wastewater treatment. Background technique [0002] The construction of industrial wastewater treatment projects is mainly to solve the problem of random discharge of sewage in the drainage system, and to improve and control the serious pollution of sewage to the local ecology. The drainage quality of industrial systems has a vital impact on people's living environment and the sustainable development of society. [0003] The quality of influent water is food industry wastewater, which has high biodegradability. Sewage concentration is high, its biochemical oxygen demand (Biochemical oxygen demand, BOD), chemical oxygen demand (Chemical oxygen demand, COD), total nitrogen content (total nitrogen, TN), total phospho...

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): C02F3/30
CPCC02F3/302C02F2209/08C02F2209/10C02F2209/40C02F2303/14
Inventor 颜学峰王蓓
Owner EAST CHINA UNIV OF SCI & 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

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