Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

MSWI process dioxin emission prediction method based on multi-window concept drift detection

A technology of concept drift and forecasting methods, which is applied in forecasting, complex mathematical operations, instruments, etc., and can solve problems affecting forecasting results, etc.

Pending Publication Date: 2022-04-12
BEIJING UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obviously, the abnormal fluctuations of these related variables will affect the prediction results of the DXN emission concentration soft sensor 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
  • MSWI process dioxin emission prediction method based on multi-window concept drift detection
  • MSWI process dioxin emission prediction method based on multi-window concept drift detection
  • MSWI process dioxin emission prediction method based on multi-window concept drift detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0125] This section modeling data is a real DXN emission concentration data from a MWSI power plant in Beijing for nearly six years, including from solid waste incineration systems, flue gas treatment systems, boiler systems, solid waste storage and transportation systems, steam power generation systems, etc. 121 process variables are shown in Table 1.

[0126] Table 1 Download 121 process variables in DXN emission concentration data

[0127]

[0128]

[0129]

[0130]

[0131]

[0132] This experiment uses 33 mark data, divided into two parts, two of whom used training sets, 1 / 3 for test sets.

[0133] In the offline modeling window, the DXN soft measurement model and the feature spatial drift detection model are constructed by historical data, and the historical data is predicted and real value. Figure 5 Indicated.

[0134] Here, set parameters α = 0.05, θ y = 0.01, θ cd = 1.

[0135] When the real training data passes through the feature spatial drift detection model,...

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 MSWI process dioxin emission prediction method based on multi-window concept drift detection, and belongs to the field of urban solid waste incineration. Dioxin (DXN) is a very toxic pollutant discharged in an MSWI (municipal solid waste incineration) process. The actual industrial process adopts a soft measurement model to realize DXN prediction, but the prediction precision of the soft measurement model is reduced due to the time-varying characteristic of the industrial process. The method comprises the following steps: firstly, establishing a random forest (RF) soft measurement model and a principal component analysis (PCA) drift detection model based on historical data; secondly, performing drift detection on the new sample through a multi-window concept drift detection strategy to determine whether the new sample is a drift sample; and finally, performing redundancy removal processing on the drift samples and judging whether the number of the drift samples meets a set threshold value or not, if so, re-training the PCA model and the RF model, and otherwise, continuing to predict a new sample by adopting a historical model. The validity of the method is verified by adopting industrial process data.

Description

Technical field [0001] The present invention belongs to the field of urban solid waste incineration. Background technique [0002] The continuous advancement of urbanization has increased the increasing amount of MuniciPal Solid Waste (MSW), how to effectively handle it has become the most critical part of the current urban pollution prevention and control strategy. Urban solid waste incineration (MSWI) technology with advantages such as reduction, efficiency, low pollution, has been widely used worldwide, and its typical process flow figure 1 Indicated. [0003] Such as figure 1 As shown, the MSWI process includes process links such as solid waste storage, solid waste incineration, steam power generation, and flue gas treatment. MSW is usually transported by the municipal transportation vehicle to the storage pool for staining. After the hopper is put into the hopper, it is pushed into the furnace row by the feeder; after drying, combustion, and fired 3 stages, will incinerate r...

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): G06Q10/04G06F17/15G06Q50/26
Inventor 汤健许超凡徐喆夏恒乔俊飞
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com