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

High-precision abnormal data detection and repair method in blast furnace smelting process

A blast furnace smelting and data technology, applied in the direction of instruments, simulators, control/regulation systems, etc., can solve the problem of low precision

Inactive Publication Date: 2017-05-17
INNER MONGOLIA UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a method that adopts global and A new method of abnormal data detection based on local combination and a new method of data patching based on autoregressive time series 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
  • High-precision abnormal data detection and repair method in blast furnace smelting process
  • High-precision abnormal data detection and repair method in blast furnace smelting process
  • High-precision abnormal data detection and repair method in blast furnace smelting process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solution of the present invention will be further described through specific implementation below.

[0022] The specific steps are:

[0023] 1. Detect the number of missing values ​​m in the sample data {y(1), y(2), ... y(k), ... y(L)} collected on-site at the blast furnace in group L, and the number of iron times x corresponding to the missing values i , and record the vector M=[x 1 x 2 … x m ] T .

[0024] 2. Calculate the sample mean and deviation (missing data does not participate in the calculation), sample mean: Sample bias:

[0025] 3. The 3σ rule globally detects the data {y(1), y(2), ... y(k), ... y(L)}, and records the iron times x whose data values ​​are outside the μ±3σ boundary i ,x i It is the number of times that abnormal data may appear; then in x i Do local analysis at all times, and calculate |y(x i )-y(x i-1 )| and |y(x i+1 )-y(x i )|, if the above differences are greater than 3σ, but |y(x i+2 )-y(x i+1 )| and |y(x i+3...

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 provides a high-precision method for detecting and repairing abnormal data in the blast furnace smelting process. This method first obtains relevant indicators through global statistics, and then finds the time point of the data that may have problems, and then specifically analyzes the slope change of the data at the relevant time point, and finally achieves the abnormality through the comparison of local and global statistics and analysis. Accurate understanding of the data. The present invention uses the autoregressive time series model to repair the problem data for the blast furnace data, selects the generalized multi-innovation least squares algorithm with faster convergence speed in the model parameter estimation, and gives the sample data length, multi-innovation amount and model Step selection method. The invention solves the problems of misdetection in the abnormal value detection of the blast furnace process data by the conventional detection method and low precision of the average value interpolation method in the repair of the abnormal temperature data of the blast furnace. The invention can also be applied to other process data detection and repair.

Description

technical field [0001] The present invention relates to a method for detecting and repairing abnormal values ​​of high-precision process record data, and relates to abnormal values ​​in blast furnace smelting production record data ("missing value" is a special case of abnormal value, so this manual refers to "missing value" It can also be used for detection and repair of data outliers in biomedicine, communication, transportation, exploration, papermaking, chemical industry, metallurgy and other complex industrial processes, aerospace and other fields. Background technique [0002] Process data is the core basis for system modeling, control, and optimization. Affected by factors such as human factors, the environment, and irresistible emergencies, there are data missing and abnormal phenomena in the process record data. The detection and repair of outliers in process data is based on the premise of data-driven modeling, optimization and control, and is a common problem that...

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 Patents(China)
IPC IPC(8): G05B17/02
Inventor 张勇赵哲刘丕亮孙采鹰崔桂梅
Owner INNER MONGOLIA UNIV OF SCI & 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