Blast furnace bosh gas volume prediction method and program for multi-clustering prototype-based T-S model

A technology of clustering prototypes and prediction methods, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve the uncertainty of hypergeometric shape of high-dimensional data, cannot fully extract feature information, and cannot find high-dimensional data. In order to achieve the effect of timely and accurate blast furnace condition information, avoid abnormal furnace conditions, and improve prediction accuracy

Inactive Publication Date: 2018-08-28
YANSHAN UNIV
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the hypergeometric shape of high-dimensional data is uncertain, and it is impossible to find a clustering prototype suitable for all kinds of high-dimensional data.
In previous studi

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
  • Blast furnace bosh gas volume prediction method and program for multi-clustering prototype-based T-S model
  • Blast furnace bosh gas volume prediction method and program for multi-clustering prototype-based T-S model
  • Blast furnace bosh gas volume prediction method and program for multi-clustering prototype-based T-S model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0024] A kind of T-S model based on multi-clustering prototype of the present invention is to the prediction method of bosh gas quantity, such as figure 1 As shown, the implementation steps of the method are as follows:

[0025] Step 1: Perform data preprocessing on the blast furnace data: use the Raida criterion to eliminate data outliers, reduce the impact of abnormal data on the prediction accuracy of the model, and fill missing values ​​with the average value of surrounding data points;

[0026] Step 2: Screen the input variables: use the Spearman rank correlation coefficient to screen the input variables that have a great influence on the bosh gas volume, and the process includes the following steps:

[0027] (1) After removing data outliers, assuming that the two variables are X and Y respectively, and the number of samples of them is N, ...

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 blast furnace bosh gas volume prediction method and program for a multi-clustering prototype-based T-S model. The method comprises the steps of performing data preprocessingon blast furnace data, and deleting abnormal values; performing variable screening by utilizing a Spearman rank correlation coefficient; selecting a hyperspherical clustering prototype-based FCM fuzzyclustering algorithm and a hyperplane clustering prototype-based NFCRMA fuzzy clustering algorithm to perform fuzzy clustering on the blast furnace data, performing calculation by using membership functions corresponding to the two fuzzy clustering algorithms to obtain two types of different T-S model antecedent rule fitness, sorting the two types of the rule fitness from high to low, and finallycalculating a weighted sum of the two types of the rule fitness to obtain weighted rule fitness; and calculating consequent parameters of the T-S model by using a least square method, and finally adjusting a weighted coefficient to improve the prediction precision of the model. The method can accurately predict a value of a blast furnace bosh gas volume index at a next moment.

Description

technical field [0001] The invention relates to the field of blast furnace ironmaking, in particular to a method and program for predicting bosh gas volume based on a multi-clustering prototype T-S model. Background technique [0002] The iron and steel industry is a pillar industry of the national economy and a symbol of the level of technological development of a country. Blast furnace ironmaking is the upstream process of the steel production process, and it is a major energy-intensive and high-polluting household. How to keep the blast furnace running smoothly and achieve the purpose of saving energy and reducing consumption is of great significance to the improvement of economic benefits of iron and steel enterprises and the sustainable development of the national economy. The blast furnace gas flow participates in the reduction reaction and heat transfer in the furnace, which is the most direct reflection of the energy utilization and temperature field distribution of...

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): G06F17/50G06K9/62
CPCG06F30/20G06F18/23
Inventor 华长春马子文李军朋关新平
Owner YANSHAN 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