A Coke Quality Index Prediction Method Based on Multilayer Neural Network

A multi-layer neural network, coke quality technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as quality index prediction

Active Publication Date: 2022-04-19
BAOTOU IRON & STEEL GRP +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the object of the invention is to provide a coke quality index prediction method based on multilayer neural network, to solve the quality index prediction problem in the coke production process of iron and steel enterprises

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
  • A Coke Quality Index Prediction Method Based on Multilayer Neural Network
  • A Coke Quality Index Prediction Method Based on Multilayer Neural Network
  • A Coke Quality Index Prediction Method Based on Multilayer Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The specific embodiment of the present invention is described below in conjunction with accompanying drawing:

[0029] The present invention adopts industrial actual production data, first cleans the data, uses gradient enhanced tree to conduct correlation analysis on factors affecting coke quality indicators, and selects the variables most relevant to ash content, sulfur content, M10, M40, CRI and CSR, etc. , and then construct training samples, establish a multi-layer neural network prediction model to predict the coke quality index, and use the intelligent optimization algorithm to optimize the variables in the model, and give the final prediction result of the coke quality index. The invention can predict the quality index of coke with high precision, meet the needs of industrial production, provide data support and guidance for subsequent production, and can also be extended to other coking product industries.

[0030] (1) Correlation analysis affecting coke qualit...

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 coke quality index prediction method based on a multilayer neural network, which belongs to the technical field of industrial information. Using the actual industrial production data, the data is firstly cleaned, and the correlation analysis of the factors affecting the coke quality index is carried out by using the gradient enhanced tree, and the factors related to the ash, sulfur, M 10 , M 40 , CRI, CSR and other most relevant variables, and then construct training samples, establish a multi-layer neural network prediction model to predict coke quality indicators, and use intelligent optimization algorithms to optimize the variables in the model to give the final coke quality indicators forecast result. The invention can predict the coke quality index with high precision, meet the needs of industrial production, provide data support and guidance for subsequent production, and can also be extended to other coking product industries.

Description

technical field [0001] The invention specifically relates to a coke quality index prediction method based on a multilayer neural network, which belongs to the field of industrial information technology. Background technique [0002] Coke, as an important solid fuel in the production process of the iron and steel industry, is obtained from coal under high temperature conditions through dry distillation and other processes. At present, the coal blending in coking plants is basically high-quality coking coal such as fat coal and coking coal. .(2018). Research on Coking Coal Analysis and Coke Quality Prediction. (Doctoral dissertation)). From the perspective of the existing production technology and the distribution of coal resources in my country, gas coal, 1 / 3 coking coal and other weakly caking coals and medium caking coals are high-quality coals in the coking process, and their reserves and output are relatively large, but in actual coking The proportion in production is lo...

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): G06Q10/06G06Q50/04G06K9/62G06N3/04G06N3/08G06N20/00
CPCG06Q10/06393G06Q10/06395G06Q50/04G06N3/08G06N20/00G06N3/045G06F18/24323Y02P90/30
Inventor 芦建文王宏卢培山江鑫王勇付利俊贾晓宗欧宇星资金凯
Owner BAOTOU IRON & STEEL GRP
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