Unlock instant, AI-driven research and patent intelligence for your innovation.

A composition prediction method of lead-zinc sintered block

A composition prediction and sintering technology, which is applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of composition detection data lag, need to wait until 3 to 4 hours before knowing, and has little guiding value, etc. problems, to achieve the effect of improving the pass rate

Active Publication Date: 2018-02-09
华楚智能科技(湖南)有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The testing process takes 1 to 2 hours, so the effect of the ingredients and other processes before the lead-zinc sintering can only be known after 3 to 4 hours, which leads to a serious lag in the detection data of the composition of the lead-zinc sintered block, and the test results have no effect on the guidance and adjustment. The proportion of various ingredients before sintering to control the composition of the finished lead-zinc sintered block is of little significance, that is, the guiding significance for real-time production is of little value

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 composition prediction method of lead-zinc sintered block
  • A composition prediction method of lead-zinc sintered block
  • A composition prediction method of lead-zinc sintered block

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0050] An embodiment of the present invention includes the following steps:

[0051] A. Establish the RBF-AR model of the composition of lead-zinc agglomerates

[0052]

[0053] where y(t+1) is the predicted t+1 The composition value of the lead-zinc sinter at time, t is the current time, t-1, ..., t-n y +1 is the historical moment, y(t) is the current value of the collected lead-zinc agglomerates, y(t-1), ..., y(t-n y +1) is the historical value of the collected lead-zinc agglomerates, e(t) is white noise, n y is the order corresponding to y, h is the number of layers of the RBF neural network, X(t) is the state dependent variable, X(t)=[y(t)] T ,

[0054] c 0 ,...,c m ,a k,0 ,...,a k,m ,z m,1 ,λ m ,m=1,2,...h,k=1,2,...,n y for

[0055] Parameters of the RBF-AR model of the composition of lead-zinc agglomerates;

[0056] B. Set up multiple sets of different n y and the value of h, each group of n is identified by the Levenberg-Marquardt algorithm, respectively ...

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 composition prediction method of a lead-zinc sintered block, which comprises the following steps: A. establishing the RBF-AR model of the composition of the lead-zinc sintered block; B. setting multiple groups of different values ​​of ny and h, respectively through nonlinear The parameter identification method identifies the parameters of the RBF-AR model corresponding to each group ny and h; C. Obtain the red information criterion value AIC corresponding to each group ny and h; D. Compare the size of the AIC corresponding to each group ny and h, and minimize The values ​​of ny and h corresponding to the AIC, the parameters of the RBF-AR model corresponding to this ny and h are substituted into the RBF-AR model to obtain the composition prediction model of the lead-zinc sintered block; E. collect y (t), y (t-AR 1), ..., y(t‑ny+1) are substituted into the composition prediction model to obtain the composition prediction value y(t+1) of the lead-zinc sintered block. The invention can quickly predict the composition of the lead-zinc sintered block at the next moment, solves the shortcoming that the detection result cannot be effectively used due to the long detection time, and uses the predicted result in time to adjust the ingredients of the sintering process, which can be real-time Guided production and improved the qualified rate of lead-zinc sintered agglomerates.

Description

technical field [0001] The invention relates to a composition prediction method for lead-zinc agglomerates. Background technique [0002] Sintering process is a very important process in the traditional lead and zinc smelting process. [0003] The content of various chemical components (such as lead, zinc, sulfur, etc.) of lead-zinc agglomerates is an important indicator to measure its quality. [0004] There are many kinds of raw materials for lead-zinc sintering, and the physical and chemical properties of the raw materials are very different. Equipped to guide. [0005] At present, after the lead-zinc agglomerate is sintered, the finished product is sampled, and the samples are analyzed by chemical methods to obtain the composition of the lead-zinc agglomerate. [0006] Since the lead-zinc sintering process is a large lagging link, it takes about 2 hours from the batching to the finished lead-zinc agglomerate, so the lead-zinc sintering plant generally samples the comp...

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): G06F17/50
Inventor 魏吉敏杨鸿波王宇星罗志辉刘懿
Owner 华楚智能科技(湖南)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More