Cement finished product specific surface area prediction method and system based on long-term and short-term memory network

A technology for long-term memory and finished cement products, which is applied in neural learning methods, biological neural network models, neural architectures, etc., and can solve the problems of multi-variable cement grinding, difficulty in establishing mechanism models, and strong coupling.

Active Publication Date: 2020-04-28
YANSHAN UNIV
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on this, it is necessary to provide a method and system for predicting the specific surface area of ​​cement products based on long

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
  • Cement finished product specific surface area prediction method and system based on long-term and short-term memory network
  • Cement finished product specific surface area prediction method and system based on long-term and short-term memory network
  • Cement finished product specific surface area prediction method and system based on long-term and short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] The method for predicting the specific surface area of ​​cement products based on the long-short-term memory network of the present embodiment is as follows:

[0090] First, select 8 input variables related to the specific surface area, first arrange the selected variable data according to time series, and then process the data according to the input format of Long Short-term Memory Networks (LSTM), and then The data is normalized as the input data of LSTM.

[0091] In this step, the production process of the entire cement mill is first analyzed, and eight process parameters related to the specific surface area of ​​cement products are selected as the input variables of the LSTM model by combining the experience and knowledge of the field engineer and the measurement process of the cement specific surface area. The time delay and duration of the cement production process, the input variables for a period of time correspond to the output of the specific surface area inde...

Embodiment 2

[0099] figure 1 It is a flow chart of the method for predicting the specific surface area of ​​cement products based on the long-short-term memory network in Embodiment 2 of the present invention. see figure 1 , the method for predicting the specific surface area of ​​cement products based on the long-short-term memory network of the present embodiment includes:

[0100] Step S1: Obtain training input set and training output set.

[0101] The training input set includes training input data at multiple moments; the training output set includes training output data at multiple moments; the training input data at one moment corresponds to the training output data at one moment; the training input data includes rolling Machine baffle opening, feeding amount, powder separator current, powder separator speed, circulation fan baffle opening, circulation fan frequency conversion feedback, cement mill host current and mill hoist current; the training output data is cement The actual...

Embodiment 3

[0140] figure 2 It is a structural diagram of a pre-built long-short-term memory network model in Embodiment 3 of the present invention; image 3 It is a structural diagram of the hidden layer in the long-short-term memory network model in Embodiment 3 of the present invention. see figure 2 with image 3 , the method for predicting the specific surface area of ​​cement products based on the long-short-term memory network of the present embodiment is as follows:

[0141] Step 1: Analyze the cement mill process and select 8 input variables related to the specific surface area. First, arrange the selected variable data in time series, then process the data according to the input format of LSTM, and then normalize the data as LSTM input data.

[0142] In step 1, the whole production process of the cement mill is first analyzed. During the normal operation of the cement mill system, various raw materials are transported by the feeding conveyor belt to the feeding bin of the r...

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 cement finished product specific surface area prediction method and system based on a long-term and short-term memory network. The method comprises the following steps: sorting training input data in a training input set according to a time sequence; inputting the sorted training input set into a pre-constructed long-term and short-term memory network model to obtain a cement finished product specific surface area prediction value at each moment; calculating a node error term of each neuron by adopting a time-based back propagation algorithm according to the trainingoutput set and the cement finished product specific surface area prediction value, wherein the node error term comprises a forgetting gate error term, an input gate error term and an output gate errorterm; training the to-be-trained parameters by adopting a random gradient descent method according to the node error term to obtain a trained long-term and short-term memory network model; and inputting the to-be-tested input set into the trained long-short-term memory network model to obtain a to-be-tested cement finished product specific surface area prediction value. The accuracy of cement finished product specific surface area prediction can be improved.

Description

technical field [0001] The invention relates to the technical field of predicting the specific surface area of ​​cement products, in particular to a method and system for predicting the specific surface area of ​​cement products based on a long-short-term memory network. Background technique [0002] The cement industry is an important basic material industry for my country's national economic construction, providing raw materials for the national economic construction. The cement mill system consisting of equipment such as roller presses and ball mills has been widely used in contemporary cement production. The specific surface area of ​​cement products is the total surface area of ​​cement powder per unit area. If the specific surface area of ​​cement is too large, it means that the cement powder particles are too fine, which will cause problems such as excessive hydration speed and cracks on the concrete surface; if the specific surface area of ​​cement is too small, then...

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): G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/045Y02P90/30
Inventor 郝晓辰郑立召史鑫杨跃赵彦涛黄高路李泽
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap