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

Control system of soda carbonization technique based on neural network and control method thereof

A neural network and process control technology, which is applied to the soda ash carbonization process control system based on neural network and its control field, can solve the problem that the utilization rate of raw materials is not high, the conversion rate of raw material utilization rate is not high, it is difficult to ensure the quality of full-load production products, and the system fluctuates greatly. and other problems to achieve the effect of increasing sodium conversion rate, improving automation level, and reducing consumption

Active Publication Date: 2011-03-30
GUANGDONG UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, although most of the carbonization processes in domestic alkali plants have adopted computer control systems, such as DCS and PLC, etc., they basically remain at the manual / automatic control level of conventional instruments, and single-loop manual / automatic control is still used for control points. The control quality depends on the continuous operation level and the operator's manual experience. The control accuracy is relatively rough, which makes the control accuracy of the system not high, and the frequent manual interference of the operator makes the system fluctuate greatly, making it difficult to guarantee full production and product quality. The quality of raw materials, the utilization rate of sodium, the conversion rate of carbon, etc. are generally not high

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
  • Control system of soda carbonization technique based on neural network and control method thereof
  • Control system of soda carbonization technique based on neural network and control method thereof
  • Control system of soda carbonization technique based on neural network and control method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The working principle of the present invention is to establish a non-linear model of carbonization tower characteristics (temperature and flow) according to the historical data of carbonization tower operation by using the black box modeling principle and applying neural network modeling algorithm by analyzing the reaction mechanism of carbonization tower. According to the established network model, the particle swarm optimization algorithm is applied to optimize the output temperature to obtain the optimal value of a set of flow, and use this optimal value as the set value of the controller to control the action of the actuator to realize the carbonization process. optimal control.

[0025] attached figure 1 It is a functional block diagram of the system, including a neural network controller 1, a neural network identifier 2, a model library 3, a particle swarm optimizer 4, a data acquisition channel 5 and a carbonization tower 6; Channel 5 is connected to the input ...

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 relates to a control system of a soda carbonization technique based on a neural network and a control method thereof, wherein, the control system comprises a neural network controller, a neural network recognizer, a model base, a particle swarm optimizer, a data acquisition channel and a carbonizer; the data acquisition channel is used for acquiring the technological parameter values of the carbonizer in real time, pretreating the data, transmitting the treated data to the neural network recognizer, modeling by the neural network recognizer, emulating and amending the modeled model, reading the amended model parameters by the neural network controller to generate control parameters, optimizing the controlled quantity by the particle swarm optimizer simultaneously to obtain agroup of optimum controlled quantities, controlling the actions of a control mechanism and finishing the modeling and optimal controlling of the carbonizer; the model base is used for storing the flow and temperature model in the soda carbonizer which is built by the neural network recognizer. The invention can model and optimally control the carbonizer, improve the automation level of units, improve the conversion rate of sodium in the production process and reduce the consumption.

Description

Technical field [0001] The invention involves the process process of the pure alkali industry and the field of automatic control. It specially involves a neural network -based pure alkali carbon chemical control system and its control method. Background technique [0002] Skin -alkali (NA2CO3) is an important basic chemical raw material and a traditional chemical product with many years of production and use. It is widely used in many industries such as chemical, medicine, glass, metallurgy, and papermaking.It is very large, occupying an important basic position in the construction of the national economy, and the development of pure alkali industry is directly related to the development of the national economy and the improvement of people's living standards. [0003] The carbonization process of pure alkali is the central link of alkali -making process, and the mechanism is more complicated.The carbonized tower is the core unit of the entire pure alkali production. It includes ...

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): G05B13/00C01D7/00
Inventor 程良伦曾莹衷柳生谢晓松
Owner GUANGDONG UNIV OF TECH