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

Model-free self-adaptive learning optimal control method and system for zinc electrolysis process

A model-free self-adaptive and control method technology, which is applied in the direction of self-adaptive control, general control system, control/regulation system, etc., can solve problems such as large time lag, insufficient sampling, inaccurate modeling of zinc electrolysis, etc., and achieve improved Stability, the effect of reducing energy consumption

Active Publication Date: 2021-04-27
CENT SOUTH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a model-free self-adaptive learning optimization control method and system for zinc electrolysis process, which solves the problem of inaccurate zinc electrolysis modeling in the prior art due to the complexity, large time lag and insufficient sampling of the zinc electrolysis process , so that it is impossible to achieve the technical problem of optimal control of the zinc electrolysis process

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
  • Model-free self-adaptive learning optimal control method and system for zinc electrolysis process
  • Model-free self-adaptive learning optimal control method and system for zinc electrolysis process
  • Model-free self-adaptive learning optimal control method and system for zinc electrolysis process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] refer to figure 1 , the zinc electrolysis process model-free self-adaptive learning type optimization control method provided by Embodiment 1 of the present invention includes:

[0044] Step S101, establishing the action network, value network, target action network, and target value network adopted by the DDPG algorithm, and randomly initializing the network parameters of the action network, value network, target action network, and target value network;

[0045] Step S102, define the state space and action space of zinc electrolysis, the action space of zinc electrolysis is the new liquid flow rate, and the state space S is specifically:

[0046] S={C 1,1 ,C 1,2 ,C 2,1 ,C 2,2 ,C 3,1 ,C 3,2 ,C 4,1 ,C 4,2 ,V C ,ε},

[0047] Among them, C 1,1 and C 1,2 Represent the concentration of acid ions and zinc ions in the new liquid, respectively, C 2,1 and C 2,2 represent the concentration of acid ions and zinc ions in the mixing tank, respectively, C 3,1 and C 3...

Embodiment 2

[0053] refer to figure 2 , the zinc electrolysis process model-free self-adaptive learning type optimization control method provided in the second embodiment of the present invention includes:

[0054] Step S201, establishing the action network, value network, target action network, and target value network adopted by the DDPG algorithm, and randomly initializing the network parameters of the action network, value network, target action network, and target value network.

[0055] DDPG (Deep Deterministic Policy Gradient, DDPG) algorithm is the abbreviation of deep deterministic gradient descent. The neural network used in DDPG is similar to the Actor-Critic form, and it also needs a policy-based neural network and a value-based neural network. In order to reflect the idea of ​​DQN, each neural network is subdivided into two, for Policy Gradient, including action network and target action network. The action network is used to output real-time actions for actors to implement i...

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 model-free self-adaptive learning type optimization control method and system in the process of zinc electrolysis. The method defines the state space and action space of zinc electrolysis, and trains the action network and action network according to the data generated by interacting with the zinc electrolysis environment. Value network, update the target action network and target value network through the soft update algorithm, obtain the zinc electrolysis DDPG model, and obtain the optimal new liquid flow corresponding to the current zinc electrolysis state according to the zinc electrolysis DDPG model, which solves the problem of zinc electrolysis in the existing technology. The complexity of the electrolysis process, large time lag, and insufficient sampling lead to inaccurate zinc electrolysis modeling, which makes it impossible to achieve the technical problems of optimal control of the zinc electrolysis process. Not only can the optimal control of the new liquid flow be achieved through self-learning, Therefore, the optimal zinc-acid ratio is obtained, and the energy consumption of the electrolysis process can be effectively reduced, thereby improving the stability of the zinc electrolysis process.

Description

technical field [0001] The invention relates to the technical field of nonferrous metallurgy, in particular to a model-free self-adaptive learning-type optimization control method and system for zinc electrolysis process. Background technique [0002] Zinc hydrometallurgy is the most important zinc smelting method in the world today, and more than 90% of zinc in the world is produced through zinc hydrometallurgy. Electrolysis is the most energy-consuming production process in the new process of wet smelting. The energy consumption of zinc electrolysis accounts for more than 80% of the energy consumption of the entire zinc production process, and electricity accounts for 30%-40% of the entire production cost. Therefore, reducing the energy consumption of the zinc electrolysis process is a top priority for enterprises, and reducing DC power consumption is the top priority of zinc electrolysis energy saving, which is of great significance for improving the market competitivenes...

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): G05B13/04
CPCG05B13/042
Inventor 李勇刚石雄涛阳春华朱红求桂卫华孙备龙双刘卫平
Owner CENT SOUTH UNIV
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

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com