BR112023004793A2 - Sistema de computador e método que provê instruções de operação para controle térmico de um alto-forno - Google Patents

Sistema de computador e método que provê instruções de operação para controle térmico de um alto-forno

Info

Publication number
BR112023004793A2
BR112023004793A2 BR112023004793A BR112023004793A BR112023004793A2 BR 112023004793 A2 BR112023004793 A2 BR 112023004793A2 BR 112023004793 A BR112023004793 A BR 112023004793A BR 112023004793 A BR112023004793 A BR 112023004793A BR 112023004793 A2 BR112023004793 A2 BR 112023004793A2
Authority
BR
Brazil
Prior art keywords
thermal control
blast furnace
domain
data
computer system
Prior art date
Application number
BR112023004793A
Other languages
English (en)
Inventor
Schockaert Cédric
Hansen Fabrice
Hausemer Lionel
Baniasadi Maryam
Bermes Philipp
Original Assignee
Wurth Paul Sa
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wurth Paul Sa filed Critical Wurth Paul Sa
Publication of BR112023004793A2 publication Critical patent/BR112023004793A2/pt

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • C—CHEMISTRY; METALLURGY
    • C21—METALLURGY OF IRON
    • C21B—MANUFACTURE OF IRON OR STEEL
    • C21B5/00—Making pig-iron in the blast furnace
    • C21B5/006—Automatically controlling the process
    • C—CHEMISTRY; METALLURGY
    • C21—METALLURGY OF IRON
    • C21B—MANUFACTURE OF IRON OR STEEL
    • C21B7/00—Blast furnaces
    • C21B7/24—Test rods or other checking devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
    • F27B1/00—Shaft or like vertical or substantially vertical furnaces
    • F27B1/10—Details, accessories, or equipment peculiar to furnaces of these types
    • F27B1/26—Arrangements of controlling devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
    • F27D19/00—Arrangements of controlling devices
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F27—FURNACES; KILNS; OVENS; RETORTS
    • F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
    • F27D21/00—Arrangements of monitoring devices; Arrangements of safety devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • C—CHEMISTRY; METALLURGY
    • C21—METALLURGY OF IRON
    • C21B—MANUFACTURE OF IRON OR STEEL
    • C21B2300/00—Process aspects
    • C21B2300/04—Modeling of the process, e.g. for control purposes; CII

Abstract

SISTEMA DE COMPUTADOR E MÉTODO QUE PROVÊ INSTRUÇÕES DE OPERAÇÃO PARA CONTROLE TÉRMICO DE UM ALTO-FORNO. A presente invenção se refere a um sistema de computador (100), um método implementado em computador e um produto de programa de computador para treinar um modelo de aprendizado de reforço (130) para prover instruções de operação para controle térmico de um alto-forno. Um modelo de aprendizado de máquina de adaptação de domínio (110) gera um primeiro conjunto de dados invariantes no domínio (22) a partir de dados de operação históricos (21) obtidos como série temporal multivariada e refletindo estados térmicos dos respectivos altos-fornos (BF1 a BFn) de múltiplos domínios. Um modelo transiente (121) de um processo do alto-forno genérico é usado para gerar dados de operação artificiais (24a) como série temporal multivariada refletindo um estado térmico de um alto-forno genérico (BFg) para uma ação de controle térmico em particular (26a). Uma rede de aprendizado profundo generativo (122) gera um segundo conjunto de dados invariantes no domínio (23a) pela transferência das características aprendidas a partir dos dados de operação históricos 21 para os dados de operação artificiais (24a). O modelo de aprendizado de reforço (130) determina (1400) uma recompensa (131) para a ação de controle térmico em particular (26a) em vista de uma dada função objetiva pelo processamento do primeiro e do segundo conjuntos de dados invariantes no domínio combinados (22, 23a). Dependendo da recompensa (131), o segundo conjunto de dados invariantes no domínio é regerado com base em parâmetros modificados (123-2), e repete-se a determinação da recompensa para aprender instruções de operação otimizadas para ações de controle térmico otimizadas a serem aplicadas para respectivos estados de operação de um ou mais altos-fornos.
BR112023004793A 2020-09-30 2021-09-28 Sistema de computador e método que provê instruções de operação para controle térmico de um alto-forno BR112023004793A2 (pt)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
LU102103A LU102103B1 (en) 2020-09-30 2020-09-30 Computer System and Method Providing Operating Instructions for Thermal Control of a Blast Furnace
PCT/EP2021/076710 WO2022069498A1 (en) 2020-09-30 2021-09-28 Computer system and method providing operating instructions for thermal control of a blast furnace

Publications (1)

Publication Number Publication Date
BR112023004793A2 true BR112023004793A2 (pt) 2023-04-18

Family

ID=72802055

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023004793A BR112023004793A2 (pt) 2020-09-30 2021-09-28 Sistema de computador e método que provê instruções de operação para controle térmico de um alto-forno

Country Status (10)

Country Link
US (1) US20230359155A1 (pt)
EP (1) EP4222562B1 (pt)
JP (1) JP2023543813A (pt)
KR (1) KR20230079093A (pt)
CN (1) CN116261690A (pt)
BR (1) BR112023004793A2 (pt)
CL (1) CL2023000841A1 (pt)
LU (1) LU102103B1 (pt)
TW (1) TW202232356A (pt)
WO (1) WO2022069498A1 (pt)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2023161707A (ja) * 2022-04-26 2023-11-08 横河電機株式会社 制御装置、制御方法、および、制御プログラム
US20230394888A1 (en) * 2022-06-01 2023-12-07 The Boeing Company Vehicle Health Management Using a Counterfactual Machine Learning Model
CN114974450B (zh) * 2022-06-28 2023-05-30 苏州沃时数字科技有限公司 基于机器学习与自动化试验装置的操作步骤的生成方法
EP4357997A1 (de) * 2022-10-19 2024-04-24 Siemens Aktiengesellschaft Verfahren zum ermitteln einer fertigungsreihenfolge von fertigungsaufträgen einer fertigungsanlage, fertigungsanlage-system, computerprogramm sowie elektronisch lesbarer datenträger
CN115859508B (zh) * 2022-11-23 2024-01-02 北京百度网讯科技有限公司 流场分析方法、元件模型生成方法、训练方法及装置
CN116011422B (zh) * 2023-03-28 2023-06-09 北京宽客进化科技有限公司 一种结构化表格数据生成方法和系统
TWI826335B (zh) * 2023-06-19 2023-12-11 中國鋼鐵股份有限公司 用於預測高爐爐料使用量的方法及其電腦程式產品
CN117311170B (zh) * 2023-11-29 2024-02-06 江苏美特林科特殊合金股份有限公司 自适应控制的镍铌合金熔炼设备多参数调整方法及系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11915105B2 (en) * 2019-02-05 2024-02-27 Imagars Llc Machine learning to accelerate alloy design

Also Published As

Publication number Publication date
JP2023543813A (ja) 2023-10-18
CN116261690A (zh) 2023-06-13
WO2022069498A1 (en) 2022-04-07
CL2023000841A1 (es) 2023-11-17
TW202232356A (zh) 2022-08-16
EP4222562A1 (en) 2023-08-09
US20230359155A1 (en) 2023-11-09
EP4222562B1 (en) 2024-04-03
KR20230079093A (ko) 2023-06-05
LU102103B1 (en) 2022-03-30

Similar Documents

Publication Publication Date Title
BR112023004793A2 (pt) Sistema de computador e método que provê instruções de operação para controle térmico de um alto-forno
Zevin et al. Priming and attentional control of lexical and sublexical pathways during naming.
BR112023022357A2 (pt) Sistemas e métodos para cálculo e rastreamento automáticos de intensidade de carbono
BR112022009400A2 (pt) Método para treinar um modelo para tradução de imagem para imagem, dispositivo de computação, método para definir um modelo de tempo de execução treinado e produto de programa de computador
BR112022017663A2 (pt) Modelo de risco híbrido para otimização de manutenção e sistema para executar tal método
BR112023002471A2 (pt) Método implementado por computador, programa de computador e sistema de controle automatizado
Wang et al. Intelligent fault diagnosis for planetary gearbox using transferable deep q network under variable conditions with small training data
BR112018015119A2 (pt) sistema e método de controle e produto de programa de computador
Kumar Espousal of Industry 4.0 in Indian manufacturing organizations: analysis of enablers
GB2579329A (en) Cache management
Xi et al. Multi-agent deep reinforcement learning strategy for distributed energy
Pyle et al. A reservoir computing model of reward-modulated motor learning and automaticity
GB2615046A (en) Automated health-check risk assessment of computing assets
WO2020059741A1 (ja) 計画装置、方法、およびプログラム
Quan et al. A case study of an adaptive design for a clinical trial with 2 doses and 2 endpoints in a rare disease area
Lanovaz et al. Using the three-component multiple-schedule to examine the effects of treatments on stereotypy
Zhao Dynamic analysis and chaos control of bertrand triopoly based on differentiated products and heterogeneous expectations
Younes et al. Activity classification at a higher level: what to do after the classifier does its best?
Xu et al. An improved generalized predictive control algorithm based on the difference equation CARIMA model for the SISO system with known strong interference
CN108549215B (zh) 一种无刷直流电机模糊化自适应pid控制优化方法
Odili et al. African buffalo optimization algorithm for tuning parameters of a PID controller in automatic voltage regulators
Yang et al. Advance of research on technology acceptance
Yates Investigating the importance of the least supported phoneme on visual word naming
Chen et al. Stable and effective trainable greedy decoding for sequence to sequence learning
Cai et al. On visualization analysis of stock data