JP2002167612A - Method for optimally controlling temperature and components in iron-making and steelmaking works - Google Patents
Method for optimally controlling temperature and components in iron-making and steelmaking worksInfo
- Publication number
- JP2002167612A JP2002167612A JP2000364185A JP2000364185A JP2002167612A JP 2002167612 A JP2002167612 A JP 2002167612A JP 2000364185 A JP2000364185 A JP 2000364185A JP 2000364185 A JP2000364185 A JP 2000364185A JP 2002167612 A JP2002167612 A JP 2002167612A
- Authority
- JP
- Japan
- Prior art keywords
- temperature
- components
- control
- analysis
- model
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 27
- 238000009628 steelmaking Methods 0.000 title claims description 16
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 21
- 229910052742 iron Inorganic materials 0.000 claims description 11
- 238000009749 continuous casting Methods 0.000 claims description 8
- 239000002184 metal Substances 0.000 description 20
- 229910052751 metal Inorganic materials 0.000 description 20
- 238000007664 blowing Methods 0.000 description 17
- 229910000831 Steel Inorganic materials 0.000 description 13
- 239000010959 steel Substances 0.000 description 13
- 238000004886 process control Methods 0.000 description 8
- 238000006477 desulfuration reaction Methods 0.000 description 7
- 230000023556 desulfurization Effects 0.000 description 7
- 230000004907 flux Effects 0.000 description 5
- 238000009529 body temperature measurement Methods 0.000 description 4
- 238000007872 degassing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 229910001021 Ferroalloy Inorganic materials 0.000 description 3
- 238000005266 casting Methods 0.000 description 3
- 238000002347 injection Methods 0.000 description 3
- 239000007924 injection Substances 0.000 description 3
- 238000005275 alloying Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 101100321669 Fagopyrum esculentum FA02 gene Proteins 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910052785 arsenic Inorganic materials 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 238000005261 decarburization Methods 0.000 description 1
- 230000005294 ferromagnetic effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 150000002505 iron Chemical class 0.000 description 1
- 229910052745 lead Inorganic materials 0.000 description 1
- 229910052748 manganese Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052750 molybdenum Inorganic materials 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 229910052718 tin Inorganic materials 0.000 description 1
- 229910052719 titanium Inorganic materials 0.000 description 1
- 229910052720 vanadium Inorganic materials 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Carbon Steel Or Casting Steel Manufacturing (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Treatment Of Steel In Its Molten State (AREA)
- Refinement Of Pig-Iron, Manufacture Of Cast Iron, And Steel Manufacture Other Than In Revolving Furnaces (AREA)
Abstract
Description
【０００１】[0001]
【発明の属する技術分野】本発明は、製銑・製鋼工場に
おける温度・成分の最適制御方法に係り、特に、製鉄工
程における溶銑及び溶鋼の温度や成分を制御する際に用
いるのに好適な、実績値が得られない場合でも、常に効
果的なモデル学習と温度や成分の制御を行うことが可能
な、製銑・製鋼工場における温度・成分の最適制御方法
に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for optimally controlling the temperature and components in a steelmaking and steelmaking plant, and more particularly to a method suitable for controlling the temperature and components of hot metal and molten steel in an iron making process. The present invention relates to an optimal control method of temperature and components in a steelmaking and steelmaking factory that can always perform effective model learning and control of temperature and components even when actual values cannot be obtained.
【０００２】[0002]
【従来の技術】一般に、製鉄所における溶銑及び溶鋼の
処理手順は図１のようになっており、各プロセスにおい
て、その温度と成分の制御が最重要課題となっている。2. Description of the Related Art Generally, a procedure for treating hot metal and molten steel in an ironworks is shown in FIG. 1. In each process, control of the temperature and components is the most important issue.
【０００３】即ち、図１において、高炉２０に挿入され
た焼結鉱は、コークスと共に高炉内で還元され、溶銑１
２となって鋳床からトピードカー２２に払い出される。
この際、脱珪剤吹込による鋳床脱珪が行われる。溶銑１
２は、トピードカー２２で保温されながら、次工程であ
るトピードカー２２内での溶銑予備処理（図１の左側）
又は脱硫設備２４（図１の右側）にて、フラックス吹込
による脱硫や脱燐が行われ、製鋼段階で要求される成分
に調整される。次いで、転炉２６において、副原料投入
と酸素吹込による脱炭吹錬が行われ、温度と成分が、所
定の目標となるように制御される。吹錬後の溶鋼１４
は、合金鉄を投入されながら、溶鋼鍋２８に移される。
溶鋼１４は、更に、溶鋼鍋２８でのＦＩ（フラックスイ
ンジェクション）（図１の左側）やＲＨ脱ガス設備３０
（図１の右側）にて、最終的な微量成分調整や脱ガスが
行われ、その後、連鋳設備３２のタンディッシュ３４を
経てモールド３６に注入され、スラブ１６となる。That is, in FIG. 1, the sintered ore inserted into the blast furnace 20 is reduced in the blast furnace together with coke,
The number 2 is paid out from the cast floor to the torpedo car 22.
At this time, the casting bed is desiliconized by blowing a desiliconizing agent. Hot metal 1
2 is a hot metal pretreatment in the topid car 22 which is the next step while keeping the temperature in the topid car 22 (left side in FIG. 1).
Alternatively, desulfurization or dephosphorization by blowing a flux is performed in a desulfurization facility 24 (on the right side in FIG. 1), and the components are adjusted to the components required in the steelmaking stage. Next, in the converter 26, decarburization blowing is performed by feeding the auxiliary raw material and blowing oxygen, and the temperature and the components are controlled so as to reach predetermined targets. Molten steel 14 after blowing
Is transferred to the molten steel pot 28 while the ferromagnetic iron is being charged.
The molten steel 14 is further subjected to FI (flux injection) (left side in FIG. 1) in a molten steel pot 28 and an RH degassing facility 30.
At (right side in FIG. 1), final adjustment of trace components and degassing are performed, and thereafter, the slab 16 is injected into a mold 36 via a tundish 34 of a continuous casting facility 32.
【０００４】以上に示した一連の製鉄工程において、製
品の制御及び管理上、温度と成分の測定が重要となる
が、通常、図１に示すｔ1〜ｔ9のタイミングで、測温又
はサンプリングにより分析が行われ、自工程でのフィー
ドバック制御や、次工程へのフィードフォード制御に利
用されている。又、各プロセスは、図２に示すように、
各々計算機（プロセスコンピュータ：プロコンと称す
る）、例えば高炉制御用の高炉プロコン４０、溶銑予備
処理用の溶銑プロコン４２、転炉制御用の転炉プロコン
４４、連鋳制御用の連鋳プロコン４６、分析用の分析プ
ロコン４８で制御され、各工程での測温結果や、前記分
析プロコン４８から、例えばネットワーク５０経由で各
プロコンに送信される分析結果に基づいて、各プロコン
毎に制御やモデルの学習が行われていた。[0004] In the series of iron making processes described above, measurement of temperature and components is important for control and management of products. Usually, analysis is performed by temperature measurement or sampling at timings t1 to t9 shown in FIG. Is used for feedback control in its own process and feedford control for the next process. Each process is, as shown in FIG.
Each computer (process computer: referred to as a process control), for example, a blast furnace process control 40 for blast furnace control, a hot process control process 42 for hot metal pretreatment, a converter process control 44 for converter control, a continuous process control process 46 for continuous casting control, analysis Control and learning of a model for each process control based on a temperature measurement result in each process and an analysis result transmitted from the analysis process control 48 to each process control via a network 50, for example. Had been done.
【０００５】[0005]
【発明が解決しようとする課題】しかしながら、このよ
うな従来の方法では、分析に時間がかかったり、分析コ
スト削減のため分析を省略されたりして、制御のための
充分な情報が得らないことがあった。又、各プロセスを
制御している計算機もプロセス毎に別であり、相互の情
報交換も、実績値のやりとりがほとんどであったため、
各計算機内でしかモデルを活用できず、充分な制御性能
が得られないという問題があった。However, in such a conventional method, it takes a long time to perform the analysis, or the analysis is omitted in order to reduce the analysis cost, so that sufficient information for control cannot be obtained. There was something. Also, the computers that control each process are different for each process, and the exchange of information was mostly the exchange of actual values.
There is a problem that the model can be used only in each computer, and sufficient control performance cannot be obtained.
【０００６】なお、特開平８−１２０３２０には、二次
精錬におけるＡＩ投入量設定に際して、ＡＩの添加工程
毎に前工程のＡＩの添加歩留り実績を反映させ、各工程
の処理時間、滞留時間を予測したＡＩ添加量を求め、該
添加量に基づく添加を行うことが記載されているが、過
去の実績値のみに基づく制御であるだけでなく、二次精
錬におけるＡＩ投入量設定にしか使われておらず、充分
な効果を発揮することはできなかった。Japanese Patent Application Laid-Open No. 8-120320 discloses that when setting the amount of AI to be added in the secondary refining, the processing time and the residence time of each step are reflected by reflecting the actual result of the AI addition yield of the preceding step for each of the AI adding steps. Although it is described that the predicted AI addition amount is obtained and the addition based on the addition amount is performed, the control is based not only on the past actual value but also on the AI input amount setting in the secondary refining. As a result, a sufficient effect could not be exhibited.
【０００７】本発明は前記従来の問題点を解消するべく
なされたもので、分析遅れやコスト削減のために実績値
が得られない場合でも、常に効果的なモデル学習と温度
や成分の制御を行うことを課題とする。The present invention has been made in order to solve the above-mentioned conventional problems. Even when an actual value cannot be obtained due to analysis delay or cost reduction, effective model learning and temperature and component control are always performed. The task is to do it.
【０００８】[0008]
【課題を解決するための手段】本発明は、製銑・製鋼工
場における温度や成分を、プロセス毎に設けられた計算
機を用いて制御するに際し、各計算機間で、温度や分析
値の実績値だけでなく、各計算機が各自の持つモデルを
用いて計算した温度や分析値の推定値を共有し、実績値
が得られないときは、他の計算機が計算した推定値を利
用して、制御やモデル学習をすることにより、高炉から
連鋳までの温度や成分を最適に制御するようにして、前
記課題を解決したものである。SUMMARY OF THE INVENTION According to the present invention, when controlling the temperature and components in a steelmaking and steelmaking factory using computers provided for each process, the actual values of the temperature and analysis values are calculated between the computers. In addition, each computer shares the estimated value of the temperature and analysis value calculated using its own model, and when the actual value is not obtained, the control using the estimated value calculated by the other computer is used. The above-mentioned problem has been solved by performing optimal control of the temperature and components from the blast furnace to the continuous casting by carrying out model learning.
【０００９】[0009]
【発明の実施の形態】以下、図面を参照して、本発明の
実施形態を詳細に説明する。Embodiments of the present invention will be described below in detail with reference to the drawings.
【００１０】本実施形態においては、図１に示したｔ1
〜ｔ9までの測温・成分サンプリングタイミングにおけ
る各温度や分析値を表すモデルを、次式のように用意す
る。ここで、Ｘは、温度と分析値で構成されるベクトル Ｘ＝（Ｔ，Ｃ，Ｎ，Ｓｉ，Ｍｎ，Ｐ，Ｓ，Ｔｉ，Ｃｒ，
Ｃｕ，Ｎｉ，Ｖ，Ｍｏ，Ｓｎ，Ａｓ，Ｐｂ，Ａｌ，Ｚ
ｎ，Ｂ） とする。又、Ｘの添字１〜９は、前記タイミングｔ1〜
ｔ9に、それぞれ対応する。In this embodiment, t1 shown in FIG.
A model representing each temperature and analysis value at the temperature measurement / component sampling timing from t9 to t9 is prepared as in the following equation. Here, X is a vector composed of temperature and analysis value X = (T, C, N, Si, Mn, P, S, Ti, Cr,
Cu, Ni, V, Mo, Sn, As, Pb, Al, Z
n, B). The subscripts 1 to 9 of X correspond to the timings t1 to t1.
t9 respectively.
【００１１】 Ｘ2＝ｆ（Ｘ1，高炉操業条件）…（１） Ｘ2´＝ｆ（Ｘ2，鋳床脱珪操業条件）…（２） Ｘ3＝ｆ（Ｘ2´，トピード操業条件）…（３） Ｘ4＝ｆ（Ｘ2´，トピード操業条件）…（４） Ｘ3´＝ｆ（Ｘ3，溶銑予備処理操業条件）…（５） Ｘ4´＝ｆ（Ｘ4，溶銑脱硫操業条件）…（６） Ｘ5＝ｆ（Ｘ3´又はＸ4´，トピード操業条件または溶銑鍋操業条件）…（７） Ｘ5″＝ｆ（Ｘ5，吹止までの吹錬操業条件）…（８） Ｘ5″＝ｆ（Ｘ5´，サブランス投入から吹止までの吹錬操業条件）…（９） Ｘ6＝ｆ（Ｘ5″，合金鉄投入操業条件）…（１０） Ｘ7＝ｆ（Ｘ6，溶鋼鍋操業条件）…（１１） Ｘ8＝ｆ（Ｘ6，溶鋼鍋操業条件）…（１２） Ｘ7´＝ｆ（Ｘ7，ＦＩ操業条件）…（１３） Ｘ8´＝ｆ（Ｘ8，ＲＨ脱ガス操業条件）…（１４） Ｘ9＝ｆ（Ｘ7´又はＸ8´，溶鋼鍋操業条件）…（１５）X2 = f (X1, blast furnace operating conditions) (1) X2 ′ = f (X2, casting bed desiliconization operating conditions) (2) X3 = f (X2 ′, topedo operating conditions) (3) X4 = f (X2 ', operating conditions of torpedo) (4) X3' = f (X3, operating conditions of hot metal pretreatment) (5) X4 '= f (X4, operating conditions of hot metal desulfurization) (6) X5 = f (X3 'or X4', Topedo operating condition or hot metal ladle operating condition) ... (7) X5 "= f (X5, blowing operation condition up to blow stop) ... (8) X5" = f (X5 ', Sublance (9) X6 = f (X5 ″, alloy iron input operating condition) (10) X7 = f (X6, operating condition of molten steel ladle) (11) X8 = f (X6, operating conditions of molten steel ladle) (12) X7 '= f (X7, FI operating conditions) ... (13) X8' = f (X8, RH degassing operating conditions) ... (14) X9 = f (X7 Or X8', ladle operating conditions) ... (15)
【００１２】通常の制御においては、例えば、 Ｘ5″＝ｆ（Ｘ5，吹止までの吹錬操業条件）…（８） であれば、Ｘ5の実績とＸ5″の目標を用いて、（８）式
の逆関数を求め、吹止までの吹錬操業条件を算出する
が、Ｘ5の実績値が得られない場合は、制御が不可能と
なってしまう。そこで、本実施形態では、実績値が得ら
れているモデルまで遡って、そこからモデルを用いてＸ
5の推定値を求めることで、制御を可能とする。ここ
で、Ｘ5の場合は、 Ｘ5＝ｆ（Ｘ3´又はＸ4´，トピード操業条件または溶銑鍋操業条件）…（７） を代入し、 Ｘ5″＝ｆ（ｆ（Ｘ3´又はＸ4´，トピード操業条件または溶銑鍋操業条件）， 吹止までの吹錬操業条件）…（１６） を用いて、吹止までの操業条件を求めることができる。In the normal control, for example, if X5 ″ = f (X5, blowing operation condition up to the shutoff) (8), then the result of X5 and the target of X5 ″ are used to obtain (8) The inverse function of the formula is obtained to calculate the blowing operation conditions up to the shutoff. However, if the actual value of X5 cannot be obtained, control becomes impossible. Therefore, in this embodiment, the model is traced back to the model for which the actual value is obtained,
Control is enabled by obtaining the estimated value of 5. Here, in the case of X5, X5 = f (X3 'or X4', torpedo operating condition or hot metal ladle operating condition) (7) is substituted, and X5 "= f (f (X3 'or X4', topedo operating condition) The operating conditions up to the blow stop can be obtained by using the conditions or the hot metal ladle operating conditions) and the blowing operation conditions up to the blow stop) (16).
【００１３】又、モデル学習の場合は、通常、例えば、 Ｘ5″＝ｆ（Ｘ5，吹止までの吹錬操業条件）…（８） であれば、Ｘ5の実績値とＸ5″の実績値を用いて、
（８）式のパラメータを逐次最小二乗法等の学習アルゴ
リズムを用いて学習するが、Ｘ5″のサンプリングを省
略した場合、学習が不可能となってしまう。そこで、Ｘ
6の実績値が分かっている場合には、 Ｘ5″＝ｆ（Ｘ5，吹止までの吹錬操業条件）…（８） Ｘ6＝ｆ（Ｘ5″，合金鉄投入操業条件）…（１０） の両式を用いて、 Ｘ6＝ｆ（ｆ（Ｘ5，吹止までの吹錬操業条件），合金鉄投入操業条件） …（１７） とし、この両式のパラメータを同時に学習することによ
り、精度のよい学習が可能となる。又、この場合、次式 Ｘ5″＝ｆ（Ｘ5´，サブランス投入から吹止までの吹錬操業条件）…（９） の信頼性が高ければ、この式よりＸ5″の推定値を求め、 ｆ（Ｘ5´，サブランス投入から吹止までの吹錬操業条件） ＝ｆ（Ｘ5，吹止までの吹錬操業条件）…（１８） として、右辺のみの学習を行うことも可能である。In the case of model learning, for example, if, for example, X5 ″ = f (X5, blowing operation conditions up to the shutoff) (8), the actual value of X5 and the actual value of X5 ″ are calculated. make use of,
The parameters of equation (8) are learned using a learning algorithm such as the sequential least squares method, but if sampling of X5 ″ is omitted, learning becomes impossible.
If the actual value of 6 is known, X5 ″ = f (X5, blowing operation conditions up to the shutoff) (8) X6 = f (X5 ″, ferroalloy input operating conditions) (10) By using both equations, X6 = f (f (X5, blowing operation conditions up to the shutoff), ferroalloy input operation conditions) ... (17) By learning the parameters of both equations simultaneously, the accuracy of Good learning becomes possible. In this case, if the reliability of the following equation X5 ″ = f (X5 ′, blowing operation conditions from sublance injection to blow stop) (9) is high, an estimated value of X5 ″ is obtained from this equation, and f (X5 ', blowing operation condition from sublance injection to blow stop) = f (X5, blowing operation condition from blow stop) (18) It is also possible to learn only the right side.
【００１４】このように、本発明によれば、対象とする
モデルの温度や成分の実績値が得られなくても、その前
後のモデルを共有することにより、精度の高い制御や学
習が可能となる。As described above, according to the present invention, even if the actual values of the temperature and the component of the target model are not obtained, it is possible to perform highly accurate control and learning by sharing the models before and after that. Become.
【００１５】[0015]
【実施例】表１のように、各計算機においてモデルを構
築し、実績値がある場合にはモデル式Ｘ1〜Ｘ9を使用し
て計算する。DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS As shown in Table 1, a model is constructed in each computer, and if there is an actual value, it is calculated using model formulas X1 to X9.
【００１６】[0016]
【表１】 [Table 1]
【００１７】実績値がない場合には、当該チャージのＸ
1〜Ｘ9の推定値をネットワーク経由で取得して計算す
る。If there is no actual value, the charge X
The estimated values of 1 to X9 are obtained via the network and calculated.
【００１８】又、表２は、表１中のモデルの各種条件の
具体的項目を示すもので、例えば高炉操業条件において
具体的項目に記載のある送風温度〜搬入パターンをもと
に溶銑温度、含有Ｓｉ量の推定は可能であり、鋳床脱珪
操業条件である脱珪剤投入量の項目から脱珪量の推定が
可能であり、次工程のトピード（又は溶銑鍋）に入る溶
銑のＳｉ量の推定ができる。Table 2 shows specific items of various conditions of the model in Table 1. For example, under blast furnace operating conditions, hot metal temperature, hot metal temperature, The amount of Si contained can be estimated, and the amount of desiliconization can be estimated from the item of the desiliconizing agent input, which is the casting bed desiliconization operating condition, and the Si content of the hot metal entering the topeed (or hot metal pot) in the next process The quantity can be estimated.
【００１９】[0019]
【表２】 [Table 2]
【００２０】又、トピード操業条件の項目の配車情報を
用いることにより温度降下量が推定でき、同様にして、
溶銑予備処理操業条件の項目のフラックス種類、フラッ
クス量、処理時間の各情報に基づけば、溶銑予備処理に
おける脱Ｓｉ、脱Ｐ、脱Ｓ量を推定することができ、更
に、この後に溶銑脱硫操業条件が加わっている場合、フ
ラックス種類及び量、処理時間から、前記脱Ｓ量に加え
て更に脱Ｓを加えられた到達Ｓ量の推定も可能である。Further, the temperature drop can be estimated by using the vehicle allocation information of the item of the toped operation condition.
Based on the flux type, flux amount, and processing time information of the hot metal pre-treatment operation conditions, it is possible to estimate the amount of de-Si, de-P, and de-S in the hot-metal pre-treatment, and then to perform hot metal desulfurization When the condition is added, it is possible to estimate the arrival S amount to which the desulfurization is further added in addition to the desulfurization amount from the type and amount of the flux and the processing time.
【００２１】同じく、トピード操業条件又は溶銑鍋操業
条件から、待機時間情報に基づいた温度降下量推定が可
能となる。Similarly, it is possible to estimate the temperature drop amount based on the standby time information from the operation conditions of the topped or hot metal ladle.
【００２２】同様に吹錬操業条件、合金鉄投入操業条件
の各項目の情報に基づけば溶鋼温度、各種成分が推定可
能となり、溶鋼鍋操業条件を含めれば温度降下量が、Ｆ
Ｉ操業条件が加わった場合、到達、脱Ｐ、脱Ｓの推定が
でき、ＲＨ脱ガス操業条件の項目が加われば、到達成分
値、温度が推定できる。これに加えて、連続鋳造等へ移
動するまでの溶鋼鍋条件が加われば、その時の温度降下
量が推定でき、連続鋳造に到達時の溶鋼温度を推定する
ことができることになる。従って、実績値がない場合
は、前記操業条件中、実績値の欠落部分を推定値で補う
ことは十分可能である。Similarly, the temperature of the molten steel and various components can be estimated based on the information on each item of the blowing operation conditions and the ferroalloy input operation conditions.
When the I operation condition is added, the arrival, de-P, and de-S can be estimated, and when the item of the RH degas operation condition is added, the attained component value and the temperature can be estimated. In addition to this, if the molten steel ladle conditions before moving to continuous casting or the like are added, the amount of temperature drop at that time can be estimated, and the molten steel temperature at the time of continuous casting can be estimated. Therefore, when there is no actual value, it is sufficiently possible to compensate for the missing part of the actual value with the estimated value in the operating conditions.
【００２３】図３は、転炉プロコンにおいて、分析コス
ト削減のため、Ｘ5″の分析を省略した際の、転炉熱バ
ランスモデルのばらつきと、本発明によるシステムを導
入し、Ｘ5´の代わりに、 Ｘ6＝ｆ（Ｘ5″，合金鉄投入操業条件）…（１０） を用いて、 Ｘ6＝ｆ（ｆ（Ｘ5，吹止までの吹錬操業条件），合金鉄投入操業条件） …（１７） のモデルパラメータを、逐次型最小二乗法で学習した場
合の、ばらつきを比較した図である。図から分かるよう
に、分析値が無くなって学習不可能となった従来のモデ
ルに比べ、本発明により分析値の代替値を用いて学習し
たモデルの誤差のばらつきの方が、格段に小さくなって
いることが分かる。FIG. 3 shows the variation of the converter heat balance model when the analysis of X5 ″ is omitted in the converter converter to reduce the analysis cost, and the system according to the present invention is introduced. X6 = f (X (5), operating condition for alloying iron)... (10), X6 = f (f (X5, operating condition for blowing iron up to the shutoff), operating condition for alloying iron) (17) FIG. 9 is a diagram comparing the variations when the model parameters of (1) and (2) are learned by the sequential least squares method. As can be seen from the figure, the variation of the error of the model learned using the alternative value of the analysis value according to the present invention is much smaller than that of the conventional model in which the analysis value is lost and learning becomes impossible. You can see that there is.
【００２４】又、その他の分析についても、３０％以
上、実績値を省略することが可能となった。In other analyzes, the actual value can be omitted by 30% or more.
【００２５】なお、本発明の適用対象は、図１に示す製
銑・製鋼工程に限定されず、一部を省略したり、他の設
備を追加した製銑・製鋼工程にも同様に適用できること
は明らかである。The object of the present invention is not limited to the iron making / steel making process shown in FIG. 1, but may be applied to the iron making / steel making process in which a part is omitted or other equipment is added. Is clear.
【００２６】[0026]
【発明の効果】本発明によれば、各計算機間で温度や分
析値の実績値だけでなく、各計算機が各自の持つモデル
を用いて計算した温度や分析の推定値を共有し、実績値
が得られないときは、他の計算機などが計算した推定値
を用いて、制御やモデル学習をするようにしたので、製
銑・製鋼工程において、より精度が高い温度・成分制御
が可能となる。又、分析コストの削減にも効果がある。According to the present invention, not only the actual value of the temperature and the analysis value but also the estimated value of the temperature and the analysis calculated by each computer using its own model are shared among the computers, and the actual value is obtained. When is not obtained, control and model learning are performed using estimated values calculated by other computers, etc., so that more accurate temperature and component control is possible in the iron making and steel making processes . It is also effective in reducing analysis costs.
【図１】製銑・製鋼工程における測温・成分サンプリン
グタイミングを説明する工程図FIG. 1 is a process diagram illustrating timing of temperature measurement and sampling of components in a steelmaking and steelmaking process
【図２】各プロセスにおける計算機制御の構成例を示す
ブロック図FIG. 2 is a block diagram illustrating a configuration example of computer control in each process.
【図３】転炉プロコンに適用した際の本発明の効果を示
す線図FIG. 3 is a diagram showing the effect of the present invention when applied to a converter converter.
１２…溶銑 １４…溶鋼 １６…スラブ ２０…高炉 ２２…トピードカー ２４…脱硫設備 ２６…転炉 ２８…溶鋼鍋 ３０…ＲＨ脱ガス設備 ３２…連鋳設備 ４０…高炉プロコン ４２…溶銑プロコン ４４…転炉プロコン ４６…連鋳プロコン ４８…分析プロコン ５０…ネットワーク DESCRIPTION OF SYMBOLS 12 ... Hot metal 14 ... Molten steel 16 ... Slab 20 ... Blast furnace 22 ... Topped car 24 ... Desulfurization equipment 26 ... Converter 28 ... Molten steel pot 30 ... RH degassing equipment 32 ... Continuous casting equipment 40 ... Blast furnace procon 42 ... Hot metal procon 44 ... Converter Process control 46: Continuous casting process 48: Analytical process 50: Network
───────────────────────────────────────────────────── フロントページの続き (51)Int.Cl.7 識別記号 ＦＩ テーマコート゛(参考） Ｇ０６Ｆ 17/60 １０６ Ｇ０６Ｆ 17/60 １０６ Ｆターム(参考） 4K002 AB02 AB04 AC10 AD02 AF01 AF04 AF05 4K013 FA01 FA02 FA11 FA12 4K014 AA01 AA02 AC03 AC14 AC16 AD01 AD17 AD23 AD25 AD27 5H004 GA34 GB03 HA01 HA04 HB01 HB04 KC01 KC27 KD62 LA15 MA38 ──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. 7 Identification symbol FI Theme coat ゛ (Reference) G06F 17/60 106 G06F 17/60 106 F term (Reference) 4K002 AB02 AB04 AC10 AD02 AF01 AF04 AF05 4K013 FA01 FA02 FA11 FA12 4K014 AA01 AA02 AC03 AC14 AC16 AD01 AD17 AD23 AD25 AD27 5H004 GA34 GB03 HA01 HA04 HB01 HB04 KC01 KC27 KD62 LA15 MA38
Claims (1)
ロセス毎に設けられた計算機を用いて制御するに際し、 各計算機間で、温度や分析値の実績値だけでなく、各計
算機が各自の持つモデルを用いて計算した温度や分析値
の推定値を共有し、 実績値が得られないときは、他の計算機が計算した推定
値を利用して、制御やモデル学習をすることにより、 高炉から連鋳までの温度や成分を最適に制御することを
特徴とする製銑・製鋼工場における温度・成分の最適制
御方法。When controlling the temperature and components in an iron and steelmaking factory using computers provided for each process, each computer is required to have not only actual values of temperature and analysis values but also each computer. When the estimated value of the temperature and analysis value calculated using the model of the model is shared, and the actual value cannot be obtained, by using the estimated value calculated by another computer, control and model learning are performed. An optimal control method of temperature and components in a steelmaking and steelmaking plant, characterized by optimally controlling the temperature and components from blast furnace to continuous casting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2000364185A JP2002167612A (en) | 2000-11-30 | 2000-11-30 | Method for optimally controlling temperature and components in iron-making and steelmaking works |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2000364185A JP2002167612A (en) | 2000-11-30 | 2000-11-30 | Method for optimally controlling temperature and components in iron-making and steelmaking works |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JP2002167612A true JP2002167612A (en) | 2002-06-11 |
Family
ID=18835172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2000364185A Pending JP2002167612A (en) | 2000-11-30 | 2000-11-30 | Method for optimally controlling temperature and components in iron-making and steelmaking works |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2002167612A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013112871A (en) * | 2011-11-30 | 2013-06-10 | Jfe Steel Corp | Method for setting end-point temperature of converter blowing |
| CN103293951A (en) * | 2013-06-14 | 2013-09-11 | 湘潭大学 | Group furnace group casting device and method automatically discharging steel materials |
| KR101424640B1 (en) | 2013-04-03 | 2014-08-01 | 주식회사 포스코 | Method for manufacturing cast metal pin iron |
| CN110850915A (en) * | 2018-08-21 | 2020-02-28 | 上海梅山钢铁股份有限公司 | Self-learning-based steelmaking molten steel process temperature control system and control method |
-
2000
- 2000-11-30 JP JP2000364185A patent/JP2002167612A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013112871A (en) * | 2011-11-30 | 2013-06-10 | Jfe Steel Corp | Method for setting end-point temperature of converter blowing |
| KR101424640B1 (en) | 2013-04-03 | 2014-08-01 | 주식회사 포스코 | Method for manufacturing cast metal pin iron |
| CN103293951A (en) * | 2013-06-14 | 2013-09-11 | 湘潭大学 | Group furnace group casting device and method automatically discharging steel materials |
| CN110850915A (en) * | 2018-08-21 | 2020-02-28 | 上海梅山钢铁股份有限公司 | Self-learning-based steelmaking molten steel process temperature control system and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560218B (en) | LF refining slagging lime addition amount prediction method and system and LF refining method | |
| CN110954670B (en) | Method and system for continuously predicting phosphorus content of converter molten pool | |
| JP2002167612A (en) | Method for optimally controlling temperature and components in iron-making and steelmaking works | |
| JP2751800B2 (en) | Liquid Steel Temperature Control Method in Steel Making Process | |
| EP3956481B1 (en) | Method for monitoring a steelmaking process and associated computer program | |
| JP4806964B2 (en) | Method for determining end temperature of vacuum degassing process | |
| CN106498113A (en) | A kind of converter smelting process of 82B steel | |
| US20080172277A1 (en) | Algorithmic framework for scheduling steelmaking production optimizing the flow of molten iron subject to inventory constraints | |
| CN110484676A (en) | The addition control method of silicon amount, the casting method of spheroidal graphite cast-iron, casting in spheroidal graphite cast-iron | |
| JPH09249903A (en) | Scheduling method in molten iron supply and demand control | |
| JPH06264129A (en) | Method for controlling end point of steelmaking in converter | |
| CN112280925B (en) | Titanium element control method for silicon steel steelmaking smelting | |
| JP4048010B2 (en) | Method for estimating phosphorus equilibrium in converters and hot metal pretreatment vessels. | |
| JP2002003909A (en) | Distribution system for molten iron and method for controlling distribution of molten iron | |
| RU2782109C1 (en) | Method for monitoring the steel production process | |
| JP6780207B2 (en) | Method of determining the number of molten steel pans used in the steelmaking process | |
| Palovaara et al. | Temperature Control of a Smelting Plant | |
| SU1196381A1 (en) | Method of controlling process section of hot metal transfer ladle-mixers-steel-making unit | |
| JPH08157923A (en) | Method for decision of charging quantity of main raw material for converter | |
| JPH05171244A (en) | Method for estimating lowest blending ratio of molten iron in converter | |
| CN118036793A (en) | Method for predicting production of tundish billets during continuous casting of multiple steel types in same tundish | |
| JP2023114592A (en) | Operational calculation device and operational calculation method | |
| SU1186645A1 (en) | Method of controlling production process at section of preparing cast iron for casting ingot moulds | |
| JPH10237527A (en) | Desiliconization control of hot metal | |
| JP3589181B2 (en) | Hot metal pretreatment method by adding flux in hot metal transport vessel |