JP7846331B2 - Operation calculation device and operation calculation method - Google Patents
Operation calculation device and operation calculation methodInfo
- Publication number
- JP7846331B2 JP7846331B2 JP2022016996A JP2022016996A JP7846331B2 JP 7846331 B2 JP7846331 B2 JP 7846331B2 JP 2022016996 A JP2022016996 A JP 2022016996A JP 2022016996 A JP2022016996 A JP 2022016996A JP 7846331 B2 JP7846331 B2 JP 7846331B2
- Authority
- JP
- Japan
- Prior art keywords
- concentration
- predetermined component
- converter
- iron source
- cold iron
- 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.)
- Active
Links
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
Landscapes
- Refinement Of Pig-Iron, Manufacture Of Cast Iron, And Steel Manufacture Other Than In Revolving Furnaces (AREA)
- Carbon Steel Or Casting Steel Manufacturing (AREA)
Description
本発明は、特に、複数工程の操業条件を一括して管理するために好適な操業演算装置および操業演算方法に関する。 This invention relates, in particular, to an operation calculation device and operation calculation method suitable for centrally managing the operating conditions of multiple processes.
従来、溶銑予備処理、転炉吹錬処理など複数の工程からなる製鋼工程においては、それぞれの工程において溶銑の成分やコストなどを最適化して操業指示が行われている。しかしながら、溶銑の成分やスクラップ銘柄などの変動により、ある一定確率で出鋼後に一部の成分が目標成分範囲の上下限値を外れてしまう場合があり、その場合には二次精錬で新たな工程を追加する（以下、工程追加）など操業コストが大きく増加してしまう。例えば、溶銑成分やスクラップ銘柄の変動により溶銑中のＳのインプット量が変動するため、単独工程ではＳ濃度を最適化することができず、計画外の二次精錬処理や目標成分範囲から外れる成分不適が発生してしまう。 Traditionally, in steelmaking processes consisting of multiple stages such as molten iron pretreatment and converter blowing, operational instructions are given for each stage by optimizing the composition and cost of the molten iron. However, due to fluctuations in the composition of the molten iron and the grade of scrap, there is a certain probability that some components may fall outside the upper and lower limits of the target composition range after tapping. In such cases, additional processes are added in secondary refining (hereinafter referred to as "additional processes"), significantly increasing operational costs. For example, because the amount of sulfur (S) input into the molten iron fluctuates due to fluctuations in the composition of the molten iron and the grade of scrap, it is not possible to optimize the S concentration in a single process, resulting in unplanned secondary refining or unsuitable components that fall outside the target composition range.
以上のように単独の工程で操業条件を最適化するのみでは、工程追加が発生する場合があるため、複数工程の操業条件を一括して最適化することが望ましい。そのためには、目標となる成分から外れる要因を複数の要因から特定し、適宜操業条件を修正して学習させる必要がある。特許文献１には、吹錬工程におけるパラメータを計算する方法として、吹錬工程内の溶鋼に含まれる成分量と溶鋼温度とを実測する第１時点と第２時点それぞれまでの第１期間および第２期間において必要な酸素量、昇熱材量、および冷却材量を算出する際に、機械学習された結果を用いて不明熱と不明酸素を予測し、前記第２期間において必要な酸素量、昇熱材量、および冷却材量は、前記第１時点における実測成分量および実測溶鋼温度などに加えて実測不明熱量と実測不明酸素量を用いて計算する技術が開示されている。
特許文献２には、溶鉄の精錬処理について一次反応式を元に成分予測を行う方法として、平衡状態の成分濃度と反応速度係数を推定し、成分濃度を都度推定する成分濃度演算装置について技術が開示されている。
As described above, optimizing operating conditions for a single process may result in the need for additional processes; therefore, it is desirable to optimize the operating conditions of multiple processes simultaneously. To achieve this, it is necessary to identify factors that cause deviations from the target composition from multiple factors and to modify the operating conditions as appropriate for learning. Patent Document 1 discloses a method for calculating parameters in a smelting process, in which the amount of oxygen, heat-generating material, and coolant required in the first and second periods, respectively, up to the first and second time points, when the amount of components contained in the molten steel and the molten steel temperature in the smelting process are measured, are predicted using machine learning results to predict unknown heat and unknown oxygen, and the amount of oxygen, heat-generating material, and coolant required in the second period is calculated using the measured amount of components and measured molten steel temperature at the first time point, as well as the measured amount of unknown heat and measured amount of unknown oxygen.
Patent Document 2 discloses a method for predicting the components of a molten iron refining process based on a first-order reaction equation. This method involves estimating the component concentrations and reaction rate coefficients at equilibrium, and then estimating the component concentrations each time.
前述したように、ある一定確率で出鋼後に一部の成分が製品規格に基づいた上限値を超えてしまう場合があり、その要因としては、転炉内に投入する溶銑や、溶銑鍋の残留スラグ、冷鉄源、副原料などの成分が予測値からずれていることが考えられる。特にスクラップなど冷鉄源については成分を予測することが難しく、特許文献１に記載の方法では、スクラップの成分については考慮されていないため、操業条件を十分に最適化することができない。特許文献２に記載の方法では、精錬反応が進行し辛い成分系については当てはまりが悪く適用範囲が限られている。そのため、精錬反応に対し有利不利にかかわらずマスバランスと過去の実績を元に成分変動を予測する技術が新たに必要となる。 As mentioned above, there is a certain probability that some components may exceed the upper limit based on product specifications after tapping. This is likely due to deviations in the components of the molten iron fed into the converter, residual slag in the molten iron ladle, cold iron source, and auxiliary raw materials from predicted values. In particular, predicting the components of cold iron sources such as scrap is difficult, and the method described in Patent Document 1 does not consider the components of scrap, thus preventing sufficient optimization of operating conditions. The method described in Patent Document 2 is not well-suited to component systems where the refining reaction is difficult, limiting its applicability. Therefore, a new technology is needed to predict component fluctuations based on mass balance and past performance, regardless of whether the refining reaction is favorable or unfavorable.
本発明は前述の問題点を鑑み、冷鉄源の成分をより正確に予測して最適な操業条件を導出する操業演算装置および操業演算方法を提供することを目的とする。 In view of the aforementioned problems, the present invention aims to provide an operational calculation device and method that more accurately predict the composition of a cold iron source and derive optimal operating conditions.
本発明に係る操業演算装置は、転炉吹錬工程の操業条件を管理して最適化する操業演算装置であって、溶銑予備処理後の溶銑中における所定の成分の濃度を取得する取得手段と、前記取得手段によって取得された前記所定の成分の濃度と、転炉吹錬工程において投入する冷鉄源中の前記所定の成分の濃度とを用いて前記転炉吹錬工程における前記所定の成分の物質収支を推定することにより、前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度を推定する転炉工程管理手段と、前記転炉工程管理手段によって推定された前記所定の成分の濃度の推定値と前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度の実績値との差分に基づき、前記冷鉄源中の前記所定の成分の濃度を補正し、前記冷鉄源の情報として前記転炉吹錬工程における冷鉄源投入量を管理する冷鉄源管理手段と、を有することを特徴とする。 The operational calculation device according to the present invention is an operational calculation device for managing and optimizing the operating conditions of a converter blowing process, and is characterized by comprising: an acquisition means for acquiring the concentration of a predetermined component in molten iron after molten iron pretreatment; a converter process management means for estimating the concentration of a predetermined component in molten steel after the converter blowing process by estimating the mass balance of the predetermined component in the converter blowing process using the concentration of the predetermined component acquired by the acquisition means and the concentration of the predetermined component in the cold iron source introduced in the converter blowing process ; and a cold iron source management means for correcting the concentration of the predetermined component in the cold iron source based on the difference between the estimated value of the concentration of the predetermined component estimated by the converter process management means and the actual value of the concentration of the predetermined component in molten steel after the converter blowing process, and managing the amount of cold iron source introduced in the converter blowing process as information on the cold iron source .
本発明に係る操業演算方法は、転炉吹錬工程の操業条件を管理して最適化する操業演算装置が実行する操業演算方法であって、溶銑予備処理後の溶銑中における所定の成分の濃度を取得する取得ステップと、前記取得ステップによって取得された前記所定の成分の濃度と、転炉吹錬工程において投入する冷鉄源中の前記所定の成分の濃度とを用いて前記転炉吹錬工程における前記所定の成分の物質収支を推定することにより、前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度を推定する転炉工程管理ステップと、前記転炉工程管理ステップによって推定された前記所定の成分の濃度の推定値と前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度の実績値との差分に基づき、前記冷鉄源中の前記所定の成分の濃度を補正し、前記冷鉄源の情報として前記転炉吹錬工程における冷鉄源投入量を管理する冷鉄源管理ステップと、を有することを特徴とする。 The operational calculation method according to the present invention is an operational calculation method executed by an operational calculation device that manages and optimizes the operating conditions of a converter blowing process, and is characterized by comprising : an acquisition step of acquiring the concentration of a predetermined component in molten iron after molten iron pretreatment; a converter process management step of estimating the concentration of a predetermined component in molten steel after the converter blowing process by estimating the mass balance of the predetermined component in the converter blowing process using the concentration of the predetermined component acquired in the acquisition step and the concentration of the predetermined component in the cold iron source to be introduced in the converter blowing process; and a cold iron source management step of correcting the concentration of the predetermined component in the cold iron source based on the difference between the estimated value of the concentration of the predetermined component estimated in the converter process management step and the actual value of the concentration of the predetermined component in molten steel after the converter blowing process, and managing the amount of cold iron source introduced in the converter blowing process as information on the cold iron source .
本発明によれば、冷鉄源の成分をより正確に予測して最適な操業条件を導出することができる。これにより、製鋼工程における複数の工程を一括して操業条件を管理して最適な操業条件を導出することができる。 According to this invention, the composition of the cold iron source can be predicted more accurately, and optimal operating conditions can be derived. This allows for the integrated management of operating conditions across multiple processes in the steelmaking process, thereby deriving optimal operating conditions.
以下、本発明の実施形態について、図面を参照しながら説明する。本実施形態では、溶銑予備処理工程および転炉工程においてインプット量が変動しやすいＳを例に説明するが、成分としてはＳに限らず、例えばＣｕなど転炉内での除去が難しい成分や、Ｍｎなどの転炉内で一定の除去可能なものについても同様に適用可能である。 The embodiments of the present invention will be described below with reference to the drawings. In this embodiment, S, whose input amount tends to fluctuate in the molten iron pretreatment process and the converter process, will be used as an example. However, the invention is not limited to S; it can also be applied to other components that are difficult to remove in the converter, such as Cu, or to components that can be consistently removed in the converter, such as Mn.
図１は、本実施形態において脱硫処理を行う工程を説明するための図である。
まず、溶銑予備処理工程で脱硫処理が行われ、製品規格に基づいて所定の濃度以下まで溶銑からＳが除去される。本実施形態では、取鍋内の溶銑に耐火物製のインペラー（回転翼）を浸漬して回転させ、溶銑と脱硫剤を機械的に混合して脱硫反応を促進する方式（ＫＲ方式）を用いるものとする。
Figure 1 is a diagram illustrating the process of performing desulfurization in this embodiment.
First, desulfurization is performed in the molten iron pretreatment process, and sulfur is removed from the molten iron to a predetermined concentration or lower according to the product specifications. In this embodiment, a method (KR method) is used in which a refractory impeller (rotating blade) is immersed in the molten iron in the ladle and rotated to mechanically mix the molten iron and the desulfurizing agent and promote the desulfurization reaction.
この工程では脱硫剤の投入量基準が粗く、処理後の溶銑中Ｓ濃度の予測値の的中率が低くなりやすい。そこで本実施形態では、後述するＫＲモデル等を用いて処理後の溶銑中Ｓ濃度を推定する。次工程の転炉工程の操業までに溶銑中Ｓ濃度の分析値（実績値）を導出できる場合には、その実績値を転炉工程の操業に利用するが、実績値を導出できない場合は、後述するＫＲモデル等を用いて処理後の溶銑中Ｓ濃度を推定し、その推定値を用いて転炉工程の操業に利用する。 In this process, the criteria for the amount of desulfurizing agent to be added are coarse, and the accuracy of the predicted sulfur concentration in the molten iron after treatment tends to be low. Therefore, in this embodiment, the sulfur concentration in the molten iron after treatment is estimated using the KR model, etc., described later. If the analytical value (actual value) of the sulfur concentration in the molten iron can be derived before the operation of the next process, the converter process, that actual value is used for the operation of the converter process. However, if the actual value cannot be derived, the sulfur concentration in the molten iron after treatment is estimated using the KR model, etc., described later, and that estimated value is used for the operation of the converter process.
また、転炉工程では、溶銑予備処理工程で生成されたスラグの一部が残留スラグとして持ち越される。本実施形態では、スラグ残留量判定用カメラの撮影や、目視、その他の方法などにより残留スラグの定量評価を行う。また、残留スラグ中の成分値（Ｓ量）については転炉工程におけるマスバランスの推定に用いられるが、過去のスラグ成分の実績の平均値を用いてもよく、溶銑予備処理の前後の溶銑中Ｓ濃度の差分から推定した値を用いてもよい。 Furthermore, in the converter process, a portion of the slag generated in the molten iron pretreatment process is carried over as residual slag. In this embodiment, the residual slag is quantitatively evaluated by methods such as photography with a slag residual amount determination camera, visual inspection, or other methods. The component values (S content) in the residual slag are used to estimate the mass balance in the converter process. This may involve using the average value of past slag component data, or a value estimated from the difference in S concentration in the molten iron before and after the molten iron pretreatment.
続いて、転炉工程においては、スクラップシュートから転炉に冷鉄源を装入し、その後、溶銑予備処理後の溶銑を転炉に装入し、脱硫剤などの副材を添加して脱硫処理を行う。本実施形態では、後述する炉内Ｓ管理モデルに基づき、転炉内のＳマスバランスを推定するとともに、吹止後の溶鋼中Ｓ濃度を推定する。また、Ｓマスバランスを推定する際に、冷鉄源からのＳ量は推定することが難しいことから、Ｓ濃度の推定値と実績値との差分に応じて銘柄毎に冷鉄源のＳ量の補正を行う。この補正の詳細は後述するが、転炉内での吹止後の溶銑中Ｓ濃度を推定するとともに、溶銑中のＳ濃度を測定し、推定値と実績値との差分を求める。そして、銘柄別に差分値を求め、その値が予め定められた標準誤差以下である場合に、その銘柄に含まれるＳ量を補正する。また、冷鉄源には、鋼材製造過程で発生する屑鉄（スクラップ）や、溶銑を鋳型に流し込んで固めた型銑、その他荒鉄、雑銑と呼ばれる溶銑が様々な形状で固まった地金、転炉粗粒ダストなどの製鉄副産物を含む。 Next, in the converter process, a cold iron source is charged into the converter from a scrap chute, and then molten iron that has undergone pre-treatment is charged into the converter, and desulfurization is performed by adding auxiliary materials such as desulfurizing agents. In this embodiment, the sulfur mass balance in the converter is estimated based on the in-furnace sulfur management model described later, and the sulfur concentration in the molten steel after blowdown is also estimated. Furthermore, since it is difficult to estimate the amount of sulfur from the cold iron source when estimating the sulfur mass balance, the amount of sulfur in the cold iron source is corrected for each brand according to the difference between the estimated value and the actual value of the sulfur concentration. The details of this correction will be described later, but the sulfur concentration in the molten iron after blowdown in the converter is estimated, and the sulfur concentration in the molten iron is measured, and the difference between the estimated value and the actual value is calculated. Then, the difference value is calculated for each brand, and if that value is less than or equal to a predetermined standard error, the amount of sulfur contained in that brand is corrected. Furthermore, cold iron sources include scrap iron generated during the steel manufacturing process, molded iron (molten iron poured into molds and solidified), other iron by-products such as crude iron, miscellaneous iron (molten iron solidified in various shapes), and converter dust.
図４は、本実施形態に係る操業演算装置１００のハードウェア構成例を示すブロック図である。
操業演算装置１００は、ＣＰＵ４０１と、ＲＯＭ４０２と、ＲＡＭ４０３と、記憶装置４０４と、入出力Ｉ／Ｆ４０５と、通信Ｉ／Ｆ４０６とを有している。ＣＰＵ４０１は、ＲＯＭ４０２に記憶された制御プログラムを読み出して各種処理を実行する。ＲＡＭ４０３は、ＣＰＵ４０１の主メモリ、ワークエリア等の一時記憶領域として用いられる。記憶装置４０４は、各種データや各種プログラム等を記憶する。表示装置４０５は、各種情報を表示する。入出力Ｉ／Ｆ４０６は、キーボードやマウスからユーザによる各種操作を受け付けたり、不図示の表示装置に演算結果を表示させたりするためのインターフェースである。通信Ｉ／Ｆ４０７は、ネットワークを介して外部装置から情報を取得するためのインターフェースである。
Figure 4 is a block diagram showing an example of the hardware configuration of the operation calculation device 100 according to this embodiment.
The operation calculation unit 100 includes a CPU 401, a ROM 402, a RAM 403, a storage device 404, an input/output interface 405, and a communication interface 406. The CPU 401 reads control programs stored in the ROM 402 and executes various processes. The RAM 403 is used as the main memory and temporary storage area for the CPU 401, such as a work area. The storage device 404 stores various data and programs. The display device 405 displays various information. The input/output interface 406 is an interface for receiving various operations from the user via a keyboard or mouse and for displaying calculation results on a display device (not shown). The communication interface 407 is an interface for acquiring information from external devices via a network.
図２は、本実施形態に係る操業演算装置１００の溶銑予備処理後の溶銑中Ｓ濃度を推定するための機能構成例を示すブロック図である。
実績データ記憶部２００には、過去の操業実績に係る実績データが保持されており、操業演算装置１００は溶銑予備処理での操業条件を管理するとともに、溶銑予備処理後のＳ濃度を推定する。操業条件ではＫＲモデルを用いて最適化した条件を用い、溶銑予備処理後のＳ濃度を推定する。
Figure 2 is a block diagram showing an example of the functional configuration of the operation calculation device 100 according to this embodiment for estimating the S concentration in molten iron after molten iron pretreatment.
The performance data storage unit 200 stores performance data related to past operational performance, and the operation calculation device 100 manages the operating conditions for molten iron pretreatment and estimates the S concentration after molten iron pretreatment. For the operating conditions, conditions optimized using the KR model are used to estimate the S concentration after molten iron pretreatment.
ここで、ＫＲモデルについて説明する。ＫＲモデルは機械学習モデルであり、ＫＲモデルでは、一次反応式に従い２変数を予測するグレイボックスモデルを導入し、モデル構築部２２０は、実績データ取得部２１０で実績データ記憶部２００から取得される１３種類のパラメータ（溶銑見込温度、溶銑量、処理前Ｃ濃度、処理前Ｓｉ濃度、処理前Ｍｎ濃度、処理前Ｐ濃度、処理前Ｓ濃度、湯面高さ、設定インペラー浸漬深さ、インペラー使用回数、ＣａＯ使用量、二次精錬滓使用量およびＡｌ灰使用量）を使用して最適化計算を行う。そして、最適化した操業条件に従って、処理後Ｓ濃度を推定する。Ｓ濃度の推定については、特許文献２に開示されたモデルを採用する。つまり、以下の（１）式を用いて処理後Ｓ濃度［％Ｓ］（質量％）を算出する。 Here, we will explain the KR model. The KR model is a machine learning model that employs a gray-box model to predict two variables according to a first-order reaction equation. The model construction unit 220 performs optimization calculations using 13 types of parameters (molten iron forecast temperature, molten iron quantity, pre-treatment C concentration, pre-treatment Si concentration, pre-treatment Mn concentration, pre-treatment P concentration, pre-treatment S concentration, molten metal surface height, set impeller immersion depth, impeller usage count, CaO usage, secondary refining slag usage, and Al ash usage) obtained from the performance data storage unit 200 by the performance data acquisition unit 210. Then, the post-treatment S concentration is estimated according to the optimized operating conditions. For the estimation of the S concentration, the model disclosed in Patent Document 2 is adopted. That is, the post-treatment S concentration [%S] (mass%) is calculated using the following equation (1).
（１）式中において、［％Ｓ］0は処理前Ｓ濃度［質量％］、Ｖは溶銑量［ｔｏｎ］、ｔは設定攪拌時間［分］を表す。また、ｆ（ｘ1）は平衡論的寄与に関する関数であり、ｇ（ｘ2）は速度論的寄与に該当する関数である。 In equation (1), [%S] 0 represents the S concentration before treatment [mass%], V represents the amount of molten iron [ton], and t represents the set stirring time [minutes]. Also, f( x1 ) is a function relating to the equilibrium theory contribution, and g( x2 ) is a function relating to the kinetic contribution.
また、ＫＲモデルは脱硫反応を一次反応に従う理想条件として置いており、推定した処理後Ｓ濃度に対し実績の処理後Ｓ濃度にばらつきが生じる。炉内Ｓ管理を安定させるためには、ばらつきを加味して実績の処理後Ｓ濃度が狙いＳ濃度以下になるよう制御する必要がある。そこで本実施形態では、モデル構築部２２０は、推定した処理後Ｓ濃度が実績の処理後Ｓ濃度をある確率以上で同じもしくは上回る領域の境界を分位点と定義し、分位点以下の操業実績から操業条件の最適計算を行う分位点計算を導入する。ここで、ある確率とは、５０％以上の範囲であらかじめ設定された値であり、望ましくは、７０％、８０％、９０％、９５％、９７％、９９％と所定の間隔を保ち高い値まで設定することで、処理後のＳ濃度の目標到達率を高めることができる値である。 Furthermore, the KR model assumes the desulfurization reaction follows ideal conditions following a first-order reaction, resulting in variability between the estimated post-treatment sulfur concentration and the actual post-treatment sulfur concentration. To stabilize in-furnace sulfur control, it is necessary to control the system so that the actual post-treatment sulfur concentration remains below the target concentration, taking this variability into account. Therefore, in this embodiment, the model construction unit 220 defines the boundary of the region where the estimated post-treatment sulfur concentration is equal to or exceeds the actual post-treatment sulfur concentration with a certain probability as a quantile, and introduces quantile calculation to perform optimal calculation of operating conditions based on operating results below the quantile. Here, the certain probability is a value predetermined within a range of 50% or more, and preferably, by setting it to a high value at predetermined intervals such as 70%, 80%, 90%, 95%, 97%, and 99%, the rate of achieving the target post-treatment sulfur concentration can be increased.
さらに本実施形態では、最適化計算において過去の操業実績から大きく乖離した操業条件を算出することを避けるために、制約条件設定部２３０は、過去の実績データから推定した操業実績の確率密度関数をもとに計算される尤度関数を評価関数に追加し、最適解探索部２４０は、モデル構築部２２０により構築されたモデルを用い、尤度関数により操業条件を信頼できる範囲から探索するようにする。そして、最適解出力部２５０は、最適解探索部２４０により探索された最適解（処理後Ｓ濃度）を出力する。 Furthermore, in this embodiment, to avoid calculating operating conditions that deviate significantly from past operating results in the optimization calculation, the constraint setting unit 230 adds a likelihood function calculated based on the probability density function of operating results estimated from past performance data to the evaluation function. The optimal solution search unit 240 uses the model constructed by the model construction unit 220 to search for operating conditions within a reliable range using the likelihood function. The optimal solution output unit 250 then outputs the optimal solution (processed S concentration) found by the optimal solution search unit 240.
以上のように本実施形態に係るＫＲモデルでは、上述したグレイボックスモデルに加え、分位点計算および尤度関数を導入して信頼度の高いＳ濃度の推定値を導出するようにしている。 As described above, the KR model according to this embodiment incorporates quantile calculation and likelihood functions in addition to the gray-box model described above to derive a highly reliable estimate of the S concentration.
図３は、本実施形態に係る操業演算装置１００の転炉工程での操業後の溶鋼中Ｓ濃度を推定するための機能構成例を示すブロック図である。
本実施形態においては、転炉内の過去の操業実績に係る実績データからし、転炉内での脱硫処理の操業条件を管理し、吹止後の溶鋼中Ｓ濃度を推定する。本実施形態では、炉内Ｓ管理モデルに従って転炉内のＳマスバランスの推定を行い、吹止後の溶鋼中Ｓ濃度を推定する。
Figure 3 is a block diagram showing an example of the functional configuration of the operation calculation device 100 according to this embodiment for estimating the sulfur concentration in molten steel after operation in the converter process.
In this embodiment, the operating conditions for desulfurization treatment in the converter are managed based on past operational data from the converter, and the sulfur concentration in the molten steel after blowdown is estimated. In this embodiment, the sulfur mass balance in the converter is estimated according to the in-furnace sulfur management model, and the sulfur concentration in the molten steel after blowdown is estimated.
ここで、炉内Ｓ管理モデルについて説明する。炉内Ｓ管理モデルでは、転炉内のＳマスバランス推定式の改善に加え、冷鉄源の積込みＳ量を推定し、銘柄毎の積込量を最適化する冷鉄源Ｓ推定モデルを導入する。まず、吹止成分推定部３５０では、以下の（２）式で表すＳマスバランス推定式を用いて吹止後の溶鋼中Ｓ濃度ＸB（質量％）を推定する。 Here, we will explain the in-furnace S management model. The in-furnace S management model improves the S mass balance estimation formula in the converter and introduces a cold iron source S estimation model that estimates the amount of S loaded into the cold iron source and optimizes the loading amount for each brand. First, in the blowdown component estimation unit 350, the S mass balance estimation formula expressed by equation (2) below is used to estimate the S concentration X B (mass%) in the molten steel after blowdown.
（２）式中、ＹBは吹止時のスラグ中Ｓ濃度［質量％］、ＶBはスクラップ等の冷鉄源を含んだ総装入溶鉄量［ｔ］、ＷBは吹止時のスラグの重量［ｔ］、Ｚpigは溶銑中のＳ量［ｋｇ］、Ｚchuteはスクラップ、型銑、主原料外鉄源等の冷鉄源Ｓ量［ｋｇ］、ＺKRslagは前工程の溶銑予備処理から持ち越された残留スラグからのＳ量［ｋｇ］、ＺLDslagは転炉スラグ（リサイクルスラグ）を用いた場合の転炉スラグからのＳ量［ｋｇ］、Ｚsubは投入副材からのＳ量［ｋｇ］を表す。なお、転炉操業が複数回吹錬および排滓を伴う操業である場合は、吹錬回数ごとにそれぞれ算出する。 (2) In the formula, Y B is the S concentration in the slag at the time of blowdown [mass%], V B is the total amount of molten iron charged, including cold iron sources such as scrap [t], W B is the weight of the slag at the time of blowdown [t], Z pig is the amount of S in the molten iron [kg], Z chute is the amount of S from cold iron sources such as scrap, molded iron, and iron sources other than the main raw material [kg], Z KRslag is the amount of S from residual slag carried over from the molten iron pretreatment process in the previous step [kg], Z LDslag is the amount of S from converter slag when converter slag (recycled slag) is used [kg], and Z sub is the amount of S from the input auxiliary materials [kg]. Note that if the converter operation involves multiple blowing and slag discharge operations, the calculation is performed for each blowing cycle.
ここで、溶銑中のＳ量Ｚpigは、溶銑予備処理推定成分出力部３１０から出力される値を用いる。溶銑予備処理推定成分出力部３１０は、溶銑予備処理後の溶銑中Ｓ濃度から溶銑中のＳ量Ｚpigを算出する。このとき、前述したように溶銑予備処理後の溶銑中Ｓ濃度は、転炉工程の操業までに溶銑中Ｓ濃度の実測値を導出できる場合にはその実測値を利用するが、分析が間に合わず実測値を導出できない場合は、前述のＫＲモデルで算出された推定値を用いるものとする。また、前工程の溶銑予備処理から持ち越された残留スラグからのＳ量ＺKRslagは、まず、スラグ残留量判定用カメラの撮影により、溶銑予備処理から持ち越されたスラグ量を計測する。そして、溶銑予備処理推定成分出力部３１０は、過去のスラグ成分の実績の平均値を残留スラグ中のＳ濃度とみなし、残留スラグからのＳ量ＺKRslagを算出する。なお、溶銑予備処理の前後の溶銑中Ｓ濃度の差分から推定した値を用いて算出してもよい。この場合も、分析が間に合わず実測値を導出できない場合は、溶銑予備処理前の溶銑中Ｓ濃度と、ＫＲモデルで算出された溶銑予備処理後の溶銑中Ｓ濃度の推定値との差分を用いて残留スラグ中のＳ濃度を推定してもよい。 Here, the amount of sulfur (S) in the molten iron, Z pig , is the value output from the molten iron pretreatment estimated component output unit 310. The molten iron pretreatment estimated component output unit 310 calculates the amount of sulfur (S) in the molten iron, Z pig , from the sulfur concentration in the molten iron after pretreatment. At this time, as mentioned above, if the measured value of the sulfur concentration in the molten iron after pretreatment can be derived before the operation of the converter process, that measured value will be used. However, if the analysis is not completed in time and the measured value cannot be derived, the estimated value calculated by the KR model described above will be used. In addition, the amount of sulfur (S) Z KR slag from the residual slag carried over from the previous process's molten iron pretreatment is first measured by taking a picture with a slag residual amount determination camera to determine the amount of slag carried over from the molten iron pretreatment. The molten iron pretreatment estimated component output unit 310 then considers the average value of past slag component data as the S concentration in the residual slag and calculates the S amount Z KRslag from the residual slag. Alternatively, the calculation may be performed using a value estimated from the difference in S concentration in the molten iron before and after molten iron pretreatment. In this case as well, if the analysis is not completed in time and an actual measured value cannot be obtained, the S concentration in the residual slag may be estimated using the difference between the S concentration in the molten iron before molten iron pretreatment and the estimated S concentration in the molten iron after molten iron pretreatment calculated by the KR model.
一方、冷鉄源Ｓ量Ｚchuteは、冷鉄源投入量計算部３４０により、冷鉄源情報取得部３２０で管理されている冷鉄源の銘柄別Ｓ濃度に基づいて算出される。冷鉄源のＳ濃度は直接測定できず、成分変動が大きい。特に他社から購入する冷鉄源は、様々な工程で発生した冷鉄源が混入されている可能性があるなど不確定要素が大きく、成分変動が特に大きい。そこで本実施形態では、この冷鉄源のＳ濃度の推定方法に着目し、冷鉄源Ｓ推定モデルを用いて機械学習により推定計算する。 On the other hand, the amount of S in the cold iron source Z chute is calculated by the cold iron source input amount calculation unit 340 based on the S concentration of each brand of cold iron source managed by the cold iron source information acquisition unit 320. The S concentration of the cold iron source cannot be measured directly, and its composition fluctuates greatly. In particular, cold iron sources purchased from other companies have many uncertainties, such as the possibility of contamination with cold iron sources generated in various processes, and their composition fluctuates especially greatly. Therefore, in this embodiment, we focus on a method for estimating the S concentration of the cold iron source and use a cold iron source S estimation model to perform estimation calculations using machine learning.
冷鉄源情報取得部３２０は、他工程で発生したスクラップや他社から購入したスクラップ、型銑、その他の副産物など数十～数百の銘柄の冷鉄源の情報を管理しており、転炉工程においては、その中からチャージ毎に異なる組み合わせの５～７銘柄を選択してスクラップシュートから投入する。なお、単一工程から発生したものは同じ銘柄として管理する。また、冷鉄源情報取得部３２０は、冷鉄源Ｓ推定モデルにより銘柄別に冷鉄源中のＳ濃度を推定し、推定値と実績値との間に差がある場合は必要に応じて補正を行う。 The cold iron source information acquisition unit 320 manages information on dozens to hundreds of types of cold iron sources, including scrap generated in other processes, scrap purchased from other companies, die-cast iron, and other by-products. In the converter process, 5 to 7 different combinations of these types are selected for each charge and fed into the scrap chute. Materials generated from a single process are managed as the same type. Furthermore, the cold iron source information acquisition unit 320 estimates the sulfur (S) concentration in each type of cold iron source using a cold iron source S estimation model, and corrects any discrepancies between the estimated and actual values as necessary.
図５は、銘柄別に冷鉄源中のＳ濃度を補正する処理手順の一例を示すフローチャートである。図５に示す各処理は、転炉工程でチャージ毎に行われ、ＣＰＵ４０１がＲＯＭ４０２に記憶された制御プログラムを読み出して実行することにより行われる。
まず、Ｓ６０１において、成分誤差計算部３７０は、転炉工程での吹止後のＳ濃度の実績値（分析値実績３００）を取得する。転炉工程の吹止後において溶鋼の成分分析が行われ、分析値実績３００としてＳ濃度の実績値が入力される。
Figure 5 is a flowchart showing an example of a processing procedure for correcting the sulfur concentration in the cold iron source for each brand. Each process shown in Figure 5 is performed for each charge in the converter process, and is carried out by the CPU 401 reading and executing a control program stored in the ROM 402.
First, in S601, the component error calculation unit 370 acquires the actual value of the S concentration after blowing in the converter process (analytical value actual 300). After blowing in the converter process, a component analysis of the molten steel is performed, and the actual value of the S concentration is input as the analytical value actual 300.
次に、Ｓ６０２において、成分誤差計算部３７０は、推定成分出力部３６０から出力された吹止後のＳ濃度の推定値とＳ６０１で入力された実績値との間の濃度差を算出する。ここで、吹止後のＳ濃度の推定値は、吹止成分推定部３５０により上述の（２）式のＳマスバランス推定式を用いて算出された値である。 Next, in S602, the component error calculation unit 370 calculates the concentration difference between the estimated S concentration after blowing, output from the estimated component output unit 360, and the actual value input in S601. Here, the estimated S concentration after blowing is the value calculated by the blowing component estimation unit 350 using the S mass balance estimation formula of equation (2) described above.
続いてＳ６０３において、成分誤差計算部３７０は、銘柄別Ｓ濃度補正値を算出する。ここで、ｋチャージ目、銘柄ｊの冷鉄源の投入量をｖj（ｋ）、総装入溶鉄量をＶ（ｋ）、ｋチャージ目の吹止後のＳ濃度の推定値と吹止後のＳ濃度の実績値との間の濃度差をΔ（ｋ）と定義する。この場合、銘柄別Ｓ濃度補正値βj（ｋ）は以下の（３）式によって算出される。
βj（ｋ）＝Δ（ｋ－１）＊Ｖ（ｋ－１）／ｖj（ｋ－１） ・・・（３）
Next, in S603, the component error calculation unit 370 calculates the brand-specific S concentration correction value. Here, vj (k) is defined as the amount of cold iron source added for charge k and brand j, V(k) is the total amount of molten iron charged, and Δ(k) is the concentration difference between the estimated value of the S concentration after blowing for charge k and the actual value of the S concentration after blowing. In this case, the brand-specific S concentration correction value βj (k) is calculated by the following equation (3).
β j (k)=Δ(k-1)*V(k-1)/v j (k-1)...(3)
なお、前述したように冷鉄源投入時は通常複数銘柄の冷鉄源を投入するが、（３）式はいずれの銘柄でも均等にＳ濃度の誤差が生じていると仮定したものとなっている。しかしながら実際には、Ｓ濃度を特定しやすい銘柄や特定しにくい銘柄など様々な銘柄が存在する。そこで、銘柄別Ｓ濃度補正値を算出する際に、銘柄の種類によって異なる補正係数（ｊ）（０＜補正係数（ｊ）≦１）を銘柄別Ｓ濃度補正値βj（ｋ）に乗算して重み付けを行ってもよい。 As mentioned above, when adding cold iron sources, multiple brands of cold iron sources are usually added, but equation (3) assumes that the error in S concentration occurs uniformly for all brands. However, in reality, there are various brands, some of which are easy to identify the S concentration of, and others which are difficult to identify. Therefore, when calculating the S concentration correction value for each brand, it is also possible to weight the S concentration correction value βj (k) for each brand by multiplying it by a correction coefficient (j) that differs depending on the type of brand (0 < correction coefficient (j) ≤ 1).
続いてＳ６０４において、成分誤差計算部３７０は、Ｓ６０３で算出した銘柄別Ｓ濃度補正値の絶対値が銘柄別標準誤差未満であるか否かを判定する。冷鉄源Ｓ推定モデルでは、吹止後のＳ濃度における推定値と実績値との誤差は、すべて冷鉄源の成分影響から発生すると仮定している。しかし、実操業では炉内残留地金の影響や型銑焼付の溶解、分析誤差など、冷鉄源Ｓ推定モデルでは表現できてない項目が残存しており、これらの影響を除く必要がある。また、元々Ｓ濃度のばらつきが小さい銘柄であっても、投入量が多い場合には補正量が大きくなり、そのまま補正値で補正してしまったら実際のＳ濃度から大きく外れてしまう。そこで銘柄別の標準誤差を用い、各銘柄の成分変動幅が標準誤差を超える場合は銘柄別のＳ濃度の補正を行わないようにしている。つまり、Ｓ６０３で算出した銘柄別Ｓ濃度補正値の絶対値が銘柄別標準誤差未満である場合はＳ６０５に進み、Ｓ６０３で算出した銘柄別Ｓ濃度補正値の絶対値が銘柄別標準誤差以上である場合はＳ６０６に進む。 Next, in S604, the component error calculation unit 370 determines whether the absolute value of the brand-specific S concentration correction value calculated in S603 is less than the brand-specific standard error. In the cold iron source S estimation model, it is assumed that the error between the estimated value and the actual value of the S concentration after blowing is entirely due to the influence of the cold iron source components. However, in actual operation, there are remaining factors that cannot be represented by the cold iron source S estimation model, such as the influence of residual metal in the furnace, melting during mold seizing, and analytical errors, and it is necessary to eliminate these influences. Furthermore, even for brands with originally small variations in S concentration, if the input amount is large, the correction amount becomes large, and if the correction value is applied as is, it will deviate significantly from the actual S concentration. Therefore, the brand-specific standard error is used, and if the component variation range of each brand exceeds the standard error, the brand-specific S concentration correction is not performed. In other words, if the absolute value of the brand-specific S concentration correction value calculated in S603 is less than the brand-specific standard error, the process proceeds to S605. If the absolute value of the brand-specific S concentration correction value calculated in S603 is greater than or equal to the brand-specific standard error, the process proceeds to S606.
なお、銘柄別の標準誤差は、冷鉄源情報取得部３２０が管理している各銘柄の冷鉄源のＳ濃度の変動に基づいて予め算出されるものである。 Furthermore, the standard error for each brand is calculated in advance based on the fluctuations in the S concentration of the cold iron source for each brand, which are managed by the cold iron source information acquisition unit 320.
Ｓ６０５において、冷鉄源情報取得部３２０は、該当する銘柄の冷鉄源のＳ濃度の補正を行う。ｋチャージ目、銘柄ｊの冷鉄源のＳ濃度をｚj（ｋ）、銘柄別残留率をαj（ｋ）とした場合、以下の（４）式に従ってＳ濃度の補正を行う。
ｚj（ｋ）＝ｚj（ｋ－１）＋αj（ｋ）×βj（ｋ） ・・・（４）
In S605, the cold iron source information acquisition unit 320 corrects the S concentration of the cold iron source for the corresponding brand. When the S concentration of the cold iron source for brand j in the k charge is zj (k) and the residual rate for the brand is αj (k), the S concentration is corrected according to the following equation (4).
z j (k)=z j (k-1)+α j (k)×β j (k) ... (4)
ここで、（４）式からわかる通り、Ｓ濃度の補正には前回の操業条件を使用している。したがって、その銘柄が使用されていない場合には（４）式を使用せず、成分補正を行わないこととする。 As can be seen from equation (4), the previous operating conditions are used to correct the S concentration. Therefore, if that particular brand is not used, equation (4) is not used, and no component correction is performed.
次に、Ｓ６０６において、成分誤差計算部３７０は、計算すべき銘柄がまだあるか否かを判定する。この判定の結果、計算すべき銘柄がまだ残っている場合はＳ６０３に戻り、次の銘柄について同様の処理を行う。一方、計算すべき銘柄がない場合はそのまま処理を終了する。 Next, in S606, the component error calculation unit 370 determines whether there are still stocks to be calculated. If, as a result of this determination, there are still stocks to be calculated, the process returns to S603 and performs the same process for the next stock. On the other hand, if there are no stocks to be calculated, the process ends.
以上のように本実施形態では、成分変動の大きい冷鉄源Ｓ量Ｚchuteの精度を高めるために、銘柄別に冷鉄源中のＳ濃度を補正によって最適化するようにしている。なお、前述したようにすべての銘柄で均等にＳ濃度の誤差が生じていると仮定して補正値を算出しているが、この処理を繰り返すことにより各銘柄で実際のＳ濃度に収束するようになる。例えば投入する６つ銘柄のうち、１つ銘柄のみが実際のＳ濃度と大きく異なるような場合であっても、チャージごとに銘柄の組み合わせを毎回変えることによって、残りの５つの銘柄のＳ濃度も異なる銘柄の組み合わせによって実際のＳ濃度に近づいていき、各銘柄で実際のＳ濃度に収束するようになる。 As described above, in this embodiment, in order to improve the accuracy of the cold iron source S amount Z chute , which has large component fluctuations, the S concentration in the cold iron source is optimized by correction for each brand. As mentioned above, the correction value is calculated assuming that the S concentration error is uniform for all brands, but by repeating this process, the S concentration will converge to the actual S concentration for each brand. For example, even if only one of the six brands used has a significantly different S concentration from the actual S concentration, by changing the combination of brands each time with each charge, the S concentrations of the remaining five brands will also approach the actual S concentration with different combinations of brands, and will converge to the actual S concentration for each brand.
次に、各銘柄の積込量について説明する。冷鉄源投入量計算部３４０は、転炉操業を行う前に、積込最適化モデルを用いて銘柄毎の積込量の最適化を行う。冷鉄源情報取得部３２０では、各銘柄の冷鉄源の成分のみならず、各銘柄の価格、在庫量、その他の制約条件に関する情報も保持している。各銘柄の積込量を最適化する際には、まず、制約条件設定部３３０によって設定されている各銘柄の制約条件（トランプエレメント管理別の銘柄別投入量規制、吹錬種別の投入量制約、突沸等の過去のトラブルを元に設定された吸着水分値別の投入量規制、在庫管理のための同一銘柄使用上限、未溶解を防ぐための溶解し辛い冷鉄源の総量上限など）により各銘柄の積込量の上限を確定し、そのうえで在庫があるか否かを判断する。そして、在庫のある複数銘柄から適宜選択し、制約条件を踏まえて冷鉄源の銘柄別Ｓ濃度の合計が、許容できる冷鉄源Ｓ量Ｚchuteの上限を超えない範囲でコスト最適点を模索する。なお、許容できる冷鉄源Ｓ量Ｚchuteの上限は、転炉工程のマスバランスおよび製品規格に応じた溶鋼中Ｓ濃度の上限値に基づいて制約条件設定部３３０により算出される。 Next, the loading amount for each type will be explained. Before starting converter operation, the cold iron source input amount calculation unit 340 optimizes the loading amount for each type using a loading optimization model. The cold iron source information acquisition unit 320 holds information not only on the components of each type of cold iron source, but also on the price, inventory quantity, and other constraints for each type. When optimizing the loading amount for each type, first, the upper limit of the loading amount for each type is determined by the constraints set by the constraint setting unit 330 (such as input amount restrictions for each type of trump element management, input amount restrictions for each type of blowing, input amount restrictions based on adsorbed moisture value set based on past troubles such as bumping, upper limit on the use of the same type for inventory management, and upper limit on the total amount of cold iron source that is difficult to dissolve to prevent undissolved material), and then it is determined whether or not there is inventory. Then, an appropriate selection is made from multiple types of cold iron sources that are in inventory, and the cost-optimal point is sought within the range where the sum of the S concentrations for each type of cold iron source does not exceed the upper limit of the acceptable cold iron source S amount Z chute , taking the constraints into account. The upper limit of the acceptable cold iron source S amount Z chute is calculated by the constraint setting unit 330 based on the mass balance of the converter process and the upper limit of the S concentration in molten steel according to the product specifications.
本実施形態に係る操業演算装置１００は、前述したＫＲモデルおよび炉内Ｓ管理モデルを組み合わせた複合モデルを構築し、溶銑予備処理工程および転炉工程を一括して管理して最適な操業条件を構築するよう制御することができる。 The operation calculation device 100 according to this embodiment constructs a composite model combining the aforementioned KR model and furnace S management model, and can control the molten iron pretreatment process and converter process in a unified manner to establish optimal operating conditions.
以上のように本実施形態によれば、吹止時のＳ濃度の推定値と実績値との差分を計算して、成分変動の大きい冷鉄源の成分を必要に応じて補正し、次回以降のチャージで反映させるようにしたので、冷鉄源の積込量の最適化を行った場合に、より精度よく操業条件の最適化を行うことができる。これにより、複合モデルを構築して溶銑予備処理および転炉工程において操業条件を一括して管理し、操業条件を最適化することができる。 As described above, according to this embodiment, the difference between the estimated and actual S concentration at the time of sintering is calculated, and the components of the cold iron source, which have large component fluctuations, are corrected as needed and reflected in subsequent charges. Therefore, when the loading amount of the cold iron source is optimized, the operating conditions can be optimized with greater accuracy. This allows for the construction of a composite model to manage operating conditions collectively in the molten iron pretreatment and converter processes, thereby optimizing the operating conditions.
（その他の実施形態）
なお、以上述べた実施形態の操業演算装置は、具体的にはコンピュータシステム或いは装置により構成されるものである。したがって、前述した機能を実現するソフトウェアのプログラムコードを記録した記憶媒体をシステム或いは装置に供給し、そのシステム或いは装置のコンピュータ（又はＣＰＵやＭＰＵ）が記憶媒体に格納されたプログラムコードを読み出し実行することによっても、達成されることは言うまでもない。
(Other embodiments)
Furthermore, the operational calculation device of the embodiment described above is specifically composed of a computer system or device. Therefore, it goes without saying that the above functions can also be achieved by supplying a storage medium containing program code for software that realizes the aforementioned functions to the system or device, and having the computer (or CPU or MPU) of that system or device read and execute the program code stored in the storage medium.
この場合、記憶媒体から読み出されたプログラムコード自体が前述した実施形態の機能を実現することになり、プログラムコード自体及びそのプログラムコードを記憶した記憶媒体は本発明を構成することになる。プログラムコードを供給するための記憶媒体としては、例えば、フレキシブルディスク、ハードディスク、光ディスク、光磁気ディスク、ＣＤ－ＲＯＭ、ＣＤ－Ｒ、磁気テープ、不揮発性のメモリカード、ＲＯＭ等を用いることができる。 In this case, the program code read from the storage medium itself will realize the functions of the embodiment described above, and the program code itself and the storage medium storing that program code will constitute the present invention. Examples of storage media that can be used to supply the program code include flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, etc.
以上説明した本発明の実施形態は、何れも本発明を実施するにあたっての具体化の例を示したものに過ぎず、これらによって本発明の技術的範囲が限定的に解釈されてはならないものである。即ち、本発明はその技術思想、またはその主要な特徴から逸脱することなく、様々な形で実施することができる。 The embodiments of the present invention described above are merely examples of how the invention can be implemented, and the technical scope of the invention should not be interpreted as being limited by them. That is, the present invention can be implemented in various forms without departing from its technical concept or its main features.
３１０ 溶銑予備処理推定成分出力部
３２０ 冷鉄源情報取得部
３３０ 制約条件設定部
３４０ 冷鉄源投入量計算部
３５０ 吹止成分推定部
３６０ 推定成分出力部
３７０ 成分誤差計算部
310 Molten iron pretreatment estimated component output unit 320 Cold iron source information acquisition unit 330 Constraint condition setting unit 340 Cold iron source input amount calculation unit 350 Blowstop component estimation unit 360 Estimated component output unit 370 Component error calculation unit
Claims (5)
溶銑予備処理後の溶銑中における所定の成分の濃度を取得する取得手段と、
前記取得手段によって取得された前記所定の成分の濃度と、転炉吹錬工程において投入する冷鉄源中の前記所定の成分の濃度とを用いて前記転炉吹錬工程における前記所定の成分の物質収支を推定することにより、前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度を推定する転炉工程管理手段と、
前記転炉工程管理手段によって推定された前記所定の成分の濃度の推定値と前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度の実績値との差分に基づき、前記冷鉄源中の前記所定の成分の濃度を補正し、前記冷鉄源の情報として前記転炉吹錬工程における冷鉄源投入量を管理する冷鉄源管理手段と、
を有することを特徴とする操業演算装置。 An operational calculation device for managing and optimizing the operating conditions of a converter blowing process,
An acquisition means for obtaining the concentration of a predetermined component in molten iron after pretreatment of molten iron,
A converter process management means estimates the concentration of the predetermined component in the molten steel after the converter blowing process by estimating the mass balance of the predetermined component in the converter blowing process using the concentration of the predetermined component obtained by the acquisition means and the concentration of the predetermined component in the cold iron source introduced in the converter blowing process ,
A cold iron source management means corrects the concentration of the predetermined component in the cold iron source based on the difference between the estimated concentration of the predetermined component estimated by the converter process management means and the actual concentration of the predetermined component in the molten steel after the converter blowing process, and manages the amount of cold iron source input in the converter blowing process as information about the cold iron source .
An operational calculation device characterized by having the following features.
前記転炉工程管理手段は、前記取得した前記残留スラグの量に基づく前記所定の成分の量を用いて前記所定の成分の物質収支を推定することを特徴とする請求項１または２に記載の操業演算装置。 The acquisition means further acquires the amount of residual slag carried over along with the molten iron that has undergone molten iron pretreatment,
The operation calculation device according to claim 1 or 2 , characterized in that the converter process management means estimates the mass balance of the predetermined component using the amount of the predetermined component based on the amount of residual slag acquired.
溶銑予備処理後の溶銑中における所定の成分の濃度を取得する取得ステップと、
前記取得ステップによって取得された前記所定の成分の濃度と、転炉吹錬工程において投入する冷鉄源中の前記所定の成分の濃度とを用いて前記転炉吹錬工程における前記所定の成分の物質収支を推定することにより、前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度を推定する転炉工程管理ステップと、
前記転炉工程管理ステップによって推定された前記所定の成分の濃度の推定値と前記転炉吹錬工程後の溶鋼中の前記所定の成分の濃度の実績値との差分に基づき、前記冷鉄源中の前記所定の成分の濃度を補正し、前記冷鉄源の情報として前記転炉吹錬工程における冷鉄源投入量を管理する冷鉄源管理ステップと、
を有することを特徴とする操業演算方法。 An operational calculation method executed by an operational calculation device that manages and optimizes the operating conditions of a converter blowing process,
A step to obtain the concentration of a predetermined component in the molten iron after pretreatment of the molten iron,
A converter process control step that estimates the concentration of the predetermined component in the molten steel after the converter blowing process by estimating the mass balance of the predetermined component in the converter blowing process using the concentration of the predetermined component obtained in the acquisition step and the concentration of the predetermined component in the cold iron source introduced in the converter blowing process ,
A cold iron source management step that corrects the concentration of the predetermined component in the cold iron source based on the difference between the estimated concentration of the predetermined component estimated by the converter process management step and the actual concentration of the predetermined component in the molten steel after the converter blowing process, and manages the amount of cold iron source input in the converter blowing process as information on the cold iron source ,
A method for calculating operations, characterized by having the following features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022016996A JP7846331B2 (en) | 2022-02-07 | 2022-02-07 | Operation calculation device and operation calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022016996A JP7846331B2 (en) | 2022-02-07 | 2022-02-07 | Operation calculation device and operation calculation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2023114592A JP2023114592A (en) | 2023-08-18 |
| JP7846331B2 true JP7846331B2 (en) | 2026-04-15 |
Family
ID=87569849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2022016996A Active JP7846331B2 (en) | 2022-02-07 | 2022-02-07 | Operation calculation device and operation calculation method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP7846331B2 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7817637B2 (en) * | 2023-10-20 | 2026-02-19 | 日本製鉄株式会社 | Estimation device, estimation method, estimation system, determination method, and computer program |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001152228A (en) | 1999-11-19 | 2001-06-05 | Kobe Steel Ltd | Method for blending main raw materials for converter |
| JP2005206900A (en) | 2004-01-23 | 2005-08-04 | Kobe Steel Ltd | Converter operating method |
| JP2020015959A (en) | 2018-07-26 | 2020-01-30 | 日本製鉄株式会社 | Constituent concentration operational unit, and constituent concentration operational method |
-
2022
- 2022-02-07 JP JP2022016996A patent/JP7846331B2/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001152228A (en) | 1999-11-19 | 2001-06-05 | Kobe Steel Ltd | Method for blending main raw materials for converter |
| JP2005206900A (en) | 2004-01-23 | 2005-08-04 | Kobe Steel Ltd | Converter operating method |
| JP2020015959A (en) | 2018-07-26 | 2020-01-30 | 日本製鉄株式会社 | Constituent concentration operational unit, and constituent concentration operational method |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2023114592A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6607577B2 (en) | Desulphurization reagent control method and system | |
| JP6573035B2 (en) | Method for estimating phosphorus concentration in molten steel and converter blowing control device | |
| JP5816148B2 (en) | Output value prediction apparatus, output value prediction method, and program thereof | |
| JP6515385B2 (en) | Hot metal pretreatment method and hot metal pretreatment control device | |
| JP7846331B2 (en) | Operation calculation device and operation calculation method | |
| JP5375318B2 (en) | Method for adjusting concentration and temperature of molten metal component and method for producing steel | |
| JP5488184B2 (en) | Scheduling parameter correcting method and correcting apparatus, schedule generating method and generating apparatus, and steel material manufacturing method | |
| JP6098553B2 (en) | Rejuvenated phosphorus amount prediction device, recovered phosphorus amount prediction method, and converter dephosphorization control method | |
| JP2007186734A (en) | Method and instrument for predicting molten steel temperature | |
| JP4407543B2 (en) | Steelmaking process operation schedule creation system, steelmaking process operation schedule creation method, and computer program | |
| JP2751800B2 (en) | Liquid Steel Temperature Control Method in Steel Making Process | |
| JPWO2019039539A1 (en) | Method for estimating phosphorus concentration in molten steel, converter blowing control device, program and recording medium | |
| JP2018178199A (en) | Method for estimating phosphorus concentration in molten steel, converter blasting control device, program and recording medium | |
| JP5924310B2 (en) | Blowing control method and blowing control device | |
| JP2004059954A (en) | Converter blowing control method | |
| JP2012214850A (en) | Molten iron temperature estimation method | |
| JP6516906B1 (en) | Wind blow calculation method, blow blow calculation program | |
| JP3786261B2 (en) | Desulfurization model creation device and its program in hot metal pretreatment, and desulfurization agent input amount calculation device and program in hot metal pretreatment | |
| JP2016017216A (en) | Control method of molten steel temperature in steel mill | |
| JP7754377B1 (en) | Information processing device, information processing method, and method for manufacturing continuous cast slab | |
| JP2025136482A (en) | Operational condition determination method, operational condition determination device, and information processing program | |
| TWI918523B (en) | Methods for estimating molten steel temperature, methods for controlling molten steel temperature, and methods for manufacturing molten steel. | |
| US20080172277A1 (en) | Algorithmic framework for scheduling steelmaking production optimizing the flow of molten iron subject to inventory constraints | |
| JP5622684B2 (en) | Production planning device and production planning method | |
| JP2008152350A (en) | Work time estimation device, work time estimation method, program, and machine-readable recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20241016 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20250828 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20251007 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20251204 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20260303 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20260316 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 7846331 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |