JPH04339511A - Method for cooling and controlling steel plate - Google Patents
Method for cooling and controlling steel plateInfo
- Publication number
- JPH04339511A JPH04339511A JP3135879A JP13587991A JPH04339511A JP H04339511 A JPH04339511 A JP H04339511A JP 3135879 A JP3135879 A JP 3135879A JP 13587991 A JP13587991 A JP 13587991A JP H04339511 A JPH04339511 A JP H04339511A
- Authority
- JP
- Japan
- Prior art keywords
- steel plate
- heat transfer
- transfer coefficient
- cooling
- cooled
- 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.)
- Withdrawn
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 166
- 239000010959 steel Substances 0.000 title claims abstract description 166
- 238000001816 cooling Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims description 24
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 239000000203 mixture Substances 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 abstract description 5
- 239000000463 material Substances 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 14
- 230000002123 temporal effect Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000002347 injection Methods 0.000 description 3
- 239000007924 injection Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 101000582320 Homo sapiens Neurogenic differentiation factor 6 Proteins 0.000 description 1
- 102100030589 Neurogenic differentiation factor 6 Human genes 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005098 hot rolling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 239000002436 steel type Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Abstract
Description
【０００１】0001
【産業上の利用分野】本発明は、ニューラルネットワー
クモデルによって鋼板成分、鋼板外形、鋼板温度の連続
的な関数値として表されている熱伝達係数と、当該鋼板
と同等の鋼板温度、鋼板成分、鋼板外形等の物理的要素
を有する過去に冷却を行った鋼板の熱伝達係数で時間的
に順序付けられた複数個の実績値に基づいて鋼板の冷却
を制御する鋼板の冷却制御方法に関する。[Industrial Application Field] The present invention relates to a heat transfer coefficient expressed by a neural network model as a continuous function value of a steel plate component, a steel plate outer shape, and a steel plate temperature, a steel plate temperature equivalent to that of the steel plate, a steel plate component, The present invention relates to a method for controlling cooling of a steel plate, which controls cooling of a steel plate based on a plurality of performance values ordered in time based on heat transfer coefficients of steel plates that have been cooled in the past and have physical elements such as the outer shape of the steel plate.
【０００２】0002
【従来の技術】現在では、熱間圧延された直後の高温の
厚鋼板を水冷によって加速急冷することで焼き入れ効果
を得、鋼板に高強度の特性を付す制御冷却と称される工
程を備えた鋼板製造装置が稼働している。[Prior Art] Currently, a process called controlled cooling is used to obtain a quenching effect by rapidly cooling a high-temperature thick steel plate immediately after hot rolling with water cooling, thereby imparting high strength properties to the steel plate. Steel sheet manufacturing equipment is now in operation.
【０００３】この冷却は、鋼板が目的の温度になるまで
行われるわけであるが、冷却を正確に行うためには鋼板
の冷え具合を冷却の制御因子として設定する必要がある
。この冷え具合は、単位温度、単位時間、単位面積当た
りの熱量で表すことができ、熱伝達係数と等価なもので
ある。[0003] This cooling is performed until the steel plate reaches a target temperature, but in order to perform the cooling accurately, it is necessary to set the degree of cooling of the steel plate as a cooling control factor. The degree of cooling can be expressed by the amount of heat per unit temperature, unit time, and unit area, and is equivalent to the heat transfer coefficient.
【０００４】この熱伝達係数を設定する１つの方法とし
ては、冷却対象となる鋼板の成分、外形、温度などの要
因によって種別区分された離散的なテーブル値として扱
い、鋼板を冷却する際に、冷却対象となる鋼板の該当種
別区分ごとに、前回の熱伝達係数の実績値から次回の冷
却における熱伝達係数の予測値を推定している。One way to set this heat transfer coefficient is to treat it as a discrete table value categorized by factors such as the composition, external shape, and temperature of the steel plate to be cooled, and when cooling the steel plate, For each applicable type of steel plate to be cooled, the predicted value of the heat transfer coefficient for the next cooling is estimated from the previous actual value of the heat transfer coefficient.
【０００５】また、熱伝達係数を設定するもう１つの方
法としては、本出願人の特願平０２−４０９０９０号で
述べられているようなニューラルネットワークモデルを
用いて、熱伝達係数を鋼板成分、鋼板外形、鋼板温度の
連続的な関数値として扱い、鋼板を冷却する際には、冷
却装置入口及び出口において検出された鋼板の温度、並
びに当該鋼板の成分、外形等の物理的要素に基づいて、
鋼板の熱伝達係数の予測値を算出する。[0005] Another method for setting the heat transfer coefficient is to use a neural network model as described in Japanese Patent Application No. 02-409090 filed by the present applicant. It is treated as a continuous function value of the steel plate outer shape and steel plate temperature, and when cooling the steel plate, it is based on the temperature of the steel plate detected at the inlet and outlet of the cooling device, as well as physical elements such as the steel plate composition and outer shape. ,
Calculate the predicted value of the heat transfer coefficient of the steel plate.
【０００６】本発明は、熱伝達係数を設定する前記２つ
の方法のうち、本出願人の特願平０２−４０９０９０号
をさらに改善するものであることから、従来の技術とし
て、本出願人の特願平０２−４０９０９０号について詳
しく説明する。Of the two methods for setting the heat transfer coefficient, the present invention further improves the applicant's Japanese Patent Application No. 02-409090. Japanese Patent Application No. 02-409090 will be explained in detail.
【０００７】本出願人の特願平０２−４０９０９０号で
述べられている鋼板の冷却制御方法は、冷却装置入口及
び出口において検出された鋼板の温度、並びに当該鋼板
の成分、外形等の物理的要素に基づいて前記鋼板の熱伝
達係数の実績値を算出し、当該実績値に基づいて次回の
鋼板冷却の際の熱伝達係数の予測値を算出し、当該予測
値に基づいて前記鋼板の冷却を制御するようにした鋼板
の冷却方法において、前記熱伝達係数を、当該検出され
た鋼板の温度及び物理的要素に基づいてニューラルネッ
トワークモデルにより鋼板成分、鋼板外形、鋼板温度の
連続的な関数値として表し、当該関数値に基づいて鋼板
の冷却を行うようにしたことを特徴とする鋼板の冷却制
御方法であり、さらに、ニューラルネットワークモデル
により鋼板成分、鋼板外形、鋼板温度の連続的な関数値
として表されている標準的な熱伝達係数に基づいて鋼板
の熱伝達係数の予測値を算出し、冷却装置入口及びその
出口において検出された鋼板の温度、並びに当該鋼板の
成分、外形等の物理的要素に基づいて、前記鋼板の熱伝
達係数の実績値を算出し、前記予測値が当該実績値に近
付くように、学習機能を用いてニューラルネットワーク
モデルで表された前記標準的な熱伝達係数の鋼板成分、
鋼板外形、鋼板温度の連続的な関数値を逐次学習更新し
て、当該更新された連続的な関数値に基づいて次回の鋼
板の冷却を行うようにしたことを特徴とする鋼板の冷却
制御方法である。[0007] The steel plate cooling control method described in Japanese Patent Application No. 02-409090 by the present applicant is based on the temperature of the steel plate detected at the inlet and outlet of the cooling device, as well as the physical properties such as the composition and external shape of the steel plate. Calculate the actual value of the heat transfer coefficient of the steel plate based on the element, calculate the predicted value of the heat transfer coefficient for the next cooling of the steel plate based on the actual value, and calculate the predicted value of the heat transfer coefficient for the next cooling of the steel plate based on the predicted value. In the method for cooling a steel plate, the heat transfer coefficient is determined by a continuous function value of the steel plate composition, the steel plate outer shape, and the steel plate temperature using a neural network model based on the detected temperature and physical factors of the steel plate. This is a steel plate cooling control method characterized in that the steel plate is cooled based on the function value expressed as The predicted value of the heat transfer coefficient of the steel plate is calculated based on the standard heat transfer coefficient expressed as The actual value of the heat transfer coefficient of the steel plate is calculated based on the actual value, and the standard heat transfer coefficient expressed by the neural network model is calculated using a learning function so that the predicted value approaches the actual value. steel plate composition,
A method for controlling cooling of a steel plate, characterized in that continuous function values of the steel plate outer shape and steel plate temperature are learned and updated sequentially, and the next cooling of the steel plate is performed based on the updated continuous function values. It is.
【０００８】[0008]
【発明が解決しようとする課題】しかしながら、本出願
人の特願平０２−４０９０９０号で述べられている鋼板
の冷却制御方法では、ニューラルネットワークモデルで
表わされた標準的な熱伝達係数を示す連続的な関数値を
、鋼板を冷却制御する毎に、当該鋼板の熱伝達係数の予
測値が当該鋼板の実績値に近づくように学習機能を用い
て修正し更新することから、もし前記関数が更新されて
から次回の更新が行われるまでの間に、鋼板の有する物
理的要素と熱伝達係数の関数関係が変化した場合には、
次回の鋼板の冷却制御に際して前記関数に基づいて算出
される熱伝達係数の予測値は、必ずしも当該鋼板の熱伝
達係数の実績値に近いものであるとは限らない。[Problems to be Solved by the Invention] However, in the steel plate cooling control method described in Japanese Patent Application No. 02-409090 of the present applicant, the standard heat transfer coefficient expressed by a neural network model is Each time a steel plate is cooled, the continuous function value is corrected and updated using a learning function so that the predicted value of the heat transfer coefficient of the steel plate approaches the actual value of the steel plate. If the functional relationship between the physical elements of the steel plate and the heat transfer coefficient changes between the update and the next update,
The predicted value of the heat transfer coefficient calculated based on the function during the next cooling control of the steel plate is not necessarily close to the actual value of the heat transfer coefficient of the steel plate.
【０００９】本発明は、このような従来の不具合を解消
するために成されたものであり、ニューラルネットワー
クにより表される標準的な熱伝達係数の他に、当該鋼板
と同等の鋼板温度、鋼板成分、鋼板外形等の物理的要素
を有する過去に冷却を行った鋼板の熱伝達係数で時間的
に順序付けられた複数個の実績値を用いることによって
、ニューラルネットワークモデルによる鋼板の物理的要
素と熱伝達係数の関係を表す関数の更新から次回の更新
までの間の時間経過に伴う熱伝達係数の実績値の挙動を
知ることができる情報を付加することにより、上記のよ
うな不具合の発生を回避させて、鋼板の熱伝達係数の予
測を常に良好な状態で行えるようにした鋼板の冷却制御
方法の提供を目的とする。[0009] The present invention was made in order to eliminate such conventional problems, and in addition to the standard heat transfer coefficient expressed by a neural network, it is possible to By using multiple actual values ordered in time based on the heat transfer coefficient of steel plates that have been cooled in the past, which have physical elements such as composition and steel plate outer shape, the physical elements and thermal By adding information that allows you to know the behavior of the actual value of the heat transfer coefficient over time between the update of the function that expresses the relationship between the transfer coefficients and the next update, the occurrence of the above-mentioned problems can be avoided. It is an object of the present invention to provide a cooling control method for a steel plate that allows prediction of the heat transfer coefficient of the steel plate in a good condition at all times.
【００１０】0010
【課題を解決するための手段】上記目的を達成するため
の本発明は、冷却装置入口及び出口において検出された
鋼板の温度、並びに当該鋼板の成分、外形等の物理的要
素に基づいて前記鋼板の熱伝達係数の実績値を算出し、
この熱伝達係数の実績値を当該鋼板の鋼板温度、鋼板成
分、鋼板外形といった物理的要素により種別化された鋼
種毎に、鋼板の冷却制御順に順序付けして計算機メモリ
ー等の記憶媒体に保存し、次回の鋼板冷却の際に、冷却
装置入口及び出口において検出された鋼板の温度、並び
に当該鋼板の成分、外形等の物理的要素に基づいて、ニ
ューラルネットワークモデルにより表された連続的な関
数値から算出した熱伝達係数と、前記記憶媒体から取り
出した当該鋼板と同等の鋼板温度、鋼板成分、鋼板外形
等の物理的要素を有する過去に冷却を行った鋼板の熱伝
達係数で時間的に順序付けられた複数個の実績値を用い
て、ニューラルネットワークによる熱伝達係数と過去の
熱伝達係数の実績値から将来の熱伝達係数の予測値を推
定する数式から、当該鋼板の熱伝達係数の設定値を算出
し、当該鋼板の冷却を行うようにしたことを特徴とする
鋼板の冷却制御方法である。[Means for Solving the Problems] The present invention achieves the above object by determining the temperature of the steel plate detected at the inlet and outlet of the cooling device, and the temperature of the steel plate based on the physical factors such as the composition and external shape of the steel plate. Calculate the actual value of the heat transfer coefficient of
The actual values of the heat transfer coefficient are stored in a storage medium such as a computer memory in order of the cooling control order of the steel plate for each steel type classified by physical factors such as the steel plate temperature, steel plate composition, and steel plate outer shape. During the next cooling of the steel plate, the temperature of the steel plate detected at the inlet and outlet of the cooling device, as well as the continuous function values expressed by the neural network model, are calculated based on the physical elements such as the composition and external shape of the steel plate. The calculated heat transfer coefficient and the heat transfer coefficient of a previously cooled steel plate having physical elements such as steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate taken out from the storage medium are temporally ordered. The set value of the heat transfer coefficient of the steel plate is determined from a mathematical formula that estimates the predicted value of the future heat transfer coefficient from the heat transfer coefficient determined by the neural network and the past heat transfer coefficient actual values. This is a method for controlling cooling of a steel plate, characterized in that the temperature is calculated and the steel plate is cooled.
【００１１】[0011]
【作用】以上のような本発明の方法によれば、熱伝達係
数がニューラルネットワークにより表される標準的な熱
伝達係数の他に、当該鋼板と同等の鋼板温度、鋼板成分
、鋼板外形等の物理的要素を有する過去に冷却を行った
鋼板の熱伝達係数で時間的に順序付けられた複数個の熱
伝達係数の実績値から成る数式として表されていること
から、冷却が行われる鋼板と同等な物理的要素を有する
鋼板の過去の実績値を参照することによって、ニューラ
ルネットワークモデルにより表された熱伝達係数の連続
的な関数の更新から更新までの間の時間経過に伴う熱伝
達係数の実績値の挙動を予測することができる。その結
果、前記関数が更新されてから次回の更新が行われるま
での間に、鋼板の有する物理的要素と熱伝達係数の関数
関係が変化した場合にあっても、最適な熱伝達係数の設
定値を得ることができることになる。そして、この設定
値に基づいて前記鋼板の冷却が行われることから、常に
所望の材質の鋼板を得ることが可能になる。[Operation] According to the method of the present invention as described above, in addition to the standard heat transfer coefficient expressed by a neural network, the heat transfer coefficient is calculated based on the steel plate temperature, steel plate composition, steel plate outer shape, etc. equivalent to the steel plate in question. It is expressed as a mathematical formula consisting of the actual values of multiple heat transfer coefficients ordered in time based on the heat transfer coefficient of a steel plate that has been cooled in the past, which has physical elements, so it is equivalent to the steel plate that is being cooled. By referring to the past performance values of steel plates with physical elements, we can calculate the performance of the heat transfer coefficient over time between updates of the continuous function of the heat transfer coefficient expressed by the neural network model. The behavior of values can be predicted. As a result, even if the functional relationship between the physical elements of the steel plate and the heat transfer coefficient changes between the time the function is updated and the next update, the optimum heat transfer coefficient can be set. You will be able to get the value. Since the steel plate is cooled based on this set value, it is possible to always obtain a steel plate of a desired material.
【００１２】0012
【実施例】以下、本発明の実施例を図面に基づいて詳細
に説明する。図１は、本発明の鋼板の冷却制御方法を示
すフローチャートである。まず、冷却制御装置が起動す
ると、上位の計算機から送られてくる制御データを読み
込む。ここで言う制御データとは、冷却対象となる鋼板
の温度、成分、外形に関するデータの総称である（ステ
ップ１）。この制御データに基づいて、前記鋼板と同等
の物理的要素を有する過去に冷却を行った鋼板の熱伝達
係数の実績値で時間的に順序付けられた複数個の前記実
績値を、最新のものから必要個数分だけ記憶装置から読
み込む（ステップ２）。本出願人の特願平０２−４０９
０９０号で述べられている方法により、ニューラルネッ
トワークモデルの順方向計算を行い、当該鋼板の標準的
な熱伝達係数を算出する（ステップ３）。ステップ２で
読み込んだ熱伝達係数の実績値と、ステップ３で算出し
た熱伝達係数の推定値から、当該鋼板の冷却制御に用い
る熱伝達係数の設定値を計算する。この計算は次式によ
る。Embodiments Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a flowchart showing a method for controlling cooling of a steel plate according to the present invention. First, when the cooling control device starts up, it reads the control data sent from the host computer. The control data referred to here is a general term for data regarding the temperature, components, and external shape of the steel plate to be cooled (Step 1). Based on this control data, a plurality of actual values of the heat transfer coefficients of steel plates that have been cooled in the past and have physical elements equivalent to those of the steel plates, which are ordered in time, are selected from the latest one. The required number of data is read from the storage device (step 2). Applicant's patent application No. 02-409
Using the method described in No. 090, a forward calculation of the neural network model is performed to calculate the standard heat transfer coefficient of the steel plate (step 3). From the actual value of the heat transfer coefficient read in step 2 and the estimated value of the heat transfer coefficient calculated in step 3, a set value of the heat transfer coefficient used for cooling control of the steel plate is calculated. This calculation is based on the following formula.
【００１３】[0013]
【数２】[Math 2]
【００１４】ただし、α ：鋼板冷却に用いる熱伝達
係数の設定値〔Ｋｃａｌ／ｍ２ ・ｈｒ・°Ｃ〕ａ ０
：定数
αＮＮ：ニューラルネットワークモデルから算出される
熱伝達係数の推定値〔Ｋｃａｌ／ｍ２ ・ｈｒ・°Ｃ〕
ｎ ：計算に用いる熱伝達係数の実績値の個数を示す
定数（ｎ≦Ｎ）
Ｎ ：当該鋼板と同等の鋼板温度、鋼板成分、鋼板外
形等の物理的要素を有する過去に冷却を行った鋼板の個
数から１を引いた数
ｂｉ ：定数
αＮ−ｉ ：当該鋼板と同等の鋼板温度、鋼板成分、鋼
板外形等の物理的要素を有する過去に冷却を行った鋼板
の熱伝達係数の実績値であり、時間的に最古のものから
α０ ，α１ ，α２ ，・・・，αＮ と順序付けら
れている前記熱伝達係数の実績値〔Ｋｃａｌ／ｍ２ ・
ｈｒ・°Ｃ〕[0014] However, α: Set value of heat transfer coefficient used for cooling steel plate [Kcal/m2 ・hr・°C] a 0
: Constant αNN: Estimated value of heat transfer coefficient calculated from neural network model [Kcal/m2 ・hr・°C]
n: Constant indicating the number of actual heat transfer coefficient values used for calculation (n≦N) N: Steel plate that has been cooled in the past and has physical elements such as steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate in question Bi: Constant αN-i: The actual value of the heat transfer coefficient of a steel plate that has been cooled in the past and has physical elements such as steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate in question. The actual values of the heat transfer coefficients [Kcal/m2 ·
hr・°C〕
【００１５】ここで、定数ａ０ ，ｂｉ ，ｎはαの予
測精度が最もよくなるように予め調整しておく（ステッ
プ４）。このようにして得られた熱伝達係数の設定値に
基づいて冷却すべき鋼板の冷却時間を演算し、その冷却
時間を注水弁開閉制御装置および鋼板搬送速度制御装置
に出力する。注水弁開閉制御装置はこの冷却時間に基づ
いて各注水弁の開閉制御を行い、また鋼板搬送速度制御
装置はこの冷却時間に基づいて鋼板が最適な搬送速度で
搬送されるようにモーターの回転速度を制御する。これ
によって、鋼板は冷却装置内を最適な搬送速度で搬送さ
れつつ、最適な冷却条件の下での冷却が行われることに
なる（ステップ５）。この鋼板の冷却が行われた後で、
当該鋼板の冷却装置入り側温度および出側温度、冷却時
間等から当該鋼板の熱伝達係数の実績値を演算によりも
とめる（ステップ６）。さらに、本出願人の特願平０２
−４０９０９０号で述べられている方法により、ニュー
ラルネットワークモデルの逆方向計算による熱伝達係数
の学習演算を行う（ステップ７）。そして当該鋼板の熱
伝達係数の実績値を、ステップ２で用いた記憶装置内に
時間的に順序付けして当該鋼板と同等の物理的要素を有
する鋼板の熱伝達係数の実績値が格納されている場所に
書き込む（ステップ８）。Here, the constants a0, bi, and n are adjusted in advance so that the prediction accuracy of α is the best (step 4). The cooling time of the steel plate to be cooled is calculated based on the set value of the heat transfer coefficient obtained in this manner, and the cooling time is output to the water injection valve opening/closing control device and the steel plate conveyance speed control device. The water injection valve opening/closing control device controls the opening and closing of each water injection valve based on this cooling time, and the steel plate conveyance speed control device adjusts the motor rotation speed based on this cooling time so that the steel plate is conveyed at the optimal conveyance speed. control. As a result, the steel plate is transported through the cooling device at an optimal transport speed and cooled under optimal cooling conditions (step 5). After this steel plate is cooled,
The actual value of the heat transfer coefficient of the steel plate is calculated from the cooling device inlet temperature and outlet temperature of the steel plate, cooling time, etc. (step 6). Furthermore, the applicant's patent application
According to the method described in No. 409090, the learning calculation of the heat transfer coefficient is performed by backward calculation of the neural network model (step 7). The actual values of the heat transfer coefficient of the steel plate are stored in the storage device used in step 2 in a chronological order, and the actual values of the heat transfer coefficient of the steel plate having the same physical elements as the steel plate are stored. Write to location (step 8).
【００１６】以上が本発明の鋼板の冷却制御である。The above is the cooling control of the steel plate according to the present invention.
【００１７】次に、本発明の鋼板の冷却制御方法により
鋼板を冷却制御した結果を示す。図２は、熱伝達係数の
予測値と実績値の時間的推移を、本発明の方法と従来の
方法と対比して示すグラフである。図２において、同図
（ａ）は本発明の方法による結果であり、同図（ｂ）は
従来の方法による結果である。図２に示すグラフの横軸
は鋼板の冷却制御の１回分を１目盛りとした時間の軸で
あり、縦軸は熱伝達係数の軸である。またグラフの中で
、実線は熱伝達係数の予測値であり、破線は熱伝達係数
の実績値である。この２つのグラフにおいて、同図（ａ
）に示す本発明の方法によれば、熱伝達係数の予測値は
、熱伝達係数の実積値の時間的挙動をよく捉えており、
実績値に対する予測誤差も小さい。一方、同図（ｂ）に
示す従来の方法によれば、熱伝達係数の予測値は、熱伝
達係数の実績値の時間的挙動をあまり捉えておらず、実
績値に対する誤差が大きい。したがって、本発明を適用
すれば熱伝達係数の最適な設定値が得られることが判る
。Next, the results of controlling the cooling of a steel plate using the steel plate cooling control method of the present invention will be shown. FIG. 2 is a graph showing the temporal changes in predicted values and actual values of the heat transfer coefficient, comparing the method of the present invention and the conventional method. In FIG. 2, (a) shows the results obtained by the method of the present invention, and (b) shows the results obtained by the conventional method. The horizontal axis of the graph shown in FIG. 2 is the axis of time, with one scale representing one cooling control of the steel plate, and the vertical axis is the axis of the heat transfer coefficient. Moreover, in the graph, the solid line is the predicted value of the heat transfer coefficient, and the broken line is the actual value of the heat transfer coefficient. In these two graphs, the same figure (a
According to the method of the present invention shown in ), the predicted value of the heat transfer coefficient well captures the temporal behavior of the actual value of the heat transfer coefficient,
The prediction error with respect to the actual value is also small. On the other hand, according to the conventional method shown in FIG. 6B, the predicted value of the heat transfer coefficient does not capture the temporal behavior of the actual value of the heat transfer coefficient very well, and has a large error with respect to the actual value. Therefore, it can be seen that the optimum set value of the heat transfer coefficient can be obtained by applying the present invention.
【００１８】[0018]
【発明の効果】以上の説明により明らかなように本発明
によれば、鋼板冷却の際の熱伝達係数の設定値の予測精
度が向上し、鋼板に対して最適な冷却が行えることから
、温度不良を低減させることができ、冷却後の鋼板材質
を安定させることができる。[Effects of the Invention] As is clear from the above explanation, according to the present invention, the accuracy of predicting the set value of the heat transfer coefficient when cooling a steel plate is improved, and the steel plate can be optimally cooled. Defects can be reduced and the quality of the steel plate material after cooling can be stabilized.
【図１】本発明の鋼板の冷却制御方法のフローチャート
である。FIG. 1 is a flowchart of a method for controlling cooling of a steel plate according to the present invention.
【図２】（ａ）は本発明の方法による熱伝達係数の予測
値と実績値の時間的推移を示すグラフ、（ｂ）は従来の
方法による熱伝達係数の予測値と実績値の時間的推移を
示すグラフである。[Fig. 2] (a) is a graph showing the temporal change in the predicted value and actual value of the heat transfer coefficient by the method of the present invention, (b) is a graph showing the temporal change in the predicted value and actual value of the heat transfer coefficient by the conventional method. It is a graph showing the transition.
Claims (1)
出された鋼板の温度、並びに当該鋼板の成分、外形等の
物理的要素に基づいて前記鋼板の熱伝達係数の実績値を
算出し、当該実績値に基づいて次回の鋼板冷却の際の熱
伝達係数の予測値を算出し、当該予測値に基づいて前記
鋼板の冷却を制御するようにした鋼板の冷却制御方法に
おいて、ニューラルネットワークモデルにより鋼板成分
、鋼板外形、鋼板温度の連続的な関数値として表された
標準的な熱伝達係数と、当該鋼板と同等の鋼板温度、鋼
板成分、鋼板外形等の物理的要素を有する過去に冷却を
行った鋼板の熱伝達係数で時間的に順序付けられた複数
個の実績値を用いて、下記に示す数式から当該鋼板の熱
伝達係数を算出し、その熱伝達係数に基づいて当該鋼板
の冷却を行うようにしたことを特徴とする鋼板の冷却制
御方法。 【数１】 ただし、α ：鋼板冷却に用いる熱伝達係数の設定値
〔Ｋｃａｌ／ｍ２ ・ｈｒ・°Ｃ〕 ａ０ ：定数 αＮＮ：ニューラルネットワークモデルから算出される
熱伝達係数の推定値〔Ｋｃａｌ／ｍ２ ・ｈｒ・°Ｃ〕
ｎ ：計算に用いる熱伝達係数の実積値の個数を示す
定数（ｎ≦Ｎ） Ｎ ：当該鋼板と同等の鋼板温度、鋼板成分、鋼板外
形等の物理的要素を有する過去に冷却を行った鋼板の個
数から１を引いた数 ｂｉ ：定数 αＮ−ｉ ：当該鋼板と同等の鋼板温度、鋼板成分、鋼
板外形等の物理的要素を有する過去に冷却を行った鋼板
の熱伝達係数の実績値であり、時間的に最古のものから
α０ ，α１ ，α２ ，・・・，αＮ と順序付けら
れている前記熱伝達係数の実績値〔Ｋｃａｌ／ｍ２ ・
ｈｒ・°Ｃ〕Claim 1: Calculate the actual value of the heat transfer coefficient of the steel plate based on the temperature of the steel plate detected at the inlet and outlet of the cooling device, and physical elements such as the composition and external shape of the steel plate, and calculate the actual value of the heat transfer coefficient of the steel plate. In a steel plate cooling control method, a predicted value of the heat transfer coefficient for the next steel plate cooling is calculated based on the calculated value, and cooling of the steel plate is controlled based on the predicted value, the steel plate components, A steel plate that has been cooled in the past and has a standard heat transfer coefficient expressed as a continuous function value of the steel plate outer shape and steel plate temperature, and physical elements such as the steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate in question. The heat transfer coefficient of the steel plate is calculated from the formula shown below using multiple actual values ordered in time with the heat transfer coefficient, and the steel plate is cooled based on the heat transfer coefficient. A method for controlling cooling of a steel plate, characterized in that: [Equation 1] Where, α: Set value of heat transfer coefficient used for steel sheet cooling [Kcal/m2 ・hr・°C] a0: Constant αNN: Estimated value of heat transfer coefficient calculated from neural network model [Kcal/m2・hr・°C〕
n: Constant indicating the number of actual heat transfer coefficient values used for calculation (n≦N) N: A steel plate that has been cooled in the past and has physical elements such as steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate in question. The number bi obtained by subtracting 1 from the number of steel plates: Constant αN-i: Actual value of the heat transfer coefficient of a steel plate that has been cooled in the past and has physical elements such as steel plate temperature, steel plate composition, and steel plate outer shape that are equivalent to the steel plate in question. The actual values of the heat transfer coefficients [Kcal/m2 ·
hr・°C〕
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP3135879A JPH04339511A (en) | 1991-05-10 | 1991-05-10 | Method for cooling and controlling steel plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP3135879A JPH04339511A (en) | 1991-05-10 | 1991-05-10 | Method for cooling and controlling steel plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH04339511A true JPH04339511A (en) | 1992-11-26 |
Family
ID=15161911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP3135879A Withdrawn JPH04339511A (en) | 1991-05-10 | 1991-05-10 | Method for cooling and controlling steel plate |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH04339511A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999013999A1 (en) * | 1997-09-16 | 1999-03-25 | Siemens Aktiengesellschaft | Method and device for cooling metals in a metal works |
| KR100977373B1 (en) * | 2007-07-19 | 2010-08-20 | 신닛뽄세이테쯔 카부시키카이샤 | Cooling control method, cooling control device, device for calculating quantity of cooling water and computer-readable recording medium storing computer program |
| JPWO2021229949A1 (en) * | 2020-05-15 | 2021-11-18 |
-
1991
- 1991-05-10 JP JP3135879A patent/JPH04339511A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999013999A1 (en) * | 1997-09-16 | 1999-03-25 | Siemens Aktiengesellschaft | Method and device for cooling metals in a metal works |
| KR100977373B1 (en) * | 2007-07-19 | 2010-08-20 | 신닛뽄세이테쯔 카부시키카이샤 | Cooling control method, cooling control device, device for calculating quantity of cooling water and computer-readable recording medium storing computer program |
| US9364879B2 (en) | 2007-07-19 | 2016-06-14 | Nippon Steel & Sumitomo Metal Corporation | Cooling control method, cooling control apparatus, and cooling water amount calculation apparatus |
| JPWO2021229949A1 (en) * | 2020-05-15 | 2021-11-18 | ||
| WO2021229949A1 (en) * | 2020-05-15 | 2021-11-18 | Ｊｆｅスチール株式会社 | Method for predicting temperature deviation in thick steel plate, method for controlling temperature deviation in thick steel plate, method for generating temperature deviation prediction model for thick steel plate, method for producing thick steel plate, and equipment for producing thick steel plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2004164648A (en) | Hybrid cascade model based predictive control system | |
| US6225609B1 (en) | Coiling temperature control method and system | |
| JP6922675B2 (en) | Manufacturing process state predictors, methods and programs, and manufacturing process control systems | |
| JP4744226B2 (en) | Learning method of cooling control model and cooling method of rolled material. | |
| JPH07191712A (en) | Method and apparatus for giving of instruction to process at inside of system to be adjusted | |
| JP6834209B2 (en) | Product status prediction device, product status control device, product status prediction method and program | |
| JPH07200005A (en) | Learning control method | |
| JP6662109B2 (en) | Product state prediction device, product state control device, product state prediction method and program | |
| JPH04339511A (en) | Method for cooling and controlling steel plate | |
| CN115608793B (en) | Finish rolling temperature regulation and control method for mechanism fusion data | |
| JPH04232214A (en) | Method and device for controlling cooling of steel plate | |
| JP2001252709A (en) | Method for temperature on outlet side of finishing mill for hot rolling | |
| JP2555116B2 (en) | Steel material cooling control method | |
| JP3144984B2 (en) | Adjustment method of molten steel temperature in steelmaking process | |
| JP2563844B2 (en) | Steel plate material prediction method | |
| JP4408221B2 (en) | Heat transfer coefficient estimation method and cooling control method in water cooling process of steel sheet | |
| CA1118074A (en) | Method of controlling a heating furnace for steel ingots | |
| JPH06246320A (en) | Method for controlling cooling of hot-rolled steel material | |
| JP2786760B2 (en) | Prediction method of rolling temperature of steel sheet in hot rolling | |
| JPH1133616A (en) | Controller for winding temperature of steel strip | |
| JPH06264153A (en) | Method for predicting slab temperature in continuous type heating furnace | |
| WO2021229727A1 (en) | Physical model identification system | |
| Muntin et al. | Digitalization as the Most Important Tool for the Improvement of Metallurgical Technologies | |
| JP2002137013A (en) | Method of setting steel strip cooling condition | |
| JP2005220432A (en) | Plate temperature cooling control method in cooling zone of continuous steel plate heat treatment equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A300 | Application deemed to be withdrawn because no request for examination was validly filed |
Free format text: JAPANESE INTERMEDIATE CODE: A300 Effective date: 19980806 |