JP5407444B2 - Deformation resistance prediction method in hot rolling - Google Patents
Deformation resistance prediction method in hot rolling Download PDFInfo
- Publication number
- JP5407444B2 JP5407444B2 JP2009058800A JP2009058800A JP5407444B2 JP 5407444 B2 JP5407444 B2 JP 5407444B2 JP 2009058800 A JP2009058800 A JP 2009058800A JP 2009058800 A JP2009058800 A JP 2009058800A JP 5407444 B2 JP5407444 B2 JP 5407444B2
- Authority
- JP
- Japan
- Prior art keywords
- deformation resistance
- data
- strain
- database
- neighborhood
- 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
Images
Landscapes
- Control Of Metal Rolling (AREA)
- Metal Rolling (AREA)
Description
本発明は、熱間圧延における圧延材の変形抵抗を予測する、熱間圧延における変形抵抗予測方法に関するものである。 The present invention relates to a deformation resistance prediction method in hot rolling, in which the deformation resistance of a rolled material in hot rolling is predicted.
熱間圧延における仕上げミルでは、圧延材を要求される寸法・形状にするため、スタンド毎の圧下位置およびロール周速を決定する必要があり、プロコンで出側速度、板温度、圧延荷重による収束計算を行っている。(例えば、特許文献１参照)
上記圧延荷重の基本となる変形抵抗には、非特許文献１で紹介されている、美坂・吉本の式に代表される実験に基づく大域的な近似式が広く用いられてきた。
In finishing mills in hot rolling, it is necessary to determine the rolling position and roll peripheral speed for each stand in order to obtain the required dimensions and shape of the rolled material. Calculation is performed. (For example, see Patent Document 1)
For the deformation resistance that is the basis of the rolling load, a global approximate expression based on an experiment represented by Misaka and Yoshimoto, which has been introduced in Non-Patent Document 1, has been widely used.
しかしながら、実際の変形抵抗は、圧延材の添加物（成分）、温度、ひずみ量、ひずみ速度など多くの影響因子を持ち、全ての圧延条件を網羅できる大域的な前記近似式を作成することは非常な困難を伴う。このため、予測時に誤差が大きくなり、圧延不良が発生するという問題があった。 However, the actual deformation resistance has many influential factors such as the additive (component) of the rolled material, temperature, strain amount, strain rate, etc., and creating the global approximate expression that can cover all rolling conditions With great difficulty. For this reason, there has been a problem that an error becomes large at the time of prediction and a rolling defect occurs.
本発明では、これら従来技術の問題点に鑑み考案されたものであり、従来のような大域的な近似モデルは作成せず、従来に比べ精度の高い変形抵抗を予測することができる、熱間圧延における変形抵抗予測方法を提供することを課題とする。 The present invention has been devised in view of these problems of the prior art, does not create a global approximate model as in the prior art, and can predict deformation resistance with higher accuracy than in the past. It is an object of the present invention to provide a method for predicting deformation resistance in rolling.
上記課題は、以下の手段により解決される。
［１］熱間圧延における変形抵抗に影響を与える因子である、歪、歪速度、板温度、変態率、入側速度、板幅、および成分組成を説明変数とし、前記変形抵抗を目的変数とし、過去のそれぞれの実績データをデータベースとして蓄える、データベース作成工程と、
これから予測しようとする変形抵抗に対応する前記説明変数のデータを要求点データとして入力する、要求点データ入力工程と、
前記データベース内に蓄えたデータと前記要求点データとの距離計算を行い、この計算した距離が短いものから予め決めた所定数を近傍データとして選択する、近傍データ選択工程と、
選択された近傍データに基づいて、要求点近傍を局所的にフィッテイングする局所モデルである重み付局所重回帰モデルを、歪、歪速度、板温度、変態率、入側速度、板幅、および成分組成のいずれか、またはそれらを組合わせて作成する、局所モデル作成工程と、
作成された局所モデルと前記要求点データに基づいて、変形抵抗を予測する、変形抵抗予測工程とを有することを特徴とする熱間圧延における変形抵抗予測方法。
The above problem is solved by the following means.
[1] Strain, strain rate, sheet temperature, transformation rate, entry speed, sheet width, and component composition, which are factors affecting deformation resistance in hot rolling, are explanatory variables, and the deformation resistance is an objective variable. , Database creation process to store each past performance data as database,
A required point data input step of inputting the data of the explanatory variable corresponding to the deformation resistance to be predicted as required point data;
Performing a distance calculation between the data stored in the database and the requested point data, and selecting a predetermined number as a neighborhood data from a short distance calculated, neighborhood data selection step,
Based on the selected neighborhood data , a weighted local multiple regression model , which is a local model that locally fits the neighborhood of the request point, is subjected to strain, strain rate, plate temperature, transformation rate, entry side velocity, plate width, and A local model creation step of creating any of the component compositions or a combination thereof ;
Wherein based on the required point data with a local model created to predict the deformation resistance, deformation resistance predicted how the hot rolling and having a deformation resistance prediction process.
本発明によれば、過去の圧延実績をデータベースに登録し、その都度データベースから予測したい圧延条件と近い過去の実績を抽出し局所モデルを作成し、作成した局所モデルに基き変形抵抗を予測するようにしたので、従来に比べ精度の高い変形抵抗予測が可能となった。また、大域的な近似式を作成する必要がないことから適用時のメンテナンスなどの手間を省くことができる。 According to the present invention, the past rolling record is registered in the database, each time a past record close to the rolling condition to be predicted is extracted from the database, a local model is created, and deformation resistance is predicted based on the created local model. As a result, the deformation resistance can be predicted with higher accuracy than before. In addition, since it is not necessary to create a global approximate expression, it is possible to save troubles such as maintenance at the time of application.
熱間圧延における仕上げミルは、前段（Ｆ１〜Ｆ４）と後段（Ｆ５〜Ｆ７）の合計7つのスタンドを備え、板を要求される寸法・形状にするため、スタンド毎の圧下位置およびロール周速を決定する必要がある。このため、プロコンで出側速度、板温度、および圧延荷重による収束計算を行っている。 The finishing mill in hot rolling has a total of seven stands (F1 to F4) and rear (F5 to F7), and the rolling position and roll peripheral speed for each stand in order to obtain the required size and shape of the plate. Need to be determined. For this reason, the convergence calculation by the delivery speed, plate | board temperature, and rolling load is performed by the process control.
圧延荷重計算の基礎となる変形抵抗モデル式は、歪依存項や歪速度依存項、温度依存項、成分硬化項、変態項から算出される多重回帰モデルであるが、そのメンテナンスはこれまで試行錯誤によっていた。 The deformation resistance model that forms the basis of rolling load calculation is a multiple regression model that is calculated from strain-dependent terms, strain-rate-dependent terms, temperature-dependent terms, component hardening terms, and transformation terms. It was by.
図２は、本発明を説明する概念図である。過去の圧延実績をモデル用元データとして事例データベースに登録し、変形抵抗の予測が必要になるその都度、データベースから予測したい圧延条件(要求点)と近い過去の実績データを抽出する。そして、抽出した実績データに基いて局所モデルを作成する。図２では、見易さのために、変形抵抗に影響与える因子である説明変数が２つの場合での局所モデル作成の様子を模式的に示している。そして最終的に作成した局所モデルから目的変数(変形抵抗)の推定値を求めるものである。 FIG. 2 is a conceptual diagram illustrating the present invention. The past rolling record is registered in the case database as model original data, and each time the deformation resistance needs to be predicted, the past record data close to the rolling condition (request point) to be predicted is extracted from the database. Then, a local model is created based on the extracted result data. In FIG. 2, for the sake of easy viewing, a state of creating a local model in the case where there are two explanatory variables that are factors affecting the deformation resistance is schematically shown. Then, the estimated value of the objective variable (deformation resistance) is obtained from the finally created local model.
図１は、本発明に係る熱間圧延における変形抵抗予測方法の処理手順例を示す図である。図に従って、以下に処理手順を説明する。 FIG. 1 is a diagram showing a processing procedure example of a deformation resistance prediction method in hot rolling according to the present invention. The processing procedure will be described below with reference to the drawing.
（１）データベース作成工程(Step01)
過去の変形抵抗実績と変形抵抗に影響を与える因子からなる実績データを、データベースに予め蓄えておく。上記因子(説明変数)としては、例えば、歪、歪速度、板温度、変態率、入側速度、板幅、成分（C，Nｂ，Ti，B，Sｉ，Mｎ，Aｌ，Cｕ，Nｉ，V，Mｏ，Cｒ，P，S，N ）組成などが挙げられる。
(1) Database creation process (Step01)
Performance data consisting of past deformation resistance results and factors affecting deformation resistance are stored in a database in advance. Examples of the factors (explanatory variables) include strain, strain rate, plate temperature, transformation rate, entry side velocity, plate width, and components (C, Nb, Ti, B, Si, Mn, Al, Cu, Ni, V). , Mo, Cr, P, S, N) composition.
（２）要求点データ入力工程(Step02)
次に、これから変形抵抗を予測したい圧延材に関するデータ(要求点データ)を入力する。
(2) Request point data input process (Step02)
Next, data (required point data) relating to the rolling material for which deformation resistance is to be predicted is input.
（３）近傍データ選択工程(Step03)
Step01で作成したデータベースの中から上記要求点データに近いデータを選択する。選択に当たっては、要求点とデータベース内のデータとの距離を計算し、この距離が短いものから予め決めた所定数を選択するようにする。距離計算の例としては、例えばユークリッド距離があるが、その他の距離計算を用いても良い。
(3) Neighborhood data selection process (Step03)
Select data close to the requested point data from the database created in Step01. In the selection, the distance between the request point and the data in the database is calculated, and a predetermined number is selected from those having a short distance. Distance Examples of calculation, for example, there is a Euclidean distance may be used other distance calculation.
（４）局所モデル作成工程(Step04)
選択した近傍データに基いて、要求点近傍を局所的にフィッテイングする局所モデルを作成する。局所モデルはいかなる形式のものでも良いが、例えば、歪、歪速度、板温度、変態率、入側速度、板幅、成分（C，Nｂ，Ti，B，Sｉ，Mｎ，Aｌ，Cｕ，Nｉ，V，Mｏ，Cｒ，P，S，N ）組成のいずれか、またはそれらの組合わせた、重み付局所重回帰モデルが好適である。
(4) Local model creation process (Step 04)
Based on the selected neighborhood data, a local model for locally fitting the neighborhood of the request point is created. The local model may be of any type, for example, strain, strain rate, plate temperature, transformation rate, entry side velocity, plate width, component (C, Nb, Ti, B, Si, Mn, Al, Cu, Ni , V, Mo, Cr, P, S, N) A weighted local multiple regression model, which is any one or a combination thereof, is preferred.
（５）変形抵抗予測工程(Step05)
前工程で作成された局所モデルにStep02で入力した要求点データを入力して、最終的に変形抵抗を予測する。
(5) Deformation resistance prediction step (Step 05)
The required point data input in Step 02 is input to the local model created in the previous process, and finally the deformation resistance is predicted.
図３は、従来手法と本発明との比較例を示す図である。従来手法と本発明での適用結果の一例であり、それぞれ縦軸に変形抵抗の予測値、横軸に変形抵抗の実測値をとりプロットしている。データベースには約６万例の圧延実績を格納し、予測したい圧延条件（影響因子の近い）データを抽出し、近似モデルとして重み付局所重回帰モデルを用いて変形抵抗(３７００点)を予測した。 FIG. 3 is a diagram showing a comparative example between the conventional method and the present invention. It is an example of the application result in the conventional method and the present invention, and each plots the predicted value of deformation resistance on the vertical axis and the actual measurement value of deformation resistance on the horizontal axis. About 60,000 cases of rolling records are stored in the database, rolling condition data (close influence factors) to be predicted is extracted, and deformation resistance (3700 points) is predicted using a weighted local multiple regression model as an approximation model .
従来手法の標準偏差が４．６[kgf/mm2]に対して、本発明での標準偏差は１．５[kgf/mm2]と、従来手法に比べて、ばらつきを７６％低減することができた。また、誤差最小〜最大の幅(レンジ)も前者が２１．５[kgf/mm2]であるのに対して、後者は１０．５[kgf/mm2]とレンジが１０[kgf/mm2]も小さくなり、結果、予測値と実測値との相関係数も０．７７から０．９８と非常に良くなっていることが分る。 While the standard deviation of the conventional method is 4.6 [kgf / mm 2 ], the standard deviation in the present invention is 1.5 [kgf / mm 2 ], which reduces variation by 76% compared to the conventional method. I was able to. The minimum (maximum) error (range) of the former is 21.5 [kgf / mm 2 ], whereas the latter is 10.5 [kgf / mm 2 ] and the range is 10 [kgf / mm 2]. ], And as a result, it can be seen that the correlation coefficient between the predicted value and the actually measured value is also very good from 0.77 to 0.98.
Claims (1)
これから予測しようとする変形抵抗に対応する前記説明変数のデータを要求点データとして入力する、要求点データ入力工程と、
前記データベース内に蓄えたデータと前記要求点データとの距離計算を行い、この計算した距離が短いものから予め決めた所定数を近傍データとして選択する、近傍データ選択工程と、
選択された近傍データに基づいて、要求点近傍を局所的にフィッテイングする局所モデルである重み付局所重回帰モデルを、歪、歪速度、板温度、変態率、入側速度、板幅、および成分組成のいずれか、またはそれらを組合わせて作成する、局所モデル作成工程と、
作成された局所モデルと前記要求点データに基づいて、変形抵抗を予測する、変形抵抗予測工程とを有することを特徴とする熱間圧延における変形抵抗予測方法。 The factors affecting the deformation resistance in hot rolling are strain, strain rate, sheet temperature, transformation rate, entry speed, sheet width, and component composition as explanatory variables, the deformation resistance as a target variable, Database creation process to store each achievement data as a database,
A required point data input step of inputting the data of the explanatory variable corresponding to the deformation resistance to be predicted as required point data;
Performing a distance calculation between the data stored in the database and the requested point data, and selecting a predetermined number as a neighborhood data from a short distance calculated, neighborhood data selection step,
Based on the selected neighborhood data , a weighted local multiple regression model , which is a local model that locally fits the neighborhood of the request point, is subjected to strain, strain rate, plate temperature, transformation rate, entry side velocity, plate width, and A local model creation step of creating any of the component compositions or a combination thereof ;
A deformation resistance prediction method in hot rolling, comprising: a deformation resistance prediction step of predicting deformation resistance based on the created local model and the required point data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2009058800A JP5407444B2 (en) | 2009-03-12 | 2009-03-12 | Deformation resistance prediction method in hot rolling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2009058800A JP5407444B2 (en) | 2009-03-12 | 2009-03-12 | Deformation resistance prediction method in hot rolling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2010207900A JP2010207900A (en) | 2010-09-24 |
| JP5407444B2 true JP5407444B2 (en) | 2014-02-05 |
Family
ID=42968659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2009058800A Active JP5407444B2 (en) | 2009-03-12 | 2009-03-12 | Deformation resistance prediction method in hot rolling |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP5407444B2 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5857759B2 (en) * | 2011-01-28 | 2016-02-10 | Ｊｆｅスチール株式会社 | Deformation resistance prediction apparatus and rolling mill control method |
| JP5907114B2 (en) * | 2013-04-18 | 2016-04-20 | Ｊｆｅスチール株式会社 | Deformation resistance prediction method and deformation resistance prediction apparatus |
| JP2021079415A (en) * | 2019-11-20 | 2021-05-27 | Ｊｆｅスチール株式会社 | Setting value computing device, rolling machine operation information computing device, rolling equipment, steel strip manufacturing method, setting value computing method, and process model server |
| JP7298578B2 (en) * | 2020-10-01 | 2023-06-27 | Ｊｆｅスチール株式会社 | Plate thickness control method, plate material manufacturing method, and plate thickness control device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6462205A (en) * | 1987-09-03 | 1989-03-08 | Kawasaki Steel Co | Control method for rolling mill in continuous rolling of metal stock |
| JPH02307611A (en) * | 1989-05-22 | 1990-12-20 | Nippon Steel Corp | Setting up method for sheet rolling |
| JP2602346B2 (en) * | 1990-06-20 | 1997-04-23 | 新日本製鐵株式会社 | Steel material design equipment |
| JP3892797B2 (en) * | 2002-11-11 | 2007-03-14 | 株式会社神戸製鋼所 | Adaptive control method for rolling mill |
| JP2006309709A (en) * | 2005-03-30 | 2006-11-09 | Jfe Steel Kk | Result prediction device, control device and quality design device |
| JP4821284B2 (en) * | 2005-11-18 | 2011-11-24 | Ｊｆｅスチール株式会社 | Operation result prediction method and system |
| JP2007260729A (en) * | 2006-03-29 | 2007-10-11 | Jfe Steel Kk | Method and device for controlling edge drop |
-
2009
- 2009-03-12 JP JP2009058800A patent/JP5407444B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| JP2010207900A (en) | 2010-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6297159B2 (en) | Method for producing metal steel alloys and / or iron alloys in hot and thick plate mills using optimized structure simulators, structure monitors and / or structure models | |
| JP5003483B2 (en) | Material prediction and material control device for rolling line | |
| JP5407444B2 (en) | Deformation resistance prediction method in hot rolling | |
| JP5704040B2 (en) | Product quality management method and product quality management device | |
| KR101516476B1 (en) | Apparatus for calculating set value, method of calculating set value, and program recording medium for calculating set value | |
| JP2021536063A (en) | Methods and electronic devices for monitoring the manufacture of metal products, related computer programs and equipment | |
| WO2022054500A1 (en) | System for predicting material characteristic value, and method for producing metal sheet | |
| JP2010106314A (en) | Method for manufacturing steel product | |
| JP6021450B2 (en) | Heating furnace operation support system | |
| JP5003362B2 (en) | Product quality control method and control device | |
| JP7135962B2 (en) | Steel plate finishing delivery side temperature control method, steel plate finishing delivery side temperature control device, and steel plate manufacturing method | |
| JP2011220708A (en) | Material prediction device for steel material | |
| JP2006309709A (en) | Result prediction device, control device and quality design device | |
| JP6020263B2 (en) | Rolling load learning control device and learning control method, and metal plate manufacturing method using the same | |
| JP7044211B2 (en) | Product information determination method, manufacturing method, system, and product information determination device | |
| JP7287416B2 (en) | Thick steel plate manufacturing specification determination support device, manufacturing specification search method, computer program, computer-readable recording medium, and thick steel plate manufacturing method | |
| JP2010235972A (en) | Manufacturing controller and manufacturing method for high tension steel sheet | |
| JP5007630B2 (en) | Product quality control method and control device | |
| JP5907114B2 (en) | Deformation resistance prediction method and deformation resistance prediction apparatus | |
| JP5176554B2 (en) | Rolled product quality control system | |
| JP6822390B2 (en) | Rough rolling time calculation method for thick steel sheets, rough rolling time calculation device for thick steel sheets, and manufacturing method for thick steel sheets | |
| JP5423524B2 (en) | Apparatus and method for determining manufacturing conditions for hot-rolled coil and method for manufacturing hot-rolled coil | |
| JP5803138B2 (en) | Crystal grain size prediction method, crystal grain size prediction device, and crystal grain size prediction program | |
| JP2006239696A (en) | Method for reducing variance in quality of hot-rolled steel sheet | |
| JP4133419B2 (en) | Hot-rolled steel sheet material prediction method, pass schedule correction or setting method, and hot-rolled steel sheet manufacturing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20120223 |
|
| RD03 | Notification of appointment of power of attorney |
Free format text: JAPANESE INTERMEDIATE CODE: A7423 Effective date: 20120321 |
|
| RD04 | Notification of resignation of power of attorney |
Free format text: JAPANESE INTERMEDIATE CODE: A7424 Effective date: 20120327 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20120613 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20130716 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20130911 |
|
| 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: 20131008 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20131021 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 5407444 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
| R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |