JPH02182815A - Method for controlling distribution of charged material in blast furnace - Google Patents
Method for controlling distribution of charged material in blast furnaceInfo
- Publication number
- JPH02182815A JPH02182815A JP88689A JP88689A JPH02182815A JP H02182815 A JPH02182815 A JP H02182815A JP 88689 A JP88689 A JP 88689A JP 88689 A JP88689 A JP 88689A JP H02182815 A JPH02182815 A JP H02182815A
- Authority
- JP
- Japan
- Prior art keywords
- distribution
- furnace
- data
- condition
- gas flow
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 239000002801 charged material Substances 0.000 title abstract 7
- 238000012821 model calculation Methods 0.000 claims abstract description 12
- 239000000463 material Substances 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 24
- 238000012545 processing Methods 0.000 abstract description 5
- 239000000571 coke Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 239000002245 particle Substances 0.000 description 7
- 239000002994 raw material Substances 0.000 description 7
- 230000007423 decrease Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 2
- 238000007664 blowing Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Abstract
Description
【発明の詳細な説明】
〔産業上の利用分野〕
本発明は高炉の操業方法、特に分布制御方法に関するも
のである。DETAILED DESCRIPTION OF THE INVENTION [Industrial Field of Application] The present invention relates to a method for operating a blast furnace, and in particular to a distribution control method.
高炉操業は非常に多くの操業因子が相互に関連し合って
成立っているものであり、さらに設備条件等から直接視
覚で炉内を監視する事が困難なため、操業レベルの維持
向上を図るためには高炉に取付けられたセンサー等の情
報を総合的に判断し、的確に制御する必要がある。この
ため現在でも高炉の日常操業管理には操業者の経験や知
識が重要なものとなっている。Blast furnace operation is made up of a large number of interrelated operating factors, and it is difficult to directly visually monitor the inside of the furnace due to equipment conditions, etc., so it is necessary to maintain and improve the operating level. In order to achieve this, it is necessary to comprehensively judge information from sensors installed in the blast furnace and control it accurately. For this reason, the experience and knowledge of operators is still important for the daily operational management of blast furnaces.
知識工学システムは、このような人間のノウハウを計算
機に取込んで処理する事が出来るため、特開昭６２−２
７０７０８号公報及び特開昭６２−２７０７１２号公報
に示されているような高炉操業管理への知識工学システ
ムの導入が進められている。操業管理のシステム化によ
り、情報の見落しや判断ミス等の問題が無くなり、操業
管理の適正化や標準化が図られる。Knowledge engineering systems can incorporate such human know-how into computers and process it.
Introduction of knowledge engineering systems to blast furnace operational management as shown in Japanese Patent Application Laid-open No. 70708 and Japanese Patent Application Laid-Open No. 62-270712 is underway. By systemizing operational management, problems such as oversight of information and misjudgment will be eliminated, and operational management will be optimized and standardized.
特開昭６２−２７０７１２号公報に開示されている知識
工学システムでは、吹抜けやスリップの予測を行うもの
であるが、対処方法の出力までは行っていない。高炉の
制御まで行っているものとして、特開昭６２−２７０７
０８号公報に開示されている高炉炉熱制御システムがあ
るが、あくまでも高炉操業の中の炉熱レベルという項目
のみの制御であり、高炉操業全体に対処し得るシステム
とはなっていない。The knowledge engineering system disclosed in Japanese Unexamined Patent Publication No. 62-270712 predicts blowouts and slips, but does not output countermeasures. Unexamined Japanese Patent Publication No. 62-2707, which even controls blast furnaces,
Although there is a blast furnace furnace heat control system disclosed in Publication No. 08, it only controls the furnace heat level during blast furnace operation, and is not a system that can handle the entire blast furnace operation.
特に日常の高炉操業と安定維持するためには高炉の操業
状況に合わせて木目細かく装入物分布制御を行う必要が
ある。炉内のガス流分布がどのような状況になっている
かを判断するには過去の経験や知識の活用が有効である
が、それに対する具体的な分布制御方法に関しては過去
の経験や知識通りにならない事が多い、これは、高炉の
装入物分布制御手段が各装入銘柄の炉内半径装入位置、
１チヤージ内の装入銘柄の分割装入方式及び分割製大量
、炉内装入面レベル等多数存在すると共に、同じ制御方
法でもその時の原料粒度構成等の条件により装入物分布
に対する効果が異なるためである。従って、過去の経験
や知識に基づいて構築した知識ベースによる推論で、そ
の時の最適な装入物分布制御方法を導き出すのは極めて
困難であるという問題があった。In particular, in order to maintain stability during daily blast furnace operation, it is necessary to perform fine-grained control of charge distribution according to the operating conditions of the blast furnace. It is effective to use past experience and knowledge to judge the situation of gas flow distribution in the furnace, but it is not possible to use past experience and knowledge to determine the specific distribution control method. This is because the blast furnace charge distribution control means adjusts the radial charging position in the furnace for each charging brand.
There are many types of split charging methods for charging brands in one charge, large quantities of split products, level of entrance surface in the furnace, etc., and even the same control method has different effects on the burden distribution depending on the conditions such as the raw material particle size composition at that time. It is. Therefore, there has been a problem in that it is extremely difficult to derive the optimal charge distribution control method at that time by reasoning based on a knowledge base built based on past experience and knowledge.
そこで、本発明はこのような問題点を解決するためにな
されたものであり常に高炉炉内のガス流及び装入物分布
状況を適確に判断し、最適な装入物分布制御を実施でき
るような高炉の操業方法を得る事を目的とする。Therefore, the present invention was made to solve these problems, and it is possible to always accurately judge the gas flow and burden distribution situation in the blast furnace, and implement optimal burden distribution control. The purpose of this study is to obtain a method for operating a blast furnace.
本発明に係る高炉の操業方法は上記課題を解決するため
になされたものであって、あらかじめ高炉炉内半径方向
のガス流や装入物の分布状況判断を行うための知識ベー
スを備えた知識工学システムにより、高炉炉内半径方向
のガス流や装入物の分布状況を推論し、該分布状況が適
正領域から外れていると判断された場合に、装入物分布
予測モデル計算を起動し、その時の装入原料条件、装入
物分布制御条件、操業条件等のオンラインデータにより
計算した炉内半径方向のガス流及び装入物分布特性の結
果をベース条件とし、該オンラインデータの中で装入物
分布制御条件のみを複数種類変更して計算した各分布特
性結果の中で、ベース条件に対する変化方向及び変化量
が、知識工学システムでの推論結果における現状の分布
状況を適正領域に戻すのに最も適する装入物分布制御条
件を選出し、該装入物分布制御条件に従って実炉アクシ
ョンを実行することを特徴とする高炉の装入物分布制御
方法である。The blast furnace operating method according to the present invention has been made in order to solve the above problems, and is a knowledge base that is equipped with a knowledge base for determining the gas flow in the radial direction in the blast furnace and the distribution status of the charge. The engineering system infers the gas flow and charge distribution in the radial direction inside the blast furnace, and if it is determined that the distribution is out of the appropriate range, the charge distribution prediction model calculation is activated. , the results of the gas flow in the radial direction of the furnace and the burden distribution characteristics calculated from online data such as charging material conditions, burden distribution control conditions, operating conditions, etc. at that time are used as the base conditions, and in this online data, Among the distribution characteristic results calculated by changing multiple types of charge distribution control conditions, the direction and amount of change relative to the base conditions will return the current distribution situation to the appropriate range based on the inference results of the knowledge engineering system. A blast furnace charge distribution control method is characterized in that the most suitable charge distribution control conditions are selected and the actual furnace action is executed in accordance with the charge distribution control conditions.
本発明においては、知識工学システムにより炉内状況の
推論を行う事により、炉内半径方向のガス流及び装入物
分布状況の変化を迅速かつ的確に捕らえ、種々の分布制
御方法による装入物分布特性変化をオンラインデータを
用いて装入物分布予測モデル計算により定量的に把握し
、計算結果の中から最適装入物分布制御方法を知識工学
システムの推論結果に基づいて選出し、実炉アクション
として採用する。In the present invention, by inferring the situation inside the reactor using a knowledge engineering system, changes in the gas flow and charge distribution in the radial direction inside the reactor can be quickly and accurately grasped, and the change in the charge distribution situation can be quickly and accurately determined using various distribution control methods. Changes in distribution characteristics are quantitatively understood through burden distribution prediction model calculations using online data, and the optimal burden distribution control method is selected from the calculation results based on the inference results of the knowledge engineering system. Adopt as an action.
以下、本発明の実施例を図面に基づいて説明する。第１
図は本発明の一実施例に係る処理及びデータの流れの説
明図である。高炉ｌからの情報は、プロセスデータ処理
２により知識工学システム及び装入物分布予測モデル計
算で使用可能な状態とする。装入物分布予測モデルとし
ては、鐵と鋼、７０（１９８４）、 Ｓ４７に示されて
いるような、炉頂部へ装入された原料の半径方向の堆積
形状や粒度分布、ガス流分布等を、装入条件やコークス
崩れ現象等を考慮して求めることができる数式モデルを
用いる。該高炉情報から、知識工学システムにより炉況
判断３を行い、炉内半径方向のガス流分布状況を把握す
る。図において、−点鎖線で囲まれた範囲は装入物分布
予測モデル計算を実行する部分であり、知識工学システ
ムによる炉況判断３の結果、装入物分布制御アクション
が必要と判定された時に起動する。該モデル計算の起動
は知識工学システムの判定結果に従い自動的に行うか、
又は炉況判断３を端末９に出力し、それに従って操業者
１２が入力端末１０の操作により行っても良い。装入物
分布予測モデルの計算は初めにプロセスデータ、知識工
学システムからの炉況判断結果のデータ、操業者の設定
データ等に基づき計算用データ作成４を行う、計算用デ
ータは、オンラインデータを用いた現在の装入物分布特
性の予測計算用のデータと装入物分布制御条件を変更し
た複数パターンの計算用データを含んだものであり、該
複数パターンのデータにより装入物分布予測モデル計算
５を行う。該複数パターンのデータによる装入物分布予
測モデル計算結果の装入物分布形状表示や現在の分布特
性から、装入物分布制御条件変更後の分布特性の変化を
示したデータの表示等を行うための計算結果後処理６を
実行する。計算結果データは出力端末１１に表示し、操
業者１３が出力端末１１に表示された装入物分布予測モ
デル計算結果と、出力端末９に表示された知識工学シス
テムによる炉内半径方向分布状況判定結果に基づいて、
最適装入物分布制御条件を選出し、実行装入物分布制御
８を行う。該最適装入物分布制御条件の選出は、知識工
学システムによる炉況判断３の結果のデータと装入物分
布予測モデル計算結果のデータを知識工学システムのデ
ータベースとして取込み、装入物分布制御条件を選出す
るための知識ベースによる推論によって実行してもよい
。Embodiments of the present invention will be described below based on the drawings. 1st
The figure is an explanatory diagram of processing and data flow according to an embodiment of the present invention. Information from the blast furnace 1 is made available for use in the knowledge engineering system and burden distribution prediction model calculations by process data processing 2. The burden distribution prediction model is based on the radial stacking shape, particle size distribution, gas flow distribution, etc. of the raw material charged to the top of the furnace, as shown in Tetsu-to-Hagane, 70 (1984), S47. , using a mathematical model that can be determined by taking into account charging conditions, coke collapse phenomena, etc. From the blast furnace information, the knowledge engineering system performs furnace condition judgment 3 and grasps the gas flow distribution situation in the radial direction inside the furnace. In the figure, the range surrounded by the - dotted chain line is the part where the burden distribution prediction model calculation is executed, and when it is determined that the burden distribution control action is necessary as a result of the furnace condition judgment 3 by the knowledge engineering system. to start. Is the model calculation automatically started according to the judgment result of the knowledge engineering system?
Alternatively, the furnace condition judgment 3 may be output to the terminal 9, and the operator 12 may operate the input terminal 10 accordingly. To calculate the burden distribution prediction model, first create calculation data 4 based on process data, furnace condition judgment result data from the knowledge engineering system, operator setting data, etc. The calculation data is obtained from online data. It includes data for predictive calculation of the current burden distribution characteristics used and data for calculation of multiple patterns with changed burden distribution control conditions, and the data of the multiple patterns is used to create a burden distribution prediction model. Perform calculation 5. Displays the shape of the burden distribution based on the calculation results of the burden distribution prediction model based on the data of the plurality of patterns, and displays data showing changes in the distribution characteristics after changing the burden distribution control conditions based on the current distribution characteristics. The calculation result post-processing 6 is executed for the calculation result. The calculation result data is displayed on the output terminal 11, and the operator 13 uses the burden distribution prediction model calculation result displayed on the output terminal 11 and the knowledge engineering system displayed on the output terminal 9 to judge the radial distribution situation in the reactor. Based on the results,
Optimum charge distribution control conditions are selected and execution charge distribution control 8 is performed. The optimal burden distribution control conditions are selected by importing the data of the results of Furnace Condition Judgment 3 by the knowledge engineering system and the data of the calculation results of the burden distribution prediction model as a database of the knowledge engineering system. It may also be performed by inference using a knowledge base to select.
個々の判断及び処理内容を図面に基づいてさらに詳しく
説明する。第２図は、知識工学システムにおける、高炉
の情報から炉内半径方向のガス流分布状況の判断に至る
までのフロー図である。ガス流及び装入物分布状況を判
断するための検出端として、装入物表面温度分布を測定
するサーモピュアー１５、炉頂部半径方向ガス温度分布
を測定する炉頂ゾンデ１６、炉周辺部のコークス及び鉱
石の層厚を測定する層厚計１７、シャフト上部高さでの
半径方向ガス温度及び成分分布を測定するシャフト上部
ゾンデ１８、炉体各部温度計１９、炉体各部圧力計２０
などがあり、これらの情報と、炉熱レベル、通気状況、
荷降上状況等の情報に基づき、知識工学システムにより
、高炉操業状況の結合判定２１を行い、装入物分布制御
アクション必要性の判定２２及び半径方向ガス流分布状
況判定２３を行う。半径方向ガス流分布状況判定２３に
おいて炉の半径方向を中心部、中間部、周辺部の３領域
に分け、ガス流割合を表現する三角ダイアグラムを用い
、現在のガス流分布状況と、目標値との偏差を捕え、以
降の最適装入物分布制御条件の選出に用いる。本発明の
実施例においては、現状のガス流分布割合は狙い値に対
し中心流が３％過多、周辺流が３％不足となっている。The individual judgments and processing contents will be explained in more detail based on the drawings. FIG. 2 is a flowchart in the knowledge engineering system from blast furnace information to determination of the gas flow distribution situation in the radial direction inside the furnace. As a detection end for determining the gas flow and charge distribution status, there is a Thermopure 15 that measures the temperature distribution on the surface of the charge, a top sonde 16 that measures the gas temperature distribution in the radial direction at the top of the furnace, and coke around the furnace. and a layer thickness gauge 17 that measures the layer thickness of the ore, a shaft upper sonde 18 that measures the radial gas temperature and component distribution at the height of the upper shaft, a thermometer 19 for each part of the furnace body, and a pressure gauge 20 for each part of the furnace body.
In addition to this information, the furnace heat level, ventilation status,
Based on information such as the unloading status, the knowledge engineering system performs a joint determination 21 of the blast furnace operating status, a determination 22 of the necessity of a charge distribution control action, and a determination 23 of the radial gas flow distribution status. In the radial gas flow distribution status determination 23, the radial direction of the furnace is divided into three areas: the center, middle, and peripheral area, and a triangular diagram expressing the gas flow ratio is used to determine the current gas flow distribution status and the target value. The deviation is captured and used for subsequent selection of optimal charge distribution control conditions. In the embodiment of the present invention, the current gas flow distribution ratio is 3% more in the center flow and 3% less in the peripheral flow than the target value.
次に、装入物分布予測モデル計算によるケース検討の例
を、第３図に基づいて説明する。装入物分布制御条件を
種々に変更したデータの作成において、本発明の実施例
では装入物分布制御手段２４として下記５項目を採用し
た。Next, an example of case study based on charge distribution prediction model calculation will be explained based on FIG. 3. In creating data with various charge distribution control conditions, the following five items were adopted as the charge distribution control means 24 in the embodiment of the present invention.
ａ、炉内半径方向原料装入位置
す、装入面レベル
Ｃ，コークス・鉱石ベース（ｌチャージの装入１ｔ）
ｄ、焼結鉱細粒使用割合
、ｅ、炉内への原料装入時の時系列排出粒度パターン
これらの制御手段毎に、現状の制御条件を基準として装
入物分布制御条件変更処理２８を行う。a, Raw material charging position in the radial direction inside the furnace, Charging surface level C, Coke/ore base (Charging 1 ton of 1 charge) d, Sinter fine grain usage ratio, e, When charging raw materials into the furnace For each of these control means, a charge distribution control condition change process 28 is performed based on the current control conditions.
ここで、現状の制御条件はオンラインデータの装入物分
布制御条件２５を使用する。以下に装入物分布制御条件
変更処理２８の内容を説明する。Here, the charge distribution control condition 25 of online data is used as the current control condition. The contents of the charge distribution control condition changing process 28 will be explained below.
ａ、炉内半径方向原料装入位置、変更
■鉱石の装入を現状より１ノツチ中心方向ヘシフトする
（以降ａ＋と記す）
■鉱石の装入を現状より１ノツチ周辺方向ヘシフトする
（以降ａ−と記す）
ｂ、装入面レベル変更
■現状より０．５ｍ上昇する（以降ｂ＋と記す）■現状
より０．５ｍ低下する（以降す−と記す）Ｃ，コークス
・鉱石ベース変更
■鉱石ベースをチャージ当たりｉｔ増加、コークスベー
スは現状の鉱石とコークスの比を一定に保つ量だけ増加
する。（以降Ｃ十と記す）■鉱石ベースをチャージ当た
り１ｔＭ少、コークスベースは現状の鉱石とコークスの
比を一定に保つ量だけ減少する（以降Ｃ−と記す）ｄ、
焼結鉱細粒使用割合変更
■現状より鉱石ベースに対する焼結鉱細粒割合を１％増
加する。（以降ｄ＋と記す）■現状より、鉱石ベースに
対する焼結鉱細粒割合を１％減少する。（以降ｄ−と記
す）ｅ、炉内への原料装入時の時系列排出粒度パターン
変更
■１ダンプ鉱石装入時の開始から終了までの時間を横軸
に取り、平均粒径を縦軸に取った平均粒径の経時変化を
直線近似した時のグラフの傾きを１％増加する。（以降
ｅ＋と記す）■上記グラフの傾きを１％減少する。（以
降ｅ−と記す）
該装入物分布制御条件変更処理２日により作成した現状
を含めた複数の装入物分布制御条件と、使用原料粒度条
件や送風条件等２６の装入物分布制御条件以外のオンラ
インデータと、設備条件等定数データ２７に基づいて計
算用データファイル２９を作成する。該計算データによ
り、装入物分布予測モデル計算３０を実行し、得られた
計算結果データファイル３１に基づき、画面表示や、現
状からの変化量の計算等の計算結果後処理３２を行う。a. Change the raw material charging position in the radial direction inside the furnace ■ Shift the ore charging from the current state toward the center of the notch (hereinafter referred to as a+) ■ Shift the ore charging from the current state toward the periphery of the notch by one notch (hereinafter a- ) b.Change the charging surface level■ Increase by 0.5m from the current level (hereinafter referred to as b+) ■Lower by 0.5m from the current level (hereinafter denoted as -)C.Change the coke/ore base■Change the ore base IT increases per charge, and the coke base increases by an amount that keeps the current ore to coke ratio constant. (hereinafter referred to as C-) ■ The ore base decreases by 1 tM per charge, and the coke base decreases by an amount that keeps the current ore and coke ratio constant (hereinafter referred to as C-) d.
Change in the ratio of sintered ore fines used ■ Increase the ratio of sintered ore fines to the ore base by 1% from the current level. (hereinafter referred to as d+) ■ Reduce the ratio of sintered ore fine particles to the ore base by 1% from the current situation. (Hereinafter referred to as d-) e. Changing the time-series discharge particle size pattern when charging raw materials into the furnace ■1 The horizontal axis is the time from the start to the end of dump ore charging, and the vertical axis is the average particle size. The slope of the graph when a linear approximation of the change in average particle diameter over time taken in 2008 is approximated by 1%. (hereinafter referred to as e+) ■Reduce the slope of the above graph by 1%. (hereinafter referred to as e-) A plurality of charge distribution control conditions including the current situation created by the charge distribution control condition change process on the 2nd day, and 26 charge distribution control conditions such as the particle size conditions of the raw material used and the air blowing conditions. A calculation data file 29 is created based on online data other than conditions and constant data 27 such as equipment conditions. Based on the calculated data, a charge distribution prediction model calculation 30 is executed, and based on the obtained calculation result data file 31, calculation result post-processing 32 such as screen display and calculation of the amount of change from the current state is performed.
第４図は、装入物分布予測モデル計算結果の出力例であ
り、（ａ）は炉内半径方向装入物堆積形状であり、３３
はコークス層、３４及び３５は鉱石層である。（ロ）は
炉内半径方向鉱石コークス比（ｏ／Ｃ）分布、（Ｃ）は
炉内半径方向鉱石平均粒度分布である。これらの分布特
性図により、現状と装入物分布制御条件変更後との分布
特性の違いを定量的に把握する。第５図は、装入物分布
予測モデル計算結果の炉内半径方向ガス流分布割合を三
角図に示したものであり、ａ＋ａ−・・・・・・ｅ−の
記号は前記のそれぞれの装入物分布条件変更を行った場
合の計算結果を表わす。該三角図により装入物分布条件
変更によるガス流分布変化を容易に把握する事ができる
０図の中で、点線の円で囲まれた領域は、１回のアクシ
ョンでのガス流分布調整許容範囲であり、過去の実炉ア
クション実績において操業の変動を生じない最大のアク
ションによるガス流分布割合の変化を現状を中心点とし
て表わしたものである。従って分布制御条件変更のアク
ションは、ガス流分布変化が該ガス流分布調整許容範囲
内のものを採用することが望ましい。Figure 4 is an example of the output of the calculation results of the burden distribution prediction model, where (a) shows the shape of the burden piled up in the radial direction in the furnace;
is a coke layer, and 34 and 35 are ore layers. (B) is the ore coke ratio (o/C) distribution in the radial direction in the furnace, and (C) is the ore average particle size distribution in the radial direction in the furnace. Using these distribution characteristic diagrams, we can quantitatively understand the difference in distribution characteristics between the current state and after changing the burden distribution control conditions. Figure 5 is a triangular diagram showing the radial gas flow distribution ratio in the furnace based on the calculation results of the burden distribution prediction model. The calculation results are shown when changing the distribution conditions. The triangular diagram allows you to easily understand changes in gas flow distribution due to changes in charge distribution conditions.In the diagram, the area surrounded by a dotted circle indicates the allowable gas flow distribution adjustment in one action. This range represents the change in the gas flow distribution ratio due to the maximum action that does not cause operational fluctuations in past actual reactor action results, with the current situation as the center point. Therefore, it is preferable that the action of changing the distribution control conditions is such that the change in gas flow distribution is within the permissible range for adjusting the gas flow distribution.
これらの計算結果の中で、ａ＋の条件が現状に対し中心
ガス流割合が３％減少し、周辺ガス流割合が３％増加す
る方向にあり、第２図の知識工学システムによる半径方
向ガス流分布状況２３の判定結果における狙い値からの
現状のズレを矯正するのに最も適したアクションである
と判定できる。Among these calculation results, the condition of a+ is such that the center gas flow ratio decreases by 3% and the peripheral gas flow ratio increases by 3% compared to the current situation, and the radial gas flow according to the knowledge engineering system in Figure 2 is It can be determined that this is the most suitable action for correcting the current deviation from the target value in the determination result of the distribution situation 23.
この判定は、第１図に示すように操業者１３が行っても
良いし、最適装入物分布制御条件選出７を行うための知
識ベースを備えた知識工学システムで行っても良い。This determination may be made by the operator 13 as shown in FIG. 1, or may be made by a knowledge engineering system equipped with a knowledge base for selecting the optimum burden distribution control conditions 7.
以上の結果より、実炉における装入物分布制御条件とし
てａ十の鉱石の装入を現状より１ノフチ中心方向へシフ
トを採用する。Based on the above results, a shift of the charging of a0 ore from the current state toward the center of the notch will be adopted as the burden distribution control condition in the actual furnace.
本発明は以上のように、知識工学システムにより炉内半
径方向分布状況を判断し、その時のオンラインデータに
基づいて装入物分布予測モデル計算を複数条件行い、こ
れらの結果から最適装入物分布制御条件を選出すること
により、的確かつ迅速な実炉分布調整アクションが実行
できる。As described above, the present invention uses a knowledge engineering system to judge the distribution situation in the radial direction in the furnace, calculates the burden distribution prediction model under multiple conditions based on the online data at that time, and calculates the optimal burden distribution from these results. By selecting control conditions, accurate and quick actual furnace distribution adjustment actions can be executed.
第１図は、本発明の処理およびデータの流れの説明図、
第２図は、本発明の知識工学システムにおける高炉の情
報から炉内半径方向のガス流分布状況の判断に至るまで
のフロー図、
第３図は、本発明の装入物分布予測モデル計算による複
数条件の計算のフロー図、
第４図は、本発明の装入物分布予測モデル計算結果の出
力例の説明図、
第５図は、本発明の装入物分布予測モデル計算結果の炉
内半径方向ガス流分布′割合をプロットした三角図であ
る。
第２図
周辺ガス流割合
第５図Figure 1 is an explanatory diagram of the processing and data flow of the present invention. Figure 2 is a flow diagram of the knowledge engineering system of the present invention from blast furnace information to determination of the gas flow distribution situation in the radial direction inside the furnace. , FIG. 3 is a flowchart of calculation of multiple conditions by the burden distribution prediction model calculation of the present invention, FIG. 4 is an explanatory diagram of an output example of the calculation result of the burden distribution prediction model of the present invention, The figure is a triangular diagram in which the ratio of the radial gas flow distribution in the furnace is plotted as a result of calculation by the burden distribution prediction model of the present invention. Figure 2 Surrounding gas flow ratio Figure 5
Claims (1)
布状況判断を行うための知識ベースを備えた知識工学シ
ステムにより、高炉炉内半径方向のガス流や装入物の分
布状況を推論し、該分布状況が適正領域から外れている
と判断された場合に、装入物分布予測モデル計算を起動
し、その時の装入原料条件、装入物分布制御条件、操業
条件等のオンラインデータにより計算した炉内半径方向
のガス流及び装入物分布特性の結果をベース条件とし、
該オンラインデータの中で装入物分布制御条件のみを複
数種類変更して計算した各分布特性結果の中で、ベース
条件に対する変化方向及び変化量が、知識工学システム
での推論結果における現状の分布状況を適正領域に戻す
のに最も適する装入物分布制御条件を選出し、該装入物
分布制御条件に従って実炉アクションを実行することを
特徴とする高炉の装入物分布制御方法。1. Infer the distribution of gas flow and charge in the radial direction inside the blast furnace using a knowledge engineering system that is equipped with a knowledge base for determining the distribution of gas flow and charge in the radial direction inside the blast furnace. If it is determined that the distribution situation is outside the appropriate range, the burden distribution prediction model calculation is started and online data such as charging material conditions, burden distribution control conditions, operating conditions, etc. Based on the results of the gas flow and charge distribution characteristics in the radial direction inside the furnace calculated by
Among the distribution characteristic results calculated by changing multiple types of burden distribution control conditions in the online data, the direction and amount of change with respect to the base conditions are determined by the current distribution based on the inference results of the knowledge engineering system. A method for controlling charge distribution in a blast furnace, comprising selecting charge distribution control conditions most suitable for returning the situation to an appropriate range, and executing actual furnace actions in accordance with the charge distribution control conditions.
Priority Applications (10)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP88689A JPH0663009B2 (en) | 1989-01-06 | 1989-01-06 | Blast furnace charge distribution control method |
| EP89313087A EP0375282B1 (en) | 1988-12-20 | 1989-12-14 | Blast furnace operation management method and apparatus |
| US07/450,390 US4976780A (en) | 1988-12-20 | 1989-12-14 | Blast furnace operation management method and apparatus |
| ES89313087T ES2085285T3 (en) | 1988-12-20 | 1989-12-14 | METHOD AND APPARATUS FOR THE MANAGEMENT OF THE OPERATION OF A HIGH OVEN. |
| EP93100520A EP0542717B1 (en) | 1988-12-20 | 1989-12-14 | Blast furnace operation management method and apparatus |
| ES94117502T ES2157233T3 (en) | 1988-12-20 | 1989-12-14 | METHOD AND APPARATUS FOR THE MANAGEMENT OF THE OPERATION OF A HIGH OVEN. |
| ES93100520T ES2097936T3 (en) | 1988-12-20 | 1989-12-14 | METHOD AND APPARATUS FOR CONDUCTING THE OPERATION OF A HIGH OVEN. |
| EP94117502A EP0641863B1 (en) | 1988-12-20 | 1989-12-14 | Blast furnace operation management method and apparatus |
| AU46884/89A AU612531B2 (en) | 1988-12-20 | 1989-12-18 | Blast furnace operation management method and apparatus |
| CN89109414.8A CN1021833C (en) | 1988-12-20 | 1989-12-20 | Blast furnace operation management method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP88689A JPH0663009B2 (en) | 1989-01-06 | 1989-01-06 | Blast furnace charge distribution control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH02182815A true JPH02182815A (en) | 1990-07-17 |
| JPH0663009B2 JPH0663009B2 (en) | 1994-08-17 |
Family
ID=11486158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP88689A Expired - Fee Related JPH0663009B2 (en) | 1988-12-20 | 1989-01-06 | Blast furnace charge distribution control method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0663009B2 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020535566A (en) * | 2017-09-19 | 2020-12-03 | コベストロ・エルエルシー | Technology for custom designing products |
-
1989
- 1989-01-06 JP JP88689A patent/JPH0663009B2/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020535566A (en) * | 2017-09-19 | 2020-12-03 | コベストロ・エルエルシー | Technology for custom designing products |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH0663009B2 (en) | 1994-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11294338B2 (en) | Use of comprehensive artificial intelligence in primary industry plants | |
| EP0542717B1 (en) | Blast furnace operation management method and apparatus | |
| EP0488318A2 (en) | Control method of and apparatus for material charging at top of blast furnace | |
| JP6897723B2 (en) | Learning model generation method, learning model generation device, blast furnace hot metal temperature control method, blast furnace hot metal temperature control guidance method, and hot metal manufacturing method | |
| An et al. | Two-layer fault diagnosis method for blast furnace based on evidence-conflict reduction on multiple time scales | |
| JPH02182815A (en) | Method for controlling distribution of charged material in blast furnace | |
| EP3989013B1 (en) | Method for controlling process, operation guidance method, method for operating blast furnace, method for producing hot metal, and device for controlling process | |
| US4466825A (en) | Process for blast furnace operation | |
| JP5608961B2 (en) | Sintering apparatus and sintering method | |
| JPH0587462A (en) | Burning controller of sintered ore | |
| RU2251721C2 (en) | Intellectual control system | |
| Kronberger et al. | Latest generation sinter process optimization systems | |
| Nistala et al. | Virtual Sinter®: Digital Twin for Integrated Sinter Plants | |
| JP3404231B2 (en) | Melting furnace control device | |
| JPH0445208A (en) | Method for controlling distribution of charged material in blast furnace | |
| JP7380604B2 (en) | Learning model generation method, learning model generation device, blast furnace control guidance method, and hot metal manufacturing method | |
| RU2078141C1 (en) | Method for charging burden material into blast furnace | |
| WO2023189335A1 (en) | Method for managing operation of sintering machine, method for manufacturing sintered ore, and control device | |
| JPH093556A (en) | Method for deciding changing action of operation in sintering machine and device therefor | |
| EP4155421A1 (en) | Method for controlling hot metal temperature, operation guidance method, method for operating blast furnace, method for producing hot metal, device for controlling hot metal temperature, and operation guidance device | |
| JPS62224608A (en) | Operating method for bell-less type blast furnace | |
| JPH05239518A (en) | Method for controlling furnace heat in blast furnace | |
| Angela | A neural network approach to the modeling of blast furnace | |
| Cui et al. | Advanced control method of rotary kiln pellet sintering process based on operation pattern optimization | |
| JPH0625370B2 (en) | Blast furnace feed charge distribution control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080817 Year of fee payment: 14 |
|
| LAPS | Cancellation because of no payment of annual fees |