JPH0743702B2 - Quality diagnosis method - Google Patents
Quality diagnosis methodInfo
- Publication number
- JPH0743702B2 JPH0743702B2 JP26567888A JP26567888A JPH0743702B2 JP H0743702 B2 JPH0743702 B2 JP H0743702B2 JP 26567888 A JP26567888 A JP 26567888A JP 26567888 A JP26567888 A JP 26567888A JP H0743702 B2 JPH0743702 B2 JP H0743702B2
- Authority
- JP
- Japan
- Prior art keywords
- value
- quality
- deduction
- operation data
- quality characteristic
- 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.)
- Expired - Fee Related
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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- General Factory Administration (AREA)
- Control By Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Testing And Monitoring For Control Systems (AREA)
Description
【発明の詳細な説明】 ［産業上の利用分野］ 本発明は、鉄鋼プロセスなどの製造プロセスにおける品
質診断方法に関し、現在の操業状況から品質特性の予測
・評価を迅速に行ない、またその対応をとることにより
品質特性不良の発生を防止するものである。Description: TECHNICAL FIELD The present invention relates to a quality diagnosis method in a manufacturing process such as a steel process, and quickly predicts and evaluates quality characteristics based on the current operating conditions, and responds thereto. By taking this, the occurrence of defective quality characteristics is prevented.
［従来の技術］ 従来、鉄鋼プロセスなどの製造プロセスにおける品質診
断は、品質特性が定量的に数式モデルで予測できるとき
に行なわれてきた。しかしながら、品質特性が定量的に
予測できないこともしばしばある。そのときにもルール
ベース等の知識工学的手法により定性的な、あるいは断
片的な経験則により品質診断システムが開発されてい
る。[Prior Art] Conventionally, quality diagnosis in a manufacturing process such as a steel process has been performed when quality characteristics can be quantitatively predicted by a mathematical model. However, quality characteristics are often not quantitatively predictable. Even at that time, a quality diagnosis system is being developed by a qualitative or fragmentary empirical rule by a knowledge engineering method such as a rule base.
しかしながら、この新しいタイプの品質診断システムに
用いられる品質予測・診断方法には定まった方法が確立
しておらずシステムごとに異なっているのが現状であ
る。However, the method of quality prediction / diagnosis used in this new type of quality diagnosis system has not been established yet, and is different for each system at present.
［発明が解決しようとする課題］ 製造プロセスの専門家の経験則により品質診断をおこな
うとき、その診断方法に定まった方法がない。そのため
個々のシステムで、そのシステムにあった方法を考案し
て実現している。[Problems to be Solved by the Invention] When quality diagnosis is performed based on the empirical rules of manufacturing process experts, there is no fixed method for the diagnosis. Therefore, each system devises and implements a method suitable for that system.
本発明は、経験則による品質診断のひとつの定型的な方
法を提供することにある。The present invention is to provide one routine method of quality diagnosis by empirical rules.
［課題を解決するための手段］ 本発明の品質診断方法は、製造プロセスにおける品質予
測に使用する複数個の操業実績データをその狙い値から
のずれでランク分けすることと、診断する複数個の品質
特性項目ごとに操業データの狙い値からのずれに起因す
る品質特性の減点値を知識ベースで表現した操業データ
のランク値と減点値との関係を用いてもとめることと、
品質特性項目ごとに各減点値を合計してその満点値から
減算することによりその評価値を求めることと、および
操業データ項目ごとに各減点の合計値を求めさらに高い
順に並べかえることにより、各品質特性項目の評点表示
と操業データの操作指示を重要度の順に行なうことから
構成される。[Means for Solving the Problems] A quality diagnosis method of the present invention is to classify a plurality of operation record data used for quality prediction in a manufacturing process according to a deviation from a target value thereof, and to perform a plurality of diagnosis. Using the relationship between the rank value and the deduction value of the operation data that represents the deduction value of the quality characteristic due to the deviation from the target value of the operation data for each quality characteristic item in the knowledge base,
By obtaining the evaluation value by summing the deduction values for each quality characteristic item and subtracting it from the full score value, and obtaining the total value of the deductions for each operation data item, and arranging them in ascending order, It consists of displaying scores of quality characteristic items and operating instructions of operating data in order of importance.
［作用］ 品質予測に使用する複数個の操業実績データがその狙い
値からのずれでランク分けされ、知識ベースで表現され
たランク値と減点値の関係から品質特性項目ごとに各操
業データの減点値が求められ、それらの合計と満点値か
らの減算でその品質特性の評価値が求められ出力され
る。また操業データ項目ごとに各減点値の合計を求めそ
の高い順に操業データの操作指示が出力される。[Operation] A plurality of operation record data used for quality prediction are ranked according to the deviation from the target value, and the points of each operation data are deducted for each quality characteristic item from the relationship between the rank value and deduction value expressed in the knowledge base. A value is obtained, and an evaluation value of the quality characteristic is obtained and output by subtracting the sum and the full-scale value. Further, the total of the deduction values is calculated for each operation data item, and the operation instruction of the operation data is output in the descending order.
［実施例］ 次に本発明の実施例について図面を参照して説明する。[Embodiment] Next, an embodiment of the present invention will be described with reference to the drawings.
実施例では、方向性電磁鋼板の被膜特性に関する品質診
断について説明する。被膜の品質診断は、脱炭ラインの
操業実績データを基に専門家の経験則によって行なわ
れ、その被膜の実績は、約10日後に得られる。そのた
め、その間の被膜不良発生が、この品質診断によって防
止される。In the examples, quality diagnosis regarding coating characteristics of grain-oriented electrical steel sheets will be described. The quality of the coating is diagnosed by the expert's empirical rule based on the operation result data of the decarburization line, and the performance of the coating is obtained after about 10 days. Therefore, the occurrence of coating defects during that time is prevented by this quality diagnosis.
第１図は、この被膜診断の実現したシステム構成を示
す。操業実績データを入力して知識ベースの知識を用い
て推論エンジンで品質を評価する。評価値等は、品質診
断結果の表示としてわかりやすく出力される。FIG. 1 shows the system configuration realized by this film diagnosis. Input the operation result data and use the knowledge of the knowledge base to evaluate the quality with the inference engine. The evaluation value and the like are output in an easy-to-understand manner as a display of quality diagnosis results.
第２図に、この被膜品質診断方法の全体流れ図を示す。FIG. 2 shows an overall flow chart of this coating quality diagnosis method.
同図の１は、脱炭ラインの操業実績データをその狙い値
からのずれでランク分けしている。このランク分けの各
範囲は、鋼種規格ごとに与えられる。In FIG. 1, 1 is the rank of the operation result data of the decarburization line, which is deviated from the target value. Each range of this rank classification is given for each steel grade standard.
第３図は、被膜予測用の知識を示す。10個の操業データ
が、狙い値からのずれによって、最大７ランクまでに層
別される。FIG. 3 shows the knowledge for film prediction. 10 operation data are classified into up to 7 ranks depending on the deviation from the target value.
第４図に、このランク分けのコーディング例を示す。FIG. 4 shows a coding example of this rank division.
鋼温１は、操業実績データのNo.5の鋼帯温度で、IF−th
en方式のルールベースでランク分けされる。Steel temperature 1 is the steel strip temperature of No. 5 in the operation result data, and IF-th
It is ranked according to the en-based rule base.
第２図の２は、診断する被膜品質特性項目ごとに減点値
を計算する。その詳しい考え方を先の第３図を用いて説
明する。In 2 of FIG. 2, a deduction value is calculated for each film quality characteristic item to be diagnosed. The detailed idea will be described with reference to FIG.
大きくは、被膜品質特性として過酸化疵、酸化不足、脱
炭異常等を評価する。この第３図は、過酸化疵Ａについ
ての評点予測知識を示しており、この品質不良の発生す
る操業パターンを太線で示している。この品質特性は80
点満点で評価され最も大きいずれパターンを示すときに
は40点という予測評点となる。Roughly speaking, peroxide defects, insufficient oxidation, abnormal decarburization, etc. are evaluated as film quality characteristics. This FIG. 3 shows the score prediction knowledge about the peroxide flaw A, and the operation pattern in which the quality defect occurs is indicated by a thick line. This quality characteristic is 80
When the mark is evaluated on a perfect scale and the pattern shows the largest one, the predicted score is 40 points.
また各操業データの不良化寄与率を70％,5％,10％，…
と与えている。In addition, the contribution ratio of failure of each operation data is 70%, 5%, 10%, ...
Is given.
この知識を用いて、各操業データの狙い値からのずれ
（ランク値）が品質特性の評点にどのくらい減点になっ
ているか求めることができる。Using this knowledge, it is possible to determine how much the deviation (rank value) from the target value of each operation data is deducted from the quality characteristic score.
例えば、操業実績データのNo.2の実績がランク６であれ
ば、この部分の狙い値のずれに起因する評価値の減点値
は、（80-40）×70/100＝28点と計算される。ランク６
よりも小さいずれについては、０〜1.0までの乗算係数
が、指定された関数で計算され、その値が減点値に乗算
される。先の例でランクが５であれば、28点×log4３＝
22.2が減点値となる。For example, if the No. 2 result of the operation result data is rank 6, the deduction value of the evaluation value due to the deviation of the target value of this part is calculated as (80-40) × 70/100 = 28 points. It Rank 6
For any smaller value, the multiplication coefficient from 0 to 1.0 is calculated by the specified function, and that value is multiplied by the deduction value. If the rank is 5 in the above example, 28 points x log 4 3 =
22.2 is the deduction value.
乗算係数は、実際の現像に対応して、第１表に示す関数
から選択することにしており、この場合計算式番４を用
いている。The multiplication coefficient is selected from the functions shown in Table 1 according to the actual development, and in this case, the calculation formula number 4 is used.
このようにして一つの被膜品質特性に対する操業実績デ
ータの狙い値からのずれに起因する減点値が求められ
る。 In this way, the deduction value due to the deviation from the target value of the operation result data for one coating quality characteristic is obtained.
他の被膜品質特性についても同様の予測知識より求めら
れる。Other coating quality characteristics can be obtained from similar predictive knowledge.
第２図にもどって、３は、被膜品質特性項目ごとに操業
実績データの減点値を合計計算し、それぞれの満点値か
らその合計値を減算する。他方、第２図の４は、操業デ
ータ項目ごとに、各被膜品質特性項目に対する減点値を
計算する。Returning to FIG. 2, in 3, the deduction values of the operation performance data are totaled for each film quality characteristic item, and the total value is subtracted from each full score value. On the other hand, 4 in FIG. 2 calculates a deduction value for each coating quality characteristic item for each operation data item.
第５図は、第２図の3,4の計算の１例を示したものであ
る。縦方向は被膜品質特性項目を表わし、横方向は操業
データ項目を示す。表の中の値は、被膜品質特性項目に
対する操業実績データの減点値である。その合計値が右
側に示される。また操業データ項目ごとに減点値の合計
が下欄に示される。この値が大きいものほど、品質特性
を改善するために重要であるので、操業データの操作指
示の際は、この大きい操業データ項目から列挙してい
る。FIG. 5 shows an example of the calculations 3 and 4 in FIG. The vertical direction represents coating quality characteristic items, and the horizontal direction represents operation data items. The values in the table are the deduction points of the operation result data for the coating quality characteristic items. The total value is shown on the right. In addition, the total of deduction points for each operation data item is shown in the lower column. The larger this value is, the more important it is to improve the quality characteristics. Therefore, in the operation instruction of the operation data, the operation data items are listed from the larger operation data item.
第６図は、被膜品質診断結果の表示例を示す。各被膜品
質特性の評点が棒グラフで示され、また重要度の高い順
に操作指示すべき操業データ項目が列挙されている。FIG. 6 shows a display example of the coating quality diagnosis result. The rating of each coating quality characteristic is shown by a bar graph, and the operation data items to be instructed by operation are listed in descending order of importance.
第７図は、操作指示の表示例で、操作すべき操業データ
とタッチ方式で指定すると数頁にわたって、チェック項
目や操作方法がわかりやすく説明される。FIG. 7 is a display example of the operation instruction, and when the operation data to be operated and the touch method are designated, the check items and the operation method are explained easily over several pages.
［発明の効果］ 以上説明したように、本発明によれば、製造プロセス等
の品質診断を行うときに、専門家の経験則を定型的なや
り方で診断することが可能となった。[Effects of the Invention] As described above, according to the present invention, it becomes possible to diagnose the expert's empirical rule in a routine manner when performing quality diagnosis of a manufacturing process or the like.
そのため同種の品質診断システムを構築することが効率
的になる。また本発明を用いて品質診断を行なうことに
よって、品質不良の発生を防止することができ、製造プ
ロセスの品質向上のうえにも大きな効果がある。Therefore, it becomes efficient to build a quality diagnosis system of the same type. Further, by performing quality diagnosis using the present invention, it is possible to prevent the occurrence of quality defects, and it is very effective in improving the quality of the manufacturing process.
第１図は、本発明の一実施例のシステム構成を示す図、
第２図は、本発明の一実施例の被膜品質診断方法の全体
流れ図、第３図は、本発明の一実施例の被膜予測用知識
を示す図、第４図は、本発明の一実施例のランク分けの
コーディング例を示す図、第５図は、本発明の一実施例
の減点予測値と合計値を示す図、第６図は、本発明の一
実施例の被膜品質診断結果の表示例を示す図、第７図
は、本発明の一実施例の表示例を示す図である、 １……操業実績データの狙い値からのずれによるランク
分け ２……品質特性項目ごとの操業実績データ減点値計算 ３……品質特性評価値計算 ４……操業データの操作指示順位計算FIG. 1 is a diagram showing a system configuration of an embodiment of the present invention,
FIG. 2 is an overall flow chart of the coating quality diagnosing method of one embodiment of the present invention, FIG. 3 is a diagram showing knowledge for coating prediction of one embodiment of the present invention, and FIG. 4 is one implementation of the present invention. FIG. 5 is a diagram showing a coding example of rank classification of an example, FIG. 5 is a diagram showing a deduction point predicted value and a total value of one embodiment of the present invention, and FIG. FIG. 7 is a diagram showing a display example, and FIG. 7 is a diagram showing a display example of an embodiment of the present invention: 1 ... Rank classification according to deviation of operation result data from a target value 2 ... Operation for each quality characteristic item Actual data deduction value calculation 3 …… Quality characteristic evaluation value calculation 4 …… Operation instruction order calculation of operation data
───────────────────────────────────────────────────── フロントページの続き (51)Int.Cl.6 識別記号 庁内整理番号 ＦＩ 技術表示箇所 Ｇ０５Ｂ 23/02 Ｔ 7618−3Ｈ ３０２ Ｙ 7618−3Ｈ ─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. 6 Identification code Internal reference number FI Technical display location G05B 23/02 T 7618-3H 302 Y 7618-3H
Claims (1)
る複数個の操業実績データをその狙い値からのずれでラ
ンク分けすることと、診断する複数個の品質特性項目ご
とに操業データの狙い値からのずれに起因する品質特性
の減点値を知識ベースで表現した操業データのランク値
と減点値との関係を用いて求めることと、品質特性項目
ごとに各減点値を合計してその満点値から減算すること
によりその評価値をもとめること、および操業データ項
目ごとに各減点の合計値を求めさらに高い順に並べかえ
ることにより、各品質特性項目の評点表示と操業データ
の操作指示を重要度の順に行なうことを特徴とする品質
診断方法。1. In a manufacturing process, a plurality of operation record data used for quality prediction are ranked according to deviations from the target value, and a plurality of quality characteristic items to be diagnosed from the target value of the operation data. The deduction value of the quality characteristic due to the deviation of is calculated using the relationship between the rank value of the operation data and the deduction value expressed in the knowledge base, and each deduction value for each quality characteristic item is totaled and By obtaining the evaluation value by subtraction, and obtaining the total value of each deduction for each operation data item and rearranging in order from the higher, the score display of each quality characteristic item and the operation data operation instruction are in order of importance. A quality diagnostic method characterized by performing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP26567888A JPH0743702B2 (en) | 1988-10-21 | 1988-10-21 | Quality diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP26567888A JPH0743702B2 (en) | 1988-10-21 | 1988-10-21 | Quality diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH02112063A JPH02112063A (en) | 1990-04-24 |
| JPH0743702B2 true JPH0743702B2 (en) | 1995-05-15 |
Family
ID=17420481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP26567888A Expired - Fee Related JPH0743702B2 (en) | 1988-10-21 | 1988-10-21 | Quality diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0743702B2 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103267834A (en) * | 2013-05-19 | 2013-08-28 | 山东出入境检验检疫局检验检疫技术中心 | Comprehensive detection and evaluation system and method for casting tin-lead solder product quality |
| WO2023233927A1 (en) * | 2022-06-03 | 2023-12-07 | オムロン株式会社 | Abnormality detection device, abnormality detection method, and program |
| WO2025243573A1 (en) * | 2024-05-24 | 2025-11-27 | Ｊｆｅスチール株式会社 | Manufacturing condition determination method, metal material manufacturing method, and manufacturing condition determination device |
-
1988
- 1988-10-21 JP JP26567888A patent/JPH0743702B2/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103267834A (en) * | 2013-05-19 | 2013-08-28 | 山东出入境检验检疫局检验检疫技术中心 | Comprehensive detection and evaluation system and method for casting tin-lead solder product quality |
| WO2023233927A1 (en) * | 2022-06-03 | 2023-12-07 | オムロン株式会社 | Abnormality detection device, abnormality detection method, and program |
| WO2025243573A1 (en) * | 2024-05-24 | 2025-11-27 | Ｊｆｅスチール株式会社 | Manufacturing condition determination method, metal material manufacturing method, and manufacturing condition determination device |
| JP7819816B1 (en) * | 2024-05-24 | 2026-02-25 | Ｊｆｅスチール株式会社 | Manufacturing condition determination method, manufacturing method of metal material, and manufacturing condition determination device |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH02112063A (en) | 1990-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bainbridge | The process controller | |
| CN110785717A (en) | Abnormal state diagnostic device and abnormal state diagnostic method for process | |
| CN109270921A (en) | A kind of method for diagnosing faults and device | |
| CN119273185A (en) | A diagnostic assessment method for military equipment maintenance and support equipment | |
| JPH0743702B2 (en) | Quality diagnosis method | |
| JP3631118B2 (en) | Plant diagnostic equipment | |
| JPH0750492B2 (en) | Quality diagnosis knowledge correction method | |
| JP2758976B2 (en) | Characteristic change prediction method and system | |
| CN113610308A (en) | Safety stock forecast method based on remaining life forecast | |
| CN118013426A (en) | Optimization method, system, electronic equipment and medium for causal effect of inclusion in steel products | |
| Yadav et al. | Forecasting time-between-failures of software using fuzzy time series approach | |
| Ananda et al. | K-Nearest Neighbor Algorithm and Case Base Reasoning on Xenia Car Damage Detection Expert System | |
| JPH0750491B2 (en) | Quality diagnosis knowledge adjustment method | |
| JPH0743352A (en) | Learning type abnormality diagnosis algorithm automatic construction method and apparatus | |
| JP2645017B2 (en) | Plant diagnostic method and apparatus | |
| JPH06262223A (en) | Prediction method of power consumption in rolling mill | |
| CN116956646B (en) | Reliability analysis method and device for numerical control machine tool, computer equipment and storage medium | |
| Anjou et al. | A computer system for occupational health epidemiology | |
| JP2724364B2 (en) | Blast furnace operation method | |
| Nguyen et al. | Prioritizing automated test cases of Web applications using reinforcement learning: an enhancement | |
| JPH0310116A (en) | Correcting method for process diagnostic knowledge | |
| JP3231860B2 (en) | Fault diagnosis device using neural network | |
| JPH0575969B2 (en) | ||
| JPH0663791B2 (en) | Process diagnosis method | |
| JPH01237494A (en) | Preventive maintenance target selection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| LAPS | Cancellation because of no payment of annual fees |