![](/images/graphics-bg.png)
Modeling of ladle metallurgical treatment using neural networks
Joint Authors
Boucherit, M. S.
Bouhouche, S.
Lahreche, M.
Bast, J.
Source
The Arabian Journal for Science and Engineering. Section B, Engineering
Issue
Vol. 29, Issue 1B (30 Apr. 2004), pp.65-81, 17 p.
Publisher
King Fahd University of Petroleum and Minerals
Publication Date
2004-04-30
Country of Publication
Saudi Arabia
No. of Pages
17
Main Subjects
Mechanical Engineering
Information Technology and Computer Science
Topics
Abstract AR
تعتمد النماذج الرياضية المستعملة في محطة تكرير الصلب السائل في صناعة الحديد و الصلب على التفاعلات الكيماوية, و تعتبر هذه الطريقة في بعض الأحيان غير كافية لذا سوف نتطرق في هذا البحث إلى استعمال طرق فعالة كطريقة الشبكة العصبية الاصطناعية, بحيث تشمل مدخلات نموذج الشبكة : المواد المستعملة, الطاقة.
و تتكون مخرجات النموذج من التركيبة الكيماوية و درجة حرارة الصلب السائل.
و قد استخدمنا هذا النموذج لاستقراء بارميترات العمليات النهائية و من تم تقييم كفاءة النموذج من خلال المدخلات و المخرجات.
و تمكننا من خلال هذه النمذجة تخفيض كلفة و إدارة الإنتاج.
Abstract EN
In the steel industry, the refining process achieves the final chemical composition and temperature of liquid steel by adjusting the optimal quantity of additives and energy.
Generally a conventional charge calculation based on mathematical and thermodynamic models that provides considerable help is used, but it is difficult to model the highly complex nature of the interaction between process variables such as thermal losses and the dynamics of non-linear chemical reactions.
Neural networks are able to identify internal relationships through training examples.
In this work, an application of identification models using a linear approach and neural networks to predict the final chemical composition and temperature for the refining process is considered.
Using an industrial process data base, the dynamics of complex reactions are modeled using the back propagation learning algorithm.
This model is used as a charge calculation to predict the final process parameters.
The performance of the model is evaluated from new inputs and outputs.
Production and quality cost management is reduced by an optimal control of the input variables such as the weights of additives (FeMn , FeSi, and coke) and heating temperature (T).
American Psychological Association (APA)
Bouhouche, S.& Lahreche, M.& Boucherit, M. S.& Bast, J.. 2004. Modeling of ladle metallurgical treatment using neural networks. The Arabian Journal for Science and Engineering. Section B, Engineering،Vol. 29, no. 1B, pp.65-81.
https://search.emarefa.net/detail/BIM-360073
Modern Language Association (MLA)
Bouhouche, S.…[et al.]. Modeling of ladle metallurgical treatment using neural networks. The Arabian Journal for Science and Engineering. Section B, Engineering Vol. 29, no. 1B (Apr. 2004), pp.65-81.
https://search.emarefa.net/detail/BIM-360073
American Medical Association (AMA)
Bouhouche, S.& Lahreche, M.& Boucherit, M. S.& Bast, J.. Modeling of ladle metallurgical treatment using neural networks. The Arabian Journal for Science and Engineering. Section B, Engineering. 2004. Vol. 29, no. 1B, pp.65-81.
https://search.emarefa.net/detail/BIM-360073
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 80-81
Record ID
BIM-360073