Advanced automatic pass schedule design for hot rolling by coupling reinforcement learning with a fast rolling model

نویسندگان

چکیده

Abstract. Rolling is a well-established forming process for producing finished or semi-finished products in various industries. Although highly automated, most rolling processes are designed manually by experts based on their knowledge, specialized heuristics and analytical models numerical simulations. This manual design approach does not lead to an optimization accounting multiple objectives. Previous work [1] has shown the potential of coupling reinforcement learning (RL) with fast (FRM) optimize hot processes. However, pass schedules do robustly reach desired final height within typical industrial tolerances. Therefore, this paper existing RL FRM extended dynamically ranges reductions. extension guarantees that target always reached exactly. In addition reduction, algorithm can determine inter-pass time, initial slab temperature velocity. For optimization, objective function, called reward considering all relevant objectives such as grain size energy consumption, was developed. An exemplary training performed defined starting (140 mm) (25 mm). The resulting, automatically fulfill including required average austenite size.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Roll Wear Prediction Model in Hot Plate Rolling

In this paper, the wear of work roll in hot plate rolling is introduced and the parameters affecting wear mechanisms in hot strip mill are investigated. In addition, different wear mechanisms in hot rolling and the differences between these mechanisms in different stands are explained. Using the finite element method and the rolling equations, a work roll wear model is proposed. Wear is modeled...

متن کامل

Numerical Simulation in Roll Pass Design for Bar Rolling

S. A. Aksenov, E. N. Chumachenko, I. V. Logashina, Higher School of Economics, Department of Mechanics and Mathematical Simulation, Moscow, Russia T. Kubina, VŠB – Technical University of Ostrava, Faculty of Metallurgy and Materials Engineering, Ostrava, Czech Republic The application of finite element simulation to the problem of roll pass design for round bar rolling is considered. Two roll p...

متن کامل

Magnificent Grain Refinement of Al-Mg2Si Composite by Hot Rolling

The effect of chemical composition and the hot rolling operations on the microstructure and mechanical properties of in situ aluminum matrix composite with Mg2Si phase as the reinforcement was studied. It was revealed that the modification by phosphorous results in the rounder (more spherical) primary and secondary (eutectic) magnesium silicide intermetallics. During hot rolling, the primary pa...

متن کامل

Time-Frequency Analysis of Hot Rolling Using Manifold Learning

In this paper, we propose a method to compare and visualize spectrograms in a low dimensional space using manifold learning. This approach is divided in two steps: a data processing and dimensionality reduction stage and a feature extraction and a visualization stage. The procedure is applied on different types of data from a hot rolling process, with the aim to detect chatter. Results obtained...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Materials research proceedings

سال: 2023

ISSN: ['2474-3941', '2474-395X']

DOI: https://doi.org/10.21741/9781644902479-65