Rolling Process Optimization in Metal Forming Systems

Rolling process optimisation in metal forming encompasses a range of strategies designed to enhance product quality, energy efficiency and process reliability in both hot and cold rolling mills. By fine-tuning roll pass schedules, roll geometry and mill settings, engineers can control strip thickness, flatness and surface integrity while minimising material waste and energy consumption. Modern approaches integrate classical mechanical models with data-driven techniques such as artificial neural networks and machine learning, enabling real-time prediction of rolling force, temperature and microstructural evolution. Advances in simulation and finite-element methods have clarified the inheritance of strip crown and flatness across multi-stand tandem mills, supporting more precise shape control. In parallel, optimisation of roll profiles and load distributions through multi-objective algorithms has delivered practical improvements in surface quality and reduction of mill scale. These developments carry global significance for sustainable steel and non-ferrous metal production, reducing carbon footprints and resource usage in large-scale manufacturing.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Research from all publishers

Recent studies have demonstrated the successful application of artificial neural network models to predict thermal shrinkage of seamless steel pipes, using sensitive network architectures to forecast final dimensions immediately after rolling and thereby reduce rejection rates. In the hot-rolling sector, experimental and simulation-based investigations of mill setting schedules have yielded regression models that link process parameters to fuel oil and electricity consumption, mill scale generation and cropping loss, pointing to optimised operational windows that lower energy use and environmental impact. In cold rolling, multi-objective optimisation of intermediate roll profiles via genetic algorithms has been shown to enhance strip flatness quality, balancing crown adjustment range and contact pressure to improve surface uniformity in six-high tandem mills. Together, these works showcase the integration of advanced modelling, statistical analysis and optimisation algorithms to address critical challenges in efficiency, sustainability and product quality.

Rolling Process Optimization in Metal Forming Systems publication trend

The graph below shows the total number of articles in rolling process optimization in metal forming systems across all publications each year (not limited to Nature Index journals).

Technical terms

Hot rolling: Metal forming process carried out at temperatures above recrystallisation, facilitating large deformations with reduced force.

Cold rolling: Metal forming process performed near ambient temperature to achieve fine surface finish and precise dimensional control.

Pass schedule: Sequence of roll reductions and mill settings designed to transform initial stock to target thickness and mechanical properties.

Flatness: Measure of deviation of the rolled strip surface from an ideal plane, critical for downstream processing and end-use performance.

Crown: Transverse thickness profile of a rolled strip, with intentional convexity to counteract roll bending and achieve uniform flatness.

Artificial neural network: Computational framework inspired by biological neurons, used to model complex nonlinear relationships in rolling process predictions.

References

1. Hybrid Model of Mathematical and Neural Network Formulations for Rolling Force and Temperature Prediction in Hot Rolling Processes. IEEE Access (2020).
2. Numerical analysis of the strip crown inheritance in tandem cold rolling by a novel 3D multi-stand FE model. The International Journal of Advanced Manufacturing Technology (2022).
3. Multi-Objective Optimization of Intermediate Roll Profile for a 6-High Cold Rolling Mill. Metals (2020).
4. Investigation and Optimization of Load Distribution for Tandem Cold Steel Strip Rolling Process. Metals (2020).
5. Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture. Results in Engineering (2023).
6. Reduction of energy and fuel consumption in the hot-rolling steel sector. Cleaner Engineering and Technology (2023).