Application of genetic algorithms to optimization of rolling schedules based on damage mechanics

Poursina, Mehrdad; Dehkordi, Noushin Torabian; Fattahi, Amin; Mirmohammadi, Hadi

doi:10.1016/j.simpat.2011.11.005

Cited by 22 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a RPOD for multi-pass rolling systems is a typical multiobjective-multi-constraint problem with the considerations of energy, design and cost efficiency, products quality and productivity, as well as the large number of design and process constraints imposed. Literature review indicates that GA is of great benefit to the handling of hybrid multi-objective-multi-constraint problems, due to its evolutionary nature, efficient parallel processing, independent on Pareto front, flexibility and ease to be conducted [22,24,25]. Thus, conventional GA is improved for the RPOD operations in this research.…”

Section: Theoretical Background and Frameworkmentioning

confidence: 99%

“…While in a study of hot strip rolling, Bagheripoor and Bisadi introduced an artificial neural network (ANN) for the prediction of rolling force and torque [19]. These approaches possess significant strength in computeraided design using empirical data and rules, as well as design and operational experience integrated as expert knowledge [20][21][22]. Moreover, the flexibility and efficiency of RPD can also be enhanced with the engagement of those expert systems [9,23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Energy Efficient Shape Rolling: Roll Pass Optimal Design and Case Studies

Huang

et al. 2019

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Shape rolling is widely employed in the production of long workpieces with appropriate cross-section profiles for other industrial applications. In the development of shape rolling systems, roll pass design (RPD) plays an essential role on the quality control of products, service life of rolls, productivity of rolling systems, as well as energy consumption of rolling operations. This study attempts to establish a generic strategy based on hybrid modeling and an improved genetic algorithm, to support the optimizations of RPD and shape rolling operations at a systematic perspective. Objectives include improving the quality and efficiency of RPD, reducing energy consumption of shape rolling, as well as releasing the demands on costly trails and expert knowledge in RPD. Hybrid modeling based on cross-disciplinary knowledge is developed to overcome the limitations of isolated single-disciplinary models. And conventional genetic algorithm is improved for the implementation of optimal design. Targeting to integrate empirical data and published reliable solutions into optimizations, a parameters estimation method is proposed to transfer the initially misaligned models into a uniform pattern. A tool based on the Matlab platform is developed to demonstrate the optimal design operations, with case studies involved to validate the proposed methodology.

show abstract

Section: Theoretical Background and Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards Energy Efficient Shape Rolling: Roll Pass Optimal Design and Case Studies

Huang

et al. 2019

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

show abstract

“…Compared with the rolling schedule optimized by empirical formula, the proposed method can well balance the rolling force and rolling power simultaneously. Poursina et al integrated power distribution cost, tension cost function, perfect shape condition into one cost function in [4]. They used the genetic algorithm to optimize the cost function and achieved a good result.…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Optimization of Rolling Schedule for Five-Stand Tandem Cold Mill

Wang

Yin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The optimization of rolling schedule is the main content of tandem cold rolling which will affect the quality of products directly. A rolling schedule with the objectives of minimum energy consumption, relative power margin and slippage preventing is established. First, in order to make the rolling schedule more accurate in the calculation process, a mathematical model combines with deep neural network is proposed to calculate the rolling force. Second, a multi-objective particle swarm optimizer with dynamic opposition-based learning is proposed to optimize the rolling schedule. It has a new particle learning strategy to update the moving position of particles. Moreover, opposition-based learning is proposed to make the particles jump out of local optima. Finally, the experiments are carried out based on the field data. Simulation results demonstrate that the accuracy of the rolling force is greatly improved. The proposed algorithm has a promising performance on both diversity and convergence. At the same time, the optimized rolling schedule can well balance the rolling power and prevent slipping between five stands comparing with the original rolling schedule. INDEX TERMS Multi-objective optimization, tandem cold rolling, deep neural network, rolling force, rolling schedule.

show abstract

“…The commonly used rolling schedule optimization algorithms consist of genetic algorithm, particle swarm optimization algorithm and penalty function method, etc. which can overcome the shortcomings of traditional methods (Yang et al, 2008;Poursina et al, 2012;Oduguwa et al, 2003;Duenas and Petrovic, 2008;Bath et al, 2004;Dhillon and Kothari, 2000;Qi et al, 2012;Hu et al, 2006;Pires et al, 2006;Gomes, 2016). Therefore, the objective function optimization method is the development trend of rolling schedule calculation.…”

Section: Introductionmentioning

confidence: 99%

Application of case-based reasoning-Tabu search hybrid algorithm for rolling schedule optimization in tandem cold rolling

Yan

Zhang

2018

View full text Add to dashboard Cite

Purpose The purpose of this study is to improve the global optimization ability of the Tabu search (TS) algorithm, and then improve the calculation efficiency and accuracy of rolling schedule in tandem cold rolling. Design/methodology/approach A case-based reasoning–Tabu search hybrid algorithm (CBRTS) has been presented. First, the case-based reasoning technology was adopted to obtain high-quality initial solution and then the TS algorithm was used for global optimization. Findings The optimization effect of CBRTS is compared with that of the traditional TS algorithm, and the analysis result indicates that the CBRTS has a faster convergence rate than TS, and the optimization results are closer to the global optimal. Meanwhile, the rolling schedule calculated by CBRTS is more reasonable, which can increase the production efficiency while giving full play to the capacity of equipment. Originality/value A CBRTS hybrid algorithm is presented. The strong dependence of the TS algorithm on the initial solution has been solved. The rolling schedule multi-objective optimization functions are established. The proposed algorithm is applied in a 1,450-mm tandem cold rolling production line. The improved method can reduce about half the iterations compared with the traditional one.

show abstract

Application of genetic algorithms to optimization of rolling schedules based on damage mechanics

Cited by 22 publications

References 15 publications

Towards Energy Efficient Shape Rolling: Roll Pass Optimal Design and Case Studies

Towards Energy Efficient Shape Rolling: Roll Pass Optimal Design and Case Studies

Multi-Objective Optimization of Rolling Schedule for Five-Stand Tandem Cold Mill

Application of case-based reasoning-Tabu search hybrid algorithm for rolling schedule optimization in tandem cold rolling

Contact Info

Product

Resources

About