Multi-objective optimization of rolling schedule based on cost function for tandem cold mill

This paper adopts equal relatively load as objective function, and makes every parameter to meet certain restrictive conditions. SUMT algorithm was used to change constraints to non-binding conditions. QPSO algorithm was applied to optimize objective functions to obtain optimal solution. This algorithm was based on classical particle swarm optimization, which, with the conduct of quantum particle, had effective global search capability, good convergence and stability. As a result, reasonable distribution of tandem cold rolling power and full use of equipment capacity were realized, resulting in the improvement of production efficiency.

Download Full-text

Multi-Objective Optimization of Parameters for Milling Using Evolutionary Algorithms and Artificial Neural Networks

Volume 14: Design, Systems, and Complexity ◽

10.1115/imece2019-11438 ◽

2019 ◽

Author(s):

Amit Banerjee ◽

Issam Abu-Mahfouz ◽

AHM Esfakur Rahman

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Evolutionary Algorithms ◽

Cost Function ◽

Machine Learning Algorithms ◽

Machining Parameters ◽

Multi Objective Optimization ◽

Nsga Ii ◽

Multi Objective ◽

Artificial Neural

Abstract Model-based design of manufacturing processes have been gaining popularity since the advent of machine learning algorithms such as evolutionary algorithms and artificial neural networks (ANN). The problem of selecting the best machining parameters can be cast an optimization problem given a cost function and by utilizing an input-output connectionist framework using as ANNs. In this paper, we present a comparison of various evolutionary algorithms for parameter optimization of an end-milling operation based on a well-known cost function from literature. We propose a modification to the cost function for milling and include an additional objective of minimizing surface roughness and by using NSGA-II, a multi-objective optimization algorithm. We also present comparison of several population-based evolutionary search algorithms such as variants of particle swarm optimization, differential evolution and NSGA-II.

Download Full-text

Heuristic multi-objective optimization for cost function weights selection in finite states model predictive control

2011 Workshop on Predictive Control of Electrical Drives and Power Electronics ◽

10.1109/precede.2011.6078690 ◽

2011 ◽

Cited By ~ 33

Author(s):

Pericle Zanchetta

Keyword(s):

Model Predictive Control ◽

Cost Function ◽

Predictive Control ◽

Multi Objective Optimization ◽

Multi Objective ◽

Finite States

Download Full-text

Robust multi-objective optimization of rolling schedule for tandem cold rolling based on evolutionary direction differential evolution algorithm

Journal of Iron and Steel Research International ◽

10.1016/s1006-706x(17)30119-x ◽

2017 ◽

Vol 24 (8) ◽

pp. 795-802 ◽

Cited By ~ 3

Author(s):

Yong Li ◽

Lei Fang

Keyword(s):

Cold Rolling ◽

Differential Evolution ◽

Differential Evolution Algorithm ◽

Multi Objective Optimization ◽

Rolling Schedule ◽

Multi Objective ◽

Tandem Cold Rolling ◽

Evolution Algorithm

Download Full-text

Multi-objective optimization of rolling schedule for tandem cold strip rolling based on NSGA-II

Journal of Manufacturing Processes ◽

10.1016/j.jmapro.2020.10.061 ◽

2020 ◽

Vol 60 ◽

pp. 257-267

Author(s):

Yu Wang ◽

Changsheng Li ◽

Xin Jin ◽

Yongguang Xiang ◽

Xiaogang Li

Keyword(s):

Multi Objective Optimization ◽

Rolling Schedule ◽

Strip Rolling ◽

Nsga Ii ◽

Multi Objective ◽

Cold Strip Rolling

Download Full-text

Load Distribution Optimization of Tandem Cold Mill Based on Quantum Chaos Multi-Objective Evolutionary Algorithm

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.774-776.1208 ◽

2013 ◽

Vol 774-776 ◽

pp. 1208-1215

Author(s):

Wan Lu Jiang ◽

Sheng Zhang ◽

Jin Na He

Keyword(s):

Evolutionary Algorithm ◽

Load Distribution ◽

Quantum Chaos ◽

Rolling Force ◽

Minimum Energy ◽

Optimization Method ◽

Nsga Ii ◽

Multi Objective ◽

Tandem Cold Mill ◽

Cold Mill

A novel quantum multi-objective evolutionary algorithm is proposed that combine the quantum computing with multi-objective evolutionary algorithm, and the quantum chromosomes is updated with the chaos in order to enhance the optimization capability of the quantum population. To verify the performance of the proposed algorithm, the functions ZDT1 and ZDT2 are optimized by the proposed algorithm and NSGA-II. The results show that the quantum chaos multi-objective evolutionary algorithm has the more powerful capability. The new proposed algorithm is applied to the load distribution optimization of tandem cold mill, and the two-objective function modal is built based on the minimum energy consumption and rolling force equilibrium. Optimizing the modal with the new algorithm, the empirical data and method of weighting, the result of quantum chaos multi-objective evolutionary algorithm is more reasonable. Therefore, the quantum chaos multi-objective evolutionary algorithm is a practicable intelligent optimization method for the load distribution optimization of tandem cold mill.

Download Full-text