Representation and control of the cold rolling process through artificial neural networks via sensitivity factors

Zárate, Luis Enrique; Bittencout, F.R.

doi:10.1016/j.jmatprotec.2007.06.063

Cited by 27 publications

(10 citation statements)

References 24 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is an amazing achievement that models like these are now used for the on-line control and automation of entire rolling mills [68][69][70][71].…”

Section: Expression Of Data and Control Algorithmsmentioning

confidence: 99%

Neural Networks and Information in Materials Science

Bhadeshia

2009

Statistical Analysis

View full text Add to dashboard Cite

Abstract:Neural networks have pervaded all aspects of materials science resulting in the discovery of new phenomena and have been used in quantitative design and control. At the same time, they have introduced a culture in which both noise and modeling uncertainties are considered in order to realize the value of empirical modeling. This review deals with all of these aspects using concrete examples to highlight the progress made, whilst at the same time emphasizing the limitations of the method. 

show abstract

“…It is an amazing achievement that models like these are now used for the on-line control and automation of entire rolling mills [68][69][70][71].…”

Section: Expression Of Data and Control Algorithmsmentioning

confidence: 99%

Neural Networks and Information in Materials Science

Bhadeshia

2009

Statistical Analysis

View full text Add to dashboard Cite

show abstract

“…The optimum selection of process conditions is an extremely important issue as these determine surface quality of the manufactured components [11][12][13]. The mathematical modelling of the process involves several parameters that may lead to difficult analytical solution [14], [15]. On the other hand, use of artificial intelligence for evaluation of experiments results has its merits mainly because of faster and more reliable creation of prediction model for the studied process, compared to classic statistical methods [16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Untitled

2017

Teh. vjesn.

View full text Add to dashboard Cite

Original scientific paper The paper deals with the comparison of usage of three basic types of neural units in order to create the most suitable model predicting determining the final thickness of the alumina layer formed at surface with current density of 1 A•dm −2 . In addition, the reliability of obtained prediction models, depending on the amount of training data, has been monitored. With properly selected range of training data it is possible to create prediction models with reliability greater than 95 % with achieved toleration 2×10 −6 mm. Keywords: anodizing; neural unit; prediction modelUsporedba primjene raznih neuralnih struktura u predviđanju debljine sloja anodnog aluminij oksida Izvorni znanstveni članak Rad se bavi usporedbom uporabe triju osnovnih vrsta neuralnih jedinica u cilju stvaranja najprikladnijeg modela koji predviđa utvrđivanje konačne debljine sloja aluminijeva oksida koji nastaje na površini uz gustoću struje od 1 A•dm −2 . Osim toga, prati se pouzdanost dobivenih modela predviđanja, ovisno o količini podataka za vježbu. Uz pravilno odabrani raspon podataka za vježbu moguće je stvoriti modele predviđanja s pouzdanošću većom od 95 % s postignutom tolerancijom 2×10 −6 mm.

show abstract

“…It was also used for transient property simulation of continuous rolling mills such as transient rolling characteristics [6] and control system performance [7]. And the interactions between interstand tension and thickness control [8], steady-state characteristic [9], and process sensitivity [10,11] of the transient processes were obtained as well.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Startup Process and Its Optimization for a Two-Stand Reversible Cold Rolling Mill

Liu

Huang

et al. 2017

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Dynamic characteristic analysis of a two-stand reversible cold rolling mill in the startup process was carried out. The delay algorithm of the interstand thickness was proposed. A new method combined with the accelerated secant and the tangent methods was established to solve the simultaneous equations. The thickness and interstand tension transition processes with different static tension establishing processes were analyzed. Both mills were operated under constant rolling force control mode in the above process. The results show that the strip thickness in the rolling gap reduces in the static mill screwdown process. The entry stand runs inversely to establish the static interstand tension. This area becomes an abnormal thickness reduction area of the incoming strip. It results in several abnormal interstand tension increases in the subsequent startup process. The tension increase leads to an impact force on the strip that is the main reason of the strip breakage in the startup process. So the static tension establishing process was optimized, and the interstand tension fluctuation and the strip breakage accidents both reduced significantly. The results are beneficial to the startup process of the two-stand reversible cold rolling mill.

show abstract

Representation and control of the cold rolling process through artificial neural networks via sensitivity factors

Cited by 27 publications

References 24 publications

Neural Networks and Information in Materials Science

Neural Networks and Information in Materials Science

Untitled

Analysis of Startup Process and Its Optimization for a Two-Stand Reversible Cold Rolling Mill

Contact Info

Product

Resources

About