J 2023

Comparison of Linear Regression and Artificial Neural Network Models for the Dimensional Control of the Welded Stamped Steel Arms

KADNÁR, Milan, Peter KÁČER, Marta HARNIČÁROVÁ, Jan VALÍČEK, František TÓTH et. al.

Basic information

Original name

Comparison of Linear Regression and Artificial Neural Network Models for the Dimensional Control of the Welded Stamped Steel Arms

Authors

KADNÁR, Milan (guarantor), Peter KÁČER, Marta HARNIČÁROVÁ (203 Czech Republic, belonging to the institution), Jan VALÍČEK (203 Czech Republic, belonging to the institution), František TÓTH, Marián BUJNA, Milena KUŠNEROVÁ (203 Czech Republic, belonging to the institution), Rastislav MIKUŠ and Marian BORŽAN

Edition

Mathematical machines and systems, Ukrajina, Institute of Mathematical Machines and Systems of the NAS of Ukraine, 2023, 1028-9763

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

20501 Materials engineering

Country of publisher

Ukraine

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

RIV identification code

RIV/75081431:_____/23:00002544

Organization unit

Institute of Technology and Business in České Budějovice

UT WoS

000958805200001

Keywords in English

welding; distortion; stamping; model; prediction; neural network

Tags

Změněno: 26/4/2023 12:31, Barbora Kroupová

Abstract

V originále

The production of parts by pressing and subsequent welding is commonly used in the automotive industry. The disadvantage of this method of production is that inaccuracies arising during pressing significantly affect the final dimension of the part. However, this can be corrected by the choice of the technological parameters of the following operation—welding. Suitably designed parameters make it possible to partially eliminate inaccuracies arising during pressing and thus increase the overall applicability of this technology. The paper is focused on the upper arm geometry of a car produced in this manner. There have been two neural networks proposed in which the optimal welding parameters are determined based on the stamped dimensions and the desired final dimensions. The Levenberg–Marquardt back-propagation algorithm and the Bayesian regularised back-propagation algorithm were used as the learning algorithm for ANNs in multi-layer feed-forward networks. The outputs obtained from the neural networks were compared with a linear prediction model based on a on the design of experiment methodology. The mean absolute percentage error of the linear regression model on the entire dataset was 3 × 10−3%. A neural network with Levenberg–Marquardt back-propagation learning algorithm had a mean absolute percentage error of 4 × 10−3. Similarly, a neural network with a Bayesian regularised back-propagation learning algorithm had a mean absolute percentage error of 3 × 10−3%.