Prediction of Mechanical Properties of Iron and Steel Based on the Quantile Model of Generalized Radial Basis Neural Network

Tong Tian; Si Yu Huang

doi:10.4028/www.scientific.net/KEM.897.29

Paper Titles

Surface Machining of Stainless Steel Cardiovascular Stents by Fluid Abrasive Machining and Electropolishing
p.3

Laser Surface Polishing of Ti6Al4V Titanium Alloy in Air, Nitrogen and Argon Environments
p.15

Study of Micro-Upsetting by Finite Element Simulation Based on Crystal Plasticity and Grain Boundary Strengthening Theories
p.21

Prediction of Mechanical Properties of Iron and Steel Based on the Quantile Model of Generalized Radial Basis Neural Network
p.29

Aqueous Stability of Cross-Linked Thermal Responsive Tissue Engineering Scaffold Produced by Electrospinning Technique
p.39

Degradation of Virgin and Recycled Polylactic Acid/Eggshell Composites Buried in Soil
p.45

Sustainable Fabrication Technology of Composite Board by Kenaf-Polypropylene for Automobile Door Interior Applications
p.51

A Study of the Effect of Reaction Time on the Preparation of Zirconium Based UiO-66 MOF
p.57

HomeKey Engineering MaterialsKey Engineering Materials Vol. 897Prediction of Mechanical Properties of Iron and...

Prediction of Mechanical Properties of Iron and Steel Based on the Quantile Model of Generalized Radial Basis Neural Network

Abstract:

Hot rolled steel is a material made by heating at high temperature. It has strong plasticity and is used in shipping industry, automobile industry, manufacturing industry, etc. Tensile strength refers to the maximum resistance to uniform plastic deformation of the material. It is an index of the mechanical properties of steel and determines the quality of steel to a certain extent. The influencing factors of tensile strength include steel processing parameters and chemical composition. As an improved model of RBF neural network, the generalized RBF neural network reduces the complexity of the model, improves the generalization ability of the model, and makes its application more extensive. In this paper, a generalized RBF neural network quantile regression model (QR-GRBFNN) is established to predict the mechanical properties of hot rolled strip, the mean percentage error (MAPE) and root mean square error (RMSE) are used as evaluation indexes. Experiments show that the model has better predictive performance.

You might also be interested in these eBooks

Material and Manufacturing Technology XII

View Preview

Info:

Periodical:

Key Engineering Materials (Volume 897)

Pages:

29-35

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.897.29

Citation:

Cite this paper

Online since:

August 2021

Authors:

Tong Tian*, Si Yu Huang

Keywords:

Generalized Radial Basis Neural Network Model, Hot Rolled Strip, Tensile Strength

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Li. W.G, Xie. L, Zhao. Y.T, Li. Z.X and Wang. W.B: Journal of Iron and Steel Research, International Vol. 27 (2020), pp.1045-1053.

Google Scholar

[2] Niu. J.Q and Li. H.L: Engineering Sciences (2013), pp.8-12.

Google Scholar

[3] Liu. Y, Zhu. J.C and Cao. Y: Journal of Iron and Steel Research, International Vol. 24 (2017), pp.1254-1260.

Google Scholar

[4] Zhao. Y.H, Yang. W, Peng. N.Q, Tang. G.B and Liu. Z.D: Journal of Iron and Steel Research, International Vol. 20 (2013), pp.9-15.

Google Scholar

[5] Wu. Y.M and Ren. Y: submitted to International Conference on Information Technology, Computer Engineering and Management Sciences (2003).

Google Scholar

[6] Koenker. R and Bassett. G.W: Econometrica Vol. 46 (1978), pp.33-50.

Google Scholar

[7] Li. H.F, Liu. Y and Luo. Y: Journal of Systems Science and Complexity Vol. 33 (2020), pp.2080-2102.

Google Scholar

[8] Paulino. Pérez-Rodríguez, Osval. A. Montesinos-López, Abelardo Montesinos-López, José Crossa: The Crop Journal Vol. 8 (2020), pp.713-722.

DOI: 10.1016/j.cj.2020.04.009

Google Scholar

[9] Wang. Z.H and Tian. J: submitted to The 2nd information Technology and Mechatronics Engineering Conference (2016).

Google Scholar

[10] Ayodele. B.V, Mustapa. S.I, Witoon. T, Kanthasamy. R, Owabor. C.N: submitted to Topics in Catalysis (2020).

Google Scholar