Artificial Neural Networks in Classification of Steel Grades Based on Non-Destructive Tests

被引：28

作者：

Beskopylny, Alexey ^{[1
]}

Lyapin, Alexandr ^{[2
]}

Anysz, Hubert ^{[3
]}

Meskhi, Besarion ^{[4
]}

Veremeenko, Andrey ^{[5
]}

Mozgovoy, Andrey ^{[4
]}

机构：

[1] Don State Tech Univ, Dept Transport Syst, Fac Rd & Transport Syst, Gagarin 1, Rostov Na Donu 344000, Russia

[2] Don State Tech Univ, Fac IT Syst & Technol, Dept Informat Syst Construct, Gagarin 1, Rostov Na Donu 344000, Russia

[3] Warsaw Univ Technol, Fac Civil Engn, Al Armii Ludowej 16, PL-00637 Warsaw, Poland

[4] Don State Tech Univ, Fac Life Safety & Environm Engn, Dept Life Safety & Environm Protect, Gagarin 1, Rostov Na Donu 344000, Russia

[5] Don State Tech Univ, Dept Motor Rd Fac Rd & Transport Syst, Gagarin 1, Rostov Na Donu 344000, Russia

来源：

MATERIALS | 2020年 / 13卷 / 11期

关键词：

non-destructive test; machine learning; clustering; steel; cone indentation; impact; artificial neural networks; INDENTATION; PREDICTION; HARDNESS;

D O I：

10.3390/ma13112445

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

Assessment of the mechanical properties of structural steels characterizing their strength and deformation parameters is an essential problem in the monitoring of structures that have been in operation for quite a long time. The properties of steel can change under the influence of loads, deformations, or temperatures. There is a problem of express determination of the steel grade used in structures-often met in the practice of civil engineering or machinery manufacturing. The article proposes the use of artificial neural networks for the classification and clustering of steel according to strength characteristics. The experimental studies of the mechanical characteristics of various steel grades were carried out, and a special device was developed for conducting tests by shock indentation of a conical indenter. A technique based on a neural network was built. The developed algorithm allows with average accuracy-over 95%-to attribute the results to the corresponding steel grade.

引用

页数：34

共 53 条

[1] Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams
Abambres, Miguel
Rajana, Komal
Tsavdaridis, Konstantinos Daniel
Ribeiro, Tiago Pinto
[J]. COMPUTERS, 2018, 8 (01)
[2] The axisymmetric contact problem of the indentation of a conical punch into a half-space with a coating inhomogeneous in depth
Aizikovich, S. M.
Vasil'ev, A. S.
Volkov, S. S.
[J]. PMM JOURNAL OF APPLIED MATHEMATICS AND MECHANICS, 2015, 79 (05): : 500 - 505
[3] Artificial Neural Network in Fibres Length Prediction for High Precision Control of Cellulose Refining
Almonti, Daniele
Baiocco, Gabriele
Tagliaferri, Vincenzo
Ucciardello, Nadia
[J]. MATERIALS, 2019, 12 (22)
[4] Machine Learning Models for Predicting and Classifying the Tensile Strength of Polymeric Films Fabricated via Different Production Processes
Altarazi, Safwan
Allaf, Rula
Alhindawi, Firas
[J]. MATERIALS, 2019, 12 (09)
[5] [Anonymous], 2019, MATERIALS
[6] [Anonymous], 2012, A95612 ASTM INT
[7] Anysz H., 2017, THESIS
[8] Designing the Composition of Cement Stabilized Rammed Earth Using Artificial Neural Networks
Anysz, Hubert
Narloch, Piotr
[J]. MATERIALS, 2019, 12 (09)
[9] Comparison of ANN Classifier to the Neuro-Fuzzy System for Collusion Detection in the Tender Procedures of Road Construction Sector
Anysz, Hubert
Foremny, Andrzej
Kulejewski, Janusz
[J]. 3RD WORLD MULTIDISCIPLINARY CIVIL ENGINEERING, ARCHITECTURE, URBAN PLANNING SYMPOSIUM (WMCAUS 2018), 2019, 471
[10] The influence of input data standardization method on prediction accuracy of artificial neural networks
Anysz, Hubert
Zbiciak, Artur
Ibadov, Nabi
[J]. XXV POLISH - RUSSIAN - SLOVAK SEMINAR -THEORETICAL FOUNDATION OF CIVIL ENGINEERING, 2016, 153 : 66 - 70

← 1 2 3 4 5 6 →