Image processing and neural network technique for size characterization of gravel particles

被引:0
作者
Hassan, Rana [1 ]
Onyelowe, Kennedy C. [2 ,3 ]
Zamel, Amr A. [4 ]
机构
[1] Zagazig Univ, Fac Engn, Struct Engn Dept, Zagazig 44519, Egypt
[2] Michael Okpara Univ Agr, Dept Civil Engn, Umudike 440109, Nigeria
[3] Kampala Int Univ, Dept Civil Engn, Kampala, Uganda
[4] Zagazig Univ, Fac Engn, Comp & Syst Engn Dept, Zagazig 44519, Egypt
来源
SCIENTIFIC REPORTS | 2024年 / 14卷 / 01期
关键词
Gravel; Image processing; Particle size; Neural network; Artificial intelligence;
D O I
10.1038/s41598-024-72700-9
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Particle size is considered one of the significant characteristics used in geotechnical practices. Traditionally, sieve analysis is utilized for coarse-grained soil. However, this method could be time consuming and take much effort, especially for large scale infrastructure projects. This paper presents an efficient method for estimating gravel particle characterization utilizing image processing and artificial neural network technique (IPNN). The proposed algorithm is performed by utilizing particle boundary delineation and shape feature extraction to train a neural network model for estimating gravel size distribution curve. It is found that excellent agreement exists between the results obtained from conventional sieve analysis and neural analysis for gravel soil particles with maximum difference in passing percentages up to only 3.70%. The proposed technique shows satisfactory results for crushed stone samples with maximum difference in passing percentages about 10.90% mainly in large diameter particles. The presented technique (IPNN) could offer a promising alternative technique for material quality control process especially in large scale projects.
引用
收藏
页数:31
相关论文
共 36 条
[1]   Elliptic tube free convection augmentation: An experimental and ANN numerical approach [J].
Abdelatief, Mohamed A. ;
Zamel, Amr A. ;
Ahmed, Saeed A. .
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER, 2019, 108
[2]   Characterization of coarse fraction of red mud as a civil engineering construction material [J].
Alam, Shamshad ;
Das, Sarat Kumar ;
Rao, B. Hanumantha .
JOURNAL OF CLEANER PRODUCTION, 2017, 168 :679-691
[3]  
Alpaydin E, 2020, Introduction to Machine Learning
[4]  
[Anonymous], 2009, STANDARD TEST METHOD, DOI DOI 10.1520/D6913-04E01
[5]  
[Anonymous], 2019, P 16 INT C BRAZ GEOP
[6]  
Arce G. R., 2005, NONLINEAR SIGNAL PRO
[7]   DOES MEDIAN FILTERING TRULY PRESERVE EDGES BETTER THAN LINEAR FILTERING? [J].
Arias-Castro, Ery ;
Donoho, David L. .
ANNALS OF STATISTICS, 2009, 37 (03) :1172-1206
[8]   Artificial neural networks: fundamentals, computing, design, and application [J].
Basheer, IA ;
Hajmeer, M .
JOURNAL OF MICROBIOLOGICAL METHODS, 2000, 43 (01) :3-31
[9]   Vision-based rock-type classification of limestone using multi-class support vector machine [J].
Chatterjee, Snehamoy .
APPLIED INTELLIGENCE, 2013, 39 (01) :14-27
[10]  
Dipova N, 2017, ACTA GEOTECH SLOV, V14, P28