Modeling packing density of granular mixtures: An artificial intelligence approach

Siavash Manafi Khajeh Pasha, H. Hazarika, S. P.G. Madabhushi, N. Yoshimoto

研究成果: Contribution to conferencePaper査読

抄録

The minimum and maximum packing density of soil-Scrap Tire Derived Materials are often estimated based on limited laboratory test results or to some extent, an empirical correlation. However precise modeling of void ratio characteristics of such materials is complex and usually involves many parameters might be beyond the capability of most of common physically based engineering methods. To solve this issue, Artificial Neural Network (ANN) method is used for simulating maximum and minimum packing density of Gravel-Tire Chips mixtures (GTCM). In this study, a series of maximum and minimum void ratio tests were conducted on GTCM with different fraction of gravel in mixture (GF=VG /VT ) at different mean particle size ratio of tire chips to gravel (D50,R /D50,G ). The outcome revealed that the ANN model is able to precisely predict void ratios of binary mixtures.

本文言語英語
出版ステータス出版済み - 2020
イベント16th Asian Regional Conference on Soil Mechanics and Geotechnical Engineering, ARC 2019 - Taipei, 台湾省、中華民国
継続期間: 10 14 201910 18 2019

会議

会議16th Asian Regional Conference on Soil Mechanics and Geotechnical Engineering, ARC 2019
Country台湾省、中華民国
CityTaipei
Period10/14/1910/18/19

All Science Journal Classification (ASJC) codes

  • Geotechnical Engineering and Engineering Geology

フィンガープリント 「Modeling packing density of granular mixtures: An artificial intelligence approach」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル