Assessing and Predicting Geogrid Reduction Factors after Damage Induced by Dropping Recycled Aggregates

To fulfill the modern concept of sustainable construction, civil engineering community has shown increased interest in alternative options to replace natural backfills for purposes. Since Recycled Construction and Demolition Waste (RCDW) proven be attractive environmental, economic, technical aspects, its behavior should assessed considering interaction with other construction materials, such as geosynthetics. Bearing mind that backfill affects durability geosynthetic this study aims assess damage caused geogrids by RCDW dropped transportation (dump) trucks. Moreover, aimed obtain an equation predict reduction factor drop process. In experimental facility, six materials (with different grain size distributions) were (using a backhoe loader) from 1.0 m 2.0 heights over three distinct geogrids; geogrid samples exhumed then tested under tensile loading. The results provided database subjected machine learning (Artificial Neural Network—ANN) induced damage. demonstrate increase height or potential energy cannot directly associated However, increases maximum uniform gradation increases, which is obtained fall continuous backfill. since ANNs do not have any traditional constraints multiple linear regression has, method solution factors, providing relative errors lower than 8% compared investigation reported study.