Effect of 32.5 and 42.5 Cement Grades on ANN Prediction of Fibrocement Compressive Strength

详细信息    查看全文

• 作者：Hamid Eskandari ; ^{Hamidiisc@yahoo.com" class="auth_mail" title="E-mail the corresponding author} ; Morteza Tayyebinia
• 关键词：Artificial neural networks ; ferrocement ; compressive strength
• 刊名：Procedia Engineering
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：150
• 期：Complete
• 页码：2193-2201
• 全文大小：1020 K

文摘

This research synthesizes findings from the literature review and experimental investigation which divided into two phases. Phase one included the design artificial neural network (ANN) to predict ferrocement compressive strength due to various materials component and validation of that by previous data from literature. The inputs of these charts were cement content, water to cement, water binder, water to cement and sand ratios. These charts can be used easily to predict the compressive strength of ferrocement if the used same compressive strength of cement.

In addition to evaluated the ANN experimental results of 12 various mixtures were carried out as per ASTM standards to effect on strength of cement to evaluate the compressive strength of mortar cubes at 28 days, with the application of different compounds mortar mixes with cement/sand ratio 2:3 and varying water/binder ratio between 0.3 to 0.6, using field sand, ASTM graded sand and two type of compressive strength of OPC (ordinary portland cement). The training and testing results of ANN in the multilayer feed-forward neural and comparison by experimental result shown that neural networks systems has strong potential for predicting compressive strength of mortars if the ferrocement component of input have same materials properties.