Title :
Compressive Strength Prediction of Building Blocks from Lightweight Raw Materials: A Neural Network Approach
Author :
Acevedo, D.J.L. ; Torres-T, Luis M. ; Gomez, Z.L.Y.
Author_Institution :
COMIMSA, FIME-UANL, San Nicolas
Abstract :
This paper presents a neural model to predict the compressive strength of building blocks using lightweight raw materials cured up to 28 days. The combination of raw materials is crucial to develop low cost building blocks with specific properties and acceptable mechanical strength. The model avoids testing a new mixture of building materials and provides new alternatives to design new components at low cost
Keywords :
construction industry; mechanical strength; neural nets; raw materials; compressive strength prediction; construction building material; construction industry; lightweight raw material; mechanical strength; neural network approach; Aggregates; Building materials; Computer networks; Construction industry; Costs; Materials testing; Mechanical factors; Neural networks; Raw materials; Training data;
Conference_Titel :
Electronics, Robotics and Automotive Mechanics Conference, 2006
Conference_Location :
Cuernavaca
Print_ISBN :
0-7695-2569-5
DOI :
10.1109/CERMA.2006.27
