Determination of the Compressive Strength of Concrete Using Artificial Neural Network

The objective of the work is to estimate compressive strength concrete by means application Artificial Neural Networks (ANNs). A database created with design variables mixtures 175, 210, and 280 kgf/cm², which are collected from certified laboratories soil mechanics city Jaen. In addition, Weka software used for selection Matlab learning, training, validation stages ANNs. Five ANNs proposed at 7th, 14th, 28th day. results show that networks obtain average error 4.69% composed an input layer eleven neurons, two hidden layers nine neurons each, as output. This method effective valid estimating a non-destructive alternative quality control in construction industry.