Artificial intelligence and its diverse applications are examples of emerging new technologies that have so far been shown to be successful in merging scientific applications. Generally, intelligent systems outperform their traditional counterparts in solving non-linear tasks. Artificial neural network (ANN) models are usually designed and used to arbitrate these non-linear problems; as they mimic the structure and function of a biological brain. In this paper, an intelligent classification system is proposed to decide the result of a routine and laborious civil engineering quality control process. The ANN model is specifically designed, implemented and tested in order to classify the compressive strength grade of different concrete mixes as low, normal or high strength. Concrete elements of varying compressive strength classes and qualities, are required to be used for different purposes and under different environmental conditions. The grade of the concrete’s strength is highly dependent on many non-linear factors and it is often conventionally determined by using civil engineering methods involving the destruction of concrete samples. Our aim is to classify the concrete strength without destructing any samples. Experimental results in this work show high efficiency in correctly classifying the compressive strength.