In this research, predictions Strength of Concrete containing different aggregate using Non-destructive (Ultrasonic) testing through Artificial Neural Networks were carrying out. For this purpose, aggregate materials gathered with the different properties from the quarries and then their destructive and nondestructive properties obtained in laboratory. The important point of this research, using different aggregate with physical, mechanical and chemical properties, and using two different methods, such as Non-destructive static and dynamic testing, Uniaxial Compressive Strength and Compressive wave velocity, respectively. Thus, model includes various types of samples, also estimate and predict model includes static and dynamic tests. The results showed that the use of artificial neural networks will not only increase the accuracy, but also reduces costs and time. In this research, predictions Strength of Concrete containing different aggregate using Non-destructive (Ultrasonic) testing through Artificial Neural Networks were carrying out. For this purpose, aggregate materials gathered with the different properties from the quarries and then their destructive and nondestructive properties obtained in laboratory. The important point of this research, using different aggregate with physical, mechanical and chemical properties, and using two different methods, such as Non-destructive static and dynamic testing, Uniaxial Compressive Strength and Compressive wave velocity, respectively. Thus, model includes various types of samples, also estimate and predict model includes static and dynamic tests.