The Study of BP Neural Network in Predicting Concrete Strength
Concrete is a mainly and commonly good combined construction material, and is consisted of many well-defined components, so mechanical properties of concrete are very complex. the compressive strength of the concrete is a main criterion in producing concrete, but the test on it is complicated because test components of concrete must be kept in the special condition an tested after 28 days. To simplify the procedures and obtain a reasonable data, the paper presents a method using the system of BP neural network predicting the strength of concrete. the system is trained and tested by using many data of strength of concrete in the past ,the test result shows that the value of the strength of concrete predicted is approximate to the experimental value, and the method presented is very efficient and reasonable in predicting the compressive strength of concrete .