Applying Artificial Intelligence to Improve On-Site Non-Destructive Concrete Compressive Strength Tests

In the construction industry, non–destructive testing (NDT) methods are often used in field to inspect compressive strength of concrete. NDT do not cause damage existing structure and relatively economical. Two popular rebound hammer (RH) test ultrasonic pulse velocity (UPV) test. One major drawback RH UPV is that concrete estimations very accurate when comparing them results obtained from destructive tests. To improve estimation, researchers applied artificial intelligence prediction models explore relationships between input values (results two tests) output (concrete strength). In-situ data a total 98 samples were collected collaboration with material laboratory Professional Civil Engineer Association. develop validate (both traditional statistical AI models). The analysis showed provide more compared regression models. research show significant improvement techniques (ANNs, SVM ANFIS) estimate