Multi-sensorial corrosion nondestructive testing data of concrete with machine learning

Aiming at the problem of poor detection performance caused by the complexity of multi-sensor data in automatic data evaluation, we design the function models of decision tree and Boosting based on machine learning. The experiments are implemented with Non-destructive Testing (NDT) data obtained from the multi-sensor detection of the corroded reinforced concrete. And the results are compared with the relatively simple logistic regression algorithm. It demonstrates that the simple and robust logistic regression algorithm is superior to the decision tree algorithm with complex decision boundaries trained by small heterogeneous data sets. However,Boosting can be used to improve detection and the corrosion analysis of reinforced concrete.