| Title |
Development of Neural-Network based Model for Predicting the Thickness and Embedded Entities of Concrete Slab using the Non-destructive Test Data |
| Authors |
Cho Bin-Ah ; Lee Seung-Chang ; Joo Hyun-Zee ; Cho Young-Sang |
| Keywords |
Non-destructive test ; Impact-Echo method ; Artificial Neural Networks ; Diagnosis system ; Concrete structure |
| Abstract |
The purpose of this study is to develop the diagnosis system for the maintenance and safety evaluation of concrete structure. This study is based on Impact-Echo(IE) method as Non-destructive test and Artificial Neural Networks(ANN) as artificial intelligence. IE method has been used to evaluate the integrity of concrete structures. This method can be applied in searching the thickness of concrete slab and the location of defects. Artificial Neural Networks(ANN) have been recently used to deal with problems involving incomplete or imprecise information. Also, it can continuously re-train the new data and accumulates new experience and knowledge. The proposed ANN-based model can predict concrete strength, thickness and the kinds of embedded entities. For this, the results of non-destructive test as signals are used for training patterns in ANN model. Futhermore, ANN-based model can predict the kinds of embedded entities which are steel plate, bar and PVC pipe, after the learning the FFT signals as input and identification number as desired-output. |