| Title |
Development of Prediction System of Concrete Strength Using Modular Neural-Network-based Model |
| Authors |
Lee Seung-Chang ; Lim Jae-Hong |
| Keywords |
Artificial Neural Network ; Prediction ; Concrete Strength ; Modular Neural Network ; Optimum Architecture |
| Abstract |
In the previous publication1), author proposed the I-PreConS (Intelligent PREdiction system of CONcrete Strength) using artificial neural networks (ANN) that provides in-place strength information of the concrete to facilitate concrete form removal and scheduling for construction. The serious problem of the system is occured, which it cannot appropriately predict the concrete strength when the curing temperature of a specific curing day is changed. This is because it uses the single neural networks, which all nodes are fully connected, and thus it can show too plastic response. As a trial to solve this problem, modular ANN is introduced, which has multiple architecture composed of five ANNs. ANN-I predicts the early concrete strength within 24 hours after pouring. From ANN-II to ANN-V predict the concrete strength at 2nd to 28th day after pouring. Through simulation study, the optimum architectures for individual five ANNs are determined and the best way for inter-connection between five ANNs is presented. As in previous study, the weighting technique and parameter condensation are effectively used in simulation study. |