原文传递
PERFORMANCE EVALUATION OF NEURAL NETWORKS IN CONCRETE CONDITION ASSESSMENT.
| 题名： | PERFORMANCE EVALUATION OF NEURAL NETWORKS IN CONCRETE CONDITION ASSESSMENT. |
| 作者： | Martinelli-DR; Shoukry-SN |
| 关键词： | Accuracy-; Concrete-; Condition-surveys; Internal-cracks; Neural-networks; Performance-evaluations; Signal-classification; Specimens-; Ultrasonic-signals; Ultrasonic-tests |
| 摘要： | A neural network modeling approach is used to identify concrete specimens that contain internal cracks. Different types of neural nets are used and their performance is evaluated. Correct classification of the signals received from a cracked specimen could be achieved with an accuracy of 75% for the test set and 95% for the training set. These recognition rates lead to the correct classification of all the individual test specimens. Although some neural net architectures may show high performance with a particular training data set, their results might be inconsistent. In situations in which the number of data sets is small, consistent performance of a neural network may be achieved by shuffling the training and testing data sets. |
| 总页数： | Transportation Research Record. 2000. (1739) pp76-82 (7 Fig., 4 Tab., 12 Ref.) |
| 报告类型： | 科技报告 |
相关文献
- NEURAL NETWORK INTERPRETATION OF ULTRASONIC RESPONSE FOR CONCRETE CONDITION ASSESSMENT.
- Evaluating Intelligent Transportation Systems, Advanced Traveler Information Systems, and Other Artificial Intelligence Applications
- Terrestrial Laser Scanning-Based Bridge Structural Condition Assessment.
- Development and Validation of Deterioration Models for Concrete Bridge Decks: Phase 1: Artificial Intelligence Models and Bridge Management System.
- Seismic Performance Evaluation of Water Supply Systems. Technical rept.
- EFFECT OF NOISY DATA ON PAVEMENT PERFORMANCE PREDICTION BY ARTIFICIAL NEURAL NETWORKS.
检索历史
应用推荐
