Logic-guided neural network for predicting steel-concrete interfacial behaviors
作者：
Highlights：
• A logic-guided neural network is presented to predict steel-concrete interfacial behaviors.
• Logic and scientific principles are utilized in the logic-guided neural network.
• Strategies are presented to utilize unstructured data and datasets with incomplete data.
• The bond stress-slip curves of steel-concrete interface are predicted.
• The logic-guided neural network achieves a desired performance of prediction.
摘要
•A logic-guided neural network is presented to predict steel-concrete interfacial behaviors.•Logic and scientific principles are utilized in the logic-guided neural network.•Strategies are presented to utilize unstructured data and datasets with incomplete data.•The bond stress-slip curves of steel-concrete interface are predicted.•The logic-guided neural network achieves a desired performance of prediction.
论文关键词：Deep learning,Incomplete data,Interfacial properties,Logic-guided neural network,Machine learning,Unstructured data
论文评审过程：Received 8 December 2020, Revised 11 October 2021, Accepted 2 March 2022, Available online 8 March 2022, Version of Record 11 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116820
