Answers are grounded in this paper and cite their sources.
Repair and replacement of damaged composites are costly and time-consuming processes, therefore a prediction of fracture is highly beneficial, and may enhance structure reliability. In this study, a case-based reasoning (CBR) methodology as a problem-solving method of artificial intelligence is utilized to predict fracture occurrence in adhesively bonded sandwich joints. CBR is an intelligent technique for solving new problems by finding previous similar problems based on the experiences and cases which have similar solutions. In this paper, the experimental data of sandwich joints which experienced static and dynamic loadings under various environmental conditions are analyzed and stored on the case base. The case base of the implemented system is also enriched by numerical simulation results. The developed tool is appropriately designed with the optimized cases which are performed to reach high robustness in the fracture prediction. Furthermore, the case-base updates while using the system by learning from the gathered data as requested problems. Therefore, higher performance in future problems can be achieved. The proposed intelligence system has a general reliability to apply for different types of joints in sandwich-structured composites in order to predict failure load and type of failure. The quality of the obtained results of this research fully demonstrated the usefulness of the proposed intelligent system.
No takes yet. Share an insight, caveat, or question.
Khosravani et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: