A Machine Learning Model for Predicting Progressive Crack Extension based on Direct Current Potential Drop Fatigue Data

Time history data collected from a Direct Current Potential Drop (DCPD) fatigue experiment at a range of temperatures was used to train a Bidirectional Long-Short Term Memory Neural Network (BiLSTM) model. The model was trained on high sampling rate experimental data from crack initiation up through the Paris regime. The BiLSTM model was able to predict the progressive crack extension at intermediate temperatures and stress intensities. The model was able to reproduce crack jumps and overall crack progression. The BiLSTM model demonstrated the potential to be used as a tool for future investigation into fundamental mechanisms such as high-temperature oxidation and new damage models.

Multi-Lead Direct Current Potential Drop Method for In Situ Health Monitoring of Ceramic Matrix Composites

The method of direct current potential drop (DCPD) can be utilized as an effective and convenient approach for in situ damage detection, and as a nondestructive evaluation technique. We present the results from use of a multiprobe DCPD technique for in situ damage detection in loading of a SiC/SiC composite. It is shown that in three different modes of loading (monotonic, fatigue, and cyclic load–unload), the sensing capabilities of DCPD technique compare well to the techniques of modal acoustic emission (AE) and digital image correlation (DIC). It was also found that DCPD technique provides a far earlier warning of failure under fatigue loading than the other two methods. In addition, we show that strategically placed multiple voltage leads on the specimen surface provide a promising way of qualitatively determining the crack initiation site. Therefore, the use of multiple lead DCPD method, together with other techniques, provides a viable option for sensing damage in ceramic matrix composites (CMCs) with complex geometries, and for applications at higher temperatures.

Multi-Lead Direct Current Potential Drop (DCPD) for In-Situ Health Monitoring of Ceramic Matrix Composites

The method of direct current potential drop (DCPD) can be utilized as an effective, and convenient approach for in-situ damage detection, and as a non-destructive evaluation technique. We present the results from use of a multiprobe DCPD technique for in-situ damage detection in loading of a SiC/SiC composite. It is shown that in three different modes of loading (monotonic, fatigue, and cyclic load-unload), the sensing capabilities of DCPD technique compares well to the techniques of modal acoustic emission (AE) and digital image correlation (DIC). It was also found that DCPD technique provides a far earlier warning of failure under fatigue loading than the other two methods. In addition, we show that strategically placed multiple voltage leads on the specimen surface provides a promising way of qualitatively determining the crack initiation site. Therefore, the use of multiple lead DCPD method, together with other techniques, provides a viable option for sensing damage in ceramic matrix composites (CMCs) with complex geometries, and for applications at higher temperatures.