Reference #: 01536
The University of South Carolina is offering licensing opportunities for AI method-apparatus for extracting crack-length from high-frequency AE signals
Background:
In metallic structures, fatigue cracks are inevitable and need to be detected and quantified. However, the crack length information is hard to be estimated. It is imperative to detect these cracks and quantify their length at the earliest to avoid catastrophic failures of these structures.
Invention Description:
The proposed invention has the capability to estimate fatigue crack length in sheet-metal structures using the information contained in the high-frequency acoustic emission (AE) signal signatures. Physics-based modeling validated by carefully conducted experiments is utilized to generate synthetic datasets for training artificial intelligence (AI) algorithms. Machine-learning AI-enabled techniques are used to sift through large experimental AE signal datasets to identify dominant trends correlated with crack-length information.
Potential Applications:
The industrial applications of this technology include aerospace, automotive, marine, defense, and other applications where fatigue crack detection in metallic structures is essential at the earliest stages.
Advantages and Benefits:
- Rapid, remote, and real-time monitoring of fatigue crack growth in sheet-metal structures
- Identify the AE signals due to crack growth and discard the AE signals not related to crack growth
- Estimate crack length information from the individual AE signals- Use the AE signals to monitor crack growth and predict remaining useful life