High Cycle S-N curve prediction for Al 7075-T6 alloy using Recurrent Neural Networks (RNNs)
This work addresses the high cost and time demands of fatigue testing for materials like aluminum alloys, offering a computational alternative, though it appears incremental as it applies an existing method (LSTM with transfer learning) to a specific material domain.
The paper tackled the problem of predicting high-cycle fatigue S-N curves for Al 7075-T6 alloy, which is costly and time-consuming to characterize experimentally, by developing a transfer learning framework using LSTM networks. The framework accurately predicted torsional S-N curves for a much higher cycle range, potentially reducing costs and improving test prioritization.
Aluminum is a widely used alloy, which is susceptible to fatigue failure. Characterizing fatigue performance for materials is extremely time and cost demanding, especially for high cycle data. To help mitigate this, a transfer learning based framework has been developed using Long short-term memory networks (LSTMs) in which a source LSTM model is trained based on pure axial fatigue data for Aluminum 7075-T6 alloy which is then transferred to predict high cycle torsional S-N curves. The framework was able to accurately predict Al torsional S-N curves for a much higher cycle range. It is the belief that this framework will help to drastically mitigate the cost of gathering fatigue characteristics for different materials and help prioritize tests with better cost and time constraints.