Inverse Reconstruction of Shock Time Series from Shock Response Spectrum Curves using Machine Learning

The paper introduces a conditional variational autoencoder (CVAE) that learns to map shock response spectrum (SRS) curves back to acceleration time series, addressing the ill‑posed inverse problem. Unlike traditional iterative optimization methods that rely on predefined sinusoidal bases, the CVAE provides a data‑driven, non‑iterative solution. Experiments show the model achieves higher spectral fidelity, generalizes well to unseen spectra, and runs three to six orders of magnitude faster than classical techniques.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.