Inverse Reconstruction of Shock Time Series from Shock Response Spectrum Curves using Machine Learning
2026-03-03 • Machine Learning
Machine Learning
AI summaryⓘ
The authors study how to recreate acceleration signals from a summary called the shock response spectrum (SRS), which is usually hard because many different signals can produce the same SRS. Traditional methods try slowly to build signals using fixed wave shapes, but this is slow and limited. The authors use a type of AI called a conditional variational autoencoder (CVAE) to quickly generate signals that match a given SRS without repeated guessing. Their method works better and much faster than older ones, and it can handle new kinds of SRS it hasn’t seen before.
Shock response spectrumSingle-degree-of-freedom systemAcceleration time historyInverse problemConditional variational autoencoderDeep generative modelingSpectral fidelityTransient accelerationsIterative optimizationExponential decay sinusoids
Authors
Adam Watts, Andrew Jeon, Destry Newton, Ryan Bowering
Abstract
The shock response spectrum (SRS) is widely used to characterize the response of single-degree-of-freedom (SDOF) systems to transient accelerations. Because the mapping from acceleration time history to SRS is nonlinear and many-to-one, reconstructing time-domain signals from a target spectrum is inherently ill-posed. Conventional approaches address this problem through iterative optimization, typically representing signals as sums of exponentially decayed sinusoids, but these methods are computationally expensive and constrained by predefined basis functions. We propose a conditional variational autoencoder (CVAE) that learns a data-driven inverse mapping from SRS to acceleration time series. Once trained, the model generates signals consistent with prescribed target spectra without requiring iterative optimization. Experiments demonstrate improved spectral fidelity relative to classical techniques, strong generalization to unseen spectra, and inference speeds three to six orders of magnitude faster. These results establish deep generative modeling as a scalable and efficient approach for inverse SRS reconstruction.