Damped sinusoidal oscillations are widely observed in many physical systems, and their analysis provides access to underlying physical properties. However, parameter estimation becomes difficult when the signal decays rapidly, multiple components are superposed, and observational noise is present. In this study, we develop an autoencoder-based method that uses the latent space to estimate the frequency, phase, decay time, and amplitude of each component in noisy multi-component damped sinusoidal signals. We investigate multi-component cases under Gaussian-distribution training and further examine the effect of the training-data distribution through comparisons between Gaussian and uniform training. The performance is evaluated through waveform reconstruction and parameter-estimation accuracy. We find that the proposed method can estimate the parameters with high accuracy even in challenging setups, such as those involving a subdominant component or nearly opposite-phase components, while remaining reasonably robust when the training distribution is less informative. This demonstrates its potential as a tool for analyzing short-duration, noisy signals.

翻译：阻尼正弦振荡在许多物理系统中广泛存在，对其分析可揭示潜在物理特性。然而，当信号快速衰减、多分量叠加且存在观测噪声时，参数估计变得困难。本研究提出一种基于自编码器的方法，利用潜空间估计含噪多分量阻尼正弦信号中各分量的频率、相位、衰减时间及振幅。我们基于高斯分布训练探究多分量情况，并通过比较高斯分布与均匀分布训练进一步分析训练数据分布的影响。通过波形重构与参数估计精度评估性能。结果表明，即使在次主导分量或近乎反相分量等挑战性场景下，该方法仍能高精度估计参数，且在训练分布信息量较少时保持较好鲁棒性。这彰显了其作为短时含噪信号分析工具的潜力。