Structural Vibration Signal Denoising Using KLD Regularized Bi-Directional LSTM

Vibration signals have been increasingly utilized in various engineering fields for analysis and monitoring purposes, including structural health monitoring, fault diagnosis and damage detection, where vibration signals can provide valuable information about the condition and integrity of structures. In recent years, there has been a growing trend towards the use of vibration signals in the field of bioengineering. Activity-induced structural vibrations, particularly footstep-induced signals, are useful for analyzing the movement of biological systems such as the human body and animals. Footstep-induced signals can provide valuable information about an individual's gait, body mass, and posture, making them an attractive tool for health monitoring, security, and human-computer interaction. However, the presence of various types of noise can compromise the accuracy of footstep-induced signal analysis. In this paper, we propose a novel 'many-to-many' LSTM model with a KLD regularizer and L1 regularization, which is effective in denoising structural vibration signals, particularly for regimes with larger amplitudes. The model was trained and tested using synthetic data generated by a single degree of freedom oscillator. Our results demonstrate that the proposed approach is effective in reducing noise in the signals, particularly for regimes with larger amplitudes. The approach is promising for a wide range of applications of footstep-induced structural vibration signals, including healthcare, security, and technology.