Adaptive filtering based system for extracting gearbox condition feature from the measured vibrations

Denoising of measured lightning electric field signals using adaptive filters in the fractional Fourier domain

“…On the other hand, denoising techniques are an essential area in engineering applications for enhancing signal-to-noise ratio of corrupted signals. These techniques include many parameters which are based on time domain, frequency domain and timefrequency analysis that allow an adequate interpretation of the original signal features [2,3]. For these reasons, the EMC-UNC and GCEM-UD research groups have been working on a program to study and classify lightning using filtering techniques in order to process and analyze the radiated electric field produced during the discharge.…”

“…However, these methods have not been widely used to remove the undesired components from original LEF signals, except for a few techniques based on the classic Fourier transform as well as on the wavelet transform (WT) [6]. Adaptive filters have been used in many signal processing applications such as signal modeling, data analysis, control, spectral analysis and equalization [3,7,8]. Various adaptive algorithms, including least mean square (LMS) and recursive least square (RLS), have been developed on various domains, e.g., Fourier [9] and Wavelet [10] to remove the noise components from original signal.…”

A Review of Early Fault Diagnosis Approaches and Their Applications in Rotating Machinery

“…Zhao et al [91] proposed a reweighted SVD strategy to denoise the signals and enhance weak features for fault diagnosis of rotating machinery. Ibrahim et al [92] used a least mean squares algorithm to reduce the noise, and then the meshing frequency sidebands was found to successfully identify gear faults. Mei et al [93] used linear multi-scale segmentation to divide the signal into segments with nearly linear frequency, then the multi-order fractional Fourier transform filter was used to filter each segment.…”

Integrative intrinsic time-scale decomposition and hierarchical temporal memory approach to gearbox diagnosis under variable operating conditions

“…A least mean squarebased adaptive filtering scheme is investigated to diagnose tooth breakage with different severities. 11 These developed techniques are effective in fault feature extraction. However, the relationships between fault features and gearbox failure modes are not explicit, which causes difficulty in identifying gearbox failure modes.…”