Time–Frequency Envelope Analysis for Fault Detection of Rotating Machinery Signals with Impulsive Noise

Lee, Donghyeon; Hong, Chang-Oh; Jeong, Weui-Bong; Ahn, Se Jin

doi:10.3390/app11125373

Cited by 12 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The signal processing methods of envelope analysis and frequency domain feature extraction have been used in some fields and achieved effective results. For instance, there is a time-frequency envelope analysis method for fault detection of rotating machinery signals 25 and an envelope spectrum analysis method for monitoring the state of centrifugal pumps. In this paper, because of the vibration signals with a regular amplitude and envelope, 26 we propose a vibration signal recognition method in the track bed defect measurement areas: we extract the envelope of the vibration signal with the help of Hilbert transformation and add the FFT attention mechanism to help the model focus on the envelope and frequency domain characteristics of the vibration signal.…”

Section: Track Bed Defect Classification Methodsmentioning

confidence: 99%

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Chen,

Lin,

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

An invisible track bed defect classification method based on distributed optical fiber sensing data acquisition and an attention Transformer model mechanism under the frequency domain is proposed. The vibration sensing data contain structural safety information of vehicles, rails, track beds, etc., covering the entire time period and entire track area of subway operation. To classify the invisible track bed defect rapidly and accurately, the original vibration signals are first reduced by downsampling and envelope signal extraction. According to the regular characteristics of different types of signals, an fast Fourier transform (FFT) Attention Transformer (FFT-Attn-Transformer) sequence feature extraction architecture with a high recognition accuracy is proposed for model training.The results demonstrate that the accuracy, precision, recall rate, and F 1-score are all above 98% using the proposed model, and the recognition accuracy of the defect test area is 99.47%, which has extremely high stability and accuracy, providing an innovative and feasible idea for the lack of effective monitoring scheme for invisible track bed defects.

show abstract

Section: Track Bed Defect Classification Methodsmentioning

confidence: 99%

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Chen,

Lin,

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

show abstract

“…Another valuable method of sound signal comparison is the Envelope Analysis Method (EAM) which is performed but out of the scope of this paper [16].…”

Section: Asat-20mentioning

confidence: 99%

Low-cost noise maker for testing acoustically guided unmanned vehicles

Mousa,

Tork,

Abdallah

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Testing the performance of the Acoustically Guided Unmanned Underwater Vehicle (AGUUV) prior to its deployment is essential to ensure its ability to perform the required tasks accurately. These systems can be deployed from boats or helicopters to scan areas of military and economic importance for threats. These threats such as aircrafts carriers, ships, submarines, divers, and autonomous surface vehicles. The problem of implementing a low-cost high-performance noise maker (LCNM) which is suitable for being used as a test target instead of different threats for AGUUVs is the motivation of this paper. Lab experiments and sea trials are performed using the proposed noise maker to demonstrate the proper operation of the AGUUV. Lab experiments showed that the radiated noise of the proposed noise maker has high power in the frequency band between 5 to 8 kHz. The measured signal to noise ratio (SNR) for the introduced LCNM is 30 dB in this band. The experimental results presented in this paper show the feasibility of using the proposed LCNM effectively to test the AGUUVs.

show abstract

“…This non-intrusive approach allows for determining of the machine's condition by analyzing amplitude or frequency of vibration signals, both before and after investigating the incipient bearing faults [9]. Vibration signal analysis is based on real-time spectral analysis in time, frequency, and time-frequency domains [10][11][12]. Time and frequency techniques are used to analyze time-series data in terms of both time and frequency, while the time-frequency domain simultaneously used both time and frequency at a same time.…”

Section: Introductionmentioning

confidence: 99%

“…Time-domain analysis provides a fundamental understanding of motor health and is relatively simple to apply, while frequency-domain techniques effectively distinguish a fault characteristic frequency from noise due to their sensitivity to noise interference. Furthermore, frequency domain signals offer the advantage of not requiring previous information to identify fault signature features [12]. In the time-domain, various statistical features such as Root Mean Square (RMS), Mean, Peak values, Kurtosis, Standard Deviation, Impulse Factor, Shape Factor are discussed [13].…”

Section: Introductionmentioning

confidence: 99%

A methodological integration of fisher score technique with intelligent machine learning methods for ball bearing fault investigation

Kumar,

Anand

2024

Eng. Res. Express

View full text Add to dashboard Cite

This paper presents an efficient approach to detect, diagnose and estimate the severity of failures in various components of bearings in induction motors using vibration signature analysis. This automated method integrates the Fisher Score feature selection method and an efficient hyperparameter tuning model with machine learning models, including Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Decision Tree (DT), to accurately classify defects in bearings. This approach ensures accurate classification of bearing defects within a reduced computation time. This work is carried out with recorded vibration signals from a laboratory experimental setup on Machine Fault Simulator (MFS), focusing on ball bearing with defects in inner race, outer race and ball itself. Time and Frequency domain analysis are employed to compute the features for fault investigation in ball bearings using machine learning models. The computed results demonstrate that the proposed feature selection method with hyperparameter tuning achieved remarkable maximum accuracy among X, Y and XY combinations of datasets, with 97% in DT, 94% in SVM and 95.23% in k-NN models during the frequency domain analysis. Notably, these model accuracies improved to 99.04% in DT, 98% in SVM and 98% in k-NN during further analysis with Fisher Score technique. Consequently, the testing loss using this hyperparameter tuning function remains very low. Overall, this paper compares the results of time and frequency domain analysis and introduces a promising approach for both efficient and accurate fault detection and severity estimation in bearings of induction motors, potentially reducing the need for extensive manpower and sensor usage.

show abstract

Time–Frequency Envelope Analysis for Fault Detection of Rotating Machinery Signals with Impulsive Noise

Cited by 12 publications

References 44 publications

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model

Low-cost noise maker for testing acoustically guided unmanned vehicles

A methodological integration of fisher score technique with intelligent machine learning methods for ball bearing fault investigation

Contact Info

Product

Resources

About