Time-frequency methods of non-stationary vibroacoustic diagnostic signals processing

Mokrzan, Daniel; Szymański, Grzegorz M.

doi:10.53502/rail-143047

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this measure is not the same as the analog in the time domain. The transformation from the quefrency domain to the frequency domain is performed using the relationship between the period and the frequency (equation 19).…”

Section: Application Of the Combined Cwt-cepstrum Methodsmentioning

confidence: 99%

The application of time-frequency methods of acoustic signal processing in the diagnostics of tram drive components

Mokrzan,

Nowakowski,

Szymański

2023

AoT

Self Cite

View full text Add to dashboard Cite

The paper presents the course of investigations and the analysis of the possibility of applying selected methods of time-frequency processing of non-stationary acoustic signals in the assessment of the technical condition of tram drive components, as well as a new combined method proposed by the authors. An experiment was performed in the form of a pass-by test of the acoustic pressure generated by a Solaris Tramino S105p tram. A comparative analysis has been carried out for an efficient case and a case with damage to the traction gear of the third bogie in the form of broken gear teeth. The recorded signal was analyzed using short-time Fourier transform (STFT) and continuous wavelet transform (CWT). It was found that the gear failure causes an increase in the sound level generated by a given bogie for frequencies within the range of characteristic frequencies of the tested device. Due to the limitations associated with the fixed window resolution in STFT and the inability to directly translate scales to frequencies in CWT, it was found that these methods can be helpful in determining suspected damage, but are too imprecise and prone to errors when the parameters of both transforms are poorly chosen. A new CWT-Cepstrum method was proposed as a solution, using the wavelet transform as a pre-filter before cepstrum signal processing. With a sampling rate of 8192 Hz, a db6 mother wavelet, and a scale range of 1:200, the new method was found to infer the occurrence of damage in an interpretation-free manner. The results were validated on an independent pair of trams of the same model with identical damage and as a reference on a pair of undamaged trams demonstrating that the method can be successfully replicated for different vehicles.

show abstract

Section: Application Of the Combined Cwt-cepstrum Methodsmentioning

confidence: 99%

The application of time-frequency methods of acoustic signal processing in the diagnostics of tram drive components

Mokrzan,

Nowakowski,

Szymański

2023

AoT

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is necessary to develop the ability to analyze in the low and medium frequency range the measurement of non-stationary vibrations originating from a rotating machine using a vibration sensor. This research is based on previous research quoted from references [18]. STFT can be defined as the subject of spectrum analysis using FFT, short signal sequences are treated as quasi-stationary.…”

Section: Introductionmentioning

confidence: 99%

Induced Draft Fan Dominant Frequency Detection Using Short-Time Fourier Transform Method

Romahadi

2023

JRM

View full text Add to dashboard Cite

Weak suction and large vibrations indicate an Induced Draft Fan (IDF) problem. The Fast Fourier Transform (FFT) method cannot be applied to non-stationary vibration signals. Therefore, this study aims to analyze non-stationary vibration signals for IDF vibration signals at start-up so that the source of damage to the IDF can be found. The research process begins with a brief measurement of both bearing locations with horizontal and axial axes. Processing of the vibration signal from the measurement using the FFT method and the Short Time Fourier Transform (STFT). Based on the STFT spectrogram graph for measurements on the horizontal and axial axes, the dominant frequency values are the same. The frequency with the largest amplitude value is at one RPM IDF or 25 Hz. High vibration at 1 RPM is a big indication that the IDF is experiencing unbalance.

show abstract

Health Monitoring of Milling Tool Inserts Using CNN Architectures Trained by Vibration Spectrograms

Patil¹,

Pardeshi²,

Patange³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

In-process damage to a cutting tool degrades the surface nish of the job shaped by machining and causes a signi cant nancial loss. This stimulates the need for Tool Condition Monitoring (TCM) to assist detection of failure before it extends to the worse phase. Machine Learning (ML) based TCM has been extensively explored in the last decade. However, most of the research is now directed toward Deep Learning (DL). The "Deep" formulation, hierarchical compositionality, distributed representation and end-to-end learning of Neural Nets need to be explored to create a generalized TCM framework to perform e ciently in a high-noise environment of cross-domain machining. With this motivation, the design of di erent CNN (Convolutional Neural Network) architectures such as AlexNet, ResNet-50, LeNet-5, and VGG-16 is presented in this paper. Real-time spindle vibrations corresponding to healthy and various faulty con gurations of milling cutter were acquired. This data was transformed into the time-frequency domain and further processed by proposed architectures in graphical form, i.e., spectrogram. The model is trained, tested, and validated considering di erent datasets and showcased promising results.

show abstract

Time-frequency methods of non-stationary vibroacoustic diagnostic signals processing

Cited by 3 publications

References 26 publications

The application of time-frequency methods of acoustic signal processing in the diagnostics of tram drive components

The application of time-frequency methods of acoustic signal processing in the diagnostics of tram drive components

Induced Draft Fan Dominant Frequency Detection Using Short-Time Fourier Transform Method

Health Monitoring of Milling Tool Inserts Using CNN Architectures Trained by Vibration Spectrograms

Contact Info

Product

Resources

About