Gear Fault Detection, Identification and Classification Using MLP Neural Network

Afia, Adel; Ouelmokhtar, Hand; Gougam, Fawzi; Touzout, Walid; Rahmoune, Chemseddine; Benazzouz, Djamel

doi:10.1007/978-981-19-4835-0_18

Cited by 6 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a band-pass filter in time and frequency, DWT decomposes the analyzed signal into a data set with a specified frequency band (Chu et al, 2019; Gu et al, 2021; Mohamed et al, 2021). However, the dyadic step in the subsampling process appears to be the most significant issue in DWT (Afia et al, 2019, 2020b, 2022). Maximal overlap discrete wavelet transform (MODWT) is an enhancement of DWT that deals with the subsampling process, but the frequency resolution remains as poor as the DWT resolution (Afia et al, 2019, 2020b, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…However, the dyadic step in the subsampling process appears to be the most significant issue in DWT (Afia et al, 2019, 2020b, 2022). Maximal overlap discrete wavelet transform (MODWT) is an enhancement of DWT that deals with the subsampling process, but the frequency resolution remains as poor as the DWT resolution (Afia et al, 2019, 2020b, 2022). Therefore, for high resolution, maximal overlap discrete wavelet packet transform (MODWPT) has been used instead of MODWT and DWT (Afia et al, 2019, 2020b, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Maximal overlap discrete wavelet transform (MODWT) is an enhancement of DWT that deals with the subsampling process, but the frequency resolution remains as poor as the DWT resolution (Afia et al, 2019, 2020b, 2022). Therefore, for high resolution, maximal overlap discrete wavelet packet transform (MODWPT) has been used instead of MODWT and DWT (Afia et al, 2019, 2020b, 2022). MODWPT decomposes the raw signal into several simple components and provides the circular shift equi-variance property (Afia et al, 2019, 2020b, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, for high resolution, maximal overlap discrete wavelet packet transform (MODWPT) has been used instead of MODWT and DWT (Afia et al, 2019, 2020b, 2022). MODWPT decomposes the raw signal into several simple components and provides the circular shift equi-variance property (Afia et al, 2019, 2020b, 2022). MODWPT provides a uniform frequency bandwidth and avoids the time-varying transformation while allowing the original signal to be reconstructed without any information loss (Afia et al, 2019, 2020b, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Intelligent fault classification of air compressors using Harris hawks optimization and machine learning algorithms

Afia

Gougam

Rahmoune

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Due to their complexity and often harsh working environment, air compressors are inevitably exposed to a variety of faults and defects during their operation. Thus, condition monitoring is critically required for early fault recognition and detection to avoid any type industrial failures. In this paper, an intelligent algorithm for reciprocating air compressor fault diagnosis is developed using real-time acoustic signals acquired from an air compressor with one healthy and seven different faulty states such as leakage inlet valve (LIV), leakage outlet valve (LOV), non-return valve (NRV), piston ring, flywheel, rider-belt and bearing defects. The proposed algorithm mainly consists of three steps: feature extraction, selection, and classification. For feature extraction, experimental acoustic signals are decomposed using maximal overlap discrete wavelet packet transform (MODWPT) by six levels into 64 wavelet coefficients (nodes). Thereafter, time domain features are calculated for each node to build each air compressor’s health state feature matrix. Each feature matrix dimension is reduced by selecting the most useful features using Harris hawks optimization (HHO) in the feature selection step. Finally, for feature classification, selected features are used as inputs for random forest (RF), ensemble tree (ET) and K-nearest neighbors (KNN) to detect, identify, and classify the compressor health states with high classification accuracy. Comparative studies with several feature extraction and selection methods prove the proposed approach’s efficiency in detecting, identifying, and classifying all air compressor faults.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent fault classification of air compressors using Harris hawks optimization and machine learning algorithms

Afia

Gougam

Rahmoune

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…The dynamic responses of gear transmission under different working conditions have been studied extensively 2,3 . Various monitoring and diagnostic methods can be proposed based on vibration signal analysis 4–8 . Liang et al 9 conducted a systematic review of the dynamic modeling of gear systems and specialized in meshing stiffness assessment and gearbox transmission path modeling under various working conditions.…”

Section: Introductionmentioning

confidence: 99%

Experimental‐based study of gear vibration characteristics incorporating the fractal topography of tooth surface

Qiu

Yuan

et al. 2023

Int Journal of Mech Sys Dyn

View full text Add to dashboard Cite

Microscopic roughness is inevitable on the gear meshing surface, which is also a key parameter affecting the dynamic response. The surface roughness exhibits self‐affine characteristics across multiscales. To explore the influence of surface fractal topography on the vibration amplitude of the gear system under different rotational speeds and loads, an experimental setup of spur gear transmission is devised. The fractal dimension and fractal roughness of the meshing surface are calculated by the power spectral density method. The relationships between gear response and fractal parameters are revealed experimentally. Results indicate that a rougher tooth surface, that is, a smaller fractal dimension or larger fractal roughness, corresponds to an intense vibration amplitude. The sensitivity of dynamic response to the tooth surface topography varies at different rotational speeds and loads. Under low speed and light load conditions, the fractal dimension and fractal roughness have a more obvious influence on the dynamic response of the gear transmission system. With the increase of speed and load, the macroworking conditions gradually become the main factor attributed to vibration amplitude.

show abstract

Spectral proper orthogonal decomposition and machine learning algorithms for bearing fault diagnosis

Afia,

Gougam,

Touzout

et al. 2023

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Gear Fault Detection, Identification and Classification Using MLP Neural Network

Cited by 6 publications

References 31 publications

Intelligent fault classification of air compressors using Harris hawks optimization and machine learning algorithms

Intelligent fault classification of air compressors using Harris hawks optimization and machine learning algorithms

Experimental‐based study of gear vibration characteristics incorporating the fractal topography of tooth surface

Spectral proper orthogonal decomposition and machine learning algorithms for bearing fault diagnosis

Contact Info

Product

Resources

About