Evaluation of Time and Frequency Condition Indicators from Vibration Signals for Crack Detection in Railway Axles

Sánchez, René–Vinicio; Lucero, Pablo; Macancela, Jean-Carlo; Rubio, Higinio; Cerrada, Mariela; Cabrera, Diego; Castejón, Cristina

doi:10.3390/app10124367

Cited by 10 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Sánchez et al [ 288 ], the authors applied two separate approaches in order to detect faults in railway axles. The first of the approaches was connected to gathering and analysis of acceleration signals measured in the longitudinal direction.…”

Section: Systematic Literature Reviewmentioning

confidence: 99%

Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review

Kostrzewski

Melnik

2021

Sensors

View full text Add to dashboard Cite

Condition monitoring of rail transport systems has become a phenomenon of global interest over the past half a century. The approaches to condition monitoring of various rail transport systems—especially in the context of rail vehicle subsystem and track subsystem monitoring—have been evolving, and have become equally significant and challenging. The evolution of the approaches applied to rail systems’ condition monitoring has followed manual maintenance, through methods connected to the application of sensors, up to the currently discussed methods and techniques focused on the mutual use of automation, data processing, and exchange. The aim of this paper is to provide an essential overview of the academic research on the condition monitoring of rail transport systems. This paper reviews existing literature in order to present an up-to-date, content-based analysis based on a coupled methodology consisting of bibliometric performance analysis and systematic literature review. This combination of literature review approaches allows the authors to focus on the identification of the most influential contributors to the advances in research in the analyzed area of interest, and the most influential and prominent researchers, journals, and papers. These findings have led the authors to specify research trends related to the analyzed area, and additionally identify future research agendas in the investigation from engineering perspectives.

show abstract

Section: Systematic Literature Reviewmentioning

confidence: 99%

Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review

Kostrzewski

Melnik

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The combination of time-and frequency-domain features has yielded outstanding results, such as in the research by Sánchez, R.-V. et al [23]. Therefore, the former condition indicators have been combined with time-domain features such as basic statistics (mean, standard deviation, RMS and shape factor), high-order statistics (kurtosis and skewness) and impulsive metrics (peak value, impulse factor, crest factor and clearance factor).…”

Section: Logmentioning

confidence: 99%

Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification

2022

View full text Add to dashboard Cite

Vibration signals captured with an accelerometer carry essential information about Rolling Element Bearings (REBs) faults in rotating machinery, and the envelope spectrum has proven to be a robust tool for their diagnosis at an early stage of development. In this paper, Cepstrum Pre-Whitening (CPW) has been applied to REBs’ signals to enhance and extract health-state condition indicators from the preprocessed signals’ envelope spectra. These features are used to train some of the state-of-the-art Machine Learning (ML) algorithms, combined with time-domain features such as basic statistics, high-order statistics and impulsive metrics. Before training, these features were ranked according to statistical techniques such as one-way ANOVA and the Kruskal–Wallis test. A Convolutional Neural Network (CNN) has been designed to implement the classification of REBs’ signals from a Deep Learning (DL) point of view, receiving raw time signals’ greyscale images as inputs. The different ML models have yielded validation accuracies of up to 87.6%, while the CNN yielded accuracy of up to 77.61%, for the entire dataset. In addition, the same models have yielded validation accuracies of up to 97.8%, while the CNN, 90.67%, where signals from REBs with faulty balls have been removed from the dataset, highlighting the difficulty of classifying such faults. Furthermore, from the results of the different ML algorithms compared to those of the CNN, frequency-domain features have proven to be highly relevant condition indicators combined with some time-domain features. These models can be potentially helpful in applications that require early diagnosis of REBs faults, such as wind turbines, vehicle transmissions and industrial machinery.

show abstract

“…The results show that the proposed method can be used to continuously monitor the integrity of the shaft and that cracks with dimensions around 8% of the total cross-sectional area can be detected. Sánchez et al [10] solved the problem of crack detection in railroad axles by evaluating several state metrics of vibration signals in the time and frequency domains. Zamorano et al [11] investigated the application of SHM in the case of railroad axle rupture by vibration analysis using the optimal choice of mother wavelet in WPT analysis.…”

Section: Introductionmentioning

confidence: 99%

An acoustic emission identification model for train axle fatigue cracks based on deep belief network

Lin,

Tang,

Zhu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming to effectively identify train axle fatigue cracks, some scholars are now trying to consider introducing acoustic emission detection technology into axle health monitoring and combining it with intelligent neural networks to achieve better monitoring results. In the field of axle fatigue crack acoustic emission identification, the commonly used methods include parameter analysis, wavelet analysis, and traditional artificial neural networks. Though these methods did work in the field of axle fatigue crack identification, they still have two deficiencies. （1）The features are manually extracted depending on large artificial experience. (2) The methods mentioned above have shallow architectures, which cannot handle some complex fatigue crack linear relationships. In this paper, an acoustic emission signal analysis method for axle fatigue cracks based on deep belief networks is proposed to overcome the aforementioned deficiencies. The main purpose of this paper is to emphasize the feasibility of the deep belief network to intelligently identify fatigue crack signals from different types of acoustic emission signals of axles and to classify crack signals at different stages. The research method is to use acoustic emission (AE) technology to obtain the axle fatigue crack AE signal, pretreat the collected time-domain signal, identify whether cracks appear, and classify the stages of crack emergence by deep belief network (DBN) so as to find the axle crack in advance. The experimental analysis results show that the method of identification of axle fatigue cracks based on DBN not only can identify fatigue crack signals but also has a very high identification rate of fatigue cracks at different stages. In the axle fatigue crack acoustic emission identification field, it can be seen that the proposed method in this paper will be a promising approach.

show abstract

Evaluation of Time and Frequency Condition Indicators from Vibration Signals for Crack Detection in Railway Axles

Cited by 10 publications

References 28 publications

Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review

Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review

Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification

An acoustic emission identification model for train axle fatigue cracks based on deep belief network

Contact Info

Product

Resources

About