A Hybrid Classification Approach to Ultrasonic Shaft Signals

Lee, Kyungmi; Estivill‐Castro, Vladimir

doi:10.1007/978-3-540-30549-1_26

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the crack size, which indicates the severity of test object, might not be accurate because the amplitude of the echoes may also be influenced by surface roughness, orientation of the defect and transducer position [13]. Moreover, compared to the structure of a plate or a pipe, cylindrical parts, such as shafts, often have special features such as multiple diameter sections, keyways, bolt holes, etc [14,15]. As a result, the ultrasonic echoes captured from the shaft are too complicated to distinguish the reflection sources due to the interpretation.…”

Section: Introductionmentioning

confidence: 99%

Severity evaluation of the transverse crack in a cylindrical part using a PZT wafer based on an interval energy approach

Xiao

Zheng

Song

2016

Smart Mater. Struct.

View full text Add to dashboard Cite

Transverse cracks in cylindrical parts can be detected by using the ultrasound based pulse-echo method, which has been widely used in industrial applications. However, it is still a challenge to identify the echoes reflected by a crack and bottom surfaces of a cylindrical part due to the multipath propagation and wave mode conversion. In this paper, an interval energy approach is proposed to evaluate the severity of the transverse crack in a cylindrical part. Lead zirconate titanate patch transducers are used to generate the ultrasound pulse and to detect the echoes. The echo signals are preprocessed and divided into two zones, the normal reflection zone and the crack reflection zone. Two energy factors evaluating the severity of the crack are computed based on the interval energy. When using this proposed method, it is not necessary to identify the echo sources since all the crack and boundary echoes are automatically taken into consideration by using the proposed method. The experimental results indicate that proposed approach is more suitable and sensitive to evaluate the transverse crack severity of cylindrical part than the traditional method.

show abstract

Section: Introductionmentioning

confidence: 99%

Severity evaluation of the transverse crack in a cylindrical part using a PZT wafer based on an interval energy approach

Xiao

Zheng

Song

2016

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…In order to find the frequency content of a signal, Fourier transform (FT) is often used for transforming the time based signal into frequency based one, i.e., the original signal is broken down into constituent sinusoids of different frequencies. The application of FT in ultrasonic inspection can be referred to [3][4][5][6].…”

mentioning

confidence: 99%

Empirical Mode Decomposition And Rough Set Attribute Reduction For Ultrasonic Flaw Signal Classification

Wang

2014

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

Feature extraction and selection are the most important techniques for ultrasonic flaw signal classification. In this study, empirical mode decomposition (EMD) is first used to obtain the intrinsic mode functions (IMFs) of original ultrasonic signals. Such IMFs and traditional time as well as frequency domain based statistical parameters are extracted as the initial features of flaw signal. After that, spectral clustering method is used for feature value discretization so that rough set attribute reduction (RSAR) can be applied to implement feature selection. Finally, the selected features are taken as input of artificial neural networks (ANNs) to train the decision classifier for flaw identification. Experimental results show that compared to conventional wavelet transform based schemes and principal components analysis, EMD combined with RSAR can improve the performance of feature extraction and selection. Using such hybrid scheme can effectively classify different ultrasonic flaw signals with high accuracy and low training elapsed time.

show abstract