Multi-variable classification model for valve internal leakage based on acoustic emission time–frequency domain characteristics and random forest

2021 ◽  
Vol 92 (2) ◽  
pp. 025108
Author(s):  
Guo-Yang Ye ◽  
Ke-Jun Xu ◽  
Wen-Kai Wu
Keyword(s):  
Acoustic Emission ◽  
Random Forest ◽  
Frequency Domain ◽  
Classification Model ◽  
Time Frequency ◽  
Emission Time

scholarly journals Time–Frequency Domain Characteristics of Acoustic Emission Signals and Critical Fracture Precursor Signals in the Deep Granite Deformation Process

2021 ◽  
Vol 11 (17) ◽  
pp. 8236
Author(s):  
Le Zhang ◽  
Hongguang Ji ◽  
Liyuan Liu ◽  
Jiwei Zhao
Keyword(s):  
Acoustic Emission ◽  
Frequency Domain ◽  
High Frequency ◽  
Wavelet Packet ◽  
Confining Pressure ◽  
Wavelet Packet Decomposition ◽  
Evolution Law ◽  
Time Frequency ◽  
Characteristic Signal ◽  
Failure Precursor

To study the crack evolution law and failure precursory characteristics of deep granite rocks in the process of deformation and failure under high confining pressure, granite samples obtained from a depth of 1150 m are tested using a TAW-2000 triaxial hydraulic servo testing machine and a PCI-II acoustic emission monitoring system. Based on the stress–strain curve and IET function, the loading process of the sample is divided into five stages: crack closure, linear elastic deformation, microcrack generation and development, macroscopic fracture generation and energy surge, and post-peak failure. The evolution trend and fracture evolution law of the acoustic emission signal event interval function in different stages are analyzed. In particular, the signals with an amplitude greater than 85 dB, a peak frequency greater than 350 kHz, and a frequency centroid greater than 275 kHz are defined as the failure precursor signals before the rock reaches the peak stress. The defined precursor signal conditions agree well with the experimental results. The time–frequency analysis and wavelet packet decomposition of the precursor signal are performed on the extracted characteristic signal of the failure precursor. The results show that the time-domain signal is in the form of a continuous waveform, and the frequency-domain waveform has multi-peak coexistence that is mainly concentrated in the high-frequency region. The energy distribution obtained by the wavelet packet decomposition of the characteristic signal is verified with the frequency-domain waveform. The energy distribution of the signal is mainly concentrated in the 343.75–375 kHz frequency band, followed by the 281.25–312.5 kHz frequency band. The energy proportion of the high-frequency signal increases with the confining pressure.

Tool Wear Monitoring in Milling Processes Based on Time-Frequency Analysis of Acoustic Emission

2011 ◽  
Vol 141 ◽  
pp. 574-577
Author(s):  
Lu Zhang ◽  
Guo Feng Wang ◽  
Xu Da Qin ◽  
Xiao Liang Feng
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Frequency Domain ◽  
Support Vector ◽  
Tool Wear Monitoring ◽  
Machining Processes ◽  
Time Frequency ◽  
Svm Model ◽  
The Status ◽  
Wear Monitoring

Tool wear monitoring plays an important role in the automatic machining processes. Therefore, it is necessary to establish a reliable method to predict tool wear status. In this paper, features of acoustic emission (AE) extracted from time-frequency domain are integrated with force features to indicate the status of tool wear. Meanwhile, a support vector machine (SVM) model is employed to distinguish the tool wear status. The result of the classification of different tool wear status proved that features extracted from time-frequency domain can be the recognize-features of high recognition precision.

scholarly journals Investigation of Relation between Fracture Scale and Acoustic Emission Time-Frequency Parameters in Rocks

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Junwen Zhang
Keyword(s):  
Acoustic Emission ◽  
Uniaxial Compression ◽  
Fracture Process ◽  
Evaluation Model ◽  
Rock Fracture ◽  
Dominant Frequency ◽  
Time Frequency ◽  
Ae Energy ◽  
Emission Time ◽  
Fracture Scale

To investigate relation between fracture scale and acoustic emission time-frequency parameters in rocks, experiments of acoustic emission monitoring of granite uniaxial compression were carried out. The AE signal energy and dominant-frequency of granite fracture process were extracted by means of AE time-frequency analysis. The relation between fracture scale and AE time-frequency parameters (energy and frequency) in granite fracture process was analyzed. The evaluation model of rock fracture scale based on AE energy and dominant-frequency was established by using the intrinsic relation between the scale of rock fracture and the time-frequency parameters of rock mass. The evolution of crack scale in the process of uniaxial compression was analyzed based on the evaluation model of rock fracture scale. Results show that the AE energy and the dominant-frequency can reflect the crack scale inside the rock. The scale of rock fracture is proportional to the AE energy, which is inversely proportional to the AE dominant-frequency. Signals with low frequency and high energy usually represent large-scale cracks. On the contrary, if the high frequency has low energy value, it indicates a small-scale crack. The theory and method of evaluation of rock rupture scale based on AE time-frequency information (energy, frequency) can describe the failure process of rock crack scale variation characteristics. It provides a way and method for investigating the characterization of fracture size evolution process of rock fracture.

scholarly journals Application of the Acoustic Emission Method for Diagnosis of On-Load Tap Changer

2017 ◽  
Vol 42 (1) ◽  
pp. 29-35 ◽  
Author(s):  
Henryk Majchrzak ◽  
Andrzej Cichoń ◽  
Sebastian Borucki
Keyword(s):  
Acoustic Emission ◽  
Frequency Domain ◽  
Time Domain ◽  
Operating Conditions ◽  
Time Frequency ◽  
Measurement Results ◽  
Tap Changer ◽  
The Time Domain ◽  
Load Tap Changer ◽  
Short Time

Abstract This paper provides an example of the application of the acoustic emission (AE) method for the diagnosis of technical conditions of a three-phase on-load tap-changer (OLTC) GIII type. The measurements were performed for an amount of 10 items of OLTCs, installed in power transformers with a capacity of 250 MVA. The study was conducted in two different OLTC operating conditions during the tapping process: under load and free running conditions. The analysis of the measurement results was made in both time domain and time-frequency domain. The description of the AE signals generated by the OLTC in the time domain was performed using the analysis of waveforms and determined characteristic times. Within the time-frequency domain the measured signals were described by short-time Fourier transform spectrograms.

Reflection technique in time‐frequency domain using multicomponent acoustic emission signals and application to geothermal reservoirs

Geophysics ◽  
2002 ◽  
Vol 67 (3) ◽  
pp. 928-938 ◽  
Author(s):  
Nobukazu Soma ◽  
Hiroaki Niitsuma ◽  
Roy Baria
Keyword(s):  
Acoustic Emission ◽  
Wavelet Transform ◽  
Frequency Domain ◽  
Random Noise ◽  
Spherical Shape ◽  
Source Distribution ◽  
S Wave ◽  
Spectral Matrix ◽  
Time Frequency ◽  
Reflected Wave

We have developed a reflection technique for estimating deep geothermal reservoir structures using acoustic emission signals as a source, which is useful when there is no proper estimating technique because of high temperature, high pressure, and great depth. Because its resolution is not high enough for comparison with methods such as well logging, we have enhanced the technique by developing a time–frequency‐domain analysis of multicomponent acoustic emission signals using a wavelet transform. The reflected wave is separated from an incoherent coda by analyzing the shape of a 3‐D hodogram: a linear shape indicates the arrival of a coherent signal such as a reflected wave, and an incoherent signal such as a coda makes a spherical shape. We construct a spectral matrix of 3‐D particle motion using a wavelet transform, as is done in a time–frequency domain. We evaluate the linearity of the 3‐D hodogram for each time and frequency by using the eigenvalues of the spectral matrix. Three‐dimensional inversion of the distribution of hodogram linearity in the time–frequency domain lets us image the deep subsurface structure. The inversion is based on the diffraction stack. We reduce the uncertainties by investigating S‐wave polarization direction, and we compensate for inhomogeneous source distribution to get reliable estimates with high resolution. We then evaluate our methods with synthetic signals. We discriminate a coherent wave from incoherent random noise in the presence of an S/N ratio of −3.7 dB and detect reflectors at correct depths with a small number of detectors. We apply the method to data from the European hot, dry rock site in Soultz‐sous‐Forêts, France, and compare our estimates with those from a number of borehole observations. The detected reflectors agree with the location of fracture zones. We demonstrate the feasibility of the method for detecting reflectors at great depths.

scholarly journals An improved method for recognizing pediatric epileptic seizures based on advanced learning and moving window technique

2021 ◽  
pp. 1-21
Author(s):  
Satarupa Chakrabarti ◽  
Aleena Swetapadma ◽  
Prasant Kumar Pattnaik
Keyword(s):  
Random Forest ◽  
Frequency Domain ◽  
Epileptic Seizure ◽  
Seizure Detection ◽  
Detection Methods ◽  
Patient Specific ◽  
Moving Window ◽  
Improved Method ◽  
Time Frequency ◽  
Statistical Measures

In this work, advanced learning and moving window-based methods have been used for epileptic seizure detection. Epilepsy is a disorder of the central nervous system and roughly affects 50 million people worldwide. The most common non-invasive tool for studying the brain activity of an epileptic patient is the electroencephalogram. Accurate detection of seizure onset is still an elusive work. Electroencephalogram signals belonging to pediatric patients from Children’s Hospital Boston, Massachusetts Institute of Technology have been used in this work to validate the proposed method. For determining between seizure and non-seizure signals, feature extraction techniques based on time-domain, frequency domain, time-frequency domain have been used. Four different methods (decision tree, random forest, artificial neural network, and ensemble learning) have been studied and their performances have been compared using different statistical measures. The test sample technique has been used for the validation of all seizure detection methods. The results show better performance by random forest among all the four classifiers with an accuracy, sensitivity, and specificity of 91.9%, 94.1%, and 89.7% respectively. The proposed method is suggested as an improved method because it is not channel specific, not patient specific and has a promising accuracy in detecting epileptic seizure.

Sign in / Sign up

Export Citation Format

Share Document