Classification of journal bearing friction states based on acoustic emission signals

2018 ◽  
Vol 85 (6) ◽  
pp. 434-442 ◽  
Author(s):  
Noushin Mokhtari ◽  
Clemens Gühmann
Keyword(s):  
Acoustic Emission ◽  
Time Domain ◽  
Journal Bearing ◽  
Prediction Method ◽  
Support Vector ◽  
Mechatronic Systems ◽  
Prediction Time ◽  
Ae Signals ◽  
Bearing Friction

Abstract For diagnosis and predictive maintenance of mechatronic systems, monitoring of bearings is essential. An important building block for this is the determination of the bearing friction condition. This paper deals with the possibility of monitoring different journal bearing friction states, such as mixed and fluid friction, and examines a new approach to distinguish between different friction intensities under several speed and load combinations based on feature extraction and feature selection methods applied on acoustic emission (AE) signals. The aim of this work is to identify separation effective features of AE signals to subsequently classify the journal bearing friction states. Furthermore, the acquired features give information about the mixed friction intensity, which is significant for remaining useful lifetime (RUL) prediction. Time domain features as well as features in the frequency domain have been investigated in this work. To increase the sensitivity of the extracted features the AE signals were transformed to the frequency-time-domain using continuous wavelet transform (CWT). Significant frequency bands are determined to separate different friction states more effective. A support vector machine (SVM) is used to classify the signals into three different friction classes. In the end the idea for an RUL prediction method by using the already determined information is given and explained.

Differentiation of journal bearing friction states and friction intensities based on feature extraction methods applied on acoustic emission signals

2017 ◽  
Vol 84 (s1) ◽  
Author(s):  
Noushin Mokhtari ◽  
Farid Rahbar ◽  
Clemens Gühmann
Keyword(s):  
Acoustic Emission ◽  
Feature Extraction ◽  
Journal Bearing ◽  
Extraction Methods ◽  
Mechatronic Systems ◽  
Mixed Friction ◽  
Feature Spaces ◽  
Prediction Time ◽  
Ae Signals ◽  
Bearing Friction

AbstractFor diagnosis and predictive maintenance of mechatronic systems, monitoring of bearings is essential. An important building block for this is the determination of the bearing friction condition. This paper deals with the possibility of monitoring different journal bearing friction states, such as mixed and fluid friction, and examines a new approach to distinguish between different friction intensities under several speed and load combinations based on feature extraction and feature selection methods applied on acoustic emission (AE) signals. The aim of this work is to identify separation effective features of AE signals to subsequently classify the journal bearing friction states. Furthermore, the acquired features give information about the mixed friction intensity, which is significant for remaining useful lifetime (RUL) prediction. Time domain features as well as features in the frequency domain have been investigated in this work. The combination of several features generates feature spaces. The position of the objects within these spaces has proved that it is possible to differentiate between journal bearing friction states with the use of AE signals and suitable feature extraction methods. In addition, features that indicate different mixed friction intensities have been found.

scholarly journals Intelligent Fault Diagnosis of Synchromesh Gearbox Using Fusion of Vibration and Acoustic Emission Signals for Performance Enhancement

2019 ◽  
Vol 10 (2) ◽  
Author(s):  
T Praveenkumar ◽  
M Saimurugan ◽  
K I Ramachandran
Keyword(s):  
Support Vector Machine ◽  
Acoustic Emission ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Support Vector ◽  
Feature Level Fusion ◽  
Sensor Signals ◽  
Early Fault Detection ◽  
Ae Signals ◽  
Level Fusion

Condition monitoring system monitors the system degradation and it identifies common failure modes. Several sensor signals are available for monitoring the changes in system components. Vibration signal is one of the most extensively used technique for monitoring rotating components as it identifies faults before the system fails. Early fault detection is the significant factor for condition monitoring, where Acoustic Emission ( AE ) sensor signals have been applied for early fault detection due to their high sensitivity and high frequency. In this paper, vibration and acoustic emission signals are acquired under various simulated gear and bearing fault conditions from the synchromesh gearbox. Then the statistical features are extracted from vibration and AE signals and then the prominent features are selected using J48 decision tree algorithm respectively. The best features from the vibration and AE signals are then fused using feature-level fusion strategy and it is classified using Support Vector Machine ( SVM ) and Proximal Support Vector Machine ( PSVM ) classifiers and it is compared with individual signals for fault diagnosis of the synchromesh gearbox. From the experiments, it is observed that the performance of the fault diagnosis system has been improved for the proposed feature level fusion technique compared to the performance of unfused vibration and AE feature sets.

scholarly journals Friction and Wear Monitoring Methods for Journal Bearings of Geared Turbofans Based on Acoustic Emission Signals and Machine Learning

Lubricants ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 29 ◽  
Author(s):  
Noushin Mokhtari ◽  
Jonathan Gerald Pelham ◽  
Sebastian Nowoisky ◽  
José-Luis Bote-Garcia ◽  
Clemens Gühmann
Keyword(s):  
Machine Learning ◽  
Acoustic Emission ◽  
Friction And Wear ◽  
Journal Bearing ◽  
Journal Bearings ◽  
Wear Volume ◽  
Time Frequency ◽  
Ae Signal ◽  
Ae Signals

In this work, effective methods for monitoring friction and wear of journal bearings integrated in future UltraFan® jet engines containing a gearbox are presented. These methods are based on machine learning algorithms applied to Acoustic Emission (AE) signals. The three friction states: dry (boundary), mixed, and fluid friction of journal bearings are classified by pre-processing the AE signals with windowing and high-pass filtering, extracting separation effective features from time, frequency, and time-frequency domain using continuous wavelet transform (CWT) and a Support Vector Machine (SVM) as the classifier. Furthermore, it is shown that journal bearing friction classification is not only possible under variable rotational speed and load, but also under different oil viscosities generated by varying oil inlet temperatures. A method used to identify the location of occurring mixed friction events over the journal bearing circumference is shown in this paper. The time-based AE signal is fused with the phase shift information of an incremental encoder to achieve an AE signal based on the angle domain. The possibility of monitoring the run-in wear of journal bearings is investigated by using the extracted separation effective AE features. Validation was done by tactile roughness measurements of the surface. There is an obvious AE feature change visible with increasing run-in wear. Furthermore, these investigations show also the opportunity to determine the friction intensity. Long-term wear investigations were done by carrying out long-term wear tests under constant rotational speeds, loads, and oil inlet temperatures. Roughness and roundness measurements were done in order to calculate the wear volume for validation. The integrated AE Root Mean Square (RMS) shows a good correlation with the journal bearing wear volume.

Study of Oil Starvation in Journal Bearing Using Acoustic Emission and Vibration Measurement Techniques

2020 ◽  
Vol 142 (12) ◽  
Author(s):  
Surojit Poddar ◽  
N. Tandon
Keyword(s):  
Acoustic Emission ◽  
Journal Bearing ◽  
Measurement Techniques ◽  
Peak Frequency ◽  
Vibration Measurement ◽  
Frequency Range ◽  
Frequency Shifts ◽  
Deformation And Fracture ◽  
Asperity Contacts ◽  
Ae Signals

Abstract This present article evaluates the state of starvation in a journal bearing using acoustic emission (AE) and vibration measurement techniques. A journal bearing requires a constant supply of oil in an adequate amount to develop a hydrodynamic film, thick enough to separate the surfaces and avoid asperity contacts. On a microscopic level, the surface interaction under starved lubrication results in deformation and fracture of asperities. This causes a proportionate increase in AE and vibration. The AE activities resulting from asperities interaction have significant energy in the frequency range of 100–400 kHz with peak frequencies in the range of 224–283 kHz. Further, the peak frequency shifts from the higher to lower side as the asperity interaction transits from the elastic to plastic contact. This information derived from the spectral analysis of AE signals can be used to develop condition monitoring parameters to proactively control the lubrication and prevent bearing failure.

Study on the Prediction Method for Brittle Failure of Hard Rock Based on Acoustic Emission Test

2012 ◽  
Vol 594-597 ◽  
pp. 376-379 ◽  
Author(s):  
S C. Xu ◽  
B R. Chen ◽  
C Y. Jin
Keyword(s):  
Acoustic Emission ◽  
Main Shock ◽  
Hard Rock ◽  
Emission Rate ◽  
Prediction Method ◽  
Triaxial Tests ◽  
True Triaxial ◽  
Acoustic Emission Test ◽  
Different Characteristics ◽  
Ae Signals

In this paper, a series of true triaxial tests indoor with acoustic emission mornitoring were conducted and the characteristics of acoustic emission rate and energy releasing rate in the section adjacent to failure were gained. According to the different characteristics of acoustic emission rate, we divided the events rate into three types which were main shock, foreshock-main shock and cluster shocks. And then, a prediction method for hard rock was put forward according to different events rate types based on the trends of AE signals in the section adjacent to failure for hard rock.

Real-Time Monitoring of Degradation of Zirconia Ceramic by Acoustic Emission

2013 ◽  
Vol 433-435 ◽  
pp. 816-820 ◽  
Author(s):  
Kai Ge Wu ◽  
Chan Yang Choe ◽  
Seung Mi Lee ◽  
Ji Ae Yoo ◽  
Chang Yong Hyun ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Low Temperature ◽  
Time Domain ◽  
Zirconia Ceramic ◽  
X Ray Diffraction ◽  
Zirconia Ceramics ◽  
X Ray ◽  
Ae Signal ◽  
Three Stages ◽  
Ae Signals

Acoustic emission (AE) technique was employed to monitor the low temperature degradation (LTD) behavior of a zirconia ceramic, which was carried out in air at 200°C. AE signals, typical waveform of which exhibited as pulse-like type, were detected during LTD and increased with the duration time of LTD. The AE signal of accumulative counts number and amplitude in time domain exhibited a roughly sigmoid variation including three stages, which reflect approximately the evolution of LTD. The AE findings were supported by X-ray diffraction (XRD) examination. It was suggested that AE technique can be used to monitor the mechanism of LTD of zirconia ceramics.

The Connector Blanking Fracture Surface Quality Prediction in Progressive Stamping Based on Support Vector Machine

2014 ◽  
Vol 620 ◽  
pp. 263-268
Author(s):  
Li Zhi Gu ◽  
Lei Wang ◽  
Tian Qing Zheng
Keyword(s):  
Support Vector Machine ◽  
Fracture Surface ◽  
Surface Quality ◽  
Influencing Factors ◽  
Dimensional Space ◽  
Orthogonal Experiment ◽  
Prediction Method ◽  
Production Model ◽  
Support Vector

The influencing factors of technical parameters on blanking fracture surface quality are quite few and complicated, including clearance, speed, die roughness and punch radius. And determination of these influencing factors and optimization of the process parameters combination are vital to the blanking with stability and duration. The determination of these parameters depending on experience of designer in production leads to a longer development period and higher cost in testing modes. In the current study, a kind of prediction method for fracture surface quality was put forward by using nonlinear mapping properties and learning capacity of the support vector machine theory in which nonlinear input can be mapped into higher dimensional space by selecting kernel function RBF, and compromise parameter with C=0, and expectation error of ε=0. 1. The final production model was obtained by practice with orthogonal experiment of four factors times three levels. Experimental verification was conducted by selecting a number of test data. Results have shown that the predicted values were in good agreement with those from tests.

Comparison of SVM, RF and SGD Methods for Determination of Programmer's Performance Classification Model in Social Media Activities

2020 ◽  
Vol 4 (2) ◽  
pp. 329-335
Author(s):  
Rusydi Umar ◽  
Imam Riadi ◽  
Purwono
Keyword(s):  
Social Media ◽  
Gradient Descent ◽  
Classification Model ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Algorithm ◽  
Vector Machines ◽  
Performance Patterns ◽  
A Company

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.

Sign in / Sign up

Export Citation Format

Share Document