Gas Turbine Condition Monitoring Using Acoustic Emission Signals

2019 ◽  
Vol 2 (3) ◽  
Author(s):  
S. Shahkar ◽  
K. Khorasani
Keyword(s):  
Acoustic Emission ◽  
Gas Turbine ◽  
Condition Monitoring ◽  
Gas Turbines ◽  
Acoustic Emissions ◽  
Time Instant ◽  
Rotary Machinery ◽  
Ae Signal ◽  
Reliable Classification ◽  
Ae Signals

Acoustic emission (AE) signals are recognized as complementary measures for detecting incipient faults and condition monitoring in rotary machinery due to their containment of sources of potential fault energy. However, determining the potential sources of faults cannot be easily realized due to the non-stationarity of AE signals. Available techniques that are capable of evoking instantaneous characteristics of a particular AE signal cannot optimally perform in a sense that there is no guarantee that these characteristics (hereinafter referred to as the “features”) remain constant when another AE signal is obtained from the system, albeit operating under the same machine condition at a different time instant. This paper provides a theoretical framework for developing a highly reliable classification and detection methodology for gas turbine condition monitoring based on AE signals. Mathematical results obtained in this paper are evaluated and validated by using actual gas turbines that are operating in power generating plants, to demonstrate the practicality and simplicity of our methodologies. Emphasis is given to acoustic emissions of similar brand and sized gas turbine turbomachinery under different health conditions and/or aging characteristics.

Acoustic Emission Signal Analysis for Tool Condition Monitoring in Microendmilling of Aluminium Alloy

2014 ◽  
Vol 984-985 ◽  
pp. 25-30
Author(s):  
Muniyandi Prakash ◽  
P. Ravisankar ◽  
Mani Kanthababu
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Aluminium Alloy ◽  
Condition Monitoring ◽  
Dominant Frequency ◽  
Tool Condition Monitoring ◽  
Tool Condition ◽  
Ae Energy ◽  
Ae Signal ◽  
Ae Signals

In this study, the effect of tool wear is correlated with acoustic emission (AE) signal during microendmilling of aluminium alloy (AA 1100). The AE signals were acquired using Kistler make AE sensor and the signal features are analyzed in time domain (root mean square (RMS)) and frequency domain (dominant frequency and amplitude). The dominant frequency of the AE signal shows increasing trend with increase in the tool wear, where as AERMSshow uneven trend. The discrete wavelet transformation technique (DWT) has also been carried out by decomposing the required AE signal in different frequency bands. The AERMSand specific AE energy were computed for the decomposed AE signals. From the specific AE energy, it is observed that shearing occurs during microendmilling and also found to be similar that of macro-regieme endmilling. The result demonstrated that the AE signals are potential indicator for tool condition monitoring in microendmilling.

scholarly journals Analysis of Acoustic Emission (AE) Signals for Quality Monitoring of Laser Lap Microwelding

2021 ◽  
Vol 11 (15) ◽  
pp. 7045
Author(s):  
Ming-Chyuan Lu ◽  
Shean-Juinn Chiou ◽  
Bo-Si Kuo ◽  
Ming-Zong Chen
Keyword(s):  
Stainless Steel ◽  
Acoustic Emission ◽  
Frequency Domain ◽  
Monitoring System ◽  
Welding Quality ◽  
Steel Sheets ◽  
Signal Features ◽  
Ae Signal ◽  
Laser Microwelding ◽  
Ae Signals

In this study, the correlation between welding quality and features of acoustic emission (AE) signals collected during laser microwelding of stainless-steel sheets was analyzed. The performance of selected AE features for detecting low joint bonding strength was tested using a developed monitoring system. To obtain the AE signal for analysis and develop the monitoring system, lap welding experiments were conducted on a laser microwelding platform with an attached AE sensor. A gap between the two layers of stainless-steel sheets was simulated using clamp force, a pressing bar, and a thin piece of paper. After the collection of raw signals from the AE sensor, the correlations of welding quality with the time and frequency domain features of the AE signals were analyzed by segmenting the signals into ten 1 ms intervals. After selection of appropriate AE signal features based on a scatter index, a hidden Markov model (HMM) classifier was employed to evaluate the performance of the selected features. Three AE signal features, namely the root mean square (RMS) of the AE signal, gradient of the first 1 ms of AE signals, and 300 kHz frequency feature, were closely related to the quality variation caused by the gap between the two layers of stainless-steel sheets. Classification accuracy of 100% was obtained using the HMM classifier with the gradient of the signal from the first 1 ms interval and with the combination of the 300 kHz frequency domain signal and the RMS of the signal from the first 1 ms interval.

Experiment on Surface Roughness and Acoustic Emission Signal in Infeed Period of Cylindrical Plunge Grinding

2013 ◽  
Vol 690-693 ◽  
pp. 2442-2445 ◽  
Author(s):  
Hao Lin Li ◽  
Hao Yang Cao ◽  
Chen Jiang
Keyword(s):  
Surface Roughness ◽  
Acoustic Emission ◽  
Acoustic Emission Signal ◽  
Feed Rate ◽  
Grinding Process ◽  
Experiment Research ◽  
Plunge Grinding ◽  
Emission Signal ◽  
Ae Signal ◽  
Ae Signals

This work presents an experiment research on Acoustic emission (AE) signal and the surface roughness of cylindrical plunge grinding with the different infeed time. The changed infeed time of grinding process is researched as an important parameter to compare AE signals and surface roughnesses with the different infeed time in the grinding process. The experiment results show the AE signal is increased by the increased feed rate. In the infeed period of the grinding process, the surface roughness is increased at first, and then is decreased.

Research on Feature Extraction Method Based on Rub-Impact Acoustic Emission Signals of Mechanical Seal End Faces

2010 ◽  
Vol 36 ◽  
pp. 68-74
Author(s):  
Chuan Jun Liao ◽  
Shuang Fu Suo ◽  
Wei Feng Huang
Keyword(s):  
Acoustic Emission ◽  
Feature Extraction ◽  
Extraction Methods ◽  
Mechanical Seal ◽  
Mechanical Seals ◽  
Feature Extraction Method ◽  
Different Types ◽  
Ae Signal ◽  
Feature Information ◽  
Ae Signals

Acoustic emission (AE) techniques are put forward to monitor rub-impacts between rotating rings and stationary rings of mechanical seals by this paper. By analyzing feature extraction methods of the typical rub-impact AE signal, the method combining of wavelet scalogram and power spectrum is found useful, and can used to attribute the feature information implicated in rub-impact AE signals of mechanical seal end faces. Both simulations and experimental research prove that the method is effective, and are used successfully to identify the typical features of different types of rub-impacts of mechanical seal end faces.

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.

Reciprocating compressor valve damage estimation under varying speeds through the acoustic emission technique

2019 ◽  
Vol 10 (5) ◽  
pp. 621-633
Author(s):  
Hoi-Yin Sim ◽  
Rahizar Ramli ◽  
Ahmad Saifizul
Keyword(s):  
Acoustic Emission ◽  
Regression Analysis ◽  
Flow Rate ◽  
Reciprocating Compressor ◽  
Damage Estimation ◽  
Content Type ◽  
Air Compressor ◽  
Ae Signal ◽  
Valve Opening ◽  
Ae Signals

Purpose The purpose of this paper is to examine the effect of reciprocating compressor speeds and valve conditions on the roor-mean-square (RMS) value of burst acoustic emission (AE) signals associated with the physical motion of valves. The study attempts to explore the potential of AE signal in the estimation of valve damage under varying compressor speeds. Design/methodology/approach This study involves the acquisition of AE signal, valve flow rate, pressure and temperature at the suction valve of an air compressor with speed varrying from 450 to 800 rpm. The AE signals correspond to one compressor cycle obtained from two simulated valve damage conditions, namely, the single leak and double leak conditions are compared to those of the normal valve plate. To examine the effects of valve conditions and speeds on AE RMS values, two-way analysis of variance (ANOVA) is conducted. Finally, regression analysis is performed to investigate the relationship of AE RMS with the speed and valve flow rate for different valve conditions. Findings The results showed that AE RMS values computed from suction valve opening (SVO), suction valve closing (SVC) and discharge valve opening (DVO) events are significantly affected by both valve conditions and speeds. The AE RMS value computed from SVO event showed high linear correlation with speed compared to SVC and DVO events for all valve damage conditions. As this study is conducted at a compressor running at freeload, increasing speed of compressor also results in the increment of flow rate. Thus, the valve flow rate can also be empirically derived from the AE RMS value through the regression method, enabling a better estimation of valve damages. Research limitations/implications The experimental test rig of this study is confined to a small pressure ratio range of 1.38–2.03 (free-loading condition). Besides, the air compressor is assumed to be operated at a constant speed. Originality/value This study employed the statistical methods namely the ANOVA and regression analysis for valve damage estimation at varying compressor speeds. It can enable a plant personnel to make a better prediction on the loss of compressor efficiency and help them to justify the time for valve replacement in future.

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.

Acoustic Emission During Athermal Martensitic Transformation in Steels

1990 ◽  
Vol 112 (1) ◽  
pp. 84-91 ◽  
Author(s):  
Xiangying Liu ◽  
Elijah Kannatey-Asibu
Keyword(s):  
Free Energy ◽  
Acoustic Emission ◽  
Martensitic Transformation ◽  
Signal Intensity ◽  
Temperature Derivative ◽  
Process Characteristics ◽  
Ae Signal ◽  
The Relationship ◽  
Ae Signals ◽  
Start Temperature

A relationship developed earlier between acoustic emission signals and the process of athermal martensitic transformation based on the free energy associated with the process is extended and verified experimentally. The relationship is found to model the process characteristics very well. The intensity of AE signal generated during transformation was found to be proportional to the temperature derivative of the fraction of martensite, the cooling rate, and volume of specimen. The AE signal was also found to be related to the carbon content of the steel. During transformation, the signal intensity was found to increase to a peak, and then tail off near the end of the transformation. Values of the martensite start temperature obtained from plots of the total RMS squared AE signals were also found to correlate well with values from the literature.

Identification of Damage Modes in Twill-Weave Composite Based on EMD of AE Event

2012 ◽  
Vol 198-199 ◽  
pp. 60-63
Author(s):  
Wen Qin Han ◽  
Jin Yu Zhou
Keyword(s):  
Acoustic Emission ◽  
Fourier Transform ◽  
Composite Materials ◽  
Acoustic Emissions ◽  
Peak Frequency ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Different Types ◽  
Twill Weave ◽  
Ae Signals

Acoustic emission (AE) monitoring is the primary technology used for the identification of different types of failure in composite materials. Tensile test were carried out on twill-weave composite specimens, and acoustic emissions were recorded from these tests. AE signals were decomposed into a set of Intrinsic Mode Functions(IMF) components by means of Empirical Mode Decomposition(EMD) , the Fast Fourier Transform (FFT) of each IMF component was performed, it was shown that the event peak frequency of each IMF component could be directly related to the materials damage modes.

Remote Condition Monitoring of a Peaking Gas Turbine

1991 ◽  
Author(s):  
Ralph E. Harris ◽  
Harold R. Simmons ◽  
Anthony J. Smalley ◽  
Richard M. Baldwin ◽  
George Quentin
Keyword(s):  
Gas Turbine ◽  
Condition Monitoring ◽  
Gas Turbines ◽  
Vibration Amplitude ◽  
Thermal Stabilization ◽  
Cost Effective ◽  
System Structure ◽  
Start Up ◽  
Data Content ◽  
Software And Hardware

This paper illustrates how software and hardware for telecommunications and data acquisition enable cost-effective monitoring of peaking gas turbines using personal computers. It describes the design and evaluation of a system which transmits data from each start-up and shutdown over 1,500 miles to a monitoring computer. It presents system structure, interfaces, data content, and management. The system captures transient sequences of acceleration, synchronization, loading, thermal stabilization, steady operation, shutdown and cooldown; it yields coherent sets of speed, load, temperature, journal eccentricity, vibration amplitude, and phase at intervals appropriately spaced in time and speed. The data may be used to characterize and identify operational problems.

Sign in / Sign up

Export Citation Format

Share Document