Pattern recognition approach for acoustic emission burst detection in a gearbox under different operating conditions

2019 ◽  
Vol 25 (17) ◽  
pp. 2295-2304
Author(s):  
Félix Leaman ◽  
Cristián Molina Vicuña ◽  
Ralph Baltes ◽  
Elisabeth Clausen
Keyword(s):  
Pattern Recognition ◽  
Acoustic Emission ◽  
Condition Monitoring ◽  
Rotational Speed ◽  
Operating Conditions ◽  
Burst Detection ◽  
Threshold Method ◽  
Planetary Gearbox ◽  
Industrial Sectors ◽  
Artificial Neural Network Ann

Diverse machines in the mining, energy, and other industrial sectors are subject to variable operating conditions (OCs) such as rotational speed and load. Therefore, the condition monitoring techniques must be adapted to face this scenario. Within these techniques, the acoustic emission (AE) technology has been successfully used as a technique for condition monitoring of components such as gears and bearings. An AE analysis involves the detection of transients within the signals, which are called AE bursts. Traditional methods for AE burst detection are based on the definition of threshold values. When the machine under study works under variable rotational speed and load, threshold-based methods could produce inadequate results due to the influence of these OCs on the AE. This paper presents a novel burst detection method based on pattern recognition using an artificial neural network (ANN) for classification. The results of the method were compared to an adaptive threshold method. Experimental data were measured in a planetary gearbox test rig under different OCs. The results showed that both methods perform similarly when signals measured under constant OCs are considered. However, when signals are measured under different OCs, the ANN method performs better. Thus, the comparative analysis showed the good potential of the approach to improve an AE analysis of variable speed and/or load machines.

Evaluation of acoustic emission burst detection methods in a gearbox under different operating conditions

2018 ◽  
Vol 25 (4) ◽  
pp. 895-906 ◽  
Author(s):  
F. Leaman ◽  
C. Niedringhaus ◽  
S. Hinderer ◽  
K. Nienhaus
Keyword(s):  
Acoustic Emission ◽  
Processing Technique ◽  
Operating Conditions ◽  
Detection Methods ◽  
Threshold Values ◽  
Burst Detection ◽  
Signal Processing Technique ◽  
Planetary Gearbox ◽  
Machine Condition Monitoring ◽  
Definition Of

In account of its abilities to follow the damage progression, also at early stages, the acoustic emission (AE) analysis has become an attractive technique for machine condition monitoring. An AE analysis involves the detection of transients within the signals, which are called AE bursts. Traditional methods for AE burst detection are based on the definition of threshold values. When the machine under analysis works under variable operating conditions, threshold-based methods could lead to poor results due to the influence of these conditions on the AE generation. The present work compares the ability of three AE burst detection methods in a planetary gearbox working under different rotational speeds and loads. The results showed that performance could be significantly improved by using factors of the root mean square value as threshold values instead of fixed values. Among the evaluated methods, the method that includes demodulation and differentiation as a signal processing technique had the best performance overall.

Real-Time Angular Velocity-Based Misfire Detection Using Artificial Neural Networks

2019 ◽  
Vol 141 (6) ◽  
Author(s):  
Pan Zhang ◽  
Wenzhi Gao ◽  
Qixin Song ◽  
Yong Li ◽  
Lifeng Wei ◽  
...  
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Angular Velocity ◽  
Operating Conditions ◽  
Diagnostic Methods ◽  
Ic Engine ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Frequency Domain Techniques ◽  
Misfire Detection

In this paper, an artificial neural network (ANN) is introduced in order to detect the occurrence of misfire in an internal combustion (IC) engine by analyzing the crankshaft angular velocity. This study presents three reliable misfire detection procedures. In the first two methods, the fault features are extracted using both time domain and frequency domain techniques, and a multilayer perceptron (MLP) serves as the pattern recognition tool for detecting the misfiring cylinder. In the third method, a one-dimensional (1D) convolutional neural network (CNN) that combines feature extraction capability and pattern recognition is adopted for misfire detection. The experimental data are obtained by setting a six in-line diesel engine with different cylinder misfiring to work under representative operating conditions. Finally, all three diagnostic methods achieved satisfactory results, and the 1D CNN achieved the best performance. The current study provides a novel way to detect misfiring in IC engines.

scholarly journals Condition monitoring of roller bearings using acoustic emission

2021 ◽  
Vol 6 (2) ◽  
pp. 367-376
Author(s):  
Daniel Cornel ◽  
Francisco Gutiérrez Guzmán ◽  
Georg Jacobs ◽  
Stephan Neumann
Keyword(s):  
Acoustic Emission ◽  
Condition Monitoring ◽  
Roller Bearing ◽  
Surface Damage ◽  
Operating Conditions ◽  
Time To Failure ◽  
Damage Initiation ◽  
Emission Signal ◽  
Repair Costs ◽  
Bearing Failures

Abstract. Roller bearing failures in wind turbines' gearboxes lead to long downtimes and high repair costs, which could be reduced by the implementation of a predictive maintenance strategy. In this paper and within this context, an acoustic-emission-based condition monitoring system is applied to roller bearing test rigs with the aim of identifying critical operating conditions before bearing failures occurs. Furthermore, a comparison regarding detection times is carried out with traditional vibration-based condition monitoring systems, with a focus on premature bearing failures such as white etching cracks. The investigations show a sensitivity of the acoustic-emission system towards lubricating conditions. In addition, the system has shown that a damaged surface can be detected at least ∼ 4 % (8 h, regarding the time to failure) earlier than by using the vibration-based system. Furthermore, significant deviations from the average acoustic-emission signal were detected up to ∼ 50 % (130 h) before the test stop and are possibly related to sub-surface damage initiation and might result in an earlier damage detection in the future.

PROPOSING A NEW ACOUSTIC EMISSION PARAMETER FOR BEARING CONDITION MONITORING IN ROTATING MACHINES

2013 ◽  
Vol 37 (4) ◽  
pp. 1105-1114 ◽  
Author(s):  
Seyed Ali Niknam ◽  
Victor Songmene ◽  
Y.H. Joe Au
Keyword(s):  
Acoustic Emission ◽  
Condition Monitoring ◽  
Rotational Speed ◽  
Rotating Shaft ◽  
The Past ◽  
Emission Parameter ◽  
Bearing Condition Monitoring ◽  
Rolling Element ◽  
Machine Parts ◽  
Ae Signals

Bearings are important machine parts and their condition is often critical to success of an operation or process, hence there is a great need for periodic knowledge of their performance. According to reported research works in the past several years, it is believed that the extracted information from acoustic emission (AE) signals can be used for bearing condition monitoring. In this work, a novel parameter based on using the ratio of AE mean (μ) and AE standard deviation (σ), formulated as μ/σ is proposed to distinguish between lubricated and dry bearings. A heavy duty test rig was used in experimental work. Various levels of radial loads and rotational speed (ω) were applied to rotating shaft, which is connected to rolling element bearings. It was found that, except few cases, regardless of various levels of radial loads used, at higher levels of rotational speed, dry and lubricated bearings can be clearly distinguished when using proposed parameter.

scholarly journals Condition Monitoring of roller bearings using Acoustic Emission

2020 ◽  
Author(s):  
Daniel Cornel ◽  
Francisco Gutiérrez Guzmán ◽  
Georg Jacobs ◽  
Stephan Neumann
Keyword(s):  
Acoustic Emission ◽  
Condition Monitoring ◽  
Roller Bearing ◽  
Surface Damage ◽  
Operating Conditions ◽  
Time To Failure ◽  
Damage Initiation ◽  
Emission Signal ◽  
Bearing Failures ◽  
Condition Monitoring System

Abstract. Roller bearing failures in wind turbines gearboxes lead to long downtimes and high repairing costs, which could be reduced by the implementation of a predictive maintenance strategy. In this paper and within this context an acoustic emission based condition monitoring system is applied to roller bearing test rigs with the aim of identifying critical operating conditions before bearing failures occurs. Furthermore, a comparison regarding detection times is carried out with a traditional vibration based condition monitoring systems, with focus on premature bearing failures such as white etching cracks. The investigations show a sensitivity of the acoustic emission system towards lubricating conditions. In addition, the system has shown, that a damaged surface can be detected at least ~ 4 % (8 hours, regarding the time to failure) earlier than by using the vibration based system. Furthermore, significant deviations from the average acoustic emission signal were detected up to ~ 50 % (130 hours) before the test stop and are possibly related to sub-surface damage initiation and might result in an earlier damage detection in the future.

scholarly journals Structural Health and Condition Monitoring with Acoustic Emission and Guided Ultrasonic Waves: What about Long-Term Durability of Sensors, Sensor Coupling and Measurement Chain?

2021 ◽  
Vol 11 (24) ◽  
pp. 11648
Author(s):  
Andreas J. Brunner
Keyword(s):  
Acoustic Emission ◽  
Process Control ◽  
Condition Monitoring ◽  
Cost Optimization ◽  
Pressure Vessels ◽  
Ultrasonic Waves ◽  
Structural Health ◽  
Industrial Sectors ◽  
Guided Ultrasonic Waves

Acoustic Emission (AE) and Guided Ultrasonic Waves (GUWs) are non-destructive testing (NDT) methods in several industrial sectors for, e.g., proof testing and periodic inspection of pressure vessels, storage tanks, pipes or pipelines and leak or corrosion detection. In materials research, AE and GUW are useful for characterizing damage accumulation and microscopic damage mechanisms. AE and GUW also show potential for long-term Structural Health and Condition Monitoring (SHM and CM). With increasing computational power, even online monitoring of industrial manufacturing processes has become feasible. Combined with Artificial Intelligence (AI) for analysis this may soon allow for efficient, automated online process control. AI also plays a role in predictive maintenance and cost optimization. Long-term SHM, CM and process control require sensor integration together with data acquisition equipment and possibly data analysis. This raises the question of the long-term durability of all components of the measurement system. So far, only scant quantitative data are available. This paper presents and discusses selected aspects of the long-term durability of sensor behavior, sensor coupling and measurement hardware and software. The aim is to identify research and development needs for reliable, cost-effective, long-term SHM and CM with AE and GUW under combined mechanical and environmental service loads.

scholarly journals Research on Pattern Recognition Method of Blockage Signal in Pipeline Based on LMD Information Entropy and ELM

2017 ◽  
Vol 2017 ◽  
pp. 1-16 ◽  
Author(s):  
Jingzong Yang ◽  
Xiaodong Wang ◽  
Zao Feng ◽  
Guoyong Huang
Keyword(s):  
Pattern Recognition ◽  
Impulse Response ◽  
Information Entropy ◽  
Operating Conditions ◽  
Support Vector ◽  
Entropy Theory ◽  
Pattern Recognition Method ◽  
Response Signal ◽  
Recognition Method ◽  
Learning Machine

Aiming at the nonstationary and nonlinear characteristics of acoustic impulse response signal in pipeline blockage and the difficulty in identifying the different degrees of blockage, this paper proposed a pattern recognition method based on local mean decomposition (LMD), information entropy theory, and extreme learning machine (ELM). Firstly, the impulse response signals of pipeline extracted in different operating conditions were decomposed with LMD method into a series of product functions (PFs). Secondly, based on the information entropy theory, the appropriate energy entropy, singular spectrum entropy, power spectrum entropy, and Hilbert spectrum entropy were extracted as the input feature vectors. Finally, ELM was introduced for classification of pipeline blockage. Through the analysis of acoustic impulse response signal collected under the condition of health and different degrees of blockages in pipeline, the results show that the proposed method can well characterize the state information. Also, it has a great advantage in terms of accuracy and it is time consuming when compared with the support vector machine (SVM) and BP (backpropagation) model.

An efficient short-time Fourier transform algorithm for grinding wheel condition monitoring through acoustic emission

2021 ◽  
Vol 113 (1-2) ◽  
pp. 585-603
Author(s):  
Wenderson N. Lopes ◽  
Pedro O. C. Junior ◽  
Paulo R. Aguiar ◽  
Felipe A. Alexandre ◽  
Fábio R. L. Dotto ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Fourier Transform ◽  
Condition Monitoring ◽  
Grinding Wheel ◽  
Short Time Fourier Transform ◽  
Short Time

scholarly journals A Numerical Investigation into the PAT Hydrodynamic Response to Impeller Rotational Speed Variation

2021 ◽  
Vol 13 (14) ◽  
pp. 7998
Author(s):  
Maxime Binama ◽  
Kan Kan ◽  
Hui-Xiang Chen ◽  
Yuan Zheng ◽  
Daqing Zhou ◽  
...  
Keyword(s):  
Rotational Speed ◽  
Distribution Systems ◽  
Water Distribution ◽  
Production Efficiency ◽  
Operating Conditions ◽  
Energy Regulation ◽  
Speed Increase ◽  
Energy Field ◽  
Long Run ◽  
Study Results

The utilization of pump as turbines (PATs) within water distribution systems for energy regulation and hydroelectricity generation purposes has increasingly attracted the energy field players’ attention. However, its power production efficiency still faces difficulties due to PAT’s lack of flow control ability in such dynamic systems. This has eventually led to the introduction of the so-called “variable operating strategy” or VOS, where the impeller rotational speed may be controlled to satisfy the system-required flow conditions. Taking from these grounds, this study numerically investigates PAT eventual flow structures formation mechanism, especially when subjected to varying impeller rotational speed. CFD-backed numerical simulations were conducted on PAT flow under four operating conditions (1.00 QBEP, 0.82 QBEP, 0.74 QBEP, and 0.55 QBEP), considering five impeller rotational speeds (110 rpm, 130 rpm, 150 rpm, 170 rpm, and 190 rpm). Study results have shown that both PAT’s flow and pressure fields deteriorate with the machine influx decrease, where the impeller rotational speed increase is found to alleviate PAT pressure pulsation levels under high-flow operating conditions, while it worsens them under part-load conditions. This study’s results add value to a thorough understanding of PAT flow dynamics, which, in a long run, contributes to the solution of the so-far existent technical issues.

scholarly journals Diamond Grinding Wheel Condition Monitoring Based on Acoustic Emission Signals

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1054
Author(s):  
Guo Bi ◽  
Shan Liu ◽  
Shibo Su ◽  
Zhongxue Wang
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Condition Monitoring ◽  
Time Domain ◽  
Diamond Wheel ◽  
Feature Representation ◽  
Grinding Wheel ◽  
Time Waveform ◽  
Original Time ◽  
Whole Life Cycle

Acoustic emission (AE) phenomenon has a direct relationship with the interaction of tool and material which makes AE the most sensitive one among various process variables. However, its prominent sensitivity also means the characteristics of random and board band. Feature representation is a difficult problem for AE-based monitoring and determines the accuracy of monitoring system. It is knottier for the situation of using diamond wheel grinding optical components, not only because of the complexity of grinding process but also the high requirement on surface and subsurface quality. This paper is dedicated to AE-based condition monitoring of diamond wheel during grinding brittle materials and feature representation is paid more attention. AE signal of brittle-regime grinding is modeled as a superposition of a series of burst-type AE events. Theory analysis manifested that original time waveform and frequency spectrum are all suitable for feature representation. Considering the convolution form of b-AE in time domain, a convolutional neural network with original time waveform of AE signals as the input is built for multi-class classification of wheel state. Detailed state division in a wheel’s whole life cycle is realized and the accuracy is over 90%. Different from the overlapping in time domain, AE components of different crack mechanisms are probably separated in frequency domain. From this point of view, AE spectrums are more suitable for feature extraction than the original time waveform. In addition, the time sequence of AE samples is essential for the evaluation of wheel’s life elapse and making use of sequential information is just the idea behind recurrent neural network (RNN). Therefore, long short-term memory (LSTM), a special kind of RNN, is used to build a regression prediction model of wheel state with AE spectrums as the model input and satisfactory prediction accuracy is acquired on the test set.

Sign in / Sign up

Export Citation Format

Share Document