A5100344649- Machine Fault Diagnosis Techniques
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Carbon Dioxide Capture Technologies
- Advanced machining processes and optimization
- Structural Integrity and Reliability Analysis
- Industrial Gas Emission Control
- Total Knee Arthroplasty Outcomes
- Membrane Separation and Gas Transport
- Advanced Algorithms and Applications
- Knee injuries and reconstruction techniques
- Adsorption and Cooling Systems
- Phase Equilibria and Thermodynamics
- Engineering Diagnostics and Reliability
- Mineral Processing and Grinding
- Microwave Engineering and Waveguides
- Water Systems and Optimization
- Zeolite Catalysis and Synthesis
- Geotechnical Engineering and Soil Stabilization
- Chemical Looping and Thermochemical Processes
- Seismic Performance and Analysis
- Structural Behavior of Reinforced Concrete
- Industrial Vision Systems and Defect Detection
- Ultra-Wideband Communications Technology
- Radio Frequency Integrated Circuit Design
Chungbuk National University
2024
Sejong University
2023-2024
Pusan National University
2009-2023
University of Ulsan
2013-2022
Korea Institute of Energy Research
2014-2022
Naver (South Korea)
2021
Asan Medical Center
2018-2019
Ulsan College
2018-2019
Ministry of Environment
2015-2018
Kookmin University
2017
This paper proposes a highly reliable fault diagnosis approach for low-speed bearings. The proposed first extracts wavelet-based features that represent diverse symptoms of multiple bearing defects. most useful are then selected by utilizing genetic algorithm (GA)-based kernel discriminative feature analysis cooperating with one-against-all multicategory support vector machines (OAA MCSVMs). Finally, each machine is individually trained its own includes the features, offering highest...
This paper presents a reliable fault diagnosis methodology for various single and multiple combined defects of low-speed rolling element bearings. method temporally partitions an acoustic emission (AE) signal selects portion the signal, which contains intrinsic information about bearing failures. then performs frequency analysis selected time-domain AE by using multilevel finite-impulse response filter banks to obtain most informative subband signals involving abnormal symptoms defects. It...
In practice, outliers, defined as data points that are distant from the other agglomerated in same class, can seriously degrade diagnostic performance. To reduce performance deterioration caused by outliers data-driven diagnostics, an outlier-insensitive hybrid feature selection (OIHFS) methodology is developed to assess subset quality. addition, a new evaluation metric created ratio of intraclass compactness interclass separability estimated understanding relationship between and outliers....
The demand for online fault diagnosis has recently increased in order to prevent severe unexpected failures machinery. To address this issue, paper first proposes a comprehensive bearing algorithm, which consists of signature extraction through time-frequency analysis and one-against-all multiclass support vector machines make reliable decisions. In addition, acoustic emission (AE) signals sampled at 1 MHz are used the early identification failures. Despite fact that proposed methodology...
Bearing failure generates impulses when the rolling elements pass cracked surface of bearing. Over past decade, acoustic emission (AE) techniques have been used to detect bearing failures operated in low-rotating speeds. However, since high sampling rates AE signals make it difficult design and extract discriminative fault features, deep neural network-based approaches proposed several recent studies. This paper proposes a convolutional network (CNN)-based diagnosis technique. In this work,...
This paper presents a novel method for diagnosing incipient bearing defects under variable operating speeds using convolutional neural networks (CNNs) trained via the stochastic diagonal Levenberg-Marquardt (S-DLM) algorithm. The CNNs utilize spectral energy maps (SEMs) of acoustic emission (AE) signals as inputs and automatically learn optimal features, which yield best discriminative models speeds. SEMs are two-dimensional that show distribution across different bands AE spectrum. It is...
This paper proposes an effective envelope analysis-based methodology for machinery condition monitoring and validates its efficacy by identifying bearing failures with 1-s acoustic emission (AE) signals sampled at 1 MHz. The proposed of low-speed bearings consists denoising to improve the signal-noise ratio acquired AE signal employing a soft-thresholding technique adaptively estimated positive negative noise levels analysis detect periodic impacts inherent in defects utilizing 2-D...
This letter presents a multi-fault diagnosis scheme for bearings using hybrid features extracted from their acoustic emissions and Bayesian inference-based one-against-all support vector machine (Bayesian OAASVM) multi-class classification. The OAASVM, which is standard extension of the binary machine, results in ambiguously labeled regions input space that degrade its classification performance. proposed OAASVM formulates feature as an appropriate Gaussian process prior, interprets decision...
Spherical storage tanks are used in various industries to store substances like gasoline, oxygen, waste water, and liquefied petroleum gas (LPG). Cracks the unaccepted defects, as can leak or spill contained substance through these cracks. Leakage from hazardous contaminate environment may lead fatal accidents. Therefore, ability detect cracks spherical is necessary avoid damage ensure public safety. In this paper, we present a crack detection case study of tank. The was performed using...
Vertically aligned Mn (10%)-doped Fe3O4 (Fe2.7Mn0.3O4) nanowire arrays were produced by the reduction/substitution of pregrown Fe2O3 nanowires. These nanowires ferromagnetic with a Verwey temperature 129 K. X-ray magnetic circular dichroism measurements revealed that Mn2+ ions preferentially occupy tetrahedral sites, substituting for Fe3+ ions. We observed substitution decreases magnetization, but increases electrical conductivity. developed highly sensitive gas sensors using these arrays,...
Pressure vessels (PV) are designed to hold liquids, gases, or vapors at high pressures in various industries, but a ruptured pressure vessel can be incredibly dangerous if cracks not detected the early stage. This paper proposes robust crack identification technique for using genetic algorithm (GA)-based feature selection and deep neural network (DNN) an acoustic emission (AE) examination. First, hybrid features extracted from multiple AE sensors that represent diverse symptoms of faults....
The ground-breaking ceremony of the10 MWe-scale dry-sorbent CO2 capture process was held in August 2012 and the construction finished October 2013. It integrated with a 500 MW power plant used slip-stream that, located at Hadong coal-fired (Unit #8), Korea Southern Power Company. From 2013, Institute Energy Research (KIER), Company, KC Cottrell have executed test operations order to find out optimal operational conditions several modification parts achieve target project goals 10 technology....
This paper proposes a fault detection methodology for bearings using envelope analysis with genetic algorithm (GA)-based adaptive filter bank. Although bandpass cooperates early identification of bearing defects, no general consensus has been reached as to which passband is optimal. study explores the impact various passbands specified by GA in terms residual frequency components-to-defect components ratio, evaluates degree defectiveness and finally outputs an optimal reliable detection.
The fact that rolling element bearing faults have an amplitude-modulating effect on their characteristic frequencies calls for sub-band analysis to determine optimal signal contains intrinsic information about faults. In this regard, it is significant accurately assess the presence of a bearing's abnormal symptoms. Hence, abnormality index (BAI) properly quantifies how much presented. Additionally, facilitate real-time based BAI, massively parallel approach introduced, where involves use...
Incipient defects in bearings are traditionally diagnosed either by developing discriminative models for features that extracted from raw acoustic emission (AE) signals, or detecting peaks at characteristic defect frequencies the envelope power spectrum of AE signals. Under variable speed conditions, however, such methods do not yield best results. This letter proposes a technique diagnosing incipient bearing under extracting different sub-bands inherently non-stationary signal, and then...
The purpose of this study is to characterize fracture modes in a concrete structure using an acoustic emission (AE) technique and data-driven approach. To clarify the damage process, specimens, which are reinforced (RC) beams, undergo four-point bending tests. During tests, impulses occurring AE signals automatically detected constant false-alarm rate (CFAR) algorithm. For each impulse, its parameters such as counts, duration, amplitude, risetime, energy, RA, AF calculated studied. mean...
This paper proposes a three-stage fault diagnosis strategy for multistage centrifugal pumps. First, the proposed method identifies and selects characteristic modes of vibration to overcome substantial noise produced by other unrelated macro-structural vibrations. In second stage, raw hybrid statistical features are extracted from in time, frequency, time-frequency domain. These result high-dimensional feature space. However, general, not all best characterize ongoing processes pump, some...