scholarly journals Crack Classification of a Pressure Vessel Using Feature Selection and Deep Learning Methods

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4379 ◽  
Author(s):  
Manjurul Islam ◽  
Muhammad Sohaib ◽  
Jaeyoung Kim ◽  
Jong-Myon Kim
Keyword(s):  
Feature Selection ◽  
Frequency Domain ◽  
Pressure Vessel ◽  
High Pressures ◽  
Early Stage ◽  
Pressure Vessels ◽  
Crack Identification ◽  
Hybrid Features ◽  
Time Frequency ◽  
Highly Effective

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 are not detected in the early stage. This paper proposes a robust crack identification technique for pressure vessels using genetic algorithm (GA)-based feature selection and a deep neural network (DNN) in an acoustic emission (AE) examination. First, hybrid features are extracted from multiple AE sensors that represent diverse symptoms of pressure vessel faults. These features stem from various signal processing domains, such as the time domain, frequency domain, and time-frequency domain. Heterogenous features from various channels ensure a robust feature extraction process but are high-dimensional, so may contain irrelevant and redundant features. This can cause a degraded classification performance. Therefore, we use GA with a new objective function to select the most discriminant features that are highly effective for the DNN classifier when identifying crack types. The potency of the proposed method (GA + DNN) is demonstrated using AE data obtained from a self-designed pressure vessel. The experimental results indicate that the proposed method is highly effective at selecting discriminant features. These features are used as the input of the DNN classifier, achieving a 94.67% classification accuracy.

scholarly journals Adsorbed Xenon Propellant Storage: Are Nanoporous Materials Worth the Weight?

2021 ◽  
Author(s):  
Melanie T. Huynh ◽  
Nickolas Gantzler ◽  
Samuel Hough ◽  
David Roundy ◽  
Praveen K. Thallapally ◽  
...  
Keyword(s):  
Pressure Vessel ◽  
High Pressures ◽  
Storage System ◽  
Large Mass ◽  
Pressure Vessels ◽  
Nanoporous Materials ◽  
Bulk Storage ◽  
Xenon Adsorption ◽  
Adsorption Data ◽  
Metal Organic

Xenon is used as a propellant for spacecraft. Conventionally, xenon is compressed to high pressures (75-300 bar) for bulk storage onboard the spacecraft. An adsorbed xenon storage system based on nanoporous materials (NPMs) could, potentially, (i) reduce the storage pressures, (ii) allow for thinner-walled and lighter pressure vessels, and (iii) if the NPM itself is sufficiently light, reduce the overall mass of the storage system and thus of the payload of the rocket launch.<br><br>To investigate, we develop a simple mathematical model of an adsorbed xenon storage system by coupling a mechanical model for the pressure vessel and a thermodynamic model for the density of xenon adsorbed in the NPM. From the model, we derive the optimal storage pressure, tailored to each NPM, with the objective of minimizing the mass of the storage materials (walls of the pressure vessel + NPM) required to store the xenon. The model enables us to: (i) rank NPMs for adsorbed xenon propellant storage, (ii) compare adsorbed storage to the baseline of bulk storage, and (iii) understand what properties of NPMs are desirable for adsorbed xenon propellant storage.<br><br>We use the model to evaluate several NPMs, mostly metal-organic frameworks (MOFs), for adsorbed xenon propellant storage at room temperature, using experimental xenon adsorption data as input. We find Ni-MOF-74 and MOF-505 outperform the traditional adsorbent, activated carbon. However, we find each optimized adsorbed xenon storage system is heavier than the optimized bulk storage system, owing dominantly to the large mass of the NPM itself. Our model suggests that, for a NPM to provide a lighter adsorbed xenon storage system compared to bulk storage, the saturation loading of xenon in the adsorbent must exceed ca. 94 mmol Xe/g adsorbent.

scholarly journals Multi-Band Frequency Window for Time-Frequency Fault Diagnosis of Induction Machines

2019 ◽  
Author(s):  
Jordi Burriel-Valencia ◽  
Ruben Puche-Panadero ◽  
Javier Martinez-Roman ◽  
Angel Sapena-Bano ◽  
Martin Riera-Guasp ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Time Window ◽  
Early Stage ◽  
Induction Machines ◽  
Frequency Domain Analysis ◽  
Frequency Resolution ◽  
Good Time ◽  
Band Frequency ◽  
Time Frequency ◽  
Multi Band

Induction machines drive many industrial processes, and their unexpected failure can cause heavy production losses. The analysis of the current spectrum can identify online the characteristic fault signatures at an early stage, avoiding unexpected breakdowns. Nevertheless, frequency domain analysis requires stable working conditions, which is not the case for wind generators, motors driving varying loads, etc. In these cases an analysis in the time-frequency domain -such as a spectrogram- is required for detecting faults signatures. The spectrogram is built using the short frequency Fourier transform, but its resolution depends critically on the time window used to generate it: short windows provide good time resolution, but poor frequency resolution, just the opposite than long windows. Therefore, the window must be adapted at each time to the shape of the expected fault harmonics, by highly skilled maintenance personnel. In this paper, this problem is solved with the design of a new multi-band window, which generates simultaneously many different narrow-band current spectrograms, and combines them into a single, high resolution one, without the need of manual adjustments. The proposed method is validated with the diagnosis of bar breakages during the start-up of a commercial induction motor.

Design and Analysis of Commercial Pressure Vessels to 500,000 Psi

1966 ◽  
Vol 88 (2) ◽  
pp. 500-506 ◽  
Author(s):  
I. Berman
Keyword(s):  
Material Property ◽  
Large Volume ◽  
Pressure Vessel ◽  
High Pressures ◽  
Pressure Vessels ◽  
New Method ◽  
Flow Strength ◽  
Property Changes ◽  
Shrink Fit ◽  
Very High

On the basis of the finiteness of the flow strength of structural materials, the pressures permitted by current methods of pressure vessel design are limited. In this paper the analysis of a new method of design of commercial large volume pressure vessels is presented. This new design, which is a controlled fluid fill, may be used for many excursions to very high pressures without failure. The pressure that may be attained seems limited only by material property changes at extreme hydrostatic pressures. Large volume commercial vessels to 500,000 psi with reasonable outer to inner diameters may be built. The controlled fluid-fill pressure vessels in addition to piercing the current upper pressure barrier is also competitive with the shrink-fit method at pressures as low as 15,000 psi.

Automated diagnosis of autism: in search of a mathematical marker

2014 ◽  
Vol 25 (6) ◽  
Author(s):  
Shreya Bhat ◽  
U. Rajendra Acharya ◽  
Hojjat Adeli ◽  
G. Muralidhar Bairy ◽  
Amir Adeli
Keyword(s):  
Nonlinear Dynamics ◽  
Frequency Domain ◽  
Early Stage ◽  
Neurodevelopmental Disorder ◽  
Nonlinear Dynamic Analysis ◽  
Autism Spectrum ◽  
Learning Ability ◽  
Diagnostic Tools ◽  
Eeg Signals ◽  
Time Frequency

AbstractAutism is a type of neurodevelopmental disorder affecting the memory, behavior, emotion, learning ability, and communication of an individual. An early detection of the abnormality, due to irregular processing in the brain, can be achieved using electroencephalograms (EEG). The variations in the EEG signals cannot be deciphered by mere visual inspection. Computer-aided diagnostic tools can be used to recognize the subtle and invisible information present in the irregular EEG pattern and diagnose autism. This paper presents a state-of-the-art review of automated EEG-based diagnosis of autism. Various time domain, frequency domain, time-frequency domain, and nonlinear dynamics for the analysis of autistic EEG signals are described briefly. A focus of the review is the use of nonlinear dynamics and chaos theory to discover the mathematical biomarkers for the diagnosis of the autism analogous to biological markers. A combination of the time-frequency and nonlinear dynamic analysis is the most effective approach to characterize the nonstationary and chaotic physiological signals for the automated EEG-based diagnosis of autism spectrum disorder (ASD). The features extracted using these nonlinear methods can be used as mathematical markers to detect the early stage of autism and aid the clinicians in their diagnosis. This will expedite the administration of appropriate therapies to treat the disorder.

scholarly journals Study on Fault Diagnosis of Rolling Bearing Based on Time-Frequency Generalized Dimension

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Yu Yuan ◽  
Xing Zhao ◽  
Jiyou Fei ◽  
Yulong Zhao ◽  
Jiahui Wang
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Early Stage ◽  
Fractal Theory ◽  
Rolling Bearing ◽  
Mechanical Equipment ◽  
Rolling Bearings ◽  
Common Component ◽  
Time Frequency ◽  
Multifractal Method

The condition monitoring technology and fault diagnosis technology of mechanical equipment played an important role in the modern engineering. Rolling bearing is the most common component of mechanical equipment which sustains and transfers the load. Therefore, fault diagnosis of rolling bearings has great significance. Fractal theory provides an effective method to describe the complexity and irregularity of the vibration signals of rolling bearings. In this paper a novel multifractal fault diagnosis approach based on time-frequency domain signals was proposed. The method and numerical algorithm of Multi-fractal analysis in time-frequency domain were provided. According to grid typeJand order parameterqin algorithm, the value range ofJand the cut-off condition ofqwere optimized based on the effect on the dimension calculation. Simulation experiments demonstrated that the effective signal identification could be complete by multifractal method in time-frequency domain, which is related to the factors such as signal energy and distribution. And the further fault diagnosis experiments of bearings showed that the multifractal method in time-frequency domain can complete the fault diagnosis, such as the fault judgment and fault types. And the fault detection can be done in the early stage of fault. Therefore, the multifractal method in time-frequency domain used in fault diagnosis of bearing is a practicable method.

scholarly journals Multi-Band Frequency Window for Time-Frequency Fault Diagnosis of Induction Machines

Energies ◽  
2019 ◽  
Vol 12 (17) ◽  
pp. 3361 ◽  
Author(s):  
Jordi Burriel-Valencia ◽  
Ruben Puche-Panadero ◽  
Javier Martinez-Roman ◽  
Angel Sapena-Baño ◽  
Martin Riera-Guasp ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Time Window ◽  
Early Stage ◽  
Induction Machines ◽  
Frequency Domain Analysis ◽  
Frequency Resolution ◽  
Good Time ◽  
Band Frequency ◽  
Time Frequency ◽  
Multi Band

Induction machines drive many industrial processes and their unexpected failure can cause heavy production losses. The analysis of the current spectrum can identify online the characteristic fault signatures at an early stage, avoiding unexpected breakdowns. Nevertheless, frequency domain analysis requires stable working conditions, which is not the case for wind generators, motors driving varying loads, and so forth. In these cases, an analysis in the time-frequency domain—such as a spectrogram—is required for detecting faults signatures. The spectrogram is built using the short time Fourier transform, but its resolution depends critically on the time window used to generate it—short windows provide good time resolution but poor frequency resolution, just the opposite than long windows. Therefore, the window must be adapted at each time to the shape of the expected fault harmonics, by highly skilled maintenance personnel. In this paper this problem is solved with the design of a new multi-band window, which generates simultaneously many different narrow-band current spectrograms and combines them into as single, high resolution one, without the need of manual adjustments. The proposed method is validated with the diagnosis of bar breakages during the start-up of a commercial induction motor.

scholarly journals Adsorbed Xenon Propellant Storage: Are Nanoporous Materials Worth the Weight?

2021 ◽  
Author(s):  
Melanie T. Huynh ◽  
Nickolas Gantzler ◽  
Samuel Hough ◽  
David Roundy ◽  
Praveen K. Thallapally ◽  
...  
Keyword(s):  
Pressure Vessel ◽  
High Pressures ◽  
Storage System ◽  
Large Mass ◽  
Pressure Vessels ◽  
Nanoporous Materials ◽  
Bulk Storage ◽  
Xenon Adsorption ◽  
Adsorption Data ◽  
Metal Organic

Xenon is used as a propellant for spacecraft. Conventionally, xenon is compressed to high pressures (75-300 bar) for bulk storage onboard the spacecraft. An adsorbed xenon storage system based on nanoporous materials (NPMs) could, potentially, (i) reduce the storage pressures, (ii) allow for thinner-walled and lighter pressure vessels, and (iii) if the NPM itself is sufficiently light, reduce the overall mass of the storage system and thus of the payload of the rocket launch.<br><br>To investigate, we develop a simple mathematical model of an adsorbed xenon storage system by coupling a mechanical model for the pressure vessel and a thermodynamic model for the density of xenon adsorbed in the NPM. From the model, we derive the optimal storage pressure, tailored to each NPM, with the objective of minimizing the mass of the storage materials (walls of the pressure vessel + NPM) required to store the xenon. The model enables us to: (i) rank NPMs for adsorbed xenon propellant storage, (ii) compare adsorbed storage to the baseline of bulk storage, and (iii) understand what properties of NPMs are desirable for adsorbed xenon propellant storage.<br><br>We use the model to evaluate several NPMs, mostly metal-organic frameworks (MOFs), for adsorbed xenon propellant storage at room temperature, using experimental xenon adsorption data as input. We find Ni-MOF-74 and MOF-505 outperform the traditional adsorbent, activated carbon. However, we find each optimized adsorbed xenon storage system is heavier than the optimized bulk storage system, owing dominantly to the large mass of the NPM itself. Our model suggests that, for a NPM to provide a lighter adsorbed xenon storage system compared to bulk storage, the saturation loading of xenon in the adsorbent must exceed ca. 94 mmol Xe/g adsorbent.

High Pressure Testing Hazards

2009 ◽  
Author(s):  
Matthew Edel ◽  
Donald Ketchum ◽  
Jasen Falcon
Keyword(s):  
High Pressure ◽  
Hydrostatic Pressure ◽  
Pressure Vessel ◽  
High Pressures ◽  
Pressure Vessels ◽  
Blast Loads ◽  
Pressure Testing ◽  
Safety Research ◽  
Back Face

Pressure vessels that operate at high pressures (greater than 10,000 psi [69 MPa]) pose several potential hazards to nearby personnel. Some of these hazards include projectile launch, water jetting, and blast loads that may occur as a result of a pneumatic or hydrostatic pressure vessel failure. In order to provide personnel protection, pressure vessels may be placed inside hardened test enclosures designed to contain these hazards. Some of the key response mechanisms that should be considered when designing such enclosures include applied blast loads for pneumatic testing), localized barrier perforation, global or gross barrier response, and generation of secondary debris from damage to a barrier, such as back-face spalling. Some of these hazards and shielding responses have been evaluated experimentally in the High Pressure Testing Safety Research Joint Industry Program [1, 2, 3]. This paper describes some of these hazards and some considerations for providing personnel protection.

Sign in / Sign up

Export Citation Format

Share Document