• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.10a
• /
• pp.435-436
• /
• 2012

• 한국초전도학회:학술대회논문집
• /
• v.15
• /
• pp.64-64
• /
• 2005

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.3
• /
• pp.96-102
• /
• 2005

Acoustic Emission(AE) technique has been applied to not only material characterization evaluation but also on-line monitoring of the structural integrity. The AE source location technique is very important to identify the source, such as crack, leak detection. Since the AE waveforms obtained from sensors are very difficult to distinguish the defect signals, therefore, it is necessary to consider the signal analysis of the transient wave-form. In this study, we have divided the region of interest into a set finite elements, and calculated the arrival time differences between sensors by using the velocities at every degree from 0 to 90. A new technique for the source location of acoustic emission in fiberboard plates has been studied by introducing Wavelet Transform(WT) do-noising technique. WT is a powerful tool for processing transient signals with temporally varying spectra. If the WT de-noising was employed, we could successfully filter out the errors of source location in fiberboard plates by arrival time difference method. The accuracy of source location appeared to be significantly improved.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.307-311
• /
• 1993

Research concerning gears included in rotating machines has been reported using the acoustic emission (AE) method, however, almost no research has been conducted using the AE method in regard to running gears in a bending fatigue processor spur gear teeth. Therefore, in this report, a power circulating-type gear testing machine was used and AE signals and crack length were measured in the bending fatigue process of case-hardened spur gear. Furthermore, the envelope of the AE signal was detected and various analysis were carried out in this data. In the course of the experiments, the following results were observed : the AE signal envelope consists mainly of contact frequency component and twice as many as this;two peaks of AE appear in each tooth contact by the tip corner contact ; as a result of the severe tip corner contact ; as a result of the severe tip corner contact with the sudden increase of crack length, AE signal becomes large.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.4
• /
• pp.308-315
• /
• 2009

Because the attenuation of AE signal in composite materials is relatively higher than that of metallic materials, it is required to develop a damage assessment technique less affected by the attenuation property of composite materials in order to use AE sensing as a damage detection method. In the signal processing procedure, it is profitable to use the leading wave that arrives first because the leading wave is less influenced by the boundary conditions. Using wavelet transform, we investigated the frequency characteristics of impact induced AE signals focused on the leading wave in advance and chose the key factors to discriminate the damaged condition quantitatively. In this research, we established a damage assessment technique using the sharing percentage of the wavelet detail components of AE signal, and conducted a low-velocity impact test on composite laminates to confirm the feasibility of the proposed signal processing method.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.6
• /
• pp.1388-1398
• /
• 1994

The fracture toughness and micro-fracture mechanisms of the porous glass and stainless fiber reinforced glass composite were evaluated by using the acoustice mission(AE) technique, fracture toughness $test(K_{IC})$ and the macroscopic observation of the specimen surface which was being under the loading. At initial portion of the loading, the AE signals with low energy, of which origins were considered as the micro-cracks formated at the crack tip, were emitted. With increasing the applied load, AE signals having higher energies were generated due to the coalesence of micro-cracks and fast fracture. Based on the such relationship between AE emission and loading condition, fracture toughness $K_{IAE}$ could be defined successfully be using the $K_I$ value corresponding to an abrupt change of the accumulated AE signal energies emitted during the fracture toughness test. In spite of its brittleness of glass material, nonlinear deformation behavior before maximum load was observed due to the formation of micro-cracks. Further, the stainless fiber may have attributed to the improvement of fracture toughness and the resistance to crack propagation comparing to noncomposited materials Finally, models of the micro-fracture process combined with the AE sources for the porous glass material and its composite were proposed paying attention to the micro-crack nucleation and its coalescence at the crack tip. Fiber fracture and its Pullout, deformation of fiber itself were also delinated from the model.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.6
• /
• pp.401-409
• /
• 2016

The formation of micro-burrs in micro-milling processes causes several problems related to productivity and surface integrity. It should be minimized and suppressed by effective monitoring of the cutting conditions. This paper presents the correlation between the micro-burr length and cutting signals in the micro-milling process of an Al alloy (Al6061-T6). The acoustic emission (AE) signals and cutting force signals are acquired during the experiments. The characteristics of the cutting signals are obtained by analyzing the AE root mean square value and resultant cutting force. In addition, the micro-burr length is measured according to the cutting conditions by analyzing a scanning electron microscopy image of the machined surface. The results of this study can be used to enhance the surface quality of micro parts.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1991.04a
• /
• pp.150-157
• /
• 1991

As the system monitoring technology become required in order to imporve the system performance and the productivity, We've studied to the detection for the tool breakage using AE sensor that is able to detection of generated high frequency strss pulse at cutting. The method of spectrum analysis are used for analysis of AE signals in detection system. The experiments are carred out in a CNC lathe.

• Journal of the Korean Society of Safety
• /
• v.16 no.4
• /
• pp.7-13
• /
• 2001

Wire electrical discharge machining experiments in conducted to investigate characteristics of acoustic emission (AE) and electrical discharge energy due to current peak (I$_{p}$), pulse on time($\tau$/on/). The AE signals are obtained with a sensor attached to workpiece side. Machining states are identified with scanning electron microscopy and residual stress analyzer. It is demonstrated that the residual stress provide reliable informations about the machining states. Moreover, machining states can be detected successfully using both the residual stress and AE count rate.e.