• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.8
• /
• pp.29-39
• /
• 2015

This paper describes a design and implementation of fuzzy-based algorithm for hand-shake state detection and error compensation in the mobile optical image stabilization(OIS) motion detector. Since the gyro sensor output of the OIS motion detector includes inherent error signals, accurate error correction is required for prompt hand-shake error compensation and stable hand-shake state detection. In this research with a little computation overhead of fuzzy-based algorithm, the hand-shake error compensation could be improved by quickly reducing the angle and phase error for the hand-shake frequencies. Further, stability of the OIS system could be enhanced by the hand-shake states of {Halt, Little vibrate, Big vibrate, Pan/Tilt}, classified by subdividing the hand-shake angle. The performance and stability of the proposed algorithm in OIS motion detector is quantitatively and qualitatively evaluated with the emulated hand-shaking of ${\pm}0.5^{\circ}$, ${\pm}0.8^{\circ}$ vibration and 2~12Hz frequency. In experiments, the average error compensation gain of 3.71dB is achieved with respect to the conventional BACF/DCF algorithm; and the four hand-shake states are detected in a stable manner.

• The KIPS Transactions:PartB
• /
• v.18B no.3
• /
• pp.147-156
• /
• 2011

This paper proposes a 3-stage (preprocessing, feature extraction, and classification) fault detection and classification algorithm for induction motors. In the first stage, a low-pass filter is used to remove noise components in the fault signal. In the second stage, a discrete cosine transform (DCT) and a statistical method are used to extract features of the fault signal. Finally, a back propagation neural network (BPNN) method is applied to classify the fault signal. To evaluate the performance of the proposed algorithm, we used one second long normal/abnormal vibration signals of an induction motor sampled at 8kHz. Experimental results showed that the proposed algorithm achieves about 100% accuracy in fault classification, and it provides 50% improved accuracy when compared to the existing fault detection algorithm using a cross-covariance method. In a real-world data acquisition environment, unnecessary noise components are usually included to the real signal. Thus, we conducted an additional simulation to evaluate how well the proposed algorithm classifies the fault signals in a circumstance where a white Gaussian noise is inserted into the fault signals. The simulation results showed that the proposed algorithm achieves over 98% accuracy in fault classification. Moreover, we developed a testbed system including a TI's DSP (digital signal processor) to implement and verify the functionality of the proposed algorithm.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.13 no.4
• /
• pp.74-80
• /
• 2005

This paper presents a misfire monitoring method by using the weight factor. According to OBD II(On-Board Diagnostics) regulations of the CARB (California Air Resources Board), an ECU (Electronic Control Unit) should detect misfires which occur in the internal combustion engine. A misfire is 1311owe4 by post-oscillations for short duration. Sometimes, the amplitude of oscillations may be as high as misfire and can be falsely detected as another misfire. To prevent this, the software designers do not attempt to detect another misfire for this short duration, during which the post oscillations exist. Because of this, ECU does not detect all the misfires and hence, the unstable state of automobile cannot be detected. If this happens for a long time, automobile may get damaged. To solve these problems, this paper suggests a new algorithm to detect misfire by using weighting factor Weighting factor is a concept to distinguish the misfire with the post oscillation and to improve the detection rate. This value of weighting factor is used for counting the misfire. This paper also shows the result of experiment done on a automobile using this software. The software is implemented using ASCET-SD which is preferred in the design of engine control. This paper's result show the possibility of improving the misfire detection by implementing this algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.4
• /
• pp.400-405
• /
• 2024

When cavitation noise occurs in ship propellers, the level of underwater radiated noise abruptly increases, which can be a critical threat factor as it increases the probability of detection, particularly in the case of naval vessels. Therefore, accurately and promptly assessing cavitation signals is crucial for improving the survivability of submarines. Traditionally, techniques for determining cavitation occurrence have mainly relied on assessing acoustic/vibration levels measured by sensors above a certain threshold, or using the Detection of Envelop Modulation On Noise (DEMON) method. However, technologies related to this rely on a physical understanding of cavitation phenomena and subjective criteria based on user experience, involving multiple procedures, thus necessitating the development of techniques for early automatic recognition of cavitation signals. In this paper, we propose an algorithm that automatically detects cavitation occurrence based on simple statistical features reflecting cavitation characteristics extracted from acoustic signals measured by sensors attached to the hull. The performance of the proposed technique is evaluated depending on the number of sensors and model test conditions. It was confirmed that by sufficiently training the characteristics of cavitation reflected in signals measured by a single sensor, the occurrence of cavitation signals can be determined.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.3
• /
• pp.30-36
• /
• 2004

As fiber reinforced composite materials are widely used in aircraft, space structures and robot arms, the study on the non-destructive testing methods of the composite materials has become an important research area for improving their reliability and safety. In this paper, the AE signal analyzer with the resonance circuit to extract the specified frequency of the acoustic emission signal were designed and fabricated. The noise levels of the fabricated AE signal analyzer by the disturbance such as impact or mechanical vibration had a very small value comparable to those of the conventional AE signal analyzer. Also, the fabricated AE signal analyzer was proved to have about the same crack detection capabilities with the conventional AE signal analyzer under the static and dynamic tensile tests of the composite materials.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2725-2736
• /
• 1998

In this paper. we present a new pitch determination method for speech analysis. namely VFF(Variable Forgetting Factor) based. by using the WRLS-VFF-VT(Weighted Recursive Least Square-Variable Forgetting Factor-Variable Threshold) algorithm. A proposed method uses VFF to identify the glottal closure points which correspond to the instants of the main excitation pulses for voiced speech. The modified EGG

• Journal of Korean Society of Water and Wastewater
• /
• v.32 no.5
• /
• pp.461-470
• /
• 2018

In this study, the leak signal was measured by using an accelerometer to analyze the basic data and methodology for the development of the leak point estimation method in the water supply pipe. The measured results were analyzed by frequency analysis and cross-correlation analysis for leakage signals, and the error range was compared and analyzed with the actual leak point distance. As a result, it was confirmed that the vibration intensity due to leakage from the water leakage point was attenuated according to the distance. In the case of the ductile iron casting used in the experiment, the intensity of the signal at the 945 Hz, 1,500 Hz, 2,300 Hz band was increased with the change of the pressure in the pipe at 4mm of leakage hole. Also, it was confirmed that as the water pressure increases, the intensity of the leak signal increases but the similarity of the signal decreases. The results of this study confirm that the accelerometer sensor can be used efficiently for leak detection and it can be used as a basic data for the analysis for the development of leak point estimation method in the future.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.5
• /
• pp.1-11
• /
• 2008

Wireless Sensor Networks is applied to improvement of life convenience or service like U-City as well as environment pollution, tunnel and structural health monitoring, storm, and earthquake diagnostic system. To increase the usability of sensor data and applicability, mobile devices and their facilities allow the applications of sensor networks to give mobile users and actuators the results of event detection at anytime and anywhere. In this paper, we present MUSNEMO(Multi-sensor centric Ubiquitous Smart sensor NEtwork using Mobile devices) developed system for providing more efficient and valuable information services with a variety of mobile devices and network camera integrated to WSN. Our system is performed based on IEEE 802.15.4 protocol stack. To validate system usability, we built sensor network environments where were equipped with five application sensors such magnetic, photodiode, microphone, motion and vibration. We also built and tested proposed MUSNEMO to provide a novel model for event detection systems with mobile framework.

• Composites Research
• /
• v.13 no.6
• /
• pp.47-54
• /
• 2000

One promising method for impact detection of composite structures is based on the use of piezopolymer thin fim (PVDf) sensor. In this paper, the relationship between the contact force and the signals of the attached strain gage and PVDF sensor to the composite plate subjected to low-velocity impact were derived. The relation for the open circuit and short circuit voltage of PVDF sensor was derived based on the equivalent circuit model of the piezoelectric sensor. The work was then extended to include experimental investigation into the use of short circuit voltage of PVDF sensor without using charge amplifier to detect low-velocity impact. The natural frequencies and damping ratio of the composite plate obtained from the vibration test were used to modify the analytical model and therefore the differences between measured and simulated signal of the modified analytical model in both forward and backward problem were considerably reduced. The reconstructed contact force and simulated sensor signals agreed well with the measured contact force, strain gage signal, and PVDF sensor singanl.