A Study on Denoising Autoencoder Noise Selection for Improving the Fault Diagnosis Rate of Vibration Time Series Data
Jun-gyo Jang, Soon-Sup Lee, Se-Yun Hwang, Jae-Chul Lee
IF 2.5
Applied Sciences
This study analyzes the impact of different types of random noise applied in Denoising Autoencoder (DAE) training on fault diagnosis performance, with the aim of improving noise removal for vibration time series data. While conventional studies typically train DAEs using Gaussian random noise, such noise does not fully reflect the complex noise patterns observed in real-world industrial environments. Therefore, this study proposes a novel approach that uses high-frequency noise components extracted from actual vibration data as training noise for the DAE. Both Gaussian and high-frequency noise were used to train separate DAE models, and statistical features (mean, RMS, standard deviation, kurtosis, skewness) were extracted from the denoised signals. The fault diagnosis rates were calculated using One-Class Support Vector Machines (OC-SVM) for performance comparison. As a result, the model trained with high-frequency noise achieved a 0.0293 higher average F1-score than the Gaussian-based model. Notably, the fault detection accuracy using the kurtosis feature improved significantly from 26.22% to 99.5%. Furthermore, the proposed method outperformed the conventional denoising technique based on the Wavelet Transform, demonstrating superior noise reduction capability. These findings demonstrate that incorporating real high-frequency components from vibration data into the DAE training process is effective in enhancing both noise removal and fault diagnosis performance.
Anomaly-Detection Framework for Thrust Bearings in OWC WECs Using a Feature-Based Autoencoder
Se-Yun Hwang, Jae-Chul Lee, S. C. Lee, Cheon-Hong Min
IF 2.8
Journal of Marine Science and Engineering
An unsupervised anomaly-detection framework is proposed and field validated for thrust-bearing monitoring in the impulse turbine of a shoreline oscillating water-column (OWC) wave energy converter (WEC) off Jeju Island, Korea. Operational monitoring is constrained by nonstationary sea states, scarce fault labels, and low-rate supervisory logging at 20 Hz. To address these conditions, a 24 h period of normal operation was median-filtered to suppress outliers, and six physically motivated time-domain features were computed from triaxial vibration at 10 s intervals: absolute mean; standard deviation (STD); root mean square (RMS); skewness; shape factor (SF); and crest factor (CF, peak divided by RMS). A feature-based autoencoder was trained to reconstruct the feature vectors, and reconstruction error was evaluated with an adaptive threshold derived from the moving mean and moving standard deviation to accommodate baseline drift. Performance was assessed on a 2 h test segment that includes a 40 min simulated fault window created by doubling the triaxial vibration amplitudes prior to preprocessing and feature extraction. The detector achieved accuracy of 0.99, precision of 1.00, recall of 0.98, and F1 score of 0.99, with no false positives and five false negatives. These results indicate dependable detection at low sampling rates with modest computational cost. The chosen feature set provides physical interpretability under the 20 Hz constraint, and denoising stabilizes indicators against marine transients, supporting applicability in operational settings. Limitations associated with simulated faults are acknowledged. Future work will incorporate long-term field observations with verified fault progressions, cross-site validation, and integration with digital-twin-enabled maintenance.
Vibration data feature extraction and deep learning-based preprocessing method for highly accurate motor fault diagnosis
Jun-gyo Jang, Chun-myoung Noh, Sung‐Soo Kim, Sung-chul Shin, Soon-Sup Lee, Jae-Chul Lee
IF 6.1
Journal of Computational Design and Engineering
Abstract The environmental regulations on vessels being strengthened by the International Maritime Organization has led to a steady growth in the eco-friendly ship market. Related research is being actively conducted, including many studies on the maintenance and predictive maintenance of propulsion systems (including electric motors and rotating bodies) in electric propulsion vessels. The present study intends to enhance the artificial intelligence (AI)-based failure-diagnosis rate for electric propulsion vessel propulsion systems. To verify the proposed AI-based failure diagnosis algorithm for electric motors, this study utilized the vibration data of mechanical equipment (electric motors) in an urban railway station. Securing and preprocessing high-quality data is crucial for improving the failure-diagnosis rate, in addition to the performance of the diagnostic algorithm. However, the conventional wavelet transform method, which is generally used for machine signal processing, has a disadvantage of data loss when the data distribution is abnormal or skewed. This study, to overcome this shortcoming, proposes an AI-based denoising auto encoder (DAE) method that can remove noise while maintaining data characteristics for signal processing of mechanical equipment. This study preprocessed vibration data by using the DAE method, and extracted significant features from the data through the feature extraction method. The extracted features were utilized to train the one-class support vector machine model and to allow the model to diagnose the failure. Finally, the F-1 score was calculated by using the failure diagnosis results, and the most meaningful feature extraction method was determined for the vibration data. In addition, this study compared and evaluated the preprocessing performance based on the DAE and the wavelet transform methods.
A Study on Denoising Autoencoder Noise Selection for Improving the Fault Diagnosis Rate of Vibration Time Series Data
Jun-gyo Jang, Soon-Sup Lee, Se-Yun Hwang, Jae-Chul Lee
IF 2.5
Applied Sciences
This study analyzes the impact of different types of random noise applied in Denoising Autoencoder (DAE) training on fault diagnosis performance, with the aim of improving noise removal for vibration time series data. While conventional studies typically train DAEs using Gaussian random noise, such noise does not fully reflect the complex noise patterns observed in real-world industrial environments. Therefore, this study proposes a novel approach that uses high-frequency noise components extracted from actual vibration data as training noise for the DAE. Both Gaussian and high-frequency noise were used to train separate DAE models, and statistical features (mean, RMS, standard deviation, kurtosis, skewness) were extracted from the denoised signals. The fault diagnosis rates were calculated using One-Class Support Vector Machines (OC-SVM) for performance comparison. As a result, the model trained with high-frequency noise achieved a 0.0293 higher average F1-score than the Gaussian-based model. Notably, the fault detection accuracy using the kurtosis feature improved significantly from 26.22% to 99.5%. Furthermore, the proposed method outperformed the conventional denoising technique based on the Wavelet Transform, demonstrating superior noise reduction capability. These findings demonstrate that incorporating real high-frequency components from vibration data into the DAE training process is effective in enhancing both noise removal and fault diagnosis performance.
Anomaly-Detection Framework for Thrust Bearings in OWC WECs Using a Feature-Based Autoencoder
Se-Yun Hwang, Jae-Chul Lee, S. C. Lee, Cheon-Hong Min
IF 2.8
Journal of Marine Science and Engineering
An unsupervised anomaly-detection framework is proposed and field validated for thrust-bearing monitoring in the impulse turbine of a shoreline oscillating water-column (OWC) wave energy converter (WEC) off Jeju Island, Korea. Operational monitoring is constrained by nonstationary sea states, scarce fault labels, and low-rate supervisory logging at 20 Hz. To address these conditions, a 24 h period of normal operation was median-filtered to suppress outliers, and six physically motivated time-domain features were computed from triaxial vibration at 10 s intervals: absolute mean; standard deviation (STD); root mean square (RMS); skewness; shape factor (SF); and crest factor (CF, peak divided by RMS). A feature-based autoencoder was trained to reconstruct the feature vectors, and reconstruction error was evaluated with an adaptive threshold derived from the moving mean and moving standard deviation to accommodate baseline drift. Performance was assessed on a 2 h test segment that includes a 40 min simulated fault window created by doubling the triaxial vibration amplitudes prior to preprocessing and feature extraction. The detector achieved accuracy of 0.99, precision of 1.00, recall of 0.98, and F1 score of 0.99, with no false positives and five false negatives. These results indicate dependable detection at low sampling rates with modest computational cost. The chosen feature set provides physical interpretability under the 20 Hz constraint, and denoising stabilizes indicators against marine transients, supporting applicability in operational settings. Limitations associated with simulated faults are acknowledged. Future work will incorporate long-term field observations with verified fault progressions, cross-site validation, and integration with digital-twin-enabled maintenance.
Vibration data feature extraction and deep learning-based preprocessing method for highly accurate motor fault diagnosis
Jun-gyo Jang, Chun-myoung Noh, Sung‐Soo Kim, Sung-chul Shin, Soon-Sup Lee, Jae-Chul Lee
IF 6.1
Journal of Computational Design and Engineering
Abstract The environmental regulations on vessels being strengthened by the International Maritime Organization has led to a steady growth in the eco-friendly ship market. Related research is being actively conducted, including many studies on the maintenance and predictive maintenance of propulsion systems (including electric motors and rotating bodies) in electric propulsion vessels. The present study intends to enhance the artificial intelligence (AI)-based failure-diagnosis rate for electric propulsion vessel propulsion systems. To verify the proposed AI-based failure diagnosis algorithm for electric motors, this study utilized the vibration data of mechanical equipment (electric motors) in an urban railway station. Securing and preprocessing high-quality data is crucial for improving the failure-diagnosis rate, in addition to the performance of the diagnostic algorithm. However, the conventional wavelet transform method, which is generally used for machine signal processing, has a disadvantage of data loss when the data distribution is abnormal or skewed. This study, to overcome this shortcoming, proposes an AI-based denoising auto encoder (DAE) method that can remove noise while maintaining data characteristics for signal processing of mechanical equipment. This study preprocessed vibration data by using the DAE method, and extracted significant features from the data through the feature extraction method. The extracted features were utilized to train the one-class support vector machine model and to allow the model to diagnose the failure. Finally, the F-1 score was calculated by using the failure diagnosis results, and the most meaningful feature extraction method was determined for the vibration data. In addition, this study compared and evaluated the preprocessing performance based on the DAE and the wavelet transform methods.
We propose a phase-aware complex-spectrogram autoencoder (AE) for preprocessing raw vibration signals of rotating electrical machines. The AE reconstructs normal components and separates fault components as residuals, guided by an input-phasor phase-orthogonality regularization that defines parallel/orthogonal residuals with respect to the local signal phase. We use a U-Net-based AE with a mask-bias head to refine local magnitude and phase. Decisions are based on residual features—magnitude/shape, frequency distribution, and projections onto the normal manifold. Using the AI Hub open dataset from field ventilation motors, we evaluate eight representative motor cases (2.2–5.5 kW: misalignment, unbalance, bearing fault, belt looseness). The preprocessing yielded clear residual patterns (low-frequency floor rise, resonance-band peaks, harmonic-neighbor spikes), and achieved an area under the receiver operating characteristic curve (ROC-AUC) = 0.998–1.000 across eight cases, with strong leave-one-file-out generalization and good calibration (expected calibration error (ECE) ≤ 0.023). The results indicate that learning to remove normal structure while enforcing phase consistency provides an unsupervised front-end that enhances fault evidence while preserving interpretability on field data.
Development and Validation of a Standardized Evaluation Procedure for Marine Application of Magnetic Bearing-Based Rotating Machinery
Il Guk Woo, Ye-Na Lee, Se-Yun Hwang, Jae-Chul Lee, Soon-Sup Lee
Journal of Ocean Engineering and Technology
Unlike conventional bearings, magnetic bearings (MBs) provide non-contact support and high reliability, but standardized evaluation criteria for marine environments have not yet been established. This study proposes and validates a standardized evaluation procedure for MB-based rotating machinery intended for marine applications. The proposed procedure consists of six steps: (1) equipment data preparation, (2) standardized simplified model generation, (3) magnetic force incorporation, (4) external load definition based on the sea state, (5) analysis (transient dynamic analysis under the defined external loads), and (6) result evaluation. A simplified turbo compressor model was constructed using ANSYS Mechanical, applying equivalent stiffness and damping coefficients to represent magnetic bearing dynamics. External loads were derived from World Meteorological Organization (WMO) Sea State and DNV-RP-C205 guidelines and applied as impulse-type accelerations. Numerical simulation results showed that rotor displacement remained within 95% of the air gap under normal conditions (Sea state 6, 0.8g, here, g = 9.8 m/s<sup>2</sup>). Under extreme loading (Sea state 8, 1.8g), the analysis indicated that the air-gap limit was exceeded, leading to contact with the backup bearings and casing. The proposed standardized simplified evaluation procedure provides a practical framework for assessing MB-based marine rotating machinery, supporting rapid design verification and classification approval.
Noise Reduction in CWRU Data Using DAE and Classification with ViT
Jun-gyo Jang, Soon-Sup Lee, Se-Yun Hwang, Jae-Chul Lee
IF 2.5
Applied Sciences
With the Fourth Industrial Revolution unfolding worldwide, technologies including the Internet of Things, sensors, and artificial intelligence are undergoing rapid development. These technological advancements have played a significant role in the dramatic growth of the predictive maintenance market for mechanical equipment, prompting active research on noise removal techniques and classification algorithms for the accurate determination of the causes of equipment failure. In this study, time series data were preprocessed using the denoising autoencoder technique, a deep learning-based noise removal method, to improve the accuracy of failure classification from mechanical equipment data. To convert the preprocessed time series data into frequency components, the short-time Fourier transform technique was employed. The fault types of mechanical equipment were classified using the vision transformer (ViT) technique, a deep learning technique that has been actively used in recent image analysis research. Additionally, the classification performance of the ViT-based technique for vibration time series data was comparatively validated against existing classification algorithms. The accuracy of failure classification was the highest when the data, preprocessed using a Denoising Autoencoder (DAE), were classified by a Vision Transformer (ViT).
Design and Implementation of High-reliability, Low-cost Automotive LED Driver System
Eun Sung Kim, Jae-Chul Lee, Kean-Seb Woo, Hoe-Kyung Jung
The Journal of the Korea Contents Association
자동차의 조명 시스템이 발전함에 따라 효율이 좋은 LED 드라이버 시스템 설계가 중요하다. 기존 자동차 LED 드라이버 시스템은 단순히 LED의 전류를 제어하고 에너지 효율을 높이는 데 집중하고 있다. 그러나 시스템의 복잡성과 가격 상승으로 인해 개선이 필요하다. 본 연구에서는 구조를 최적화하여 고신뢰성과 저비용의 차량용 LED 드라이버 시스템 및 반도체 통합 설계를 제안한다. 제안 시스템은 LED 조명의 효과적인 전류조절, 비용 및 구조 최적화를 통해 성능과 안정성을 동시에 보장한다. 실험 결과, 비용은 약 15% 절감되고, 신뢰성 시험 항목을 모두 충족하였다. 본 연구는 차량 조명 분야에서 더 효율적인 LED 조명 시스템 구현에 기여할 것이다. 또한, LED 생산 공정에서 발생할 수 있는 소자의 편차를 제어할 수 있는 반도체를 개발하여 비효율적인 공정을 줄일 수 있을 것이다.
Development of Equipment for Generating and Measuring Vibration Data for Electric Motor
Jun-gyo Jang, Youngsub Lee, Jae-Chul Lee, Donghoon Kang, Dong-geon Kim, Soon-Sup Lee
Journal of the Society of Naval Architects of Korea
As the Marine Environment Protection Committee (MEPC) of the International Maritime Organization (IMO) continues to strengthen regulations regarding ship fuel emissions, the importance of eco-friendly vessels is increasing, accompanied by advancements in related technologies. To ensure the safe operation of electric propulsion ships, extensive research is required on the maintenance and predictive maintenance technologies of propulsion systems, such as motors and rotors. However, due to the limited availability of operational data from electric propulsion ships that have not yet been commercialized conducting such studies poses significant challenges. In response, this study presents the development of a device specifically designed to generate and measure vibration data for electric motors used in electric propulsion ships. The device simulates potential failure causes, such as bearing failure and shaft misalignment, using a small-scale electric propulsion motor. During the development process, issues such as current leakage were identified and addressed through the installation of insulation pads and the replacement of couplings. To validate the performance of the developed device, vibration data from the electric motor in a normal operating state were collected and compared with data obtained using a verified measurement instrument, the oscilloscope. The results confirmed the effectiveness of the device in accurately generating and measuring relevant vibration data.
A Study on the Optimization of the Coil Defect Detection Model Based on Deep Learning
Chun-myoung Noh, Jun-gyo Jang, Sung-Soo Kim, Soon-Sup Lee, Sung-chul Shin, Jae-Chul Lee
IF 2.5
Applied Sciences
With increasing interest in smart factories, considerable attention has been paid to the development of deep-learning-based quality inspection systems. Deep-learning-based quality inspection helps productivity improvements by solving the limitations of existing quality inspection methods (e.g., an inspector’s human errors, various defects, and so on). In this study, we propose an optimized YOLO (You Only Look Once) v5-based model for inspecting small coils. Performance improvement techniques (model structure modification, model scaling, pruning) are applied for model optimization. Furthermore, the model is prepared by adding data applied with histogram equalization to improve model performance. Compared with the base model, the proposed YOLOv5 model takes nearly half the time for coil inspection and improves the accuracy of inspection by up to approximately 1.6%, thereby enhancing the reliability and productivity of the final products.
