Research Topics
Domain Knowledge-informed Artificial Intelligence for System Condition Monitoring
We integrate domain knowledge (signal processing, rule-based analysis, physical relationship, etc.) to artificial intelligence to enhance the prediction/evaluation performance.
Research of interest includes
1) Prognostics and Health Managment (PHM) of rotating machinery
2) Manufacturing quality monitoring
3) Non-destructive testing using ultrasonic signal
Artificial Intelligence (Deep Learning)
Deep Learning-based PHM
J. M. Ha and O. Fink, "Domain knowledge-informed Synthetic fault sample generation with Health Data Map for cross-domain Planetary Gearbox Fault Diagnosis," Mechanical Systems and Signal Processing (MSSP), Vol 202, 2023 (IF: 8.4)
J. M. Park, J. O. Yoo, T. H. Kim, J. M. Ha#, and Byeng D. Youn#, "Multi-head De-noising Autoencoder based Multitask (MDAM) model for fault diagnosis of rolling element bearings under various speed conditions," Journal of Computational Design and Engineering (JCDE), Vol 10 (4), 2023 (IF: 4.9)
T. W. Hwang, J. M. Ha#, and B. D. Youn#, "Robust deep learning-based fault detection of planetary gearbox using enhanced health data map (enHDMap) under domain shift problem," Journal of Computational Design and Engineering (JCDE), Vol 10 (4), 2023 (IF: 4.9)
Deep Domain Adaptation for PHM
under In-homogeneous Operating Condition
J. M. Ha, B. D. Youn#, “A Health Data Map-Based Ensemble of Deep Domain Adaptation under Inhomogeneous Operating Conditions for Fault Diagnosis of a Planetary Gearbox,” IEEE Access, Vol 9, 2021, pp. 79118-79127 (IF: 3.745)
Deep Learning-based Signal Enhancement
for Ultrasonic Testing (Non-destructive Testing)
J. M. Ha, H. M. Seung, W. J. Choi#, “Autoencoder-based detection of near-surface defects in ultrasonic testing,” Ultrasonics, Vol 119, 2022 (IF: 2.598)
Vibration Signal Processing
Time Synchronous Averaging (TSA) for Gearbox
to extract fault-related features while reducing random noise
J. M. Ha, B. D. Youn#, “Autocorrelation-based time synchronous averaging for condition monitoring of planetary gearboxes in wind turbines,” Mechanical Systems and Signal Processing, Vol 70-71, 2016, pp.161-175 (IF: 6.471)
Minimum Entropy Deconvolution (MED)
to highlight fault-induced impulse signals
J. M. Ha, B. D. Youn#, “Fault Diagnosis of a Planetary Gearbox by Dnorm-based Time Synchronous Averaging (DTSA) Encapsulating Results from Multiple Minimum Entropy Deconvolution (MED) Filters,” Journal of Sound and Vibration, 2022 (IF: 3.123)
Vibration Signal Visualization for Fault Detection
J. M. Ha, J. H. Park, K. M. Na, Y. H. Kim, B. D. Youn#, "Tooth-wise Fault Identification for a Planetary Gearbox Based on a Health Data Map,” IEEE Transactions on Industrial Electronics, Vol 65 (7), 2018, pp. 5903 – 5912 (IF: 9.59)