물리 정보 기반 인공지능을 활용한 기어박스 고장진단 = Fault Diagnosis of a Gearbox using Physics-information-based Artificial Intelligence

다국어 초록 (Multilingual Abstract)

Research on vibration-based gearbox fault diagnosis using artificial intelligence (AI) has been actively conducted in recent years. However, a problem exists whereby the performance of AI models that have been optimized to solve certain problems such as classification based on the pattern analysis of training data can be significantly degraded when the characteristics of the measured vibration signals are varied by the various changes in the operating environments. In this study, a physics-based kernel that can extract fault-related features based on physical information on the defect characteristics is designed. Unlike typical AI model kernels, the proposed physics-based kernel was fixed to prevent it from being learned, allowing physical information to be reliably extracted. This allows the development of a robust gearbox fault diagnosis in various domains, including non-stationary operating conditions that occur in actual industrial settings. The proposed idea was the validated on a gearbox testbed operated under various operating conditions. Consequently, the proposed method outperforms the conventional method, while retaining its physical robustness and capability for accurate gearbox fault diagnosis.

국문 초록 (Abstract)

최근 인공지능을 활용한 진동 기반 기어박스 고장진단에 대한 연구가 활발히 진행되어왔다. 하지만학습용 데이터의 패턴을 분석하여 분류 등의 주어진 문제를 해결하도록 최적화되는 인공지능 모델의 특성상, 운용환경 변화에 따라 측정되는 진동신호의 특성이 달라지는 경우 성능이 크게 저하될 수 있다는 문제가제기되어 왔다. 본 연구에서는 기어박스 결함으로 인해 발생할 수 있는 현상의 물리적 특성을 고려하여 인공지능의 성능을 향상시킬 수 있는 방법론을 제안한다. 이를 위해 결함 특성에 기반한 물리 정보를 통해 특성인자를 추출할 수 있는 물리 기반 커널을 설계하였다. 제안된 물리 기반 커널은 일반적인 인공지능 모델의커널과는 다르게 학습이 불가하도록 고정되어 보다 강건하게 물리 정보를 추출할 수 있다. 이를 통해, 실제산업 현장에서 발생하는 비정상 운용조건 등의 다양한 도메인 변화 문제에 대해 강건한 기어박스 고장진단을 수행할 수 있도록 하였다. 제안된 기법의 검증을 위해 다양한 운용조건에 대한 기어 테스트베드 실험을수행한 결과, 제안 방법을 통해 운용조건 변화에 무관하게 물리적으로 유의미한 결함 인자가 추출되며 이에따라 강건한 기어박스 고장진단이 가능함을 확인하였다.

참고문헌 (Reference)

• 1 T. Zhang, "Vibration-based Structural Damage Detection via Phased-based Motion Estimation Using Convolutional Neural Networks" 178 : 109320-, 2022
• 2 T. Wang, "Vibration based Condition Monitoring and Fault Diagnosis of Wind Turbine Planetary Gearbox : A Review" 126 : 662-685, 2019
• 3 M. Nie, "Review of Condition Monitoring and Fault Diagnosis Technologies for Wind Turbine Gearbox" 11 : 287-290, 2013
• 4 M. Shadoughi, "Physics-based Convolutional Neural Network for Fault Diagnosis of Rolling Element Bearings" 19 (19): 4181-4192, 2019
• 5 Y. Li, "Non-stationary Vibration Feature Extraction Method based on Sparse Decomposition and Order Tracking For Gearbox Fault Diagnosis" 124 : 453-469, 2018
• 6 P. D. McFadden, "Model for the Vibration Produced by a Single Point Defect in a Rolling Element Bearing" 96 (96): 69-82, 1984
• 7 D. Ulyanov, "Instance Normalization : The Missing Ingredient for Fast Stylization"
• 8 X. Zhou, "Fault Feature Extraction for Rolling Bearings based on Parameter-adaptive Variational Mode Decomposition and Multi-point Optimal Minimum Entropy Deconvolution" 173 : 108469-, 2021
• 9 N. Huang, "Fault Diagnosis of Bearing in Wind Turbine Gearbox under Actual Operating Conditions Driven by Limited Data with Noise Labels" 70 : 1-10, 2020
• 10 J. M. Ha, "Domain Knowledge-informed Synthetic Fault Sample Generation with Health Data Map for Cross-domain Planetary Gearbox Fault Diagnosis"
• 11 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016
• 12 S. Tang, "Deep Learning-based Intelligent Fault Diagnosis Methods Toward Rotating Machinery" 8 : 9335-9346, 2019
• 13 Y. J. Cha, "Deep Learning-based Crack Damage Detection Using Convolutional Neural Networks" 32 (32): 361-378, 2017
• 14 Q. Li, "Deep Balanced Domain Adaptation Neural Networks for Fault Diagnosis of Planetary Gearboxes with Limited Labeled Data" 156 : 107570-, 2020
• 15 O. Janssens, "Convolutional Neural Network based Fault Detection for Rotating Machinery" 377 : 331-345, 2016
• 16 Y. Lei, "Condition Monitoring and Fault Diagnosis of Planetary Gearboxes : A Review" 48 : 292-305, 2014
• 17 R. Liu, "Artificial Intelligence for Fault Diagnosis of Rotating Machinery : A Review" 108 : 33-47, 2018
• 18 L. Hong, "An Explanation of Frequency Features Enabling Detection of Faults in Equally Spaced Planetary Gearbox" 73 : 169-183, 2014
• 19 L. Hong, "A Time Domain Approach to Diagnose Gearbox Fault based on Measured Vibration Signals" 333 (333): 2164-2180, 2014
• 20 H. Gu, "A Review on Wind Turbines Gearbox Fault Diagnosis Methods" 23 (23): 26-43, 2021
• 21 V. Sharma, "A Review on Vibration-based Fault Diagnosis Techniques for Wind Turbine Gearboxes Operating under Nonstationary Conditions" 102 (102): 507-523, 2021
• 22 J. M. Ha, "A Health Data Map-based Ensemble of Deep Domain Adaptation under Inhomogeneous Operating Conditions for Fault Diagnosis of a Planetary Gearbox" 9 : 79118-79127, 2021