A Health Data Map-Based Ensemble of Deep Domain Adaptation Under Inhomogeneous Operating Conditions for Fault Diagnosis of a Planetary Gearbox

A deep learning model trained under a specific operating condition of the gearbox often experiences an overfitting problem, which makes it impossible to diagnose faults under different operating conditions. To solve this problem, this paper proposes an ensemble of deep domain adaptation approaches with a health data map. As a fundamental approach to alleviate the domain shift problem due to inhomogeneous operating conditions, the vibration signal is transformed into an image-like simplified health data map that visualizes a tooth-wise fault of the gearbox. The simplified health data map enables the use of a conventional convolutional neural network (CNN) model. To solve the remaining domain shift problem even with the simplified health data map, this study employs a maximum classifier discrepancy (MCD), which is a typical domain adaptation method. To further enhance its performance, a discrepancy-scale factor-based MCD and its ensemble approach are proposed. The proposed method is demonstrated with a 2 kW planetary gearbox testbed operated under stationary and non-stationary speed conditions. The results present that the proposed method outperforms conventional CNN and MCD even under the inhomogeneous operating condition of the gearbox.

[1]  Shahin Hedayati Kia,et al.  Gear Tooth Surface Damage Fault Detection Using Induction Machine Stator Current Space Vector Analysis , 2015, IEEE Transactions on Industrial Electronics.

[2]  Yaguo Lei,et al.  Condition monitoring and fault diagnosis of planetary gearboxes: A review , 2014 .

[3]  Meng Hee Lim,et al.  A Review on Convolutional Neural Network in Bearing Fault Diagnosis , 2019, MATEC Web of Conferences.

[4]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[5]  Mohammad Modarres,et al.  Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings , 2017 .

[6]  James Bailey,et al.  On the Convergence and Robustness of Adversarial Training , 2021, ICML.

[7]  D. Jimenez,et al.  Dynamically weighted ensemble neural networks for classification , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[8]  Wei Gao,et al.  A Novel Fault Diagnosis Method for Rotating Machinery Based on a Convolutional Neural Network , 2018, Sensors.

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[10]  Byeng D. Youn,et al.  Optimal vibration image size determination for convolutional neural network based fluid-film rotor-bearing system diagnosis , 2020 .

[11]  David He,et al.  On the Use of a Single Piezoelectric Strain Sensor for Wind Turbine Planetary Gearbox Fault Diagnosis , 2015, IEEE Transactions on Industrial Electronics.

[12]  Neil Genzlinger.  A. and Q , 2006 .

[13]  Moncef Gabbouj,et al.  Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Industrial Electronics.

[14]  Balaji Lakshminarayanan,et al.  Deep Ensembles: A Loss Landscape Perspective , 2019, ArXiv.

[15]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[16]  Darryll J. Pines,et al.  A review of vibration-based techniques for helicopter transmission diagnostics , 2005 .

[17]  Bo Zhang,et al.  Recent Advances of Generative Adversarial Networks in Computer Vision , 2019, IEEE Access.

[18]  Kate Saenko,et al.  Return of Frustratingly Easy Domain Adaptation , 2015, AAAI.

[19]  Jiawei Xiang,et al.  Bearing defect size assessment using wavelet transform based Deep Convolutional Neural Network (DCNN) , 2020 .

[20]  Galina L. Rogova,et al.  Combining the results of several neural network classifiers , 1994, Neural Networks.

[21]  P. McFadden.  Interpolation techniques for time domain averaging of gear vibration , 1989 .

[22]  Xin Huang,et al.  Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform , 2019, Comput. Ind..

[23]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Bongtae Han,et al.  Autocorrelation-based time synchronous averaging for condition monitoring of planetary gearboxes in wind turbines , 2016 .

[25]  Zhang-Quan Shen,et al.  Dynamically weighted ensemble neural networks for regression problems , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[26]  Bo Zhang,et al.  Bearing Fault Diagnosis Under Variable Working Conditions Based on Domain Adaptation Using Feature Transfer Learning , 2018, IEEE Access.

[27]  Byeng D. Youn,et al.  Classification of operating conditions of wind turbines for a class-wise condition monitoring strategy , 2017 .

[28]  Niaoqing Hu,et al.  A deep convolutional neural network based fusion method of two-direction vibration signal data for health state identification of planetary gearboxes , 2019, Measurement.

[29]  Oleksandr Makeyev,et al.  Neural network with ensembles , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[30]  A. Poularikas.  The transforms and applications handbook , 2000 .

[31]  Byeng D. Youn,et al.  Toothwise Fault Identification for a Planetary Gearbox Based on a Health Data Map , 2018, IEEE Transactions on Industrial Electronics.

[32]  Yi Qin,et al.  Fault diagnosis of planetary gearbox using a novel semi-supervised method of multiple association layers networks , 2019, Mechanical Systems and Signal Processing.

[33]  Michael Cogswell,et al.  Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks , 2015, ArXiv.

[34]  Yong Li,et al.  Planetary Gear Fault Diagnosis via Feature Image Extraction Based on Multi Central Frequencies and Vibration Signal Frequency Spectrum , 2018, Sensors.

[35]  Jianjun Hu,et al.  End-To-End Convolutional Neural Network Model for Gear Fault Diagnosis Based on Sound Signals , 2018, Applied Sciences.

[36]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[37]  Mark J. van der Laan,et al.  The relative performance of ensemble methods with deep convolutional neural networks for image classification , 2017, Journal of applied statistics.

[38]  Ke Zhao,et al.  A deep transfer maximum classifier discrepancy method for rolling bearing fault diagnosis under few labeled data , 2020, Knowl. Based Syst..

[39]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[40]  Ran Zhang,et al.  Fault Diagnosis from Raw Sensor Data Using Deep Neural Networks Considering Temporal Coherence , 2017, Sensors.

[41]  Tao Zhang,et al.  Deep Model Based Domain Adaptation for Fault Diagnosis , 2017, IEEE Transactions on Industrial Electronics.

[42]  Jay Lee,et al.  Deep learning-based cross-domain adaptation for gearbox fault diagnosis under variable speed conditions , 2020, Measurement Science and Technology.

[43]  Peng Wang,et al.  An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox , 2017, Sensors.