Semi-supervised learning and condition fusion for fault diagnosis

Abstract Supervised learning has been developed to collect condition monitoring (CM) data for fault diagnosis and prognosis. However, labeling the condition monitoring data is expensive due to the use of field knowledge while unlabeled CM data contain significant information of normal conditions or faults, which cannot be explored by supervised learning. Manifold regularization (MR) based semi-supervised learning (SSL) is first introduced to fault detection by utilizing both labeled and unlabeled CM data, and then a new single-conditions labeled mode based on MR is proposed for SSL learning. This approach, leveraged by effectively exploiting the embedded intrinsic geometric manifolds, outperforms supervised learning in both single-conditions labeled and all-conditions labeled modes within the application of two real-life fault detection datasets. The experimental results also suggest that most effective classifier in practical application could be trained by the SSL approach and fault type representation with medium load condition. The improved predictive performance implies that the manifold assumption of MR has its inherent fundamentals. Finally, the manifold fundamental of single-conditions labeled mode is analyzed with dimensionality reduction.

[1]  Chih-Chung Wang,et al.  Rotating machine fault detection based on HOS and artificial neural networks , 2002, J. Intell. Manuf..

[2]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[3]  Quansheng Jiang,et al.  Machinery fault diagnosis using supervised manifold learning , 2009 .

[4]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[5]  Yaguo Lei,et al.  New clustering algorithm-based fault diagnosis using compensation distance evaluation technique , 2008 .

[6]  J. Lee.  Strategy and challenges on remote diagnostics and maintenance for manufacturing equipment , 1997, Annual Reliability and Maintainability Symposium.

[7]  V. Rai,et al.  Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform , 2007 .

[8]  Gang Niu,et al.  Multi-agent decision fusion for motor fault diagnosis , 2007 .

[9]  Carey Bunks,et al.  CONDITION-BASED MAINTENANCE OF MACHINES USING HIDDEN MARKOV MODELS , 2000 .

[10]  Anoushiravan Farshidianfar,et al.  Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine , 2007 .

[11]  Ying Peng,et al.  A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction , 2011 .

[12]  Qiang Yang,et al.  A Manifold Regularization Approach to Calibration Reduction for Sensor-Network Based Tracking , 2006, AAAI.

[13]  Alexander Zien,et al.  Semi-Supervised Classification by Low Density Separation , 2005, AISTATS.

[14]  G. S. Yadava,et al.  Applications of artificial intelligence techniques for induction machine stator fault diagnostics: review , 2003, 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED 2003..

[15]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[16]  Ming Liang,et al.  Mechanical fault detection using fuzzy index fusion , 2007 .

[17]  Yung C. Shin,et al.  A Bayesian machine learning method for sensor selection and fusion with application to on-board fault diagnostics , 2010 .

[18]  Chengliang Liu,et al.  Leave-one-out manifold regularization , 2012, Expert Syst. Appl..

[19]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs , 2007 .

[20]  Shaoze Yan,et al.  A revised Hilbert–Huang transformation based on the neural networks and its application in vibration signal analysis of a deployable structure , 2008 .

[21]  Jinwu Xu,et al.  Multiple manifolds analysis and its application to fault diagnosis , 2009 .

[22]  Mikhail Belkin,et al.  Beyond the point cloud: from transductive to semi-supervised learning , 2005, ICML.

[23]  Li Wei,et al.  Semi-supervised time series classification , 2006, KDD '06.

[24]  Fan-Tien Cheng,et al.  Development of an e-Diagnostics/Maintenance framework for semiconductor factories with security considerations , 2003, Adv. Eng. Informatics.

[25]  Jie Zhang.  Improved on-line process fault diagnosis through information fusion in multiple neural networks , 2006, Comput. Chem. Eng..

[26]  Rui Silva,et al.  TOOL WEAR MONITORING OF TURNING OPERATIONS BY NEURAL NETWORK AND EXPERT SYSTEM CLASSIFICATION OF A FEATURE SET GENERATED FROM MULTIPLE SENSORS , 1998 .

[27]  Jaime Campos,et al.  Development in the application of ICT in condition monitoring and maintenance , 2009, Comput. Ind..

[28]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[29]  Richard Chiou,et al.  Remote, condition-based maintenance for web-enabled robotic system , 2009 .

[30]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[31]  Heikki Mannila,et al.  Random projection in dimensionality reduction: applications to image and text data , 2001, KDD '01.

[32]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[33]  Andrew Blake,et al.  Sparse and Semi-supervised Visual Mapping with the S^3GP , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[34]  Vikas Sindhwani,et al.  On semi-supervised kernel methods , 2007 .

[35]  Saara A. Brax,et al.  Developing integrated solution offerings for remote diagnostics: A comparative case study of two manufacturers , 2009 .

[36]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble , 2007 .

[37]  Benoît Iung,et al.  On the concept of e-maintenance: Review and current research , 2008, Reliab. Eng. Syst. Saf..

[38]  Alexander Ypma,et al.  Learning methods for machine vibration analysis and health monitoring , 2001 .