A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance

The area of predictive maintenance has taken a lot of prominence in the last couple of years due to various reasons. With new algorithms and methodologies growing across different learning methods, it has remained a challenge for industries to adopt which method is fit, robust and provide most accurate detection. Fault detection is one of the critical components of predictive maintenance; it is very much needed for industries to detect faults early and accurately. In a production environment, to minimize the cost of maintenance, sometimes it is required to build a model with minimal or no historical data. In such cases, unsupervised learning would be a better option model building. In this paper, we have chosen a simple vibration data collected from an exhaust fan, and have fit different unsupervised learning algorithms such as PCA T2 statistic, Hierarchical clustering, K-Means, Fuzzy C-Means clustering and model-based clustering to test its accuracy, performance, and robustness. In the end, we have proposed a methodology to benchmark different algorithms and choosing the final model.

[1]  F. Gu,et al.  Fault detection and diagnosis using Principal Component Analysis of vibration data from a reciprocating compressor , 2012, Proceedings of 2012 UKACC International Conference on Control.

[2]  Tarun Gupta,et al.  Modified Rank Order Clustering Algorithm Approach by Including Manufacturing Data , 2016 .

[3]  Stefan Byttner,et al.  Wisdom of Crowds for Intelligent Monitoring of Vehicle Fleets , 2015 .

[4]  Jay Lee,et al.  Watchdog Agent - an infotronics-based prognostics approach for product performance degradation assessment and prediction , 2003, Adv. Eng. Informatics.

[5]  Zhen Sun,et al.  A real-time fault detection and isolation strategy for gas sensor arrays , 2017, 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).

[6]  R. Keith Mobley,et al.  An introduction to predictive maintenance , 1989 .

[7]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[8]  Malika Charrad,et al.  NbClust: An R Package for Determining the Relevant Number of Clusters in a Data Set , 2014 .

[9]  Andreas Gössling,et al.  Architecture of a Predictive Maintenance Framework , 2007, 6th International Conference on Computer Information Systems and Industrial Management Applications (CISIM'07).

[10]  Michael Grüninger,et al.  Introduction , 2002, CACM.

[11]  Daria Battini,et al.  Sustainable Packaging Development for Fresh Food Supply Chains , 2016 .

[12]  Jay Lee,et al.  Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment , 2014 .

[13]  Adrian E. Raftery,et al.  mclust Version 4 for R : Normal Mixture Modeling for Model-Based Clustering , Classification , and Density Estimation , 2012 .

[14]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[15]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[16]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[17]  Adrian E. Raftery,et al.  Model-Based Clustering, Discriminant Analysis, and Density Estimation , 2002 .

[18]  L. Pan,et al.  A Novel Fuzzy C-Means Clustering Algorithm for Image Thresholding , 2004 .

[19]  Konstantinos C. Gryllias,et al.  Rolling element bearing fault detection in industrial environments based on a K-means clustering approach , 2011, Expert Syst. Appl..

[20]  Premaratne Samaranayake,et al.  Aircraft maintenance planning and scheduling : an integrated framework , 2012 .

[21]  Jean-Christophe Lapayre,et al.  A new industrial cooperative tele-maintenance platform , 2004, Comput. Ind. Eng..

[22]  Bo Fan,et al.  Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis , 2014 .

[23]  Abdelmalek Kouadri,et al.  Fault detection and diagnosis in a cement rotary kiln using PCA with EWMA-based adaptive threshold monitoring scheme , 2017 .