Fault Detection Assessment Architectures based on Classification Methods and Information Fusion

Classifiers based on machine learning are popular in literature, in order to support predictive maintenance of machinery. Depending on the process data, one classifier can assess target classes better than others. It often happens that the classifiers complement each other. A fusion strategy is needed in order to exploit the strength of each classifier. This paper presents fault detection assessment architectures based on information fusion and classification methods. It proposes the use of information fusion methods and different architectures, in order to improve the overall result of the fault detection assessment. Dempster-Shafer and Yager rules of combination are used to fuse the classification method predictions. The rules of combination improve the results by complementing the classifiers performance. A comparison between centralized and decentralized architectures is presented. The results show that the information fusion using decentralized architectures improves the overall performance of the fault detection assessment.

[1]  Liqun Hou,et al.  Novel Industrial Wireless Sensor Networks for Machine Condition Monitoring and Fault Diagnosis , 2012, IEEE Transactions on Instrumentation and Measurement.

[2]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[3]  安藤 寛,et al.  Cross-Validation , 1952, Encyclopedia of Machine Learning and Data Mining.

[4]  Andreas Schwung,et al.  Assistance system for a bulk good system based on information fusion , 2017, 2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA).

[5]  Anouar Ben Hassena,et al.  Comparison and fusion of classifiers applied to a medical diagnosis , 2017, 2017 14th International Multi-Conference on Systems, Signals & Devices (SSD).

[6]  Tina R. Patil,et al.  Performance Analysis of Naive Bayes and J 48 Classification Algorithm for Data Classification , 2013 .

[7]  Lie Guo,et al.  Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine , 2012, Expert Syst. Appl..

[8]  Francisco Herrera,et al.  Data Preprocessing in Data Mining , 2014, Intelligent Systems Reference Library.

[9]  Uwe Aickelin,et al.  Data classification using the Dempster–Shafer method , 2014, J. Exp. Theor. Artif. Intell..

[11]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[12]  Martin Hromada,et al.  Anomaly Detection System Based on Classifier Fusion in ICS Environment , 2017, 2017 International Conference on Soft Computing, Intelligent System and Information Technology (ICSIIT).

[13]  Florentin Smarandache,et al.  Advances and Applications of DSmT for Information Fusion (Collected Works) , 2004 .

[14]  Duan-Yu Chen,et al.  Machine-learning-based single-phase-to-ground fault detection in distribution systems , 2017, 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2).

[15]  Andreas Schwung,et al.  Fault detection using probabilistic prediction and data fusion on a bulk good system , 2017, 2017 52nd International Universities Power Engineering Conference (UPEC).

[16]  Dahai Zhang,et al.  A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost , 2018, IEEE Access.

[17]  Dibo Hou,et al.  Detection of water-quality contamination events based on multi-sensor fusion using an extented Dempster–Shafer method , 2013 .

[18]  Elizabeth A. Cudney,et al.  Total Productive Maintenance: Strategies and Implementation Guide , 2015 .

[19]  Adi Soeprijanto,et al.  Rotor bars fault detection by DFT spectral analysis and Extreme Learning Machine , 2016, 2016 International Symposium on Electronics and Smart Devices (ISESD).