AUTHORS: Emad Ali
Download as PDF
ABSTRACT: This paper deals with the problem of modelling and monitoring the fault-free states of an industrial process without complete knowledge about the entire machine components. The aim thereby is to automatically detect the deviations in performance as fault symptoms. For that type of data-based modelling, the algorithms of clustering are selected with an emphasis on the computational load and application complexity. Kohonen neural networks (self-organizing maps) are found suitable for the task due to the ability to efficiently operate on high dimensional data and because of their robustness against uncertainties. They reveal drawbacks from the perspective of identifying the deviating variable in the input space. A novel structure is designed to solve this dilemma by combining multi one-dimensional domains and their statistical relationships, where Kohonen and Bayesian algorithms would be directly applicable. The structure is introduced and applied to simulate the human supervisors in the way of learning normal operation and hence, attempts to automatically identify the deviating variable in a high amount of data. An example application is proposed for detecting the wear degradation fault in a real electrohydraulic drive that widely used in many industrial machines. The algorithm can be realized locally or integrated remotely in cloud architectures.
KEYWORDS: condition monitoring, unsupervised machine learning, self-organizing maps, abnormality isolator, artificial neural networks, fault detections.
REFERENCES:
[
1] Aldrich, C. and Auret, L. 2013. Unsupervised process monitoring and fault diagnosis with machine learning methods. Advances in computer vision and pattern recognition, 2191- 6586.
[2] Alhajj, R. S. 2014. Encyclopedia of social network analysis and mining. Springer, New York.
[3] Cao, S. and Rhinehart, R. R. 1995. An efficient method for on-line identification of steady state. Journal of Process Control 5, 6, 363– 374.
[4] Du, K.-L. And Swamy, M. N. S. 2014. Neural networks and statistical learning. Springer, London.
[5] El-Betar A. et al. 2006. Fault Diagnosis of a Hydraulic Power System Using an Artificial Neural Network. JKAU: Eng. Sci. 17, 117– 137.
[6] Fernandes G. et al., Ed. 2012. Automated Method for Recognizing Steady State Intervals on The Series in Gas Turbines Test Bench 1, Spain.
[7] Isermann, R. and Balle, P. 1997. Trends in the Application of Model-Based Fault Detection and Diagnosis of Technical-processes. Control Eng. Practice 5, 709–719.
[8] Ivantysyn, J. and Ivantysynova, M. 2003. Hydrostatic pumps and motors. Principles, design, performance, modelling, analysis, control and testing / Jaroslav Ivantysyn and Monika Ivantysynova. Tech Books International, New Delhi.
[9] Jiang, T. e. a. 2003. Application of steady-state detection method based on wavelet transform. Computers & Chemical Engineering 27, 4, 569–578.
[10] Kohonen, T. SOM Toolbox 2.0. https:// www.cis.hut.fi/projects/somtoolbox/. Accessed 15 May 2018.
[11] Kohonen, T. 1998. The self-organizing map. Neurocomputing 21, 1-3, 1–6.
[12] Kohonen, T. 2001. Self-organizing maps. Springer series in information sciences, 0720- 678X 30. Springer, Berlin, London.
[13] Kohonen, T. and Honkela, T. 2007. Kohonen network.
[14] Navidi, W. C. 2011. Statistics for engineers and scientists. McGraw-Hill, New York.
[15] Neubert, T. 2002. Untersuchungen von drehzahlveränderbaren Pumpen. Dissertation.
[16] Penman, J. 1994. Feasibility of using unsupervised learning, artificial neural networks for the condition monitoring of electrical machines. IEE Proc., Electr. Power Appl. 141, 6, 317.
[17] Ramdén, T. 1998. Condition monitoring and fault diagnosis of fluid power systems. Approaches with neural networks and parameter identification / Teresia Ramdén. doctoral.
[18] Ristic, M. 2008. Development of Variablespeed Drives. IFK.
[19] Saxena, A. e. a. 2017. A review of clustering techniques and developments. Neurocomputing 267, 664–681.
[20] Torikka T. 2010. Bewertung von Analyseverfahren zur Zustandsüberwachung einer Axialkolbenpumpe. doctoral, RWTH Aachen.
[21] Zhou, D. 2014. The Application of Bayesian Networks in System Reliability. Master, ARIZONA STATE UNIVERSITY.
