Call for Paper

CAE solicits original research papers for the July 2021 Edition. Last date of manuscript submission is June 30, 2021.

Read More

A CNC Machine Fault Diagnosis Methodology based on Bayesian Networks and Data Acquisition

Abdelkabir Bacha, Jamal Benhra, Ahmed Haroun Sabry. Published in Networks.

Communications on Applied Electronics
Year of Publication: 2016
Publisher: Foundation of Computer Science (FCS), NY, USA
Authors: Abdelkabir Bacha, Jamal Benhra, Ahmed Haroun Sabry
10.5120/cae2016652353

Abdelkabir Bacha, Jamal Benhra and Ahmed Haroun Sabry. A CNC Machine Fault Diagnosis Methodology based on Bayesian Networks and Data Acquisition. Communications on Applied Electronics 5(8):41-48, August 2016. BibTeX

@article{10.5120/cae2016652353,
	author = {Abdelkabir Bacha and Jamal Benhra and Ahmed Haroun Sabry},
	title = {A CNC Machine Fault Diagnosis Methodology based on Bayesian Networks and Data Acquisition},
	journal = {Communications on Applied Electronics},
	issue_date = {August 2016},
	volume = {5},
	number = {8},
	month = {Aug},
	year = {2016},
	issn = {2394-4714},
	pages = {41-48},
	numpages = {8},
	url = {http://www.caeaccess.org/archives/volume5/number8/643-2016652353},
	doi = {10.5120/cae2016652353},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

In this work, a Bayesian Networks based fault diagnosis system for industrial machines is proposed. For this purpose, an experimental setup of a CNC machine is given as a test rig. This fault diagnosis system is composed of three levels: The first level concerns a set of sensors that are connected directly to the machine’s main organs. The second level is a microcontroller based data acquisition interface that calibrates and transfers the measured data to the third level. The last level is a set of machine learning algorithms that are executed in a computer. These algorithms perform BN structure learning and exploit this structure for classifying the new arrival data from the CNC machine and determining if it presents a faulty or a normal situation.

References

  1. J. Pearl, Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, 2014.
  2. G. F. Cooper and E. Herskovits, “A Bayesian method for the induction of probabilistic networks from data,” Machine learning, vol. 9, no. 4, pp. 309–347, 1992.
  3. D. Koller and N. Friedman, Probabilistic graphical models: principles and techniques. MIT press, 2009.
  4. O. François and P. Leray, “Etude comparative d’algorithmes d’apprentissage de structure dans les réseaux bayésiens,” Rencontres des Jeunes Chercheurs en IA, 2003.
  5. D. Margaritis, “Learning Bayesian network model structure from data,” US Army, 2003.
  6. G. F. Cooper, “The computational complexity of probabilistic inference using Bayesian belief networks,” Artificial intelligence, vol. 42, no. 2–3, pp. 393–405, 1990.
  7. P. Leray, “Réseaux bayésiens: apprentissage et modélisation de systèmes complexes,” Université de Rouen, 2006.
  8. G. F. Cooper and E. Herskovits, “A Bayesian method for constructing Bayesian belief networks from databases,” in Proceedings of the Seventh conference on Uncertainty in Artificial Intelligence, 1991, pp. 86–94.
  9. N. Z. Kamal MEDJAHER Amine Mechraoui, “Bayesian Based Fault Diagnosis: Application to an Electrical Motor.” .
  10. U. Lerner, R. Parr, D. Koller, G. Biswas, and others, “Bayesian fault detection and diagnosis in dynamic systems,” in AAAI/IAAI, 2000, pp. 531–537.
  11. A. Bacha, A. H. Sabry, and J. Benhra, “Design of a data acquisition system to be used in fault diagnosis,” in 2015 Third World Conference on Complex Systems (WCCS), 2015, pp. 1–6.
  12. A. Bacha, A. H. Sabry, and J. Benhra, “An industrial fault diagnosis system based on bayesian networks,” International Journal of Computer Applications, vol. 124, no. 5, 2015.
  13. A. Bacha, A. H. Sabry, and J. Benhra, “Aide au diagnostic de défaillances des machines industrielles basé sur les réseaux bayésiens,” in Xème Conférence Internationale: Conception et Production Intégrées, 2015.
  14. P. Jahnke, “Machine Learning Approaches for Failure Type Detection and Predictive Maintenance,” tu-darmstadt, 2015.
  15. M. J. Flores, J. A. Gámez, A. M. Mart

Keywords

Fault diagnosis, Fault detection, Bayesian Networks, CNC machine, Flexible manufacturing, Data acquisition.