Artificial Intelligent Systems for Quality Assurance in Small Series Production

Abstract:

The major challenge faced by a quality assurance (QA) system applied to small series production (SSP) is to guarantee the needed quality level already at the first run. Its called first time right on time. The SSP has some particular characteristics as the great diversity of product types and the continuous introduction of new products. Thus, the QA system has to adapt itself constantly to the new production conditions and support continuous process improvements. In this context, this paper presents the development of intelligent systems for QA in the diagnosis of SSP defects. The two systems developed are based on Artificial Intelligence techniques (Bayesian Networks, Expert Systems and Multiagent Systems) that analyze information from the metrological systems (such as a machine vision system) in the SSP line. The goal is to ensure that the cause of a defect will be fixed. The paper will present the context of the SSP, describe two solutions for quality assurance in SSP and will finish with the presentation of the results in the context of a SSP line for Printed Circuit Boards (PCB) mounting.

• Periodical: Key Engineering Materials (Volume 613)
• Pages: 279-287
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.613.279
• Online since: May 2014
• Authors: Marcelo Ricard Stemmer*, Camila Pontes Brito da Costa, Jaqueline Vargas, Mário Lúcio Roloff
• Keywords: Bayesian Network (BN), Expert System, Quality Assurance, Small Series Production

References

[1] T. Pyzdek, Process Control for Short and Small Runs, Quality Progress (1993) 51–60.

[2] S. -Y. Lin, Y. -J. Lai, S.I. Chang, Short-run statistical process control: Multicriteria part family formation, Quality and Reliability Engineering International 13 (1997) 9-24.

DOI: 10.1002/(sici)1099-1638(199701)13:1<9::aid-qre58>3.0.co;2-w

[3] M. M. Doro, Solução integrada para auxiliar na garantia da qualidade na produção em pequenos lotes, Doctor thesis, Faculty of Mechanical Engineering at the Federal University of Santa Catarina (2009).

[4] J. Gausemeier, U. Frank , H. Giese, F. Klein, O. Oberschelp, A. Schmidt, B. Schulz , H. Vöcking, K. Witting , Selbstoptimierende Systeme des Maschinenbaus: Definition und Konzepte, HNI Verlagsschriftenreihe 155 ( 2004).

[5] X. Jiang, Y. Zhang, K. Zhao and W. Wang, Research on multi-type & small batch oriented process quality control system under network environment, IEEE International Conference Automation and Logistics (2008) 869-874.

DOI: 10.1109/ical.2008.4636272

[6] V. R. Dave, D. A. Hartman, W. H. King, M. J. Cola and R.U. Vaidya, Strategy for small- lot manufacturing - in process monitoring and control, Los Alamos Science 28 (2003).

[7] T. Pfeifer and M. Merget, Methodology to estimate the feasibility of inspection tasks in concurrent engineering, Proceedings of the International Conference on TQM and Human Factors (1999) 194-199.

[8] Q. Li, L. Zhu and Z. Xu, Fuzzy Petri- Nets Based Fault Diagnosis for Mechanical - electric Equipment, IEEE International Conference on Control and Automation (2007) 2539-2543.

DOI: 10.1109/icca.2007.4376820

[9] V. F. Victor, Sistema especialista para detecção de falhas em comandos elétricos, Master thesis at the Federal University of Rio Grande do Norte (2005).

[10] N. R., Jennings, K. Sycara, and M. Wooldridge, A roadmap of agent research and development, Autonomous Agents and Multiagent Systems (1998) 7-38.

[11] J. Vargas, Sistema especialista de diagnóstico e tomada de decisão para garantia de qualidade na montagem de placas de circuito impresso em pequenas séries, Master thesis at the Federal University of Santa Catarina (2012).

DOI: 10.47749/t/unicamp.2002.279063

[12] R. H. Bordini, J. F. Hübner, and M. Wooldridge, Programming multi agent systems in AgentSpeak using Jason, Wiley, (2007).

DOI: 10.1002/9780470061848

[13] E., Charniak, Bayesian Networks without Tears, AI Magazine 12 No. 4 (1991) 50-63.

[14] D., Nikovski, Constructing Bayesian Networks for Medical Diagnosis from Incomplete and Partially Correct Statistics, IEEE Transactions on Knowledge and Data Engineering 12 No. 4 (2000) 509-516.

DOI: 10.1109/69.868904

[15] M., Stemmer, M. Roloff, C. Schneider, M. Doro, T. Pfeifer, R. Schmitt and A. Pavim, Handling small series production inspection requirements through the use of cognitive and flexible metrology strategies, Proceedings of the 7th CIRP International Conference on Intelligent Computation in Manufacturing Engineering (2010).

DOI: 10.1007/978-1-84996-432-6_81

[16] M. M. Doro, Treinamento de Garantia da Qualidade em Placas Eletrônicas - Defeitos e Causas, Labelectron, SC, Brazil, (2012).

[17] Information on http: /www. norsys. com/netica. html.

[18] G. F. Cooper, The computational complexity of probabilistic inference using Bayesian belief networks (research note), Journal of Artificial Intelligence 42 Issue 2-3 (1990) 393-405.

DOI: 10.1016/0004-3702(90)90060-d