Improvement of Manufacturing Process by Reducing of the Failures Ratio through Genetic Algorithm

Abstract:

This research introduces a new approach of using Failure Mode and Effect Analysis (FMEA) and Genetic Algorithm to improvement of manufacturing process – welding process. FMEA analysis is used to measure the weight of failures by calculating the Risk Priority Number (RPN) value for welding process. By FMEA we have identified precisely the main causes which lead to the appearance of many failures for which the RPN value is highest. Then we have established the parameters which are directly responsible of these causes. By using these parameters we have got a function that actually has to be improved optimized. This is going to be the objective function for the Genetic Algorithm.

• Periodical: Applied Mechanics and Materials (Volume 834)
• Pages: 61-66
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.834.61
• Online since: April 2016
• Authors: Nadia Belu*, Laurentiu Mihai Ionescu, Daniel Constantin Anghel, Nicoleta Rachieru
• Keywords: Effect Analysis, Failure Mode, Genetic Algorithm, Improvement, Welding Process

References

[1] K. Tahera, C.M. Eckert, C.F. Earl, Optimizing Overlap between Testing and Design in M. Abramovici, R. Stark (Eds. ), Smart Product Engineering: Proceedings of the 23rd CIRP Design Conference, Bochum, Germany, March 11th - 13th, 2013, Springer-Verlag Berlin Heidelberg, 2013, pp.201-210.

DOI: 10.1007/978-3-642-30817-8

[2] J. Sahno, E. Shevtshenko, T. Karaulova, K. Tahera, Framework for Continuous Improvement of Production Processes, Inzinerine Ekonomika-Engineering Economics 26(2), (2015) 169–180.

DOI: 10.5755/j01.ee.26.2.6969

[3] M. S. Yang, Y. Li, Y. Liu, X. Q. Gao, A Method for Problem Selection in the 6σ Definition Stage, Advanced Materials Research, Vols. 139-141, Oct. (2010) 1485-1489.

DOI: 10.4028/www.scientific.net/amr.139-141.1485

[4] V. Karandikar, S. Sane, S. Sane, S. Jahagirdar, S. Shinde, Process Improvement in a Filter Manufacturing Industry through Six Sigma DMAIC Approach, International Journal of Current Engineering and Technology, Vol. 4, No. 4 (2014) 2546- 2556.

[5] D.H. Stamatis, Failure Mode and Effect Analysis: FMEA from Theory to Execution, second ed., ASQC Press, New York, (2003).

[6] A. Misztal, Technical Determinants of Success in Quality Management Systems Implementation in the Automotive Industry, World Academy of Science, Engineering and Technology, International Journal of Social, Behavioral, Educational, Economic and Management Engineering Vol: 9, No: 8, (2015).

[7] Chrysler Corporation, Ford Motor Company, General Motors Corporation, Potential Failure Modes and Effects Analysis (FMEA). Reference Manual, 4th ed., (2008).

[8] C. Ştirbu, C. Anton, L. Stirbu and R. Badea, Improved By Prediction of the PFMEA Using the Artificial Neural Networks Proceeding of International Conference on Applied Electronics, Czech Republic, Pilsen, September (2011) 1-4.

[9] A. Mazare, L. Ionescu, G. Serban, V. Barbu, Evolvable Hardware with Boolean Functions Network Implementation, Proceeding of International Conference on Applied Electronics, Czech Republic, Pilsen, September (2011) 1-6.

[10] K. Paneerselvam, S. Aravindan, A. Noorul Haq, Hybrid of ANN with genetic algorithm for optimization of friction vibration joining process of plastics. J. Advan. Manuf. Technol. 42 (2009) 669–677.

DOI: 10.1007/s00170-008-1641-z