{"title":"Computer Aided Design Solution Based on Genetic Algorithms for FMEA and Control Plan in Automotive Industry","authors":"Nadia Belu, Laurentiu M. Ionescu, Agnieszka Misztal","volume":104,"journal":"International Journal of Industrial and Manufacturing Engineering","pagesStart":2672,"pagesEnd":2678,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10001721","abstract":"In this paper we propose a computer-aided solution\r\nwith Genetic Algorithms in order to reduce the drafting of reports:\r\nFMEA analysis and Control Plan required in the manufacture of the\r\nproduct launch and improved knowledge development teams for\r\nfuture projects. The solution allows to the design team to introduce\r\ndata entry required to FMEA. The actual analysis is performed using\r\nGenetic Algorithms to find optimum between RPN risk factor and\r\ncost of production. A feature of Genetic Algorithms is that they are\r\nused as a means of finding solutions for multi criteria optimization\r\nproblems. In our case, along with three specific FMEA risk factors is\r\nconsidered and reduce production cost. Analysis tool will generate\r\nfinal reports for all FMEA processes. The data obtained in FMEA\r\nreports are automatically integrated with other entered parameters in\r\nControl Plan. Implementation of the solution is in the form of an\r\napplication running in an intranet on two servers: one containing\r\nanalysis and plan generation engine and the other containing the\r\ndatabase where the initial parameters and results are stored. The\r\nresults can then be used as starting solutions in the synthesis of other\r\nprojects. The solution was applied to welding processes, laser cutting\r\nand bending to manufacture chassis for buses. Advantages of the\r\nsolution are efficient elaboration of documents in the current project\r\nby automatically generating reports FMEA and Control Plan using\r\nmultiple criteria optimization of production and build a solid\r\nknowledge base for future projects. The solution which we propose is\r\na cheap alternative to other solutions on the market using Open\r\nSource tools in implementation.","references":"[1] McDermott R., Mikulak R., Beauregard M., The basics of FMEA, 2nd\r\nEdition, Taylor & Francis Group, 270 Madison Avenue, New York,\r\n2009.\r\n[2] S. Helvacioglu and E. Ozen, Fuzzy based failure modes and effect\r\nanalysis for yacht system design, Ocean Engineering, vol.79, pp. 131\u2013\r\n141, March, 2014.\r\n[3] Chrysler Corporation, Ford Motor Company, General Motors\r\nCorporation, Potential Failure Modes and Effects Analysis (FMEA).\r\nReference Manual, 4th ed., 2008.\r\n[4] ISO\/TS 16949:2009, Quality management systems. Particular\r\nrequirements for the application of ISO 9001:2008 for automotive\r\nproduction and relevant service part organizations, International\r\nOrganization for Standardization, Geneva, Switzerland 2009.\r\n[5] Advanced Product Quality Planning and Control Plan APQP. Reference\r\nManual. 2nd Edition. AIAG, 2008.\r\n[6] N. Belu, A.-R. Al Ali and N. Khassawneh, Application of Control Plan -\r\nPPAP Tool in Automotive Industry Production, Quality - Access to\r\nSuccess, vol. 14, no. 136 pp. 68-72, October, 2013.\r\n[7] A. Maria Jaya Prakasha, T. Senthilvelan and R. Gnanadass\r\n\u201cOptimization of process parameters through fuzzy logic and genetic\r\nalgorithm \u2013 A case study in a process industry\u201d, Applied Soft\r\nComputing, vol. 30, pp. 94\u2013103, May 2015.\r\n[8] Z. Yang, S. Bonsall and J. Wang, Fuzzy rule-based Bayesian reasoning\r\napproach for prioritization of failures in FMEA, IEEE Transactions on\r\nReliability, vol. 57, pp. 517\u2013528, 2008.\r\n[9] J. Yang, H.-Z. Huang, L.-P. He, S.-P. Zhu, D. Wen, Risk evaluation in\r\nfailure mode and effects analysis of aircraft turbine rotor blades using\r\nDempster\u2013Shafer evidence theory under uncertainty, Engineering\r\nFailure Analysis, vol. 18 pp. 2084\u20132092, 2011.\r\n[10] H.-C. Liu, L. Liu, Q.-H. Bian, Q.-L. Lin, N. Dong, P.-C. Xu, Failure\r\nmode and effects analysis using fuzzy evidential reasoning approach and\r\ngrey theory, Expert Systems Applications, vol. 38, pp. 4403\u20134415, 2011.\r\n[11] Y.-M. Wang, K.-S. Chin, G.K.K. Poon and J.-B.Yang, Risk evaluation\r\nin failure mode and effects analysis using fuzzy weighted geometric\r\nmean, Expert Systems Applications, vol. 36, pp. 1195\u20131207, 2009.\r\n[12] C. \u015etirbu, C. Anton, L. Stirbu and R Badea, Improved by prediction of\r\nthe PFMEA using the artificial neural networks in the electrical industry,\r\nInternational Conference on Applied Electronics, Pilsen, September\r\n2011.\r\n[13] C. L. Chang, P. H Liu and C. C Wei, Failure mode and effects analysis\r\nusing grey theory, Integrated Manufacturing Systems, vol. 12(3),\r\npp.211\u2013216, 2001.\r\n[14] K. S., Chin, Y. M. Wang, G. K. K. Poon, and J. B. Yang, Failure mode\r\nand effects analysis by data envelopment analysis, Decision Support\r\nSystems, vol. 48(1), pp. 246\u2013256, 2009.\r\n[15] K. H. Chang and C. H. Cheng, Evaluating the risk of failure using the\r\nfuzzy OWA and DEMATEL method, Journal of Intelligent\r\nManufacturing, vol. 22(2), pp. 113\u2013129, 2011.\r\n[16] J. Holland, Adaptation in Natural and Artificial Systems, Cambridge,\r\nMA: MIT Press, 1992.\r\n[17] A. Misztal, N. Belu, N. Rachieru, \u201cComparative analysis of awareness\r\nand knowledge of APQP requirements in Polish and Romanian\r\nautomotive industry\u201d, Applied Mechanics and Materials, Vol. 657\r\n(2014) pp. 981-985.\r\n[18] M. Butlewski, M. Jasiulewicz-Kaczmarek, A. Misztal, M. S\u0142awi\u0144ska,\r\n\u201cDesign methods of reducing human error in practice\u201d, in: Safety and\r\nReliability: Methodology and Applications - Proceedings of the\r\nEuropean Safety and Reliability Conference ESREL 2014 Wroc\u0142aw,\r\n(ed.) T. Nowakowski, M. M\u0142y\u0144czak, A. Jodejko-Pietruczuk, S.\r\nWerbi\u0144ska-Wojciechowska, pp. 1101-1106, CRC Press, London 2015.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 104, 2015"}