OPEN ACCESS
Quality policy has an impact on the production flows control by the way of the reworks rate. The using of a quality management approach, as TQM, is useful but however often inadequate. The proposed approach must be seen as a supplement to such quality management. This approach is broken down into two steps. The goal of the first one is to reduce the reworks rates by tuning optimally and on line the process in function of the lot characteristics and the values of the environmental factors. This tuning uses a model linking the different influent factors with the default occurrence. This model is extracted from the production dataset by using a learning approach. It is used to simulate an experimental design in order to find the optimal tuning of the controllable parameters. The second step evaluates the impact of the residual reworks rates on the production flows. It uses a combination of different indicators in order to obtain a cartography of the considered workshop that highlights different workshop behavior areas. The final goal is to associate the good production control rule to each of these areas. All this approach is applied to the case of a manufacturer of high-finished lacquered panels.
reworks, flows perturbation, indicator, simulation, quality, neural network, learning, knowledge extraction, cartography
Abouzahir O., Gautier R., Gidel T. (2003). Pilotage de l’amélioration des process par les coûts de non-qualité. 10e Séminaire CONFERE, Belfort, France.
AFGI (1992). Evaluer pour évaluer, les indicateurs de performance au service du pilotage industriel. Association Française de Gestion Industrielle, ouvrage collectif AFGI.
Agard B. and Kusiak A. (2005). Exploration des bases de données industrielles à l’aide du datamining – Perspectives. 9e colloque national AIP PRIMECA.
Colledani M., Tolio T. (2006). Impact of quality control on production system performance. CIRP Annals-Manufacturing Technology, vol., 55, n° 1, p. 453-456.
Crosby P.B. (1979). Quality is Free, Mc Graw-Hill, New-York.
Disney M.S., Towill, D.R. (2003). On the bullwhip and inventory variance produced by an ordering policy. Omega, vol. 31, n° 3, p. 157-167.
Engelbrecht A.P. (2001). A new pruning heuristic based on variance analysis of sensitivity information. IEEE transactions on Neural Networks, p. 1386-1399.
Feigenbaum A.V. (1951). Quality control: Principles, practice and administration: An industrial management tool for improving product quality and design and for reducing operating costs and losses, McGraw-Hill, New-York.
Garvin D. (1984). What does product quality really mean. Sloan management review, vol. 26, n° 1, p. 25-48.
Hajek P., Olej V. (2010) Municipal revenue prediction by ensembles of neural networks and support vector machines. WSEAS Transactions on Computers, vol. 9, p. 1255-1264.
Ishikawa K. (1986). Guide to quality control, Asian Productivity Organization, Tokyo.
Kannan V.R., Tan K.C. (2005). Just in time, total quality management, and supply chain management : understanding their linkages and impact on business performance. Omega, vol. 33, p.153-162.
Love P.E.D., Li H., Mandal P. (1999). Rework: a symptom of a dysfunctional supply chain. European Journal of Purchasing & Supply Management, vol. 5, n° 1, p. 1-11.
Meyer D., Leisch F., Hornik K. (2003). The support vector machine under test. Neurocomputing, vol. 55, p. 169-186.
Nguyen D., Widrow B. (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptative weights. Proc. of the Int. Joint Conference on Neural Networks IJCNN'90, vol. 3, p. 21-26.
Noyel M., Thomas P., Charpentier P., Thomas A., Brault T. (2013). Implantation of an on-line quality process monitoring. 5th International Conference on Industrial Engineering and Systems Management IESM’13, Rabat, Maroc.
Noyel M., Thomas P., Charpentier P., Thomas A., Brault T. (2014). Flow disturbance analysis in workshops with high reworks rate. Advances in Production Management Systems APMS’14, Ajaccio, France.
Noyel M. (2015). Contrôle intégré du pilotage d’atelier et de la qualité des produits. Application à la société ACTA mobilier. Thèse de l’Université de Lorraine.
Paliwal M., Kumar U.A. (2009). Neural networks and statistical techniques: A review of applications. Expert Systems with Applications, vol. 36, p. 2-17.
Patel M.C., Panchal M. (2012). A review on ensemble of diverse artificial neural networks. Int. J. of Advanced Research in Computer Engineering and Technology, vol. 1, n° 10, p. 63-70.
Setiono R., Leow W.K. (2000). Pruned neural networks for regression. 6th Pacific RIM Int. Conf. on Artificial Intelligence PRICAI’00, Melbourne, Australia.
Taguchi G. (1989). Quality Engineering in Production Systems, Mc Graw-Hill, New-York.
Talib F., Rahman Z. (2012). Total quality management practices in manufacturing and service industries: a comparative study. Int. J. Advanced Operations Management vol. 4, n° 3, p. 155-176.
Thomas P., Bloch G. (1997). Initialization of one hidden layer feedforward neural networks for non-linear system identification. 15th IMACS World Congress on Scientific Computation, Modelling and Applied Mathematics WC'97, Berlin, Allemagne.
Thomas P., Bloch G., Sirou F., Eustache V. (1999). Neural modeling of an induction furnace using robust learning criteria. J. of Integrated Computer Aided Engineering, vol. 6, n° 1, p. 5-23.
Thomas P., Noyel M., Suhner M.C., Charpentier P., Thomas A. (2013). Neural Networks ensemble for quality monitoring. 5th International Joint Conference on Computational Intelligence IJCCI'13, Vilamoura, Portugal.
Thomas P., Suhner M.C., (2015). A new multilayer perceptron pruning algorithm for classification and regression applications. Neural Processing Letters., vol. 42, n° 2, p. 437-458.
Vollmann T.E., Berry W.L., Whybark C.D. (1984). Manufacturing Planning and Control Systems, Dow Jones-Irwin, New-York.