A novel hybrid intelligent system for multi-objective machine parameter optimization

详细信息    查看全文

• 作者：Raquel Redondo (1)
  Javier Sedano (2)
  Vicente Vera (3)
  Beatriz Hernando (3)
  Emilio Corchado (4) (5)
  
  1. Department of Civil Engineering ; University of Burgos ; Burgos ; Spain
  2. Department of AI and Applied Electronics ; Castilla y Le贸n Technological Institute ; Burgos ; Spain
  3. Facultad de Odontolog铆a ; UCM ; Madrid ; Spain
  4. Department de Inform谩tica y Autom谩tica ; Universidad de Salamanca ; Salamanca ; Spain
  5. IT4Innovations ; Ostrava ; Czech Republic
  
• 关键词：Hybrid intelligent system ; Dental milling process ; Optimization ; Unsupervised learning ; Identification systems ; Multi ; objective optimization
• 刊名：Pattern Analysis & Applications
• 出版年：2015
• 出版时间：February 2015
• 年：2015
• 卷：18
• 期：1
• 页码：31-44
• 全文大小：1,988 KB
• 参考文献：1. Corchado E, Sedano J, Curiel L, Villar JR (2012) Optimizing the operating conditions in a high precision industrial process using soft computing techniques. Expert Systems聽29(3):276鈥?99. http://dx.doi.org/10.1111/j.1468-0394.2011.00588.x
  2. Frank M, Hamprecht F (2011) Image-based supervision of a periodically working machine. Pattern Anal Appl 1鈥?0. http://dx.doi.org/10.1007/s10044-011-0245-7
  3. Huang L, Suh IH, Abraham A (2011) Dynamic multi-objective optimization based on membrane computing for control of time-varying unstable plants. Inf Sci 181(11):2370鈥?391 CrossRef
  4. Das MK, Kishor N (2009) Adaptive fuzzy model identification to predict the heat transfer coefficient in pool boiling of distilled water. Expert Syst with Appl 36(2, Part 1):1142鈥?154 CrossRef
  5. Esen H, Inalli M (2009) Modelling of a vertical ground heat pump system by using artificial neural networks. Expert Syst Appl 36(7):10229鈥?0238 CrossRef
  6. Ljung L (1999) System identification, theory for the user, 2nd edn. Prentice-Hall, Upper Saddle River
  7. Sedano J, Corchado E, Curiel L, Villar J, Bravo PM (2009) The application of a two-step AI model to an automated pneumatic drilling process. Int J Comput Math 86(10):1769鈥?777 CrossRef
  8. Sedano J, Curiel L, Corchado E, de la Cal E, Villar JR (2010) A soft computing based method for detecting lifetime building thermal insulation failures. Integr Comput-Aided Eng 17(2):103鈥?15
  9. Vera V, Corchado E, Redondo R, Sedano J, Garc铆a 脕E (2013) Applying soft computing techniques to optimise a dental milling process. Neurocomputing 109:94鈥?04.聽http://dx.doi.org/10.1016/j.neucom.2012.04.033
  10. Kalyani S, Swarup K (2012) Design of pattern recognition system for static security assessment and classification. Pattern Anal Appl聽15 (3):299鈥?11. http://dx.doi.org/10.1007/s10044-011-0218-x
  11. Miyazaki T, Hotta Y, Kunii J (2009) A review of dental CAD/CAM: current status and future perspectives from 20聽years of experience. Dent Mater J 28(1):44鈥?6 CrossRef
  12. Fuster-Torres MA, Albalat-Estela S, Alca帽iz-Raya M, Pe帽arrocha-Diago M (2009) CAD/CAM dental systems in implant dentistry: Update. Med Oral Patol Oral Cir Bucal 14(3):E141鈥揈145
  13. Beuer F, Schweiger J, Edelhoff D (2008) Digital dentistry: an overview of recent developments for CAD/CAM generated restorations. Br Dent J 204(9):497鈥?02 CrossRef
  14. Weaver J, Johnson G, Bales D (1991) Marginal adaptation of castable ceramic crowns. J Prosthet Dent 66:747鈥?53 CrossRef
  15. (2005) Glossary of Prosthodontic Terms. J Prosthet Dent 94: 92
  16. Wolfart S, Martin S, Kern M (2003) Clinical evaluation of marginal fit of a new experimental all鈥攃eramic system before and after cementation. Int J Prosthodont 6:587鈥?92
  17. Francine E, Omar M (2004) Marginal adaptation and microleakage of Procera All Ceram crowns with four cements. Int J Prosthodont 17:529鈥?35
  18. McLean J, von Fraunhofer JA (1971) The estimation of cement film by an in vivo technique. Br Dent J 131:107鈥?11 CrossRef
  19. Karlsson S (1993) The fit of Procera titanium crowns. An in vitro and clinical study. Acta Odontol Scand 51:129鈥?34 CrossRef
  20. Vera V, Sedano J, Corchado E, Redondo R, Hernando B, Camara M, Laham A, Garcia AE (2011) A hybrid system for dental milling parameters optimisation. In: 6th International conference on hybrid artificial intelligence systems. Wroclaw, Poland HAIS 2011, Part II, LNAI 6679, pp 437鈥?46
  21. Corchado E, Gra帽a M, Wozniak M (2012) Editorial: new trends and applications on hybrid artificial intelligence systems. Neurocomputing 75(1):61鈥?3 CrossRef
  22. Chang Hsu-Hwa, Chen Yan-Kwang (2011) Neuro-genetic approach to optimize parameter design of dynamic multiresponse experiments. Appl Soft Comput 11(1):436鈥?42 CrossRef
  23. Corchado E, Abraham A, Ponce Leon Ferreira de Carvalho AC (2010) Hybrid intelligent algorithms and applications. Inf Sci 180(14):2633鈥?634
  24. Abraham A, Corchado E, Corchado JM (2009) Hybrid learning machines. Neurocomputing 72(13鈥?5):2729鈥?730 CrossRef
  25. Borrajo ML, Baruque B, Corchado E, Bajo J, Corchado JM (2011) Hybrid neural intelligent system to predict business failure in small-to-medium-size enterprises. Int J Neural Syst 21(4):277鈥?96 CrossRef
  26. Fujita S (2009) Retrieval parameter optimization using genetic algorithms. Inf Process Manage 45:664鈥?82 CrossRef
  27. Oliveira ALI, Braga PL, Lima RMF, Corn茅lio ML (2010) Ga-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation. Inf Softw Technol 52:1155鈥?166 CrossRef
  28. Dorigo M, St眉tzle T (2004) Ant Colony Optimization. Bradford Co, Scituate CrossRef
  29. Liu Y, Zhou C, Guo D, Wang K, Pang W, Zhai Y (2010) A decision support system using soft computing for modern international container transportation services. Appl Soft Comput 10(4):1087鈥?095 CrossRef
  30. Twycross J, Aickelin U (2010) Information fusion in the immune system. Inf Fusion 11(1):35鈥?4 CrossRef
  31. Corchado E, Herrero A (2011) Neural visualization of network traffic data for intrusion detection. Appl Soft Comput 11(2):2042鈥?056 CrossRef
  32. Foug猫res A (2011) Modelling and simulation of complex systems: an approach based on multi-level agents. IJCSI Int J Comput Sci Issues 8(6):8鈥?7
  33. Castro JL, Navarro M, S谩nchez JM, Zurita JM (2009) Loss and gain functions for CBR retrieval. Inf Sci 179(11):1738鈥?750 CrossRef
  34. Pearson K (1901) On lines and planes of closest fit to systems of points in space. Phil Mag 2(6):559鈥?72 CrossRef
  35. Hotelling H (1933) Analysis of a complex of statistical variables into Principal Components. J Educ Psychol 24:417鈥?44 CrossRef
  36. Oja E, Ogawa H, Wangviwattana J (1992) Principal components analysis by homogeneous neural networks, part 1, the weighted subspace criterion. IEICE Trans Inf Syst E75D:366鈥?75
  37. Diaconis P, Freedman D (1984) Asymptotics of graphical projections. Ann Stat 12(3):793鈥?15 CrossRef
  38. Corchado E, MacDonald D, Fyfe C (2004) Maximum and minimum likelihood hebbian learning for exploratory projection pursuit. Data Min Knowl Disc 8(3):203鈥?25 CrossRef
  39. Friedman JH (1987) Exploratory projection pursuit. J Am Stat Assoc 82(397):249鈥?66 CrossRef
  40. Pedrycz W, Lee D, Pizzi N (2010) Representation and classification of high-dimensional biomedical spectral data. Pattern Anal Appl 13(4):423鈥?36 CrossRef
  41. Gunala S, Edizkanb R (2008) Subspace based feature selection for pattern recognition. Inf Sci 178(19):3716鈥?726 CrossRef
  42. Corchado E, Fyfe C (2003) Connectionist techniques for the identification and suppression of interfering underlying factors. Int J Pattern Recognit Artif Intell 17(8):1447鈥?466 CrossRef
  43. Fyfe C, Corchado E (2002) Maximum likelihood hebbian rules. In: Verleysen M (ed) Proceedings of the 10th Eurorean Symposium on Artificial Neural Networks, Bruges, Belgium, April 24-26 (ESANN 2002), pp 143鈥?48
  44. Corchado E, Han Y, Fyfe C (2003) Structuring global responses of local filters using lateral connections. J Exp Theor Artif Intell 15(4):473鈥?87 CrossRef
  45. Seung H, Socci N, Lee D (1998) The rectified Gaussian distribution. Adv Neural Inf Process Syst 10:350鈥?56
  46. N酶rgaard M, Ravn O, Poulsen NK, Hanse LK (2000) Neural networks for modelling and control of dynamic systems. Springer-Verlag, London CrossRef
  47. Schoukens J, Rolain Y, Pintelan R (2004) Improved approximate identification of nonlinear systems. In: 21st IEEE instrumentation and measurement technology conference, Como, Italy, pp 2183鈥?186
  48. Hanne T (2000) Global multi-objective optimization using evolutionary algorithms. J Heuristics 6(3):347鈥?60 CrossRef
  49. Srinivas N, Deb K (1995) Multi-objective function optimization using nondominated sorting genetic algorithms. Evol Comput J 2(3):221鈥?48 CrossRef
  50. Deb K, Pratap A, Agarwal S, Meyarivan T (2000) A fast elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6:182鈥?97 CrossRef
  51. Luciano S谩nchez L, Villar JR (2008) Obtaining transparent models of chaotic systems with multi-objective simulated annealing algorithms. Inf Sci 178:952鈥?70 CrossRef
  52. Demuth H, Beale M, Hagan M (2010) Neural Network Toolbox User鈥檚 Guide. The Mathworks Inc., Natick
  53. The Math Works. Global Optimization Toolbox. The MathWorks Inc., URL: http://www.mathworks.com/products/global-optimization/index.html
  54. Fletcher R (1987) Practical methods of optimization, 2nd edn. Wiley & Sons, Chichester
  55. Dennis JE, Schnabel RB (1983) Numerical methods for unconstrained optimization and nonlinear equations. Prentice-Hall, Englewood Cliffs
  56. Riedmiller M, Braun H (1993) A directive adaptive method for faster backpropagation learning: The RPROP algorithm. In: Proceedings for IEEE International Conference on Neural Networks
  57. Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525鈥?33 CrossRef
  58. Mackay DJC (1992) Bayesian interpolation. Neural Comput 4(3):415鈥?47 CrossRef
  
• 刊物类别：Computer Science
• 刊物主题：Pattern Recognition
  
• 出版者：Springer London
• ISSN：1433-755X

文摘

This multidisciplinary research presents a novel hybrid intelligent system to perform a multi-objective industrial parameter optimization process. The intelligent system is based on the application of evolutionary and neural computation in conjunction with identification systems, which makes it possible to optimize the implementation conditions in the manufacturing process of high precision parts, including finishing precision, while saving time, financial costs and/or energy. Empirical verification of the proposed hybrid intelligent system is performed in a real industrial domain, where a case study is defined and analyzed. The experiments are carried out based on real dental milling processes using a high precision machining centre with five axes, requiring high finishing precision of measures in micrometers with a large number of process factors to analyze. The results of the experiments which validate the performance of the proposed approach are presented in this study.