A neural network-based approach for optimising rubber extrusion lines

The current study shows how data mining and artificial intelligence techniques can be used to introduce improvements in the rubber extrusion production process. One of the keys for planning manufacturing values is prior knowledge of the properties of the material to be extruded. At present, such information is obtained through laboratory trials performed on samples taken off line after the elastomers have been manufactured, with the subsequent cost and delays. In view of these problems, the present study proposes a neural model capable of predicting the characteristics of rubber from the composition of the mixture and the mixing conditions, without having to wait for laboratory results, thus guaranteeing the traceability of the product in the process and the values according to their specific characteristics and also achieving a reduction in costs deriving from smaller amounts of discarded material during the performance of the tests, etc.

[1]  A. Limper,et al.  Produktionskneter mit variablem Rotorspalt : Praktische Erfahrungen , 2000 .

[2]  James J.C. Busfield,et al.  The effect of liquids on the dynamic properties of carbon black filled natural rubber as a function of pre-strain , 2000 .

[3]  C. Pillai,et al.  Processability characteristics and physico-mechanical properties of natural rubber modified with cashewnut shell liquid and cashewnut shell liquid–formaldehyde resin , 2002 .

[4]  Mamadou Kaba Traoré,et al.  Design of a monitoring environment for manufacturing systems management and optimization , 2003, Int. J. Comput. Integr. Manuf..

[5]  P. K. Freakley.  The single-rotor continuous mixing system , 2002 .

[6]  D. El-Nashar,et al.  Effect of Mixing Conditions and Chemical Cross-Linking Agents on the Physicomechanical and Electrical Properties of NR/NBR Blends , 2003 .

[7]  Manuel Castejón Limas,et al.  Outlier Detection and Data Cleaning in Multivariate Non-Normal Samples: The PAELLA Algorithm , 2004, Data Mining and Knowledge Discovery.

[8]  Zhang Anqiang,et al.  A study on rheological properties of carbon black extended powdered SBR using a torque rheometer , 2003 .

[9]  James L. White,et al.  Comparison of intermeshing rotor and traditional rotors of internal mixers in dispersing silica and other fillers , 2000 .

[10]  Joaquín B. Ordieres Meré,et al.  Estimation of mechanical properties of steel strip in hot dip galvanising lines , 2004 .

[11]  Kim Seng Lee,et al.  Feature-Based Parametric Design of a Gating System for a Die-Casting Die , 2002 .

[12]  John W. Sammon,et al.  A Nonlinear Mapping for Data Structure Analysis , 1969, IEEE Transactions on Computers.

[13]  Mir Hamid Reza Ghoreishy,et al.  Finite Element Analysis of Mixing in Partially Filled Twin Blade Internal Mixers , 1998 .

[14]  R. Herbiet.  Einfluss von Prozessparametern beim Compoundieren von halogenfrei flammgeschützten, hochgefüllten Polymersystemen im Innenmischer , 2000 .

[15]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[16]  Chun-Yin Wu,et al.  Optimal Shape Design of an Extrusion Die Using Polynomial Networks and Genetic Algorithms , 2002 .

[17]  Edmund Haberstroh,et al.  Analysis methods for the prediction of rubber compound quality for mixing in internal mixers , 1999 .

[18]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[19]  J. Ordieres,et al.  Intelligent methods helping the design of a manufacturing system for die extrusion rubbers , 2003, Int. J. Comput. Integr. Manuf..

[20]  Gustavo A. Schwartz,et al.  Prediction of Rheometric Properties of Compounds by Using Artificial Neural Networks , 2001 .

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Swapan K. Saha,et al.  Rheological and morphological characteristics of polyvinylchloride/polychloroprene blends––effect of temperature and mixing speed , 2001 .

[23]  Chakrit Sirisinha,et al.  Relationships among blending conditions, size of dispersed phase, and oil resistance in natural rubber and nitrile rubber blends , 2001 .

[24]  Ana González-Marcos,et al.  Steel annealing furnace robust neural network model , 2005 .

[25]  An adaptive neuro-fuzzy inference system as a soft sensor for viscosity in rubber mixing process , 2000 .

[26]  V. Nassehi,et al.  Evaluation of Stress-Effective Flow in Rubber Mixing , 2001 .

[27]  Aleksey D. Drozdov,et al.  The nonlinear viscoelastic response of carbon black-filled natural rubbers , 2002 .

[28]  M. Cassidy,et al.  Extrusion of rubber : Prediction of die swell , 1997 .

[29]  Eliseo P. Vergara.  Outlier Detection and Data Cleaning in Multivariate Non-Normal Samples: The PAELLA Algorithm ∗ , 2004 .

[30]  Jaafar Sahari,et al.  Mathematical modelling of thermoplastic natural rubber melt flow in a double feed extrusion system , 1998 .

[31]  Daniel Peña Sánchez de Rivera.  Análisis de datos multivariantes , 2002 .

[32]  Narongrit Sombatsompop,et al.  Effects of the actual diameters and diameter ratios of barrels and dies on the elastic swell and entrance pressure drop of natural rubber in capillary die flow , 2002 .

[33]  R. Regalia,et al.  CAD- und CFD-Simulation bei Innenmischern , 1999 .

[34]  H. Ismail,et al.  Cure characteristics and vulcanizate properties of a natural rubber compound extended with convoluted rubber powder , 2000 .