Improvement of surface roughness models for face milling operations through dimensionality reduction

Surface roughness generation is influenced by many complex and interrelated factors. Moreover, in real industrial conditions many different milling tools have to be used to create a final product. Hence, the acquisition of experimental data used to set up artificial intelligence models of individual tools is a complicated task. The aim of this paper is to present a new strategy to improve the artificial intelligence models used to predict surface roughness with small datasets. The new strategy proposed in this paper relies on dimensionality reduction to minimise the number of experiments required to train the models. Unlike in most other approaches, the dimensionality reduction is not applied to set an a priori determined dimension. In the proposed approach, the scale of dimensionality reduction is controlled by the quality of roughness prediction models created with the transformed data. This strategy has been tested on high torque milling operations using multilayer perceptrons i.e. the most frequently used artificial intelligence models for this task. Experiments were conducted to obtain data to train the models. Finally, a comparison was made of the models' performance with and without dimensionality reduction based on Principal Component Analysis, which confirmed the merits of the proposed technique.

[1]  Cevdet Gologlu,et al.  The effects of cutter path strategies on surface roughness of pocket milling of 1.2738 steel based on Taguchi method , 2008 .

[2]  Balázs Kégl,et al.  Intrinsic Dimension Estimation Using Packing Numbers , 2002, NIPS.

[3]  Joaquim Ciurana,et al.  Surface roughness monitoring application based on artificial neural networks for ball-end milling operations , 2011, J. Intell. Manuf..

[4]  Hojjat Adeli,et al.  Enhanced probabilistic neural network with local decision circles: A robust classifier , 2010, Integr. Comput. Aided Eng..

[5]  Aminah Robinson Fayek,et al.  A multi-criteria optimization framework for industrial shop scheduling using fuzzy set theory , 2010, Integr. Comput. Aided Eng..

[6]  Miguel Arizmendi,et al.  Effect of tool setting error on the topography of surfaces machined by peripheral milling , 2009 .

[7]  M. Brezocnik,et al.  Integrated Genetic Programming and Genetic Algorithm Approach to Predict Surface Roughness , 2003 .

[8]  Mirko Ficko,et al.  Prediction of surface roughness with genetic programming , 2004 .

[9]  Eyüp Sabri Topal,et al.  The role of stepover ratio in prediction of surface roughness in flat end milling , 2009 .

[10]  Wlodzislaw Duch,et al.  Support Vector Machines for Visualization and Dimensionality Reduction , 2008, ICANN.

[11]  Bor-Tsuen Lin,et al.  Adaptive network-based fuzzy inference system for prediction of surface roughness in end milling process using hybrid Taguchi-genetic learning algorithm , 2009, Expert Syst. Appl..

[12]  Daniel T. Larose,et al.  Data mining methods and models , 2006 .

[13]  B. Samanta,et al.  Surface roughness prediction in machining using soft computing , 2009, Int. J. Comput. Integr. Manuf..

[14]  Pramod K. Varshney,et al.  Modern Approaches in Applied Intelligence - 24th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2011, Syracuse, NY, USA, June 28 - July 1, 2011, Proceedings, Part I , 2011, IEA/AIE.

[15]  Concha Bielza,et al.  A Bayesian network model for surface roughness prediction in the machining process , 2008, Int. J. Syst. Sci..

[16]  Thomas W. Rauber,et al.  Diagnosing multiple faults in oil rig motor pumps using support vector machine classifier ensembles , 2011, Integr. Comput. Aided Eng..

[17]  Shinn-Ying Ho,et al.  Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neuro-fuzzy inference system , 2002 .

[18]  Alexander M. Bronstein,et al.  Nonlinear Dimensionality Reduction by Topologically Constrained Isometric Embedding , 2010, International Journal of Computer Vision.

[19]  Nicole Vincent,et al.  A PCA-Based Technique to Detect Moving Objects , 2007, SCIA.

[20]  Antonio Vallejo Guevara,et al.  Surface Roughness and Cutting Tool-Wear Diagnosis Based on Bayesian Networks , 2007 .

[21]  Qingquan Wu,et al.  View invariant head recognition by Hybrid PCA based reconstruction , 2008 .

[22]  Concha Bielza,et al.  Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process , 2009, Expert Syst. Appl..

[23]  George-Christopher Vosniakos,et al.  Predicting surface roughness in machining: a review , 2003 .

[24]  Michel Verleysen,et al.  Nonlinear Dimensionality Reduction , 2021, Computer Vision.

[25]  Der-Chiang Li,et al.  A non-linear quality improvement model using SVR for manufacturing TFT-LCDs , 2012, J. Intell. Manuf..

[26]  George-Christopher Vosniakos,et al.  Prediction of surface roughness in CNC face milling using neural networks and Taguchi's design of experiments , 2002 .

[27]  Utpal Roy,et al.  A neural network model for selecting machining parameters in fixture design , 1996 .

[28]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[29]  Surjya K. Pal,et al.  Tool wear monitoring and selection of optimum cutting conditions with progressive tool wear effect and input uncertainties , 2011, J. Intell. Manuf..

[30]  J. Ciurana,et al.  Surface Roughness Generation and Material Removal Rate in Ball End Milling Operations , 2010 .

[31]  L. N. López de Lacalle,et al.  Mechanistic modelling of the micro end milling operation , 2008 .

[32]  Chandrasekhar Nataraj,et al.  Surface roughness prediction in machining using Computational Intelligence , 2008 .

[33]  Joseph C. Chen,et al.  An in-process surface recognition system based on neural networks in end milling cutting operations , 1999 .

[34]  Guillem Quintana,et al.  Avoiding neural network fine tuning by using ensemble learning: application to ball-end milling operations , 2011 .

[35]  Andrés Bustillo,et al.  A soft computing system using intelligent imputation strategies for roughness prediction in deep drilling , 2012, J. Intell. Manuf..

[36]  Maciej Grzenda.  Prediction-oriented dimensionality reduction of industrial data sets , 2011, IEA/AIE'11.