ORIGINAL ARTICLE Artificial neural networks for machining processes surface roughness modeling Fabricio J. Pontes & João R. Ferreira & Messias B. Silva & Anderson P. Paiva & Pedro Paulo Balestrassi Received: 7 July 2009 / Accepted: 19 November 2009 / Published online: 15 December 2009 # Springer-Verlag London Limited 2009 Abstract In recent years, several papers on machining processes have focused on the use of artificial neural networks for modeling surface roughness. Even in such a specific niche of engineering literature, the papers differ considerably in terms of how they define network archi- tectures and validate results, as well as in their training algorithms, error measures, and the like. Furthermore, a perusal of the individual papers leaves a researcher without a clear, sweeping view of what the field’ s cutting edge is. Hence, this work reviews a number of these papers, providing a summary and analysis of the findings. Based on recommendations made by scholars of neurocomputing and statistics, the review includes a set of comparison criteria as well as assesses how the research findings were validated. This work also identifies trends in the literature and highlights their main differences. Ultimately, this work points to underexplored issues for future research and shows ways to improve how the results are validated. Keywords Artificial neural networks . Machining . Surface roughness . Modeling Nomenclature AFM Abrasive flow machining AISI American Iron and Steel Institute ANN Artificial neural networks ART Adaptive resonance theory (a class of artificial network) BP Backpropagation algorithm CNC Computer numerical controlled d Depth of cut (mm) DOE Design of experiments ECM Electrochemical machining EDM Electrical discharge machining f Feed (mm/v) F Activation function in a multilayer perceptron H Total number of neurons in a layer of a multilayer perceptron K Number of radial units in a radial basis function network LM Levenberg–Marquadt algorithm MAE Mean average error MLP Multilayer perceptron MSE Mean square error QN Quasi-Newton algorithm R a Average surface roughness (μm) R t Peak-to-valley roughness (μm) R m Maximum roughness (μm) r Tool nose radius (mm) RBF Radial basis function RMSE Root mean square error RSM Response surface methodology R 2 Pearson coefficient SOM Self-organizing maps F. J. Pontes : J. R. Ferreira : A. P. Paiva : P. P. Balestrassi (*) Industrial Engineering Institute, Federal University of Itajuba, Itajuba, Minas Gerais, Brazil e-mail: pedro@unifei.edu.br F. J. Pontes e-mail: fabriciojosepontes@uol.com.br J. R. Ferreira e-mail: jorofe@unifei.edu.br A. P. Paiva e-mail: andersonppaiva@unifei.edu.br M. B. Silva Sao Paulo State University, Guaratingueta, Sao Paulo, Brazil e-mail: messias@dequi.eel.usp.br Int J Adv Manuf Technol (2010) 49:879–902 DOI 10.1007/s00170-009-2456-2