Heuristic techniques to optimize neural network architecture in manufacturing applications

被引:20
作者
Ciancio, Claudio [1 ]
Ambrogio, Giuseppina [1 ]
Gagliardi, Francesco [1 ]
Musmanno, Roberto [1 ]
机构
[1] Univ Calabria, Dept Mech Energy & Management Engn, I-87036 Arcavacata Di Rende, Italy
关键词
Neural network architecture design; Genetic algorithm; Tabu search; Taguchi; Decision trees; 2D numerical simulations;
D O I
10.1007/s00521-015-1994-9
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Nowadays application of neural networks in the manufacturing field is widely assessed even if this type of problem is typically characterized by an insufficient availability of data for a robust network training. Satisfactory results can be found in the literature, in both forming and machining operations, regarding the use of a neural network as a predictive tool. Nevertheless, the research of the optimal network configuration is still based on trial-and-error approaches, rather than on the application of specific techniques . As a consequence, the best method to determine the optimal neural network configuration is still a lack of knowledge in the literature overview. According to that, a comparative analysis is proposed in this work. More in detail four different approaches have been used to increase the generalization abilities of a neural network. These methods are based, respectively, on the use of genetic algorithms, Taguchi, tabu search and decision trees. The parameters taken into account in this work are the training algorithm, the number of hidden layers, the number of neurons and the activation function of each hidden layer. These techniques have been firstly tested on three different datasets, generated through numerical simulations in the Deform2D environment, in an attempt to map the input-output relationship for an extrusion, a rolling and a shearing process. Subsequently, the same approach has been validated on a fourth dataset derived from the literature review for a complex industrial process to widely generalize and asses the proposed methodology in the whole manufacturing field. Four tests were carried out for each dataset modifying the original data with a random noise with zero mean and standard deviation of one, two and five per cent. The results show that the use of a suitable technique for determining the architecture of a neural network can generate a significant performance improvement compared to a trial-and-error approach.
引用
收藏
页码:2001 / 2015
页数:15
相关论文
共 53 条
[41]   Comparison of a genetic algorithm and simulated annealing for automatic neural network ensemble development [J].
Soares, Symone ;
Antunes, Carlos Henggeler ;
Araujo, Rui .
NEUROCOMPUTING, 2013, 121 :498-511
[42]   The optimisation of neural network parameters using Taguchi's design of experiments approach: an application in manufacturing process modelling [J].
Sukthomya, W ;
Tannock, J .
NEURAL COMPUTING & APPLICATIONS, 2005, 14 (04) :337-344
[43]   Introduction to multi-layer feed-forward neural networks [J].
Svozil, D ;
Kvasnicka, V ;
Pospichal, J .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1997, 39 (01) :43-62
[44]   Effect of cutting-edge geometry and workpiece hardness on surface residual stresses in finish hard turning of AISI 52100 steel [J].
Thiele, JD ;
Melkote, SN ;
Peascoe, RA ;
Watkins, TR .
JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME, 2000, 122 (04) :642-649
[45]   An ANN approach for predicting subsurface residual stresses and the desired cutting conditions during hard turning [J].
Umbrello, D. ;
Ambrogio, G. ;
Filice, L. ;
Shivpuri, R. .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2007, 189 (1-3) :143-152
[46]  
Umbrello D, 2004, P 7 ESAFORM C, P757
[47]   Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network [J].
Unal, Muhammet ;
Onat, Mustafa ;
Demetgul, Mustafa ;
Kucuk, Haluk .
MEASUREMENT, 2014, 58 :187-196
[48]   A genetic algorithm-based artificial neural network model for the optimization of machining processes [J].
Venkatesan, D. ;
Kannan, K. ;
Saravanan, R. .
NEURAL COMPUTING & APPLICATIONS, 2009, 18 (02) :135-140
[49]  
Wang XZ, 2013, NEUROCOMPUTING, V102, P3, DOI [10.1016/j.neucom.2011.12.053, 10.1016/j.neucom.2011.11053]
[50]   GENETIC ALGORITHMS AND NEURAL NETWORKS - OPTIMIZING CONNECTIONS AND CONNECTIVITY [J].
WHITLEY, D ;
STARKWEATHER, T ;
BOGART, C .
PARALLEL COMPUTING, 1990, 14 (03) :347-361