Artificial neural network prediction of material removal rate in electro discharge machining

被引:73
作者
Panda, DK [1 ]
Bhoi, RK
机构
[1] Govt Def, Minist Def, Def R&D Org, Inst Technol Management, Landour Cantt 248179, Mussoorie UA, India
[2] Univ Coll Engn, Dept Mech Engn, Burla, India
关键词
back propagation; crater; current; epoch; feed forward; hidden layer; interelectrode distance; material removal rate (MRR); neurons; neural network; power; pulse duration; pulse interval; r-squared efficiency; sum square error;
D O I
10.1081/AMP-200055033
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Thermal erosion theory is widely accepted as an explanation of the erosion process in electro-discharge machining (EDM). Theoretical models are based on the solution of the transient heat conduction equation, which is modeled considering suitable assumptions with appropriate initial and boundary conditions. The closed form solutions result only after considering too many assumptions, which are far from actual machining conditions. The growth of the plasma channel, energy sharing between electrodes, process of vaporization, formation of recast layer, plasma-flushing efficiency, and temperature sensitivity of thermal properties of the work material are a few physical phenomena that render the machining process highly complex and stochastic. The mathematical consideration of all these complex phenomena is very difficult. Therefore, mathematical prediction of material removal rate when compared with the experimental results shows wide variation. In such circumstances, an attempt has been made to develop an artificial feed forward neural network based on the Levenberg-Marquardt back propagation technique of appropriate architecture of the logistic sigmoid activation function to predict the material removal rate. Such a neural network model is expected to perform well under the stochastic environment of actual machining conditions without understanding the complex physical phenomena exhibited in electro-discharge machining. The validity of the neural network model is checked with the experimental data, and we conclude that the artificial neural network model for EDM provides faster and more accurate results.
引用
收藏
页码:645 / 672
页数:28
相关论文
共 34 条
[1]  
ANDERSON K, 1991, INTELLIGENT ENG SYST, P717
[2]  
[Anonymous], 1994, Fundamentals of Neural Networks
[3]  
BALLEYS F, 1997, STORM SPARKS SHAPES, P17
[4]   COMMON MISCONCEPTIONS ABOUT NEURAL NETWORKS AS APPROXIMATORS [J].
CARPENTER, WC ;
BARTHELEMY, JF .
JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 1994, 8 (03) :345-358
[5]  
CHRYSSOLOURIS G, 1989, ASME SENSORS CONTROL
[6]  
CROOKALL JR, 1977, ANN CIRP, P113
[7]   THEORETICAL-MODELS OF THE ELECTRICAL-DISCHARGE MACHINING PROCESS .1. A SIMPLE CATHODE EROSION MODEL [J].
DIBITONTO, DD ;
EUBANK, PT ;
PATEL, MR ;
BARRUFET, MA .
JOURNAL OF APPLIED PHYSICS, 1989, 66 (09) :4095-4103
[8]  
Haykin S., 1998, NEURAL NETWORKS COMP
[9]  
HORSTEN HJ, 1973, ANN CIRP, V22, P49
[10]  
HORSTEN HJA, 1971, ANN CIRP, V20, P43