Online adaptive learning system for reconfigurable machine tool

Authors:
V. Marinescu;I. C. Constantin;A. Epureanu;M. Banu;F. B. Marin
Affiliations:
Manufacturing Science and Engineering Department, Dunarea de Jos University, Galati, Romania;Manufacturing Science and Engineering Department, Dunarea de Jos University, Galati, Romania;Manufacturing Science and Engineering Department, Dunarea de Jos University, Galati, Romania;Manufacturing Science and Engineering Department, Dunarea de Jos University, Galati, Romania;Manufacturing Science and Engineering Department, Dunarea de Jos University, Galati, Romania
Venue:
WSEAS Transactions on Systems and Control
Year:
2008

Citing 5
Cited 2

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Support-Vector Networks

Machine Learning
SVM-based clause-dependency determination in syntactic analysis

ACS'06 Proceedings of the 6th WSEAS international conference on Applied computer science
Versatile communication solution for PLC based control systems

CONTROL'06 Proceedings of the 2nd WSEAS international conference on Dynamical systems and control
Stochastic finite element based on stochastic linearization for stochastic nonlinear ordinary differential equations with random coefficients

NOLASC'06 Proceedings of the 5th WSEAS international conference on Non-linear analysis, non-linear systems and chaos

On-line econometric modeling of the manufacturing system and process

MAMECTIS'09 Proceedings of the 11th WSEAS international conference on Mathematical methods, computational techniques and intelligent systems
Assessment of the competitive management efficiency in the manufacturing processes

ICOSSSE '09 Proceedings of the 8th WSEAS international conference on System science and simulation in engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Batch manufacturing is a widely used technique in today economy. The conceptual change of the way in which the manufacturing machines are controlled is the most important aspect in which is possible to conform with the market demands so their reconfigurability would not affect competitiveness. The problem to be solved in this paper consists in a control method development for predictive control based on prediction of the controlled variables deviation values in respect with their programmed values and also to predict the process parameters for which chatter will appear. The basic idea is to use the data set obtained by monitoring the process during the manufacturing of the previous workpieces and during the current workpiece in order to predict the controlled variable value and to train a clasiffier algorithm. The method proposed consists in determining of the causal relation between one controlled variable and the monitored variables and then predicting its value in order to compensate the deviation from the program.