Abstract
In this article we present an educational achievement of an alternative control of the IRB1600 ABB robot, using an explicit path specification, using a laser pointer and a CCD camera. With this system we measured the execution times of instructions data transfer between computers and robot equipment system to evaluate and improve the quality of similar systems in which there are mechatronics and computer processes that require synchronization of several adjacent processes. The experimental recorded data will be analyzed using Self-Organizing Feature Maps (SOFM) and as result it is shown that in the transmission of data sets significant run time dependencies can not be found. Also a run time prediction method will be developed and tested using Nonliniar AutoRegressive (NAR) type neural networks. The method has satisfactory result.
M., Fernandez-Delgado, M., Reboreda, E., Cernadas, S., Barro, A comparison of several neural networks to predict the execution times in injection molding production for automotive industry, Neural Comput & Applic (2010) 19:741-754, DOI 10.1007/s00521-009-0332-5, Springer-Verlag London Limited 2010.
G., P., Zhang, V., Berardi, Time series forecasting with neural network ensembles: an application for exchange, rate prediction. Journal of the Operational Research Society, 52, 652-664., 2001.
C. A. Mitrea, C. K. M. Lee and Z. Wu, A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study, International Journal of Engineering Business Management, Vol. 1, No. 2 (2009) pp. 19-24
S., Hajar Arbain, A., Wibowo, Neural Networks Based Nonlinear Time Series
Regression for Water Level Forecasting of Dungun River, Journal of Computer Science 8 (9): 1506-1513, 2012, ISSN 1549-3636, 2012 Science Publications
S., Dietz, Autoregressive Neural Network Processes, Univariate, Multivariate and Cointegrated Models with Application to the German Automobile Industry Inaugural-Dissertation zur Erlangung des akademischen Grades eines Doktors der Wirtschaftswissenschaften der Universit?t Passau, Oktober 2010. |
