الفهرس 
Tntroduction
Network ArchitectureOnly 14 pages are availabe for public view
 |  | from | 126 |  |  |
| | | from | 126 | | |
Abstract
Traditional spare parts demand forecasting techniques concentrate on
traditional forecasting techniques. These single mathematical function-based
forecasting techniques, although they have achieved a certain degree of success in
spare parts forecasting, are unable to represent the relationship of demand for spare
parts as accurate as a multiprocessing node-based feed-forward network. Artificial
Neural Network technology has been adopted because of its ability to learn complex
and non-linear relationships that are difficult to model with conventional
techniques. Neural Networks can be trained to solve problems that are difficult for
conventional computers or human beings.
This research investigates the applicability of neural networks in spare parts
demand forecasting by incorporating the back-propagation learning process into
historical data of parts demand.
Empirical results indicate that utilizing a back-propagation neural network
outperforms conventional forecasting techniques in terms of forecasting accuracy.
Key words: Conventional forecasting techniques, feed-forward network,
back-propagation, Artifictial Neural Networks, spare parts.