A neural network approach for machine breakdown repair time
Research on neural network applications have been carried out very extensively in recent days. The current trends in manufacturing sectors for solving their business operational problems have been very difficult and subjective. Many organizations have used various methods to solve machine breakdo...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/48144/1/ChanthuruThevendramMFKM2013.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Research on neural network applications have been carried out very extensively in
recent days. The current trends in manufacturing sectors for solving their business
operational problems have been very difficult and subjective. Many organizations
have used various methods to solve machine breakdown's repair time, either reducing
the time taken to repair or eliminate the particular occurrence. The traditional way
for solving these machine breakdown issues was to predict the machine breakdown
occurrence through preventive maintenance. Hence, in the present study, a neural
network method was proposed to optimize the mean repair time for machine
breakdown with regression models were evaluated from the trained neurons. The
neurons were represented by the samples of repair time of previous years' record of a
single machine. The results shows that the set of samples of repair time have
critically influenced the optimized mean repair time for the machine. Various
methodologies were used by comparing several grouped machine breakdown
phenomena which showed more accurate regressions. The use of neural network, in
the end of the study, gives significant changes in predicting machine breakdown
repair time for the future years. |
|---|