Health status estimation of transceiver testing machine using adaptive neuro fuzzy inference system
The purpose of this study is to improve existing maintenance triggering process for Transceiver Testing Machine (TTM) in Finisar by identifying the influence factors and design a new Adaptive Neuro Fuzzy Inference System (ANFIS) model as a machine learning model approach. The ANFIS model have a capa...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/98388/1/MuhammadAmzariNajmiMSC2018.pdf.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The purpose of this study is to improve existing maintenance triggering process for Transceiver Testing Machine (TTM) in Finisar by identifying the influence factors and design a new Adaptive Neuro Fuzzy Inference System (ANFIS) model as a machine learning model approach. The ANFIS model have a capability to learn the behavior of its production historical data and estimate the health status. This health status will be used as a trigger alarm for maintenance team to perform maintenance task instead of just using default expiry time setting as a reference. The ANFIS model were validated using production historical data from several scenarios as case studies. The accuracy of training and testing data were analyzed in this study. It is shown that the ANFIS model developed give good performance and results of this study can be used as adequate reference to improve the maintenance triggering process in industry such as Finisar. |
|---|