Processing time estimation in precision machining industry using AI / Lim Say Li
Processing time estimation of a machining process is a crucial task in order to gain higher profits, stand out amongst the competition and also grow the customer portfolio in precision machining industry. By having an accurate processing time estimation, a wellplanned production schedule can be e...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2017
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/8488/ http://studentsrepo.um.edu.my/8488/7/PROCESSING_TIME_ESTIMATION_IN_PRECISION_MACHINING_INDUSTRY_USING_AI.pdf |
| _version_ | 1848773671514013696 |
|---|---|
| author | Lim, Say Li |
| author_facet | Lim, Say Li |
| author_sort | Lim, Say Li |
| building | UM Research Repository |
| collection | Online Access |
| description | Processing time estimation of a machining process is a crucial task in order to gain higher
profits, stand out amongst the competition and also grow the customer portfolio in
precision machining industry. By having an accurate processing time estimation, a wellplanned
production schedule can be established and machine capacity availability can be
checked to meet customer�s estimated time of delivery (ETD). These time estimations are
usually done and revised by a tooling process expert. However, the estimation of each
and every individual is different based on their knowledge and experiences. In this
research, a system is designed to estimate processing time by using artificial intelligence
knowledge. Wire electrical discharge machining (WEDM) process is focused and the
time taken for the processing is analysed. Input variables such as material type of job,
size of copper wire used to run the process, operation mode set for the WEDM machine,
number of cuts and the thickness of workpiece are considered as important in estimating
the processing time. The objectives of this project are to design a system for processing
time estimation, to estimate the processing time required for specific machining process
and to verify the accuracy of processing time estimation. Neural Network (NN) model is
chosen as the artificial intelligence approach used in this research. Levenberg-Marquardt
algorithm is used as the training algorithm. The results show that the data best validation
performance is 7.1085 at epoch 27. An AI approach for processing time estimation by
implementing desired input parameters and machining data is tested and completed.
Keywords: artificial intelligence, artificial neural network, precision machining, time
estimation |
| first_indexed | 2025-11-14T13:46:07Z |
| format | Thesis |
| id | um-8488 |
| institution | University Malaya |
| institution_category | Local University |
| last_indexed | 2025-11-14T13:46:07Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | um-84882020-06-15T19:40:06Z Processing time estimation in precision machining industry using AI / Lim Say Li Lim, Say Li T Technology (General) TJ Mechanical engineering and machinery Processing time estimation of a machining process is a crucial task in order to gain higher profits, stand out amongst the competition and also grow the customer portfolio in precision machining industry. By having an accurate processing time estimation, a wellplanned production schedule can be established and machine capacity availability can be checked to meet customer�s estimated time of delivery (ETD). These time estimations are usually done and revised by a tooling process expert. However, the estimation of each and every individual is different based on their knowledge and experiences. In this research, a system is designed to estimate processing time by using artificial intelligence knowledge. Wire electrical discharge machining (WEDM) process is focused and the time taken for the processing is analysed. Input variables such as material type of job, size of copper wire used to run the process, operation mode set for the WEDM machine, number of cuts and the thickness of workpiece are considered as important in estimating the processing time. The objectives of this project are to design a system for processing time estimation, to estimate the processing time required for specific machining process and to verify the accuracy of processing time estimation. Neural Network (NN) model is chosen as the artificial intelligence approach used in this research. Levenberg-Marquardt algorithm is used as the training algorithm. The results show that the data best validation performance is 7.1085 at epoch 27. An AI approach for processing time estimation by implementing desired input parameters and machining data is tested and completed. Keywords: artificial intelligence, artificial neural network, precision machining, time estimation 2017 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/8488/7/PROCESSING_TIME_ESTIMATION_IN_PRECISION_MACHINING_INDUSTRY_USING_AI.pdf Lim, Say Li (2017) Processing time estimation in precision machining industry using AI / Lim Say Li. Masters thesis, University of Malaya. http://studentsrepo.um.edu.my/8488/ |
| spellingShingle | T Technology (General) TJ Mechanical engineering and machinery Lim, Say Li Processing time estimation in precision machining industry using AI / Lim Say Li |
| title | Processing time estimation in precision machining industry using AI / Lim Say Li |
| title_full | Processing time estimation in precision machining industry using AI / Lim Say Li |
| title_fullStr | Processing time estimation in precision machining industry using AI / Lim Say Li |
| title_full_unstemmed | Processing time estimation in precision machining industry using AI / Lim Say Li |
| title_short | Processing time estimation in precision machining industry using AI / Lim Say Li |
| title_sort | processing time estimation in precision machining industry using ai / lim say li |
| topic | T Technology (General) TJ Mechanical engineering and machinery |
| url | http://studentsrepo.um.edu.my/8488/ http://studentsrepo.um.edu.my/8488/7/PROCESSING_TIME_ESTIMATION_IN_PRECISION_MACHINING_INDUSTRY_USING_AI.pdf |