Abstract
dc:description.abstractManufacturing sector have been plagued by bottlenecks from time immemorial, leading to loss of productivity and profitability, various research effort has been expended towards identifying and mitigating the effects of bottlenecks on production lines. However, traditional approaches often fail in identifying moving bottlenecks. The current data boom and giant strides made in the machine learning field proffers an alternative means of using the large volume of data generated by machines in identifying bottlenecks. In this study, a hierarchical agglomerative clustering algorithm is used in identifying potential groups of bottlenecks within a serial production line. A serial production line with five workstations and zero buffer was simulated in ARENA® with data regarding blocked, producing and starvation time extracted. The extracted data was preprocessed using Python 3.7 to obtain a matrix of ones and zeros. The resultant matrix was fed into a complete linkage hierarchical agglomerative clustering algorithm to obtain clusters containing potential bottleneck workstations. Results obtained was validated using results obtained from simulation and an Elbow plot.
Degree
thesis:*- Name thesis:degree_name
- MS
- Level thesis:degree_level
- Problem/Project Report
- Discipline thesis:degree_discipline
- Industrial and Managements Systems Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Adeyinka, Funmilayo Mofoluwasola
- Contributors dc:contributor
-
- Bhaskaran Gopalakrishnan
- Donald Adjeroh
- Thorston Wuest
- Imtiaz Ahmed
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Identifier
- https://researchrepository.wvu.edu/etd/10288