Fuzzy-Genetic based approach in decision making for repair of turbochargers using additive manufacturing
Additive manufacturing (AM) is an effective technology for repairing and restoring automotive components. However, the effectiveness of additive manufacturing technology in repair and restoration is highly influenced by several factors related to components and process. The objective of this paper i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2023
|
| Online Access: | http://journalarticle.ukm.my/22839/1/16%20%282%29.pdf http://journalarticle.ukm.my/22839/ https://www.ukm.my/jkukm/volume-3505-2023/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Additive manufacturing (AM) is an effective technology for repairing and restoring automotive components. However, the effectiveness of additive manufacturing technology in repair and restoration is highly influenced by several factors related to components and process. The objective of this paper is to improve the decision-making in repair and restoration of a turbocharger with AM. In this article, a Fuzzy-Genetic approach was presented as a decision-making tool for repairing a remanufacturable component. Fuzzy logic (FL) is deployed as the method to model the design parameters of a turbocharger, such as design complexity, failure mode, damage size, disassembleability, preprocessing, temperature, durability, pressure ratio and mass flow rate to model the relationship between the inputs and outputs using Mamdani model with their membership functions. Genetic algorithm optimization method was used to optimize the cost of the repairing process once the decision on whether the turbocharger was repairable was determined by the Fuzzy system. The FL approach applied rules affecting the process, the robustness and accuracy of the model increases with a higher number of rules. The work focuses on the dataset related to design information, which represents as a knowledge base for decision parameters on design optimization to automate repair process during remanufacturing. The results showed the effects of the design parameters on repairing and replacement decisions, and how the fuzzy model related the inputs to the outputs based on the generated rules. In conclusion, FGA method can be used to improve the repair and restoration process of a turbocharger through AM technology. |
|---|