Industrial robots have increased their presence on the market in recent years increasing the importance of smart maintenance. Unexpected downtime due to robot cable damage is the main cause for production downtime in manufacturing plants. There is also a strong trend towards consolidating tools for computer aided design and engineering of manufacturing processes and plants. This thesis provides a machine learning implementation in a simulated environment using a Gaussian process for determining dynamic cable parameters such as Young’s modulus and damping in order to increase cable simulation value. Better simulations will result in more confident programming measures of avoiding dangerous motions and thereby increasing cable lifetime. Results obtained from simulations show that it is possible to obtain dynamic cable parameters in certain error margin using just a few markers.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:umu-167766 |
| Date | January 2019 |
| Creators | Lukowiaks, Jakub |
| Publisher | Umeå universitet, Institutionen för datavetenskap |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | UMNAD ; 1224 |
Page generated in 0.0019 seconds