Predicting the error of a Robot’s positioning repeatability with artificial neural networks
Fragment książki (Rozdział monografii pokonferencyjnej)
MNiSW
20
Poziom I
| Status: | |
| Autorzy: | Kluz Rafał, Antosz Katarzyna, Trzepiecinski Tomasz, Gola Arkadiusz |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Strony: | 41 - 48 |
| Scopus® Cytowania: | 2 |
| Bazy: | Scopus |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | NIE |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| Industrial robots are an integral part of modern manufacturing systems. In order to fully use their potential, the information related to the robot’s accuracy should be known first of all. In most cases, the information considering robot’s errors, provided in a technical specification, is scarce. That’s why, this paper presents the issues of determining the error of industrial robots positioning repeatability. A neural mathematical model that allows for predicting its value with the error less than 5% was designed. The obtained results were compared to a classical mathematical model. It was revealed that a well-trained neural network enables the prediction of the error of positioning repeatability with the doubled accuracy. |
