[127] Digital twins: neural networks for the implementation of digital twins of gearboxes
A Zippo1, L Bergamini1, G D’Elia2, F Pellicano1, G Dalpiaz2, G Iarriccio1 and M Molaie1
1Università degli Studi di Modena e Reggio Emilia, Italy
2Università degli Studi di Ferrara, Italy
Digital twins (DTs) are widely used for the design and prognostic analysis of mechanical devices. For the implementation of optimised, effective DTs of gearboxes, engineers often lean on the ISO standards and codes. However, the use of standards could be considered not trivial to set-up, slow and with license problems for its portability. Neural networks (NNs), also implemented on open-source software, have been proven to be able to create links between input and output quantities without the need for knowing the underlying laws if trained properly. Here, we trained a NN with a huge dataset created by using standards for a simple gearbox. By comparing with the standards, we found that the accuracy of a NN depends on the safety factor, the physical characteristics of the gearbox and correct set-up of the NN. This result is of paramount interest since it reveals that NNs can be used for the implementation of accurate digital twins when proper training on a wide dataset is carried out.
