Using Neural Networks by Modelling Semi-Active Shock Absorber
This work addresses data scarcity issues for automotive engineers developing digital twins, though it is incremental as it builds on existing augmentation methods.
The paper tackled the challenge of insufficient data for training neural network-based digital twins in automotive control systems by adapting time series augmentation techniques to stationary data, resulting in improved handling of regression tasks for modeling semi-active shock absorbers.
A permanently increasing number of on-board automotive control systems requires new approaches to their digital mapping that improves functionality in terms of adaptability and robustness as well as enables their easier on-line software update. As it can be concluded from many recent studies, various methods applying neural networks (NN) can be good candidates for relevant digital twin (DT) tools in automotive control system design, for example, for controller parameterization and condition monitoring. However, the NN-based DT has strong requirements to an adequate amount of data to be used in training and design. In this regard, the paper presents an approach, which demonstrates how the regression tasks can be efficiently handled by the modeling of a semi-active shock absorber within the DT framework. The approach is based on the adaptation of time series augmentation techniques to the stationary data that increases the variance of the latter. Such a solution gives a background to elaborate further data engineering methods for the data preparation of sophisticated databases.