Data Set Description: Identifying the Physics Behind an Electric Motor -- Data-Driven Learning of the Electrical Behavior (Part I)
This work addresses the need for precise control in electric vehicles to optimize performance, but it is incremental as it focuses on providing a dataset rather than a novel method.
The paper tackles the problem of accurately modeling the dynamic behavior of electric vehicle drive trains to improve efficiency and range, by publishing a dataset of about 40 million data points from test bench measurements for comparing machine learning modeling approaches.
Two of the most important aspects of electric vehicles are their efficiency or achievable range. In order to achieve high efficiency and thus a long range, it is essential to avoid over-dimensioning the drive train. Therefore, the drive train has to be kept as lightweight as possible while at the same time being utilized to the best possible extent. This can only be achieved if the dynamic behavior of the drive train is accurately known by the controller. The task of the controller is to achieve a desired torque at the wheels of the car by controlling the currents of the electric motor. With machine learning modeling techniques, accurate models describing the behavior can be extracted from measurement data and then used by the controller. For the comparison of the different modeling approaches, a data set consisting of about 40 million data points was recorded at a test bench for electric drive trains. The data set is published on Kaggle, an online community of data scientists.