Development of an electronic differential system for electric vehicles based on deep neural network

Background. Modern cars typically use a transmission system where an internal combustion engine transmits force through a gearbox to a differential shaft, which then transmits torque to the wheels. In electric vehicles, however, electric motors can be attached directly to the wheels through a reduction gearbox. With a right control system, these vehicles can apply different torque to the wheels on each side of the vehicle, significantly enhancing handling. This set-up is known as an electronic differential. Its implementation can vary from simple, using the Ackerman–Jeantand model, which cannot fully replace a simple mechanical differential, to complex systems employing robust control mechanisms with yaw torque. The latter method requires a rather complex control system and expensive sensors. A third –innovative approach involves using neural networks to control electric vehicle speeds.

Aim. The aim is to provide materials and software for implementing an electronic differential using artificial neural networks to expand the solutions available for controlling multiple electric derives in various electric vehicles.

Materials and Methods. The neural network considers multiple factors affecting the operation of electronic differential by selecting special coefficients, weights, to neurons within the network. As a basis for obtaining data, special route maps based on the transition curve will be used.

Results. Testing yielded a prediction accuracy of 0.7273, with a standard deviation of 0.064 for the training set and 0.065 for the testing set.

Conclusion. Employing neural networks for controlling electric drives is a promising alternative to traditional algorithms. Owing to their flexibility, these neural networks can also implement additional driver assistance functions, such as ESP, ABS, cruise control, etc.