Artificial Intelligence Enters Automotive Development

In the new test environment at DFKI in Kaiserslautern (Germany), special analysis methods of artificial intelligence for use in test procedures in automotive development are being researched and developed, with focus on machine learning technologies such as deep learning and time series analysis. IAV plans to apply the potential of the AI technology to development procedures and methodologies in powertrain development. This includes the use of AI in engine control systems such as ECUs as well as sounding out the potential of AI to increase the efficiency and robustness of the development process.

The application potential of intelligent data analysis methods for monitoring and optimizing test data, ECUs and test benches in the automotive industry is regarded as extraordinary high. For example, a modern engine control unit has more than 50,000 setting parameters that are decisive for fuel consumption, wear and tear and the overall performance of the engine. Deep learning technologies, or more precisely the use of neural networks in the control unit, enable the latter to “learn” independently how to optimally adjust the input variables. The use of such networks in the time series analysis of engine test data also opens up new approaches to predictive engine health monitoring, thus improving the prediction of wear and maintenance cases. Such methods are to be researched and developed in the new research laboratory.

At the same time, FLaP, as the new lab is called, will also work on new visualization options for the diverse measurement data from the neural networks. The aim is to create a toolbox of AI tools that can be used intuitively and appropriately by automotive engineers.

“In addition to the promising possibilities for use on existing hardware in production vehicles, FLaP also investigates novel applications for self-learning neural networks,” says Prof. Dr. Andreas Dengel, Head of the Smart Data & Knowledge Services Research Unit at DFKI. “The aim is both to gain fundamental knowledge in the long term and to develop concrete solutions to current problems in the short term.”