Porsche uses AI in engine development

When developing vehicles to make propulsion systems more efficient and at the same time optimize their development process, the German automaker Porsche uses artificial intelligence (AI).

When we talk about artificial intelligence when developing powertrains, we are not only talking about internal combustion engines, Porsche also uses this technology for the development of electric powertrains.

Artificial intelligence applied in engine development - Porsche
Porsche Image

Internal combustion engines

In one of the AI ​​use cases, Porsche It is used by AI to solve to predict the content of gases in engine oil. When there is a high gas content in an engine of this type, the oil that lubricates the engine begins to foam, thus reducing its lubricating capacity.

To solve this problem, the circuit must be designed so that less gas is generated. The problem is that to measure this, it is almost impossible to do it with the engine running and it is here, in this problem, that Porsche uses artificial intelligence to solve it.

A new process created by the German automaker now makes it possible to predict with a high degree of accuracy the gas content in the oil at any given time and the first engine in which they applied this advanced technology was in the boxer of the Porsche Cayman GTA, an engine 6-cylinder.

Battery Status in Electric Vehicles

The German automaker’s subsidiary company, called Porsche Engineering, with the application of an AI algorithm, can already determine how lithium-ion batteries age, which implies a much more reliable range prediction.

In this process, the algorithm uses the internal resistance of the battery and, among other variants, uses data such as temperature and state of charge. In addition, it also includes long-term test data.

In this case, the AI ​​adapts to the driver’s profile, that is, his way of using the vehicle, in order to obtain a reduction of the autonomy much closer to reality.

PERL methodology

Porsche Engineering uses a methodology it calls PERL (Reinforcement Learning by Porsche Engineering) which according to Matthias Bach, Senior Director of Engine Application and Mechanics at Porsche Engineering, “goes beyond the specific solution of individual tasks, because it understands systemic relationships and learns to make strategic decisions«.

Bach also comments that “with reinforcement learning, we can reduce development time while achieving better results than would be possible with conventional methods”,

At present this method is undergoing practical tests in the motor area, but in the future they plan to use it also in other tests in electricity / electronics and also in the chassis.

Follow us on Twitter through @Geeksroom and do not miss all the news, free courses and other articles. You can also follow us through our Youtube channel to see our videos and through Instagram to see our images!


Source: Geeks Room by feedproxy.google.com.

*The article has been translated based on the content of Geeks Room by feedproxy.google.com. If there is any problem regarding the content, copyright, please leave a report below the article. We will try to process as quickly as possible to protect the rights of the author. Thank you very much!

*We just want readers to access information more quickly and easily with other multilingual content, instead of information only available in a certain language.

*We always respect the copyright of the content of the author and always include the original link of the source article.If the author disagrees, just leave the report below the article, the article will be edited or deleted at the request of the author. Thanks very much! Best regards!