Skoda Auto says its AI-based app can already recognise ten vehicle patterns with 90% accuracy - including for components such as the steering system and air conditioning compressor.
Skoda Auto is trialling a new smartphone app called 'Sound Analyser' that uses artificial intelligence (AI) to quickly and accurately identify the need for any servicing of cars.
The app's program records noises made by the respective Skoda vehicles when they are running and compares them with stored sound patterns. If there happens to be any discrepancy, the app uses an algorithm to determine what the issues are and how they can be resolved.
Skoda says this is how AI used in the 'Sound Analyser' app helps make vehicle maintenance more efficient and reduce the time a car spends at the garage. The app has been trialled in 14 countries including Germany, Russia, Austria and France, since June 2019 with a total of 245 Skoda dealers taking part in the pilot project.
The carmakers says the app is already able to recognise ten patterns with an accuracy of over 90% – including for components such as the steering system, air conditioning compressor and the clutches in the direct-shift gearbox. It has been set up to recognise further sound patterns.
Technical basis for Sound Analyser is provided by the neural network algorithms. The app first converts the audio file of the running vehicle sound into a spectrogram that visually depicts the acoustic signals. Then, using AI, this representation is compared with the stored recordings to identify deviations. The app then categorises the potential need for upcoming maintenance or repairs based on predetermined patterns. “Sound Analyser is a prime example of the new opportunities digitalisation at Skoda can create, even in terms of after sales," says Stanislav Pekar, Head of After Sales at Skoda Auto.