Skoda uses AI to further enhance accuracy of car diagnostics

by Autocar Pro News Desk , 07 Oct 2020


Skoda Auto’s Aftesales department and Skoda Auto DigiLab are trialling a new smartphone app called ‘Sound Analyser’.

The app uses artificial intelligence (AI) and helps to quickly and accurately identify the need for any servicing. The program records noises made by the respective vehicle whilst it is running and compares them with stored sound patterns. In the event of any discrepancies, the app uses an algorithm to determine what they are and how they can be resolved. In this way, ‘Sound Analyser’ helps to make vehicle maintenance more efficient, reduce the time a car spends at the garage and achieve even higher levels of customer satisfaction.

Commenting on the app, Stanislav Pekar, Head of Aftersales at Skoda Auto, said, “Sound Analyser is a prime example of the new opportunities digitalisation at Skoda can create, even in terms of after sales. We will continue to consistently use artificial intelligence technologies to offer our customers an even more personalised service, thus enhancing the customer experience even further.”

Klaus Blum, Head of Skoda IT, added, “At Skoda, we are consistently looking to comprehensively digitalise processes, products and services for our customers along the entire value chain. In order to be able to recognise the potential of innovations early on, develop them quickly and use them intelligently, we are continuously coordinating with the specialist departments to jointly implement new digitalisation projects.”

The software can recognise 10 patterns – with an accuracy of over 90% including for components such as the steering system, the AC compressor, and the clutches in the direct-shift gearbox (DSG).

How the ‘Sound Analyser’ app works
The ‘Sound Analyser’ app uses artificial intelligence to reliably, clearly and quickly assess the current condition of wearing parts and notify technicians of any required servicing. For this purpose, the program considers various vehicle-specific parameters and analyses the usage profile of the respective car. To this end, Sound Analyser makes it even easier for technicians to perform accurate diagnostics on a vehicle as they will only need a standard smartphone or tablet to use the app.

Although the program is highly complex, its operation is intuitive: the sounds made whilst the vehicle is running can be recorded using a smartphone. An algorithm then compares the recording with stored sound patterns and, based on this, provides a concrete description of the result. The software is already able to recognise ten patterns – with an accuracy of over 90 per cent – including for components such as the steering system, the air conditioning compressor, and the clutches in the direct-shift gearbox (DSG). The app is also set up to recognise further sound patterns.

Neural network algorithms provide the technical basis for ‘Sound Analyser’. The app first converts the audio file into a spectrogram that visually depicts the acoustic signals. Using artificial intelligence, this representation is then compared with the stored recordings to identify deviations. To this end, the app categorises the potential need for upcoming maintenance or repairs based on predetermined patterns.

Trials underway at 245 dealers in 14 countries
The smartphone app has been trialled in 14 countries – including Germany, Russia, Austria and France – since June 2019. A total of 245 Skoda dealers have been taking part in the pilot project. They are instrumental in providing the audio recordings for the software’s ‘learning process’ and are thus directly contributing to the program’s development.

The gradual introduction of technologies for determining any acoustic deviations from the norm will open up a wealth of new possibilities in terms of sensor-based, predictive maintenance in future. In addition, the vehicle’s online connection can be used to arrange an appointment directly with the responsible garage if necessary.