KI-gestützte Diagnose

Challenge

Vehicle diagnostics currently requires extensive prior knowledge and a lot of time.

Solution

Development of a method for the automated detection of potentially defective components in the vehicle with the help of AI.

Added value

The complexity due to different vehicle types can be better managed and the vehicle diagnosis is therefore more efficient..

The Hella Gutmann company develops intelligent solutions for the repair and maintenance of cars and motorcycles of all brands and models, especially in cooperation with independent workshops.

In the AI marketplace, the company is primarily dedicated to AI-supported vehicle diagnostics. Conventionally, potentially defective components in the vehicle are identified using error codes and sensor values. Currently, a mechanic in the workshop needs a lot of time and extensive vehicle knowledge to create a well-founded diagnosis based on read error codes or measured sensor values (e.g. injection quantity). In addition, a large number of different vehicle brands are repaired in independent workshops, which increases the complexity.

Automatically detect defective components with AI

The aim of this project is to develop and test methods for the automated detection of potentially defective components in the vehicle with the help of AI. In particular, suitable methods for data pre-processing and the training of machine learning models with the help of vehicle data (error codes, sensor readings and mileage readings) are to be developed and validated.

A demonstrator for the AI marketplace

With this project, Hella Gutmann is developing a demonstrator in the form of a service that uses machine learning models to provide a list of potentially defective components for a specific vehicle diagnostic case. The integration of this service into a product is planned for the future. With the help of this AI solution, mechanics will in future be able to better manage the complexity that arises from different vehicle types and thus carry out vehicle diagnostics much faster,