AI-assisted Diagnosis
The challenge: Vehicle diagnostics currently require extensive prior knowledge and a significant amount of time.
The solution: The development of a procedure for automated detection of potentially defective components in vehicles using AI is underway.
The added value: The complexity arising from different vehicle types is better manageable, resulting in improved efficiency in conducting vehicle diagnostics.
Using AI, it is possible to detect faulty components in vehicles
Hella Gutmann develops intelligent solutions for the repair and maintenance of cars and motorcycles of all brands and models, particularly in collaboration with independent workshops.
On the AI Marketplace, the company focuses on AI-based vehicle diagnostics. Traditionally, potentially faulty components in vehicles are identified based on error codes and sensor values. Currently, mechanics require a significant amount of time in the workshop and extensive automotive knowledge to make informed diagnoses based on retrieved error codes or measured sensor values (e.g., injection quantity). Additionally, independent workshops repair a large number of different vehicle brands, which increases complexity.
Automatically detecting faulty components with AI
The goal of the project is to develop and test methods for the automated detection of potentially faulty components in vehicles using artificial intelligence. In particular, suitable methods for data preprocessing and training machine learning models using vehicle data (error codes, sensor measurements, and mileage conditions) will be developed and validated.
Furthermore, the suitability of common machine learning models for application in vehicle diagnostics will be investigated. Finally, these models will be integrated into a predictive model for faulty components. This predictive model will be gradually optimized through feedback from automotive experts and transformed into a demonstrator for AI-based vehicle diagnostics.
A demonstrator for the AI Marketplace
With this project, Hella Gutmann is developing a demonstrator in the form of a service that utilizes machine learning models to provide a list of potentially faulty components for a specific vehicle diagnostic case. Integration of this service into a product is planned for the future. With the help of this AI solution, mechanics will be able to better manage the complexity arising from different vehicle types and significantly expedite the vehicle diagnostic process.
Let us show you interesting and helpful content in the quickest way possible.