AWS re:Invent 2025 - Revolutionizing Audi's Welding Inspection System through AI (IND367)

Watch	Topic	Details
YouTube	Introduction to AI in Manufacturing	Top 500 manufacturers lose 1.4 trillion annually due to inefficiencies caused by production bottlenecks. The cost of one hour of unplanned downtime has doubled in the past five years. Manufacturers face challenges of increasing innovation, maintaining high quality, and keeping production costs low. AI can help by synthesizing information, automating routine tasks, enhancing data-driven decision making, and preserving knowledge.
YouTube	Audi's Digital Production Platform (DPP)	Audi and Volkswagen Group have been collaborating on the DPP for 5 years. DPP aims to centralize data management, connect over 120 factories to the cloud, and build smart use cases. DPP has led to decreased complexity, increased efficiency, and decreased production costs.
YouTube	Resistance Spot Welding Analytics Use Case	Audi developed a use case for resistance spot welding analytics using AI. The system checks 5 million welding spots per day via AI, compared to 10,000 points per day with ultrasonic devices. The architecture includes an edge gateway based on AWS IoT Greengrass, MQTT for real-time data, Kinesis for streaming data, and SageMaker for machine learning model training. The model is deployed in an application account, and results are stored in a time series database for visualization. The system uses infrastructure as code to automate deployment and make it easy to implement in multiple plants.
YouTube	Weld Splatter Detection Use Case	Audi developed a computer vision use case for detecting weld splatters in real-time. The system uses 8 cameras with 20 megapixels to capture images of the car body. The AI model runs on an industrial PC with a GPU on the shop floor and provides results in 20 seconds. The architecture includes MQTT for real-time control, a Kubernetes cluster for edge gateway, and S3 for image storage. The model is deployed on-prem using edge packaging and MQTT for triggering deployment actions.
YouTube	Key Learnings and Future Plans	Data quality is fundamental for every AI use case. Start small, think on one, and scale gradually. The architecture should be composable and allow for continuous refactoring. Bringing business and IT together is crucial for successful AI implementation in manufacturing. Audi and Volkswagen Group plan to expand the DPP partnership for the next 5 years, focusing on integration, experience, and data management layers.

Watch on YouTube

Description

Learn how Audi implemented an AI-powered quality control system, transforming a traditional welding inspection processes. The system analyzes 1.5 million weld points across 300 vehicles per shift, expanding upon previous manual ultrasound inspections that covered only 5,000 points per vehicle. This AI integration enables production staff to focus on addressing potential anomalies, significantly enhancing quality monitoring efficiency. Following its success, Volkswagen Group is expanding this technology across multiple sites, including Audi Brussels, VW Emden, and Audi Ingolstadt. The implementation process includes site-specific AI model retraining to accommodate varying welding parameters, demonstrating a scalable approach to manufacturing quality control optimization.

Learn more:
AWS re:Invent: https://go.aws/reinforce.
More AWS events: https://go.aws/3kss9CP

Subscribe:
More AWS videos: http://bit.ly/2O3zS75
More AWS events videos: http://bit.ly/316g9t4

ABOUT AWS:
Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts.
AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

#AWSreInvent #AWSreInvent2025 #AWS