“Artificial intelligence is a quantum leap for efficiency in our production,” says Gerd Walker, member of the board of management for production and logistics at Audi. “We are transforming our plants into smart factories where AI acts as a partner, providing our employees with tailored support.

“AI-controlled robots are taking over tasks that are ergonomically strenuous, and chatbots are providing additional relief,” explains Walker. “We are bringing together decades of production expertise, our own innovative strength and the expertise of strong partners.”

Audi is putting Edge Cloud 4 Production (EC4P) into operation across its production network. According to Walker, EC4P makes it possible to combine traditional automation technology with flexibility and computing power from the cloud.

It enables Audi engineers to simplify production processes, reduce the amount of hardware required on site and introduce new functions more quickly. “That makes processes more stable, reduces maintenance costs and increases IT security,” says Walker.

Assemblers are receiving build orders and work instructions from a central source in real time. The move to the cloud has already eliminated the need for more than 1,000 industrial PCs.

In the body shop at Audi’s assembly plant in Neckarsulm, Germany, which produces A5 and A6 sedans, EC4P is now being used in a highly automated production environment for the first time.

Virtual programmable logic controllers are replacing local hardware controllers. Industrial devices, including 100 robots, work together via the EC4P with millisecond precision. An automated detection system identifies weld splatter on the underbody of a car body, marks it with light and instructs a robot to grind the blemishes.

Audi engineers are also developing ProcessGuardAIn for monitoring manufacturing processes. The platform combines various system and plant data from production at a uniform quality level. It bundles decades of expert knowledge, as well as plant and process data, in a standardized, scalable modular system.

Based on machine and sensor data, ProcessGuardAIn already monitors production steps in real time and detects anomalies at an early stage. According to Walker, early fault detection simplifies manual work steps and reduces follow-up costs.

“In the next stages of development, ProcessGuardAIn will provide data-based recommendations for action and guide employees step by step via an app,” says Walker. “In the future, ProcessGuardAIn will serve as a central tool for predictive maintenance and quality assurance, monitoring all manufacturing processes.”