AI Production Tour
Showcase of industrial AI applications for engineering, production, maintenance, quality, logistics and human-machine collaboration.
The AI Production Tour introduces selected Artificial Intelligence use cases implemented within a real production environment. It shows how AI can interact with machines, processes, data and operators to support modern manufacturing.
Unlike a conventional production tour that follows one complete product flow, this tour highlights concrete AI applications across different industrial contexts. Visitors discover how analytical AI, generative AI, agentic AI and physical AI can be used to improve decision-making, increase flexibility, optimise operations and enable new forms of human-machine collaboration.
Each use case demonstrates a practical application of AI on the shopfloor or in engineering-related processes — from AI-supported reporting and process monitoring to predictive maintenance, engineering automation and robotic handling.
Overview
Artificial Intelligence is becoming a key enabler for the next generation of manufacturing. In industrial environments, AI can support people and machines by analysing data, recognising patterns, generating technical content, guiding decisions and even controlling physical processes.
The AI Production Tour brings these capabilities into a tangible factory context. The tour focuses on real use cases that show how AI can be applied in engineering, production planning, intralogistics, manufacturing, maintenance, quality assurance and circular production systems.
Visitors gain insight into different types of AI:
- Analytic AI identifies patterns, anomalies and trends in machine, process or quality data.
- Generative AI creates or supports technical content such as reports, diagrams, documentation or process descriptions.
- Agentic AI acts as an intelligent assistant that can coordinate tasks, interpret inputs and trigger workflows.
- Physical AI connects AI capabilities with robotics, machines, sensors and automation systems in the real world.
Together, these technologies demonstrate how intelligent systems can make manufacturing more adaptive, transparent and efficient.
1. Intelligent Field Reporting
This use case demonstrates how AI can simplify maintenance and field reporting through familiar digital channels such as smartphones, messaging applications and wearable devices.
With Companion by Vertical Data, operators can send pictures, voice messages and location data directly from the field. The AI assistant interprets the information, structures the content and generates professional reports or follow-up documents within minutes. This reduces manual documentation effort and helps technicians capture information while they are still close to the machine or process.
The solution shows how agentic AI can support industrial service teams by turning unstructured field inputs into actionable documentation and workflow outputs.
AI Category
Agentic AI, Generative AI
Application Area
Maintenance, Field Service, Reporting
Partner
2. High-Speed Process Monitoring
This use case shows how AI and computer vision can monitor extremely fast industrial processes that are difficult to analyse manually.
Using the solution from Pandia, production processes can be recorded with smartphones, cameras or high-speed imaging systems. The AI detects anomalies or quality issues in real time and can learn process behaviour during operation. This supports the identification of deviations, instabilities or recurring defects.
The use case is especially relevant for quality assurance, production optimisation and fast troubleshooting on the shopfloor.
AI Category
Analytic AI, Computer Vision AI
Application Area
Production, Quality Control, Process Optimisation
Partner
3. AI-Assisted Engineering
This use case focuses on the AI-supported creation of technical engineering diagrams for industrial processes.
With AITEXA, users can sketch, describe or input process information, while the system assists in generating structured engineering diagrams such as P&ID layouts. By combining process understanding with AI-assisted recognition, the application helps accelerate early engineering work and reduce repetitive documentation tasks.
The use case demonstrates how generative AI can support product and process design by translating human input into technical engineering content.
AI Category
Generative AI, Engineering AI
Application Area
Product Design, Process Design, Engineering
Partner
4. Predictive Machine Monitoring
This use case demonstrates how AI can continuously analyse machine and process data to detect abnormal behaviour before failures occur.
The moneo Industrial AI Assistant by ifm monitors industrial data streams, recognises anomalies and identifies patterns that may indicate wear, instability or upcoming maintenance needs. By supporting predictive maintenance, it helps improve machine availability, reduce unplanned downtime and make maintenance decisions more data-driven.
The use case shows how analytic AI and machine learning can transform raw industrial data into practical operational insights.
AI Category
Analytic AI, Machine Learning
Application Area
Production, Maintenance, Predictive Maintenance
Partner
5. Vision-Guided Robotic Handling
This use case combines AI-based vision, robotic guidance and flexible feeding for automated component handling.
With Asyril EYE+ XTD, industrial components can be detected, identified and localised in real time. This enables robots to pick and handle parts more accurately, even when parts vary in position, orientation or geometry. In combination with flexible feeding systems, the application increases automation flexibility and reduces the need for rigid mechanical fixtures.
The use case demonstrates how physical AI connects perception, decision-making and robotic action in a production environment.
AI Category
Physical AI, Analytic AI, Machine Vision
Application Area
Intralogistics, Production Automation, Robotic Handling
Partner