Connected resilient logistics design & planning
General Information
Challenge, Value & Description
Performance, Access & Contact
1 – General Information
Partners
Sectors addressed
Application categories covered
Lifecycle level covered
Digital Engineering
Planning & Commissioning
Smart Production & Operations
Smart Logistics
Smart Maintenance
Customer Service
Circularity
Quinta da Marquesa, 2954-024 Q.ta do Anjo, Portugal
Geographical Scope
- Europe
- Southern Europe (Italy, Spain, Portugal, Greece)
Gallery
2 – Challenge, Value & Description
Challenge
In the RE4DY Project, Volkswagen AutoEuropa currently relies on manual sequencing for its Automated Storage and Retrieval System (AS/RS) in car glass assembly. This involves handling vast amounts of manufacturing data while ensuring timely part delivery in a constantly changing logistics environment. The challenge is to transition from manual processes to an automated AS/RS sequencing system that can adapt to production variations and optimize logistics in real time.
Value
By leveraging artificial intelligence and simulation techniques, the pilot aims to create a real-time, self-learning virtual factory. This will optimize logistics by reducing waiting times and improving sequencing accuracy. Additionally, it will enhance decision-making for logistics operators, ultimately improving efficiency and flexibility in Volkswagen AutoEuropa’s production ecosystem.
Description
The VWAE pilot enables seamless data exchange between logistics planners, shop floor operators, and digital systems. Big Data ETL processes collect and harmonize data from ERP, RTLS, and production systems. Planners analyze scenarios using simulation tools and AI-driven insights. Once an optimal logistics scenario is defined, it is digitally shared with stakeholders via automated communication tools and E-Paper displays.
This ensures real-time updates to logistics service providers and shop floor teams. Machine learning models further refine future planning by continuously integrating feedback from execution data.
Infraestructure Elements
- PLC / Industrial PC
- Data Centre
- Field Devices
Platforms & Tools used
Acquisition: Real-Time Location System (RTLS) to capture the coordinates of line-feeding assets. | ERP (VWAE) to provides weekly part consumption data. •| FIS (VWAE Production System) to supply real-time production.
Analysis: Big Data Processing & Analytics Service – Uses AI, machine learning models, and data mining. | Qlik Sense – Used for data visualization and business intelligence. | Simulation Tool (ASSECO-CEIT, TWISERION) – Simulates logistics optimization scenarios
Preparation: Big Data Extract, Transform, Load (ETL) System – Cleans, harmonizes, and integrates data from various sources before processing]
Storage: Big Data Storage: Uses HDFS, MongoDB, PostgreSQL, MinIO, and MS SQL for structured and unstructured data storage.
Usage: • E-Paper Displays – Used for real-time logistics updates and communication with shop floor operators. | Digital Twin Simulation – Tests different logistics scenarios before implementation
Sharing: Apache Kafka & Spark – Facilitate data streaming and integration between different systems. | BI Dashboards & Reporting – Provide visibility into logistics processes
Other platforms & tools: Apache Superset & Apache Druid – Used for big data visualization and querying
3 – Performance, Access & Contact Info
Performance
The VWAE pilot demonstrated improved logistics efficiency through AI-driven autonomous planning, digital shop floor updates, and resource optimization. Initial experiments showed a 5% increase in cost savings, 10% reduction in planning time, and faster deployment of logistics updates using E-Paper displays.
The simulation tool optimized asset usage, reducing inefficiencies in line-feeding operations. Machine learning models improved scenario forecasting, enhancing flexibility in demand fluctuations.
Early results confirmed shortened reaction times, reduced manual efforts, and increased system adaptability, validating the resilient, data-driven logistics approach for Volkswagen Autoeuropa’s internal supply chain.
Lessons Learned & Observations
From a technical perspective, the pilot highlighted the importance of data harmonization and integration across multiple sources (ERP, RTLS, production systems) to enable accurate AI-driven logistics planning. The use of digital twins and machine learning significantly improved scenario forecasting but required high-quality, structured data for optimal results.
From an implementation standpoint, automating logistics planning reduced manual workload, but stakeholder adaptation to new digital tools (e.g., E-Paper displays) required training and gradual rollout.
From a data perspective, ensuring real-time updates and secure data exchanges was key to improving operational efficiency and reactivity to demand fluctuations.
Replication Potential & Feasibility Assessment
The VWAE pilot has high replication potential for automotive and manufacturing logistics, especially in large-scale, high-mix production environments.
Technically, the use of AI, digital twins, and simulation tools is feasible but requires integrated data systems and IT infrastructure upgrades.
Economically, initial investments in automation and digitalization may be high, but cost savings from efficiency gains (reduced planning time, optimized resources) make it financially viable long-term.
Replication feasibility depends on data availability, system interoperability, and stakeholder training, ensuring seamless adoption in similar logistics-driven industries.