AI REGIO | Regions and DIHs alliance for AI-driven digital transformation of European Manufacturing SMEs

Summary

The AI REGIO project aims at filling 3 major gaps currently preventing AI-driven DIHs from implementing fully effective digital transformation pathways for their Manufacturing SMEs:

  • at policy level the Regional vs. EU gap;
  • at technological level the Digital Manufacturing vs. Innovation Collaboration Platform gap;
  • at business level the Innovative AI (Industry 5.0) vs Industry 4.0 gap.

POLICY.

Regional smart specialization strategies for Efficient Sustainable Manufacturing and Digital Transformation (VANGUARD initiative for Industrial Modcernisation) are so far insufficiently coordinated and integrated at cross-regional and pan-EU level. SME-driven >AI innovations cannot scale up to become pan-EU accessible in global marketplaces as well as SME-driven experiments remain trapped into a too local dimension without achieving a large scale dimension. Regional vs. EU Gap.

TECHNOLOGY.

Digital Manufacturing Platforms DMP and Digital Innovation Hubs DIH play a fundamental role in the implementation of the Digital Single Market and Digitsing European Industry directives to SMEs, but so far such initiatives, communities, innovation actions are running in a quite independent if not siloed way, where very often Platform-related challenges are not of interest for DIHs and Socio-Business impact not of interest for DMP. DMP vs. DIH Gap.

BUSINESS.

Many Industrial Data Platforms based on IOT Data in Motion and Analytics Data at Rest have been recently developed to implement effective Industry 4.0 pilots (I4MS Phase III platforms). The AI revolution and the new relationship between autonomous systems and humans (Industry 5.0) has not been properly addressed in I4MS so far. AI I5.0 vs. I4.0 Gap.

AI REGIO is following the 4 steps for VANGUARD innovation strategy (learn-connect-demonstrate-commercialize) by constantly aligning its methods with the AI DIH Network initiative and its assets with I4MS/DIH BEinCPPS Phase II and MIDIH / L4MS Phase III projects. AI REGIO: Industry 5.0 for SMEs

More information & hyperlinks
Web resources: https://cordis.europa.eu/project/id/952003
https://www.airegio-project.eu
Start date: 01-10-2020
End date: 30-09-2023
Total budget - Public funding: 9 200 080,00 Euro - 7 999 207,00 Euro
Twitter: @ai_regio
Cordis data

Original description

The AI REGIO project aims at filling 3 major gaps currently preventing AI-driven DIHs from implementing fully effective digital transformation pathways for their Manufacturing SMEs: at policy level the Regional vs. EU gap; at technological level the Digital Manufacturing vs. Innovation Collaboration Platform gap; at business level the Innovative AI (Industry 5.0) vs Industry 4.0 gap.
POLICY. Regional smart specialization strategies for Efficient Sustainable Manufacturing and Digital Transformation (VANGUARD initiative for Industrial Modcernisation) are so far insufficiently coordinated and integrated at cross-regional and pan-EU level. SME-driven >AI innovations cannot scale up to become pan-EU accessible in global marketplaces as well as SME-driven experiments remain trapped into a too local dimension without achieving a large scale dimension. Regional vs. EU Gap.
TECHNOLOGY. Digital Manufacturing Platforms DMP and Digital Innovation Hubs DIH play a fundamental role in the implementation of the Digital Single Market and Digitsing European Industry directives to SMEs, but so far such initiatives, communities, innovation actions are running in a quite independent if not siloed way, where very often Platform-related challenges are not of interest for DIHs and Socio-Business impact not of interest for DMP. DMP vs. DIH Gap.
BUSINESS. Many Industrial Data Platforms based on IOT Data in Motion and Analytics Data at Rest have been recently developed to implement effective Industry 4.0 pilots (I4MS Phase III platforms). The AI revolution and the new relationship between autonomous systems and humans (Industry 5.0) has not been properly addressed in I4MS so far. AI I5.0 vs. I4.0 Gap.
AI REGIO is following the 4 steps for VANGUARD innovation strategy (learn-connect-demonstrate-commercialize) by constantly aligning its methods with the AI DIH Network initiative and its assets with I4MS/DIH BEinCPPS Phase II and MIDIH / L4MS Phase III projects. AI REGIO: Industry 5.0 for SMEs

Status

SIGNED

Call topic

DT-ICT-03-2020

Update Date

27-10-2022
Geographical location(s)
Structured mapping
Unfold all
/
Fold all
Results:

The troubleshooting system implemented in the Experiment is an AI-driven advanced solution that improved an already existing system, totally deterministic. The new solutions instead is based on a probabilistic approach. Compared to the previous one, it is:

  • more robust: each answer modifies the probability associated with each component without deleting or discarding any of them
  • more flexible: the system also includes the ability to skip a specific question
  • more efficient: the tool can determine the best question based on the probability associated with each component. 

The experiment has achieved the following objectives:

Provide a tool able to help operators to find the exact sheet they need for production line.

The tool can significatively decrease time usually needed to find out, handle and pick up the sheet that is needed from the production line.

The tool is expected to self-learn over time.

Shorten the engineering cycle => automatic feedback and decision making

Save time and reduce cost => reduce manual operations, automation process

Automatic recommendation for printing configuration and additive manufacturing feasibility => Covering all the lifecycle (ideation, request, design, simulation …)

Increased Overall Equipment Effectiveness

Reduced Carrying Cost of Inventory

Increased On Time Orders

improved accuracy of robot arm during milling operations

Improved Reliability of Maintenance and Service

Reduced Working Capital

Improved Customers Acceptance

Decreased Number of training data to adapt the model to new applications

Decreased Training time

An adaptive support system for training and guidance in assembly making use of an AI based adaptive algorithm  based on both productivity and quality as well as operator capacity and needs 

Score the quality of measurement

Detect failures and their root causes

Provide methods for the continual learning of AI model

Provide a specific user solution designed to help decision making of operators

Provide automatically feasible resource suggestions to the system designer

Reduce time used for system design and reconfiguration planning

Allow more alternative resources to be considered during design and planning, leading to potentially innovative solutions  

Reduce humane errors in search and filtering

Automating the search and filtering of feasible resources and resource combinations for specific product requirements from large search spaces.

Automating the identification of required reconfiguration actions on current layout.

Deployment of an IIoT platform serving IILAB demonstrators

Increased real time visibility on a production system

Increased flexibility and efficiency of a production system

Increased robustness of operations of robotic mobile manipulators

Real-time Production Data Monitoring

Industrial Autonomous Systems Reliability

Enhance production and control strategy with AI,

Improve  Worker’s safety using AI to identify unsafe working conditions

Improve predictive maintenance accuracy

Enable remote and highly interactive control strategy for working environment

Improved fault detection

Increased facility availability

Reduced maintenance service costs (for the customer)

Reduced analysis & diagnosis times (of the Maintenance Service provider)

Monitoring and prediction of water consumption

Automatic detection of water leakages

Optimization of the water pipes network maintenance and installation planning

Automation and integration of the manual Quality Control  (QC)

Objectiveness and precision of the QC

Productive increase of QC supervisors 

Online prediction of the maximum number of pieces to be produced by a specific machine according to the current status of the tooling and the readings of its control parameters.

Optimization of machine control parameters configuration to maximize the tooling life while the quality of the production is maintained.

Maximization of the tooling usage time of every machine, while maintaining the machining quality.

Optimization of machine control parameters configuration to maximize the tooling life while the quality of the production is maintained

Coordination of the tooling change in all the machines. This objective would  face the tooling change considering the impact of machines among themselves, instead of just one by one.

Results:

Optimize the Handling

Reduce Technical Checks by Humans

Improve data quality

SWARM platform aims to enable building blocks to digitalize the life cycle, project management, collaborative conception and additive manufacturing prototyping. 

It creates a unique and consistent source of data across the entire product lifecycle form the idea to production, including customer feedback, training and after-sale service.

Better life cycle and project management for plastronic product and automatic generation of the control process on the basis of specifications and other project documents.

The experiment provide a useful tool to help the enterprise to optimize the inventory and the use of resources, support components purchasing, support day to day production management on shop floor, support on-time delivery, improve quality.

Higher product quality, higher production flexibility, optimized costs

Optimization of maintenance intervals 

Reduction of regular service intervals such as (scanner cleaning, ..) by replacing a service call according to schedule with a service call according to actual need

Early detection of sensor faults (Lidar, IMU, Camera, ...) to ensure a proactive fault clearance of the system

Increase of productivity and quality of work (increase competiveness)

Increase  in workers employability

Increase in job satisfaction and reduction of work-related stress

Having insights on the accuracy of measurement in real-time is important not only for the end-user, as it can add a layer of subjectivity to the observations conclusions, but it also impacts the network management maintenance strategy.

The AI model reduces the time spent by the maintenance staff and optimize the routine of maintenance.

Estimate the weather conditions at the city of Purmerend to help operators on the decision making

Increase AI based projects at ARMAC BV

Increase the heat delivery on set point 

Reduce heat loss

Letting the designers and reconfiguration planners to use their time for the actual design and planning tasks, instead of cumbersome search and filtering of feasible resources and resource combinations from various catalogues with somewhat incomparable information. 

Reducing human errors in resource search and filtering (e.g. potential alternative resources overlooked by human, selecting resources with incompatible interfaces) 

Increasing the amount of alternative resource solutions considered, leading potentially to more efficient production system configurations. This may mean, e.g. faster throughput time, better product quality, reduced investment cost or some other improvement, depending on the target KPIs. 

Reducing the time used for system design and reconfiguration planning activity, and thus lowering the design costs.

Increased visibility on the execution of a production schedule

Increased flexibility and efficiency of a production system

Increased robustness of operations of robotic mobile manipulators

Reduction of maintenance costs and number of faults

Optimization of production quality (reduction of discards), costs (times, maintenance)

Optimization of safety and wellness of operators

Higher reliability and availability of stamping facilities by reducing downtime due to unforeseen breakdowns.

Reduced the analysis times of specialized personnel.

Reduce the costs of the Predictive Maintenance service for stamping companies, facilitating the access of SMEs to the advantages of failure prevention technologies

Improved ability to failure anticipation by being possible a much faster analysis,

Improve competitiveness of the stamping sector by reducing production costs due to unforeseen failures, as well as the Predictive Maintenance service provider

Optimize water consumption.

Generate Reports and Field Maps

Identify malfunction in the water consumption.

Prevent unintendedly water leakages. 

Identify and Predict water consumption

Measure water quality

Early estimating the potential faultiness could help local manufacturing companies on planning, controlling and executing productive activities in an optimized and predictive manner.

Production planning optimization

Reduced costs 

Optimized efficiency and effectiveness of the manufacturing systems

 

Tooling savings.

Operators savings. Less operators needed for machines management. 

Increase of the production due to increase of the machine availability.

Increase of quality of pieces and tools life time.