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

Improved fault detection

Increased facility availability

Reduced maintenance service costs (for the customer)

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

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 …)

improved accuracy of robot arm during milling operations

Increased Overall Equipment Effectiveness

Reduced Carrying Cost of Inventory

Increased On Time Orders

Provide methods for the continual learning of AI model

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

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 

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

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.

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.

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

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.

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. 

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

Score the quality of measurement

Detect failures and their root causes

Monitoring and prediction of water consumption

Automatic detection of water leakages

Optimization of the water pipes network maintenance and installation planning

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

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.

Higher product quality, higher production flexibility, optimized costs

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.

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

Increase of productivity and quality of work (increase competiveness)

Increase  in workers employability

Increase in job satisfaction and reduction of work-related stress

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

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.

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.

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

Optimize the Handling

Reduce Technical Checks by Humans

Improve data quality

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

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.

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