Projects overview
ETEKINA | HEAT PIPE TECHNOLOGY FOR THERMAL ENERGY RECOVERY IN INDUSTRIAL APPLICATIONS
01-10-2017
-31-03-2022
R-ACES | fRamework for Actual Cooperation on Energy on Sites and Parks
01-06-2020
-31-03-2023
CyberFactory#1 | Addressing opportunities and threats for the Factory of the Future (FoF)
17-12-2018
-30-06-2022
AI REGIO | Regions and DIHs alliance for AI-driven digital transformation of European Manufacturing SMEs
01-10-2020
-30-09-2023
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
KITT4SME | platform-enabled KITs of arTificial intelligence FOR an easy uptake by SMEs
01-10-2020
-31-03-2024
Better Factory | Grow your manufacturing business
01-10-2020
-30-09-2024
GRECO | Fostering a Next Generation of European Photovoltaic Society through Open Science
01-06-2018
-31-05-2021
COALA | COgnitive Assisted agile manufacturing for a LAbor force supported by trustworthy Artificial Intelligence
01-10-2020
-30-09-2023
- Pioneering application of an open, privacy-focused digital assistant in manufacturing. The COALA Digital Intelligent Assistant (DIA) core software will base on the privacy-focused open assistant Mycroft, addressing industry-grade security, privacy, and ethics needs.
- Introduction of digital-assistant-mediated prescriptive quality analytics using manufacturing resource data. The PREVENTION (PREscriptiVE aNalyTIcs for quality optimizatiON) service of COALA will address Prescriptive Quality Analytics.
- Proof-of-concept for the effective augmentation of prescriptive quality analytics via a voice-first interaction.The DIA will use voice as a primary medium (voice-first) to receive user input and provide responses – this speeds up the interaction, is hands-free, and in general an advantage over, oftentimes, overloaded graphical interfaces.
- Pioneering use of an explanation engine with a focus on manufacturing analytics. Fundamental research and the prototype development of the so-called “WHY engine” will enable the assistant to explain its responses (e.g. predictions and advices).
- Introduction of a novel performance measurement procedure (“X”-WHY test) for the explicability of AI-systems, such as digital assistants in manufacturing. It identifies how many WHY questions the user expects to ask in a scenario in a row. Then, the test measures how many questions in a row the assistant is capable of answering.
- Joint application of a Machine Avatar (Digital Twin). This feature is able to track and manage the information gathered by each IoT-connected machine with a Product Avatar, able to track the lifecycle of each product.
- Availability of machine and product information through avatars in sharable environment, independent of the data format and totally product-agnostic.
- A cognitive advisor with dedicated human-assisted AI methods for enabling transfer of tacit knowledge of experts to novice workers.
- Introduction of a new didactic concept to teach workers AI competencies.
- Pioneering use of digital assistant for on-the-job training with a voice-first interface.
- Availability of a new concept for tacit knowledge transfer based on small training datasets.
- Change management process to prepare the adoption of digital assistants at work.
- Pioneering use of an explanation engine with a focus on on-the-job training.
- COALA highly involes in the Digital Innovation Hubs (DIHs) and other regional innovation infrastructures to address SMEs issues that may not be able to afford the education of their labor force, through COALA's didactic concept or related services.
- A cost/benefit analysis will be included in the exploitation plan to verify the affordability for SMEs.
Evaluation of the use case implementations will provide lessons learned and recommendations for further development and research of the COALA solution.
The COALA vision for AI in manufacturing is the development of human-centered digital assistant that provides a more proactive and pragmatic approach to support operative situations characterized by cognitive load, time pressure, and little or zero tolerance for quality issues. COALA will help shaping the complementarity in the collaboration between the AI-based assistant and the human so that
- the AI will take over time consuming and stressful tasks reliably and credibly, while
- the human will focus on understanding and problem solving in complex, knowledge-intensive situations.
COALA’s AI-focused education and training concept will prepare the human-side of the collaboration by offering concept for teaching professionals systematically and, in the language of the workers, about the capabilities, risks, and limitations of AI in manufacturing. The COALA solution will transform how workers perform their jobs and it allows companies to maintain or increase the quality of their production processes and their products.
STAR | Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines
01-01-2021
-31-12-2023
XMANAI | Explainable Manufacturing Artificial Intelligence
01-11-2020
-30-04-2024
ASSISTANT | leArning and robuSt deciSIon SupporT systems for agile mANufacTuring environments
01-11-2020
-31-10-2023
TEAMING.AI | Human-AI Teaming Platform for Maintaining and Evolving AI Systems in Manufacturing
01-01-2021
-30-06-2024
I4MS4Ts | I4MS Tools and Technologies for Transformation
01-06-2020
-30-11-2022
InterQ | Interlinked Process, Product and Data Quality framework for Zero-Defects Manufacturing
01-11-2020
-31-10-2023
i4Q | Industrial Data Services for Quality Control in Smart Manufacturing
01-01-2021
-31-12-2023
TINKER | FABRICATION OF SENSOR PACKAGES ENABLED BY ADDITIVE MANUFACTURING
01-10-2020
-31-03-2024
OPTIMAI | Optimizing Manufacturing Processes through Artificial Intelligence and Virtualization
01-01-2021
-30-06-2024
Grade2XL | Application of Functionally Graded Materials to Extra-Large Structures
01-03-2020
-31-08-2024
Manufacturing systems are often characterised by ‘silos’ of data which cannot be accessed easily horizontally, and by varied and incompatible data types. By utilising a single data bus for all data to be transmitted on, standards are more easily implemented and all data is accessible by all equipment.
This is particularly important in this context where diverse sources of data (such as metrology systems, CAD data) must be analysed by software (e.g. data analytics, metrology software), and then used to adapt a process (e.g. robotic pathing, machining processes).
When a manufacturing system is fixed and will repeat the same tasks, having hard-coded and non-dynamic data exchange may be sufficient. When a system is reconfigurable and flexible, being able to define data sources and destination in software is critical (so-called software-defined networking).
Integration of adaptive robot control technology into a complex and variable manufacturing process allows for accurate positioning of assembly components despite variability in component manufacture, existing assembly deviation, and the robots themselves.
This allows for progress towards jig-less assembly – saving non-recurring costs in the assembly of large, low batch products. Rather than building large, welded jigs and fixtures, robots are used to position and align parts. As the robots can easily be reused, this saves significant time and money.
Note: Since this demonstrator implementation, the Adaptive Robot Control and K-CMM technologies are now available from True Position Robotics .
SMEs often have an advantage over larger companies by being agile and able to change to meet demands more easily. However, this is only possible with an agile and flexible data system. For many SMEs, this burden is carried by human workers, with manual and often paper-based data management and exchange systems.
By implementing a common manufacturing service bus for data, this reliance on human data input (and the associated risk of error and time burden for skilled engineers) can be reduced, and data standards can be more easily implemented.
Though the integration of adaptive robot control represents a significant upfront cost, the ability to save money on fixturing in the long term makes the creation of low batches of large, accurate products a more realistic proposition for small to medium enterprises.
As the robots can be re-used over and over for different situations, it enables significant flexibility in what products and product variants can be built.
For flexible, reconfigurable systems where everything is connected together and must utilise a common data format, selecting the correct data format and a common structure for its use is key. B2MML worked very well for this application, but there is still scope for variation in the way terms and variables are defined, which must be settled on.
Converting an agreed process plan for manufacturing into the B2MML has some degree of automation, but also required a large amount of manual processing. More time should have been spent on automating this process.
Ideally, all components of the system would communicate directly with the service bus. Practically, not all devices will support the service bus, so use of an intermediary communication protocol such as OPC UA may be necessary.
Although process control may all be centralised with a manufacturing service bus, safety systems may not be. This can cause unexpected system behaviour when the system starts a new process unless the safety system is fully understood by the users.
Selection of flexible technologies and standards does not necessarily mean that any given implementation using those technologies will be flexible. A system implementation must be designed specifically to be flexible and future proof.
The ARC robotic control system is extremely effective for bringing a robot / part to a specific and highly accurate location. However, it does not allow for accuracy along a path, so would not be appropriate for continuous path accuracy e.g. robotic milling or welding.
The large amount of metal in the cell (robots, parts) dramatically lowered the accuracy that was possible with the RFID positioning system. Rather than being able to track parts to a specific location, we could determine no better than if a part was inside or outside the cell. Active RFID tags may help mitigate this.
K-CMM technology was extremely effective, but subject to line-of-sight restrictions for large assemblies such as aerospace fuselages.
When integrating technologies and solutions from multiple equipment vendors, the challenge is almost always interoperability and standards compliance. The ARC system was comparatively simple to integrate and commission, but integration into the larger context of a manufacturing process with a SCADA and other physical devices was more of a challenge.
Proprietary Reconfigurable Flooring – A bespoke reconfigurable floor system is being installed that allows for fixtures and robots to be rapidly moved and securely and accurately fixed in place. A lack of a common or established standard in this area was noted.
BOOST 4.0 | Big Data Value Spaces for COmpetitiveness of European COnnected Smart FacTories 4.0
01-01-2018
-31-12-2020
Improved fault detection
Increased facility availability
Reduced maintenance service costs (for the customer)
Reduced analysis & diagnosis times (of the Maintenance Service provider)