Relevant:
Associated Results
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.
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: