FLOIM | Flexible Optical Injection Moulding of optoelectronic devices
01-09-2018
-31-08-2022
01-09-2018
-31-08-2022
01-10-2018
-31-03-2022
The ROSSINI platform implementation of a Safety Aware Control Architecture makes it possible for robots to optimally schedule the tasks reacting to a changing environment. in fact, each action to be execute is sent to a dynamic planner that dynamically optimizes its execution in terms of trajectory to follow and/or interactive behaviour to reproduce while considering the variable safety conditions in the working area.
01-07-2015
-30-06-2018
01-10-2017
-31-03-2021
01-10-2017
-31-03-2021
Z-Bre4k will provide a complete monitoring solution at component, machine and system level by combining the high capabilities and effectiveness in sensors and actuation, networking and computational power, utilisation of better and smarter technologies (e.g. material and tools). The latest technologies and algorithms will be utilized for adaptive systems while surpassing the fact that they are disjointed, overwhelmed by complexity, vulnerable to external influence and poor Predictive Capabilities.
A real-time adaptive simulator with high fidelity will be a demonstrator (remote or local) of the machine’s state, in which a fast-forward simulation mechanism (prognostic models) predicts the potential events of breakdown of components and machines. What-if capabilities will allow the maintenance planners to find the most effective and cost-efficient schedules for component replacement and maintenance plans.
Strategies to improve maintainability and increase operating life of production will be applied to update the existing and to develop a set of new strategies based on real data in order to improve maintainability and operating life of production systems. This approach will use a method to translate optimization objectives defined at production and factory levels, into optimized maintenance policies at asset/production process levels.
At the asset and machine level, the Z-BR3AK solution will perform a condition monitoring and generate health status reports. Attention will be given to the faults detection through FMEA analysis (FMECA) to allow remedial actions and synchronise the manufacturing process. The proposed engine will perform monitoring, inspection and control at component, machine, system and product level to issue warnings, alerts (e.g. about deviations from production and quality requirements), reports on (potential) failures or failure prone situations and pass related information to a higher-level Z-Bre4k DSS (for decision support at manufacturing and enterprise level).
01-10-2017
-30-09-2020
01-09-2017
-31-08-2021
01-11-2017
-30-04-2021
01-10-2017
-31-03-2021
01-09-2017
-31-08-2020
UPTIME will provide a unified predictive maintenance management framework and a smart predictive maintenance information system covering the whole prognostic lifecycle. It will contribute to improve smart predictive maintenance systems capable to integrate information from many different sources and of various types, in order to more accurately estimate the process performances and the remaining useful life.
In UPTIME Whirlpool Business Case, each sensor is directly connected to the respective PLC (Programmable Logic Controller), which is on board of the specific equipment. The internal SCADA system is then gathering the data from each PLC and send them to Whirlpool MOM software, which in turn stores them into the database (SQL Server).
01-09-2017
-29-02-2020
01-11-2017
-31-10-2020
01-10-2017
-31-03-2021
01-10-2017
-30-09-2020
The SERENA cloud-based platfrom will provide insight towards the optimisation of the production process considering the maintenance operations that ensuring a non-interrupted production.
01-10-2017
-30-09-2020
01-10-2017
-30-09-2020
01-06-2017
-31-05-2019
01-12-2023
-30-11-2026
01-06-2023
-31-05-2027
01-10-2016
-31-03-2020
ROSSINI provides several advances beyond the state of the art, developing a Safety Aware Control Architecture for robot cognitive perception and optimal task planning and execution.
In order to enable actual perception, ROSSINI leverages on a data processing technique for real-time image recognition, to obtain a semantic scene map that adapts to dynamic working conditions.
ROSSINI adopts also algorithms for motion prediction of humans and moving entities, and embeds their stochastic information in the dynamic semantic scene map. This allows the robot to further refine its planning in order to maximize performance while preserving safety.
In this way, ROSSINI introduces a novel perception and control architecture blending safety and performance oriented planning/control that wants to reach the goal of optimising the trade-off between human operator safety and manufacturing productivity.