The SpinEye project aims to create and demonstrate a world class Vision System for detecting screw holes in products, specifically in the electronics and automotive industry. SpinEye is a vision-based system for cobots that removes the need for expensive fixtures and handling uncertainties in screwdriving tasks, leading to increased product quality.
The project incorporates the implementation of an automated and integrated Smart Maboratory Management System with ancillary subsystems that enable machine-to-machine communication, eliminating human error. In order to accomplish this goal, innovative deep learning methods based on the development of recurrent neural networks (RNN) will be built to analyze data from interconnected machines and detect abnormal behavior.
The project incorporates the implementation of a continuous streaming video recorder system, resulting to error detection automation and slab sorting (classification). For this purpose, innovative deep learning methods will be designed, based on the development of large-scale convolutional and competitive neural networks (Convolutional Neural and Generative Adversarial Networks), in order to enable the analysis of the slabs and the collection of quality features and data regarding shape, perimeter, volume and / or color.
The innovative project “Vigilant 4.0” has been designed and implemented in collaboration with ALUMIL SA. Its innovation has to do with the application of Machine Learning and Artificial Intelligence technologies to optimize the production process of aluminium profiles. This project contributes substantially to the extrusion factory transformation towards autonomy. The outcomes of this experiment indicate significant gains for the customers such as scrap reduction, avoidance of unnecessary processing and time-to-market minimization.
The innovative project “CAD Explorer” has been designed and implemented in collaboration with ALUMIL SA. It refers to an AI-based Visual Similarity tool that uses a simplified die sketch as input and can find the closest design matches of the customer’s database, based on its cutting-edge image similarity, deep-learning based algorithm. The use of such a tool enables the Sales Managers to quickly search and retrieve the most relevant Die Codes. CAD Explorer adopted IDS protocol to ensure sovereignty for critical corporate data. The outcomes of this experiment indicate significant gains for the customers such as the reduction of Time-to-Quote while ensuring corporate data sovereignty.
FLAME Future Media Internet (FMI) is an initiative designed to create a sustainable Future Media Internet ecosystem through experimentation, collaboration and innovation.
IMRA is about a marathon framework for outdoor running events designed to be deployed in 5G infrastructures. The experiment objectives are (i) to provide an intriguing application to marathon audiences, (ii) to leverage the FLAME’s platform to achieve the best possible QoE for the end-users, (iii) to experiment by deploying and benchmarking D-Cube’s technologies on a new and disruptive 5G platform, (iv) to provide valuable feedback to the FLAME consortium regarding the feasibility of the deployment of Deep learning technologies on the FLAME platform.
DIATOMIC, is an exclusive network of Digital Innovation Hubs—part of the EC’s Smart Anything Everywhere initiative. It is a pan-European business and technology ecosystem, with focus on health, agrifood, and manufacturing sectors, uniquely suited to microelectronics startups/ SMEs seeking to accelerate the time to market of novel digitized products and services.
D-Cube is proud to be a part of one of 8 winning consortia, collaborating with Ingenno Berlin, on the CYRUS experiment. CYRUS is a holistic Quality Assessment (QA) solution for aluminium extrusion.
The MIDIH “Manufacturing Industry Digital Innovation Hubs” project aims at realizing services to support the ICT Innovation for Manufacturing SMEs.
The INART experiment proposed and demonstrated a novel way of Augmented Reality (AR) guided assembly in a manufacturing environment. The AR driven assembly process is drastically changing the way an assembly is presented to the workers as well as the way workers and supervisors interact in an immersive way in the manufacturing process.The experiment was conducted at the AIC (Automotive Intelligence Center) didactic factory at Bilbao
TRIANGLE is an EC funded project under the Fire+ initiative. The project is developing a pre-5G testbed to help app developers and device manufacturers in the evolving 5G sector to test and benchmark new mobile applications in Europe utilizing existing and extended FIRE testbeds.
The experiment incorporated a simulated streaming environment hosted in the TRIANGLE testbed facilities that reproduced live content recordings. Remote experimentation was achieved for a largely challenging setting, live streaming VR media demonstrating the capabilities of an appropriately orchestrated testbed.