The improvement potential in conventional aero engines will be realized over the next decades. While a number of evolutionary improvements remain, the limits to thermal efficiency are becoming visible in terms of material constraints, NOx emissions and engine operability. The propulsive efficiency improvement potential is also small and constrained by transmission losses, nacelle and intake drag, engine weight and - for open-rotors - by noise and integration challenges. If the continuous increase in air travel is to become sustainable - as the ACARE 2020 and Flightpath 2050 goals require - then a revolutionary step change in aircraft technology is required. Current aircraft/engine conceptual design methodologies are centered on the disciplines of aerodynamics, structures, and gas turbine performance. Key aspects of unconventional concepts - such as hybrid electric propulsion - are thus hard to capture within existing design tools. TRADE proposes the integration of three new aspects into aircraft/engine conceptual design. First, an advanced structural model quantifies the impact of the installation of heavy equipment on the sizing of the aircraft structure. Second, refined on-board system models capture design and performance trades in electric power systems, gas turbines, and thermal management. Finally, an operational and mission model enables flight dynamic analyses and an assessment of handling qualities of diverging aircraft configurations. All improvements build on extensive model assets of the consortium members. TRADE also delivers the integration of these new aspects into a conceptual design environment. The environment is suitable for the design of hybrid electric aircraft, and the consortium will apply it for configuration assessment and optimization at sub-system as well as whole-aircraft level. TRADE fulfills all the topic requirements of JTI-CS2-2016-CFP04-LPA-01-28, and opens the path to a technological breakthrough in the aeronautics community.

While Industrial robots are very successful in many areas of industrial manufacturing, assembly automation still suffers from complex time consuming programming and the need of dedicated hardware. ABB has developed FRIDA (Friendly Robot for Industrial Dual Arm Assembly), a collaborative inherently safe assembly robot that is expected to reduce integration costs significantly by offering a standardized hardware setup and simple fitting of the robot into existing workplaces. Internal Pilot testing at ABB has however shown that when FRIDA is programmed with traditional methods the programming time even for simple assembly tasks will remain very long. The SARAFun project has been formed to enable a non-expert user to integrate a new bi-manual assembly task on a FRIDA robot in less than a day. This will be accomplished by augmenting the FRIDA robot with cutting edge sensory and cognitive abilities as well as reasoning abilities required to plan and execute an assembly task. The overall conceptual approach is that the robot should be capable of learning and executing assembly tasks in a human like manner. Studies will be made to understand how human assembly workers learn and perform assembly tasks. The human performance will be modelled and transferred to the FRIDA robot as assembly skills. The robot will learn assembly tasks, such as insertion or folding, by observing the task being performed by a human instructor. The robot will then analyze the task and generate an assembly program, including exception handling, and design 3D printable fingers tailored for gripping the parts at hand. Aided by the human instructor, the robot will finally learn to perform the actual assembly task, relying on sensory feedback from vision, force and tactile sensing as well as physical human robot interaction. During this phase the robot will gradually improve its understanding of the assembly at hand until it is capable of performing the assembly in a fast and robust manner.

ROSIN will create a step change in the availability of high-quality intelligent robot software components for the European industry. This is achieved by building on the existing open-source “Robot Operating System” (ROS) framework and leveraging its worldwide community. ROS and its subsidiary ROS-Industrial (European side led by TU Delft and Fraunhofer) is well-known, but its European industrial potential is underestimated. The two main critiques are (1) is the quality on par with industry, and (2) is there enough European industrial interest to justify investing in it? Partially, the answer is “yes and yes”; ample industrial installations are already operational. Partially however, the two questions hold each other in deadlock, because further quality improvement requires industrial investment and vice versa. ROSIN will resolve the deadlock and put Europe in a leading position. For software quality, ROSIN introduces a breakthrough innovation in automated code quality testing led by IT University Copenhagen, complemented with a full palette of quality assurance measures including novel model-in-the-loop continuous integration testing with ABB robots. Simultaneously, more ROS-Industrial tools and components will be created by making 50% of the ROSIN budget available to collaborating European industrial users and developers for so-called Focused Technical Projects. ROSIN maximizes budget efficacy by alleviating yet another deadlock; experience shows that industry will fund ROS-Industrial developments, but only after successful delivery. ROSIN provides pre-financing for developers which will be recovered into a future revolving fund to perpetuate the mechanism. Together with broad education activities (open for any EU party) led by Fachhochshule Aachen and community-building activities led by Fraunhofer, ROSIN will let ROS-Industrial reach critical mass with further self-propelled growth resulting in a widely adopted, high-quality, open-source industrial standard.

We are at the beginning of a new industrial revolution (Industry 4.0): disruptive technologies such as cyber-physical systems, machine-to-machine communication, Big Data and machine learning, and human-robot collaboration will transform the manufacturing and industrial automation sectors. However, Industry 4.0 will only become a reality through the convergence of Operational and Information Technologies (OT & IT). The European Parliament, says that “a very wide range of skills is required for [Industry 4.0] implementation. […] the convergence of IT, manufacturing, automation technology and software requires the development of a fundamentally new approach to training IT experts.” The FORA interdisciplinary, international, intersectoral network will train the next generation of researchers to lead this convergence and cross the IT-OT gap. The convergence will be achieved through the new concept of Fog Computing, which is a logical extension from Cloud Computing towards the edge of the network (where machines are located), enabling applications that demand guarantees in safety, security, and real-time behavior. Research objectives focus on: a reference system architecture for Fog Computing; resource management mechanisms and middleware for deploying mixed-criticality applications in the Fog; safety and security assurance; service-oriented application modeling and real-time machine learning. Our ambitious objectives require individuals with a unique combination of interdisciplinary and intersectoral skills. Thus, FORA’s 15 ESRs will receive integrated training across key areas (computer science, electrical engineering, control engineering, industrial automation, applied mathematics and data science) necessary to fully realize the potential of Fog Computing for Industry 4.0 and will move between academic and industrial environments to promote interdisciplinary and intersectoral learning.

Machine learning have revolutionized the way we use computers and is a key technology in the analysis of large data sets. The FUDIPO project will integrate machine learning functions on a wide scale into several critical process industries, showcasing radical improvements in energy and resource efficiency and increasing the competitiveness of European industry. The project will develop three larger site-wide system demonstrators as well as two small-scale technology demonstrators. For this aim, FUDIPO brings together five end-user industries within the pulp and paper, refinery and power production sectors, one automation industry (LE), two research institutes and one university. A direct output is a set of tools for diagnostics, data reconciliation, and decision support, production planning and process optimization including model-based control. The approach is to construct physical process models, which then are continuously adapted using “good data” while “bad data” is used for fault diagnostics. After learning, classification of data can be automated. Further, statistical models are built from measurements with several new types of sensors combined with standard process sensors. Operators and process engineers are interacting with the system to both learn and to improve the system performance. There are three new sensors included (TOM, FOM and RF) and new functionality of one (NIR). The platform will have an open platform as the base functionality, as well as more advanced functions as add-ons. The base platform can be linked to major automation platforms and data bases. The model library also is used to evaluate impact of process modifications. By using well proven simulation models with new components and connect to the process optimization system developed we can get a good picture of the actual operations of the modified plant, and hereby get concurrent engineering – process design together with development of process automation.