Within the framework of the sub-project, research is being conducted on the development of methods and procedures for the analysis and prediction of system behavior, for example, in order to identify causes of quality deviations and to propose quality measures. For this purpose, the interdependencies are modeled first qualitatively and then quantitatively by means of so-called effect networks, whereby the data standards of the Asset Administration Shell and OPC-UA are used as a basis in order to establish compatibility and direct system integration in the digital twin.

A competence center for logistics and health-related services will be established in the project in collaboration with practitioners and scientists. RessourcE intends to initiate sustainable transfer structures between research and practice and develop innovations for effective work design, leadership and opportunities for human resource development in the field of low-qualified work. Technical solutions for ergonomic work design and diversity-oriented competence development in low-qualified work are developed, piloted and tested regarding broad applicability. These solutions include, for example, assistance systems for physical work, concepts for supporting mental health, or software tools for systematic selection of suitable assistance technologies.

Within the framework of the proposed project, CAREads is a web application that ideally supports users from the care sector in creating professional job offers. By providing as little information as possible (company website, job title), CAREads will be able to generate advertisements with modern designs and appealing, individualised texts. In the background, intelligent processes develop suggestions based on the user's needs. The basis for this is an extensive collection, processing and evaluation of published job advertisements, which are used to train machine learning models. The individualisation in design and text is realised by analysing the specified company website with regard to corporate identity or design, photos and texts and then using this content as input for the AI models trained for the care sector. Evaluations and adaptations of the suggested job offers flow into the AI models via a feedback loop in order to take greater account of the subjective impressions of the users over time.

Translated with www.DeepL.com/Translator (free version)

The KoMAR project is developing a flexible Augmented Reality (AR) multi-user application that connects digital models with real objects. Several people can interact simultaneously in an AR 3D scenario. The goal is context-based and robust interaction in virtual space. The project aims to develop new multi-user functions, such as location-independent participation in AR conferences and joint manipulation of virtual objects. For this, BIBA is developing a potential assessment of collaborative robots in industrial assembly as a first use case. Here, AR enables the early involvement of planning and assembly personnel in a real context without physical system adaptations.

The Mittelstand-Digital Centre Bremen-Oldenburg pursues the goal of increasing the level of digitalisation of SMEs in the Northwest Metropolitan Region through individual support measures.

In addition to the classic manufacturing industry and production-related services such as logistics, the focus is also on the consumer-oriented service industry, such as tourism, gastronomy or the creative industry. The participation of the BIBA enables, among other things, the transfer of knowledge from the research projects to industry, the implementation of infrastructure and demonstrators, as well as the implementation of local events and online formats.

Food, especially chilled and frozen, is increasingly ordered online and must be shipped to customers while complying with the cold chain. The polystyrene or EPS boxes that are used nowadays for shipping of chilled and frozen goods, offer good technical properties, such as insulation or food safety, but have ecological disadvantages, not least because of the fossil raw materials. In order to improve the environmental balance of food transportation, the project is being developing an innovative packaging solution that consists largely of recyclable or bioplastics and uses insulating effects of a vacuum. In addition, an efficient return in terms of reusability is strived through a compactable design.

Assembly assistance systems store data for quality assurance. Data analysis of process steps that can lead to production errors through error propagation does not exist yet. OptiAssist develops an AI-based system for identifying anomalies in the assembly process through unsupervised learning; after that, the effort of the assembly operations is reweighted in the priority graph. Based on optimization, an expert system suggests process changes to the process planner on appropriate dashboards. To increase user acceptance, strategies are developed for a suitable time to reschedule the assembly process.

In AITeach, an innovative system is being developed that automates the creation of assembly sequence plans and instructions for assembly assistance systems in the context of work preparation in variant-rich assembly. For this purpose, an innovative software system is to be developed that analyzes sensor data using intelligent algorithms and AI methods with regard to the demonstrated activities. The goal is the automatic recognition of manual assembly work steps, an easy-to-understand preparation and presentation of the recognized activities by means of text-based instructions as well as a visualization based on a digital twin.

WASABI aims at providing SMEs with the tools and knowledge to improve workers capacities and performance, providing advanced user interfaces for continuous augmented hybrid-decision-making. Such interfaces assist employees in interacting with complex software, effectively reducing its skill floor. In consequence, humans will find using software easier and be more open to applying it effectively at work. WASABI’s advanced interfaces will cover, for instance, situation analysis, intervention identification, action

planning and execution, and impact monitoring and mitigation. One of the key technologies in WASABI’s solution portfolio is the digital intelligent assistant (DIA) - an anthropomorphic, task-oriented AI with a conversational interface. A network of DIHs that will help boosting impact by guiding SMEs in this new path will be created and integrated within other existing DIH networks. Our customized, federated, white-label shop will include such DIAs and skill-packages to help organizations reach their sustainability goals. Blue-collar and white-collar workers will be capable of using it for hands-free or eyes-free computer-interaction, AI-based advice and guidance, and augmented analytics.

Incoming goods inspection is still done manually in many SMEs. Automation of these processes optimizes incoming goods, reduces errors along the entire supply chain and creates competitiveness in the market for transport and warehouse logistics. The implementation of this automation, be it through own development or use of existing solutions on the market, is very costly and not feasible for many SMEs.

This is where the research project "Pakur" comes in, in order to enable SMEs in the logistics segment to implement (partially) automated data acquisition in incoming goods inspection or inventory. Recent breakthroughs in the field of image processing using neural networks are to be used to develop an easy-to-use, automatic, digital standard solution for identifying and counting packages based on images of the palletized goods. In doing so, the employee is to be supported by an app in order to accelerate the process of receiving and inventorying goods while minimizing potential errors. Here, algorithms are to be developed and neural networks trained that are capable of recognizing the individual elements, such as packages or bags, on a pallet without error, even in heterogeneous environments, analyzing their packing pattern and then deriving the number of elements correspondingly per unit load. This information can then be passed on directly to a possible inventory management system. Errors are thus detected at an early stage and incorrect information in the system is avoided.

The focus of the development is on the creation of the algorithms, based on current, innovative research. The transfer into practice is realized by a ready-to-use, open source software library that can be easily used by third parties and an open source demo application for the smartphone. This ensures that third parties can also actively use the result and apply it to other areas.

In Port2Connect (Intelligent Port Logbook for the Efficient and Sustainable Use of Port Infrastructure), a digital port logbook is being developed that increases the transparency and visibility of processes in the port and enables automatic planning and optimisation with artificial intelligence.

processes in the port and enables automatic planning and optimisation with artificial intelligence. Through the intelligent monitoring and assistance system, ships are digitally accompanied and monitored during their stay in the port. In particular, this is intended to achieve the goals for more efficient use as well as sustainable protection against damage to the existing port infrastructure and an improvement in the climate by reducing emissions.

The port logbook is being developed as an example for 2,200 metres of the Stromkaje in Bremerhaven. Various requirements are placed on such a system. These include the recording and allocation of emissions as well as the location of the berths directly on the Weser, which are exposed to the river current and the tidal range caused by the tides. Furthermore, in order to use the berths efficiently, ships in the port must be moved more frequently. In addition, large container ships in particular pose an increased risk of damage to the infrastructure, and it is precisely these ships that account for a large proportion of the port’s total emissions.

In the SYDITIL project, a systemic digital twin (DT) for logistics is being developed. The technological basis is Σ, a language and method for describing complex socio-technical systems, and the WorldLab software. Based on the application scenarios warehouse logistics and port logistics the DT will be developed and evaluated. The intended solution will help to continuously improve the logistics processes. For this purpose, the DT is constantly updated with data gathered from the logistics systems and simulates possible scenarios as well as forecasts upcoming risks. If necessary, the DT sents alerts to control and monitoring systems to optimize logistics operations. In addition, the visualization of simulation and forecast results supports decision-making for future planning.

Stress and scarce attention are the main causes of work accidents in industry, and they affect workers' performance. Physical, physiological, and psychological aspects related to stress have already been studied through the analysis of biometric data, but they have never been integrated with neuro-physiological/psychological data. No-Stress captures the motion of workers while performing manufacturing tasks by real-time collecting neurophysiological parameters and interacting with voice assistance to gather reactions and feedback. The causes of stress will be identified by analyses of workers' data to redesign the work environment with a human-centred approach focused on worker well-being. The project will develop a monitoring system for manufacturing companies to improve their working conditions and production efficiency. The use case providers with worker assistance sector operators will work to redesign manufacturing contexts focusing on workers.

In this project we develop an autonomous indoor blimp drone for safety hazard detection in shipyards. Due to the highly dynamic work environment of the ships construction site, shipyards are subject to an increased risk of accidents. In an extension to the current state of the art, the blimp-based drone system will drastically increase flight times while decreasing noise levels. The risk of additional harm from the drone is close to zero due to the lightweight construction. To ensure robust identification of safety hazards we develop an optical sensor system which uses state-of-the-art AI algorithms for detection.

The TrackInWare Project is an ambitious initiative to develop a high-precision positioning system based on Ultra-Wideband (UWB) and Bluetooth Low Energy (BLE) technology. By combining these two technologies, we aim to significantly improve location determination, thereby increasing process efficiency in logistics and production.

Bremer Institut für Produktion und Logistik (BIBA), is responsible for developing the hardware for the beacons and anchors. These beacons are equipped with an E-Ink display, enabling the recording of status messages and thus enhancing clarity and user-friendliness.

The development process is being carried out in close collaboration with SigScan, a leading provider in wireless communication. The project is coordinated by Aerospace Valley, an organization committed to promoting innovation and technology transfer in the aerospace industry.

A key goal of the project is to test the results in real production and logistics environments. To this end, we have already established partnerships with Sonae and Whirlpool, two leading companies in their respective sectors. At Sonae, the developed technologies will be tested in logistics, while Whirlpool will implement them in their production processes.

The TrackInWare Project aims to enhance the efficiency of production and logistics processes through precise positioning. With the intelligent use and integration of UWB and BLE technology, we are confident that we can make a significant contribution to the optimization and modernization of these sectors.

Smart Power will provide knowledge of two industry4.0 application domains - namely smart manufacturing and smart micro grids - and furthermore unlock the potential by show casing the interconnection of those. Best practices of cross-domain integration will not only provide know-how to future employees, but open the mind set of skilled work-forces to enable competetiveness and advances by broadening possible solution space with taught opportuniƟes from the industry4.0 paradigm.

The training addresses professionals, entrepreneurs,students and life-long learners with skill-driven self-learning course material, which will transfer key principles, methodologies and technologies addressing actual industry problems and challenges. Alongside the problem solving of those real-world scenarios, participants will be encouraged to establish disruptive thinking across domains –

primarily in the cross-domain integration of smart factories and smart grids, but will not be limited to these.

The European production landscape is facing major challenges that require sustainable and robust, but at the same time, highly efficient production systems that have the ability to respond to significant changes at high speed.

The global objective of the project RaRe2 is to create a flexible and resilient ecosystem platform enabled by the interaction of many European organizations that cooperate in the fast reconfiguration of process chains through collaborative systems and adaptable workforce upskilling.

In the project, digital twins of production and logistics systems augmented with forecasting, reconfiguration and optimization functions will be developed at different hierarchical levels along the entire value chain. In addition, methods for flexible and robust workforce planning will be developed. In the next step, the developed methods will be integrated in an ecosystem platform.

This research has been funded by the European Union's Horizon Europe Framework Programme (HORIZON) under project reference HORIZON-CL4-2022-TWIN-TRANSITION-01.

The hyBit project plays a important role in the realization of the EU's goal of a climate-neutral economy by means of green hydrogen in a holistic energy transition. The overarching question of the project is: How can climate neutrality be achieved through the targeted technical, economic, ecological, legal and social design of hydrogen hubs? In five steps, pilot applications are defined via flexible modeling of logistics systems that run on hydrogen. For this purpose, transformation paths, infrastructure concepts and roadmaps will first be developed and simulated. The results and simulation performance will be made available to a central transformation platform, which will combine them with the results of other issues beyond mobility and logistics.

NebulOuS will introduce an appropriate meta-operating system that encompasses brokerage capabilities across the cloud computing continuum. Specifically, it will enable the emergence of ad-hoc fog brokerage ecosystems that exploit IoT/edge and fog nodes, in parallel to multi-cloud resources to cope with the requirements of hyper distributed applications. Such applications will be managed by NebulOuS considering the full life-cycle support of edge and cloud resources to enable hosting nodes across organisational units of the same or different business entities or reach private datacentres of telecom providers, constituting ad-hoc cloud computing continuums. BIBA will integrate the research on distributed digital twins and their orchestration in the cloud computing continuum and employ the NebulOuS solution in an application scenario in the domain of crisis management and communication.

Intelligent and interactive AR-based assistance systems have great potential for supporting intralogistics work processes. Still, they have only been used occasionally in this form in practice, especially in SMEs.

The object of the AR Improve research project is intelligent and interactive AR assistance systems that combine current AR hardware with sensor technology and image-processing methods.

By providing an interactive guide, which is being developed together with SMEs, decision-makers can make well-founded decisions about the needs-based and human-oriented use of AR assistance systems without detailed knowledge of AR technology.

Fablabs Erasmus+ project aims to develop training material for supporting Fablab users, and Fablab Tutors/Teachers, including contents for design, coding and manufacturing with main focus on IoT, 5G, AI/Big Data and Blockchain technologies. The main project objectives include:

 

• Development of learning and teaching strategies and concept/guidelines for FabLabs mainly oriented to IoT related technologies like Blockchain and AI/Big Data.
• Development of didactic methods covering several target groups (University degree studies and general public), - development of learning material (blended learning including e-learning, face-to-face, workshops).
• Development of curriculum for training of design, manufacturing of prototypes using IoT, and AI/Big data technologies applied to industry or similar.
• Organization of training activities for tutors.
• Test of the learning material and tutorial during testing initiatives (courses).
• Optimization of learning content for tutors.

  Within this project the learning content will be developed with a learner-centered approach and using case studies from selected branches of industry (examples) to let learners understand the industrial/practical relevance of the topic and show the linkage of principles and methods with relevant applications. Testing courses/workshops will be run at different targets (from apprenticeship to University level) for integrated testing, assessment and optimization of developed tools and contents.

 

Freight transport in Germany today is mainly carried out by road and rail. However, the further increase in transport volumes is pushing the systems to their limits, as evidenced by increased congestion and more frequent delivery delays, among other things. Another challenge is the high environmental impact of road and rail transport. A lower-emission alternative and supplement to land-based transport is water-based freight transport by inland waterway vessel. The increased use of this mode of transportation requires the provision of additional decentralized transhipment points (so-called MicroPorts) for the intelligent and efficient linking of land- and water-based freight transport.

The aim of the project is the technical design of a network of decentralized transhipment hubs for linking land- and waterborne freight transport. The basic idea is to use existing infrastructure, especially bridges, for the installation of the MicroPorts. Based on this, a simulation-based evaluation will be carried out to assess the new transhipment concept's economic efficiency and sustainability. The expected project results thus provide the basis for the planning and implementation of decentralized transhipment points for combined land- and water-based freight transport in the future.

The aim of the project is to develop an off-the-shelf system for the most intuitive access possible to complex information through natural and low-threshold communication in combination with optical image recognition processes. At the same time, it shall provide experienced users with direct, fast and contactless access to a wide range of functions. For data protection reasons, personal image and voice data will be processed by an integrated computing unit.

The BiT-Data Project is dedicated to efficiently harnessing the complexity and volume of production data. Our goal is to develop a platform that collects production data and provides it through standardized communication protocols. This allows for swift and transparent data processing, leading to improved operational management and decision-making.

A significant feature of our platform is the easy application of AI algorithms. These offer the possibility of presenting key metrics of the production facility in an accessible manner. Our focus is on designing these algorithms so that they can be used and adjusted by users with minimal effort.

Our pilot application case is the human-robot collaboration in the production of bipolar plates for hydrogen fuel cells. In this endeavor, we are joined by BIBA, a renowned research partner. BIBA focuses on developing and integrating AI algorithms that use image data from an optical camera to make statements about the quality of the fuel cells.

Our approach is multifaceted, including the trial of various procedures for quality control and fault detection. The results of our research work are incorporated into a guide that simplifies the use of these algorithms in production. An integral part of this guide is the demonstration of the integration of the AI algorithms into a graphical data pipeline tool. This practical section illustrates the straightforward application and the potential of the developed algorithms.

With the BiT-Data Project, we aim to make production processes more efficient, accurate, and productive through intelligent handling of data. We believe that smart data utilization and processing are key components for future competitiveness in the manufacturing industry.

Many production processes in industry are changing towards cyber-physical systems in which physical and computational elements as well as human operators are interconnected. As a result, human work in production is undergoing profound changes toward collaboration with automated and autonomous systems and their monitoring. In such hybrid cyber-physical production systems (CPPS), the quality of collaboration and interaction between the human operator and technical systems is a key success factor.

Hybrid CPPS require an integrated system design consisting of technical, organizational and human-centered viewpoints to ensure their successful implementation and usability. Consequently, the goal of the project is to contribute to the integration of human factors in hybrid CPPS. Interdependencies between the quality and performance of human work and the design of hybrid CPPS are determined and used to derive design principles for planning and redesign of work systems.

A demonstrator is to be built that serves as a platform for conducting studies with participants within a model hybrid CPPS. It contains several workstations that represent different processing steps and can be used flexibly as manual or automated workstations. Thus, different variants of hybrid CPPS can be modeled and investigated with regard to their effects on the system performance and on the operators. The results are used to determine the underlying relationships between different design variants and key figures for system performance and the perception of work.

The cargo handling environment in ports is characterized by the handling of heavy and large loads, in which humans are essential despite the progress of automation. In the specific application of automobile handling, the vehicles are prepared for the respective target market in technical centers. For this purpose, tires and trailer couplings, for example, have to be moved and mounted by humans. In addition, there is a large number of additional car parts that have to be picked and, in some cases, assembled in an overhead position. As a result, a high physical strain is placed on the employees, which leads with increasing age to a degree of physical impairment. Within the scope of the project MEXOT, the challenges identified are addressed with a socio-technical development approach. To this end, the use of exoskeletons is targeted, aiming to research on intelligent work ergonomics, which examines human-machine interaction in combination with exoskeletons and automated guided vehicles (AGVs). Motion sensors will be integrated into a passive exoskeleton to track the movement patterns of the employees. First, this information is used to enrich data for an external incentive system that rewards employees for wearing the exoskeleton correctly and integrates gamification approaches to increase motivation. In a second step, the data and process information are used to activate or deactivate individual "elastomeric muscles", aiming at a higher wearing flexibility for activities that do not require physical support. In the third step, the movement information of the exoskeleton will be used to develop a sophisticated pick- and assembly-by-motion concept, which, in combination with the camera system of the AGV, enables the registration of individual work steps in picking and assembly. For the AGV, further research is conducted on increasing productivity and reducing the workload of employees through process-specific and worker-individualized material supply. Moreover, voice- and gesture-based functionalities are implemented for human-machine interaction with the AGV.

This project aims at reducing technological barriers towards using a fleet of robots in warehouses and conventional manufacturing environments. In this project, learning material was created to upskill university students and professionals in advanced autonomous navigation concepts, specifically how to leverage existing open-source software libraries on mobile robot platforms. From the end-user perspective, our education materials helped industries using mobile robot solutions to perform complex debugging/maintenance without overly relying on their third-party supplier. This will save time spent tuning motion planning libraries without fully understanding the effect of underlying hyperparameters. In the second phase, the project will be expanded to include collaboration with manipulators to implement an efficient interface based on ROS2 components using the e.DO Cube from COMAU as an example. Based on this example, additional learning units related to ROS2 will be created to establish a fully comprehensive intralogistics scenario.

Herausforderungen bei der Nutzung von Cloud-Technologien und verteiltem Edge Computing für eine tragfähige IoT-Plattform bestehen darin, hochaufgelöste Daten verfügbar zu machen und zu verarbeiten und dort mit KI-Modellen zu verknüpfen. Der Modellbildung kommt hierbei eine besondere Bedeutung zu, da das Verhalten der Systeme in einem komplexen Varianten-raum beschrieben werden muss, und es dabei auch kontinuierliche Veränderungen über eine Lebensdauer von 20 Jahren zu berücksichtigen gilt. Klassische IoT Plattformen und Strukturen, wie sie bereits u.a. in der Windenergiebranche eingesetzt werden, können die Dynamik des tatsächlichen Lebenszyklus von komplexen Produktsystemen wie Windenergieanlagen (WEA) nur unzureichend abbilden. Insbesondere unter Einbeziehung eines modularen WEA-Ansatzes ist die monolithische Errichtung von digitalen Zwillingen nicht ausreichend. In diesem Vorhaben soll daher ein flexibles, dezentrales Konzept für sogenannte „Micro Digital Twins“ (MDTs) entwickelt und gemeinsam mit dem Verbundpartner Nordex implementiert werden. Dabei wird besonderes Augenmerk auf universelle Anwendbarkeit in der Domäne und eine hohe Anpassungsfähigkeit des Konzeptes an die Weiterentwicklung des Standes der Technik gelegt.

The aim of the project is to develop an intelligent modular end effector-component protection system for safe and intuitive cooperation between humans and robots. The protection system is to consist of a protective cocoon that is installed on the end effector and encloses both it and the component. In this way, people in the direct cooperative working area of the robot can be protected from hazards. Integrated sensors will detect people in the vicinity at an early stage and automatically keep them at a distance. With the help of intelligent control strategies, robot movements should be possible both spontaneously (avoidance) and anticipatory, so as not to interrupt processes unnecessarily. Interaction modules are to intuitively indicate the robot's next movement so that the movement can be anticipated and also serve as an interface for the input of commands. Thus, for the first time, humans can also react intuitively to the robot, which increases work safety and minimizes safety-related interruptions.

In the project, a vocational education and training platform for employees in logistics is to be developed on the basis of an existing platform (MARIDAL), which enables demand-oriented and individual learning and offers flexible learning paths. The platform envisaged in this project is a digital learning ecosystem. AI is used to personalise the user experience and support learning. In addition, certificates can be issued - also for external persons.

TOKIOS aims to integrate innovative methods and techniques from the fields of statistics and artificial intelligence into the integration and system tests of aircraft. The addressed methods are to be applied to offline data, which is of the order of magnitude of big data.

The tasks of the BIBA focus on the development of data integration solutions and the analysis framework in order to be able to set up and use analysis chains in an interoperable manner. Furthermore, the analysis tool is geared towards the needs of the test engineer for future test processes

Agriculture must increasingly address issues of sustainability and quality management. In this context, feed is also becoming increasingly important from a cost perspective. The goal of the project is the realization of a cloud platform for farmers, traders, and feed producers to individually configure feed, produce it according to demand and deliver it just-in-time. In addition to the integration of weather-dependent demand and price forecasts, the focus is on the development of a simulation-based supply chain control with optimization of the life cycle assessment.

TRICK will provide a complete, SME affordable and standardised platform to support the adoption of sustainable and circular approaches: it will enable enterprises to collect product data and to access to the necessary services on a dedicated marketplace, open to third party solutions. TRICK demo will be run in 2 highly complex and polluting domains: textile-clothing as main pilot and perishable food for replication. BIBA focusses on the adaption of the B2B marketplace to the needs for a Circular information management (CIM).

i4Q will provide a complete solution consisting of sustainable IoT-based Reliable Industrial Data Services (RIDS) able to manage the huge amount of industrial data coming from cost-effective, smart, and small size interconnected factory devices for supporting manufacturing online monitoring and control. The i4Q Framework will guarantee data reliability with functions grouped into five basic capabilities around the data cycle: sensing, communication, computing infrastructure, storage, and analysis and optimisation; based on a microservice-oriented architecture for the end users. With i4Q RIDS, factories will be able to handle large amounts of data, achieving adequate levels of data accuracy, precision and traceability, using it for analysis and prediction as well as to optimise the process quality and product quality in manufacturing, leading to an integrated approach to zerodefect manufacturing.

i4Q Solutions will efficiently collect the raw industrial data using cost-effective instruments and state-of-the-art communication protocols, guaranteeing data accuracy and precision, reliable traceability and time stamped data integrity through distributed ledger technology. i4Q Project will provide simulation and optimisation tools for manufacturing line continuous process qualification, quality diagnosis, reconfiguration and certification for ensuring high manufacturing efficiency and optimal manufacturing quality.

BIBA focuses on: 1) the creation of data quality guidelines for manufacturing and 2) the extension of its software QualiExplore to support a) production data quality knowledge, and b) production line certification under the aspect of data quality. The extension of QualiExplore includes the integration of a digital assistant (conversational AI).

ENHANCE aims at strengthening the cooperation between 3 EU and 4 PC universities across recent research outcomes related to MPQ 4.0. From a capacity-building perspective, this consortium will improve the capacity of HEI in PC with innovative programmes. It will develop new competencies and skills to transfer later to socio-economic partners. ENHANCE will guarantee the sustainability of the consolidated learning programs and materials through the creation of 2 new DIH in PC.

ACROBA project aims to develop and demonstrate a novel concept of cognitive robotic platforms based on a modular approach able to be smoothly adapted to virtually any industrial scenario applying agile manufacturing principles. The novel industrial platform will be based on the concept of plug-and-produce, featuring a modular and scalable architecture which will allow the connection of robotic systems with enhanced cognitive capabilities to deal with cyber-physical systems (CPS) in fast-changing production environments. ACROBA Platform will take advantage of artificial intelligence and cognitive modules to meet personalisation requirements and enhance mass product customisation through advanced robotic systems capable of self-adapting to the different production needs. A novel ecosystem will be built as a result of this project, enabling the fast and economic deployment of advanced robotic solutions in agile manufacturing industrial lines, especially industrial SMEs. The characteristics of the ACROBA platform will allow its cost-effective integration and smooth adoption by diverse industrial scenarios to realise their true industrialisation within agile production environments. The platform will depart from the COPRA-AP reference architecture for the design of a novel generic module-based platform easily configurable and adaptable to virtually any manufacturing line. This platform will be provided with a decentralized ROS node-based structure to enhance its modularity. ACROBA Platform will definitely serve as a cost-effective solution for a wide range of industrial sectors, both inside the consortium as well as additional industrial sectors that will be addressed in the future. The Project approach will be demonstrated by means of five industrial large-scale real pilots, Additionally, the Platform will be tested through twelve dedicated hackathons and two Open calls for technology transfer experiments.

Research on digitalization and applications of artificial intelligence are advancing rapidly. In spite of excellent results, which are published by publicly funded research projects, there is still a lack of systematic solutions for SMEs that provide robustness and reproducibility of AI and at the same time take the restrictions of software and infrastructure in SMEs into account. The overall aim of the ecoKI project is to close this gap. ecoKI supports SMEs by developing an infrastructure for increasing energy efficiency through AI technologies. ecoKI pursues the following goals:

 

1. Make digitization and AI modules(solutions) more generic in the area of energy efficiency. Moreover, make the available AI and digitalization solutions as easy as possible to use.
2. Reduction of barriers that SMEs encounter when they begin to use of digitization and machine learning solutions for increase energy efficiency.

 

Humans are at the center of knowledge-intensive manufacturing processes. They must be skilled and flexible to meet the requirements of their work environment. The training of new workers in these processes is time consuming and costly for companies. Many industries suffer from the shortage of skilled workers caused, e.g. by the demographic change. A second challenge for the manufacturing sector is the continuous competition through high quality products. COALA will address both challenges through the innovative design and development of a voice-first Digital Intelligent Assistant for the manufacturing sector. The COALA solution will base on the privacy-focused open assistant Mycroft. It integrates prescriptive quality analytics, AI system to support on-the-job training of new workers, and a novel explanation engine - the WHY engine. COALA will address AI ethics during design, deployment, and use of the new solution. Critical components for the adoption of the solution are a new didactic concept to reach workers about opportunities, challenges, and risks in human-AI collaboration, and a concurrent change management process. Three use cases (textile, white goods, liquid packaging) will evaluate the results in common manufacturing processes with significant economic relevance. We expect to reduce the failure cost in manufacturing by 30-60% with the prescriptive quality analytics feature and the assisted worker training. For the change over time we expect a reduction of 15% to 30% by shortening the worker training time.

The manufacturing of large-scale parts needs the implementation of holistic data management and integrated automation methodology to achieve the desired levels of precision using modular and more flexible equipment. Large-part manufacturing is characterised by a high level of required customisation (built-customer specific). Furthermore, the manufacturing of complex and large-scale parts involves a variety of subassemblies that must be manufactured and assembled first.

This high degree of personalisation implies a great effort in the design and the posterior verification after manufacturing, to achieve high precision. Nevertheless, this customised product-centric design requires an optimisation of the resources of the workshop (i.e. workers, machines, devices) for a responsive, reconfigurable and modular production. In addition, there is the worker-centric approach: performing key labour-intensive tasks while maintaining the industry-specific knowledge and skills of the workers.

PENELOPE proposes a novel methodology linking product-centric data management and production planning and scheduling in a closed-loop digital pipeline for ensuring accurate and precise manufacturability from the initial product design. PENELOPE is built over five pillars for developing a common methodology and vision deployed in four industrial-driven pilot lines in strategic manufacturing sectors: Oil&Gas, Shipbuilding, Aeronautics and Bus&Coach; with potential replicability to further industrial sectors. Moreover, it will be set up a pan-European network of Didactic Factories and showrooms, providing training and upskilling capabilities enabling the workforce transition towards Industry 4.0 and multi-purpose testbeds, for assisting the dedicated industry adaption. PENELOPE envisions to highly-increase EU manufacturing sector competitiveness by increasing production performance, quality and accuracy while ensuring workers’ safety and resource efficiency.

In the funded project "compARe", an AR-based technical assistance system is developed that uses image processing methods to support service technicians in the maintenance of wind turbines. The project will focus on tasks that only allow defect detection by comparing the current status with a previously documented status or a target status. Thus, the system can help avoid damage to the WTG and increase maintenance measures' efficiency.

Employing AI-based image processing methods, such as Convolutional Neural Networks (CNN), defects in components can be detected, classified, and evaluated. Furthermore, the comparison of component states based on historical data is possible. Mobile assistance systems have proven to be very promising for the support of service technicians in wind energy. The use of these computing-intensive image processing methods on mobile devices is a challenge. However, it offers great potential in combination with mobile Augmented Reality (AR) technology. In this way, virtual information on the change of component conditions can be provided directly about the components concerned in the field of vision of the service technicians.

ePIcenter will create an interoperable cloud-based ecosystem of user-friendly extensible Artificial Intelligence-based logistics software solutions and supporting methodologies that will enable all players in global trade and international authorities to co-operate with ports, logistics companies and shippers, and to react in an agile way to volatile political and market changes and to major climate shifts impacting traditional freight routes. This will address the ever-increasing expectations of 21st century consumers for cheaper and more readily available goods and bring in Innovations in transport, such as hyperloops, autonomous/robotic systems (e.g. “T-pods”) and new last-mile solutions as well as technological initiatives such as blockchain, increased digitalisation, single windows, EGNOS positional precision and the Copernicus Earth Observation Programme.

The vision of LEVEL-UP is the development of a holistic operational and refurbishment framework applicable both to new and existing manufacturing equipment to achieve dynamic utilisation and maintenance with upgraded remedial actions for sustainability. The LEVEL-UP solution will be demonstrated in the operational environment of Vertical Lathes, Milling machines, Presses, woodworking, Pultrusion, Extrusion, Inspection and CNC equipment to achieve (i) increased efficiency, (ii) extended lifetime and reliability, and (iii) increased ROIC. To do so, LEVEL-UP will offer a scalable platform covering the overall lifecycle, ranging from the digital twins setup to the refurbishment and remanufacturing activities towards end of life.

The precondition of the sketched vision is the achievement of the interoperability from the data till the service layer. BIBA will provision the semantic mediator for the lifecycle of large industrial equipment. The connections between the data aggregator with the higher ontologies and the Knowledge base will be achieved through semantic models and ontologies

The manufacturing industry is facing major challenges due to increasing global competition, low-cost production in developing countries and scarce raw materials. EIT Manufacturing is an initiative of the European Institute of Innovation and Technology (EIT), in which BIBA is one of 50 core partners.

EIT Manufacturing’s mission is to bring European manufacturing actors together in innovation ecosystems that add unique value to European products, processes, services – and inspire the creation of globally competitive and sustainable manufacturing. To do so, the initiative has six strategic objectives:

 

1. Excellent manufacturing skills and talents: adding value through an upskilled workforce and engaged students.
2. Efficient manufacturing innovation ecosystems: adding value through creating ecosystems for innovation, entrepreneurship and business transformation focused on innovation hotspots.
3. Full digitalization of manufacturing: adding value through digital solutions and platforms that connect value networks globally.
4. Customer-driven manufacturing: adding value through agile and flexible manufacturing that meets global personalized demand.
5. Socially sustainable manufacturing: adding value through safe, healthy, ethical and socially sustainable production and products.
6. Environmentally sustainable manufacturing: adding value by making industry greener and cleaner.

   EIT Manufacturing aims for the following goals by 2030:

   • Create and support 1000 start-ups

   • 60% of manufacturing companies adopt sustainable production practices

   • EUR 325 million investment attracted by EIT Ventures

   • 50 000 people trained and up- or re- skilled

   • Create 360 new solutions

   • 30% of material use is circular

 

Offshore wind energy is a key technology for generating renewable energies. Due to its complex processes regarding installation, operation and service, and therefore relatively high costs, offshore wind energy converters still cannot compete with today’s energy market prices. To create a competitive offshore WEC with a Levelised Cost of Electricity (LCoE) target of €35/MWh ReaLCoE takes a holistic approach and scrutinises costs in each link of the value chain.

As a key element of ReaLCoE, BIBA focusses on the digitisation of future offshore WECs and their adhered value chain. Besides the integration of sensors and the implementation of a condition-based monitoring system, the digital representation of the WECs through a digital twin (“product avatar”) takes a major part in BIBAs contribution to ReaLCoE. Building on this, a concept for predictive maintenance will be developed and realized. Furthermore, BIBA will develop optimised logistic and installation concepts and will conduct various performance simulations for a further reduction of supply chain and installation costs. To validate the concept, a technology platform for a first prototype of a digitised 12+MW turbine as well as a pre-series array of 4-6 WEC will be installed, demonstrated and tested.