i4Q

Industrial Data Services for Quality Control in Smart Manufacturing

Show project description Hide project description

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).

Duration 01.01.2021 - 31.12.2023, Funded by H2020

Contact persons

Projektlogo COgnitive Assisted agile manufacturing for a LAbor force  unterstützt durch vertrauenswürdige künstliche Intelligenz
Project website

COALA

COgnitive Assisted agile manufacturing for a LAbor force supported by trustworthy Artificial Intelligence

Show project description Hide project description

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.

Duration 01.10.2020 - 30.09.2023, Funded by H2020

Contact persons

Projektlogo Geschlossener digitaler Regelkreis für eine flexible und modulare Herstellung großer Komponenten

PeneloPe

Closed-loop digital pipeline for a flexible and modular manufacturing of large components

Show project description Hide project description

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.

Duration 01.10.2020 - 30.09.2024, Funded by H2020

Contact person


Project website

ASSURED

Future Proofing of ICT Trust Chains: Sustainable Operational Assurance and Verification Remote Guards for Systems-of-Systems Security and Privacy

Show project description Hide project description

ASSURED’s vision is to introduce a ground-breaking policy-driven, formally verified, runtime assurance framework in the complex CPS domain. As the demand for increasingly autonomous CPSs grows, so does the need for certification mechanisms to ensure their safety. Current methods towards software and system validation requires exhaustive offline testing of every possible state scenario PRIOR to fielding the system. In this context, novel assurance services ensure that the control output of such controllers does not put the system or people interacting with it in danger, especially in safetycritical applications as the ones envisaged in the ASSURED Demonstrators. ASSURED leverages and enhances runtime property-based attestation and verification techniques to allow intelligent (unverified) controllers to perform within a predetermined envelope of acceptable behaviour, and a risk management approach to extend this to a larger SoS. ASSURED elaborates over the coordination of deployed TEE agents in horizontal scope, encompassing numerous technologies applicable to everything from edge devices to gateways in the cloud. Such technologies DICE for binding devices to firmware/software, trusted execution environments, formal modelling of protocols and software processes, software attestation, blockchain technology for distributed verification of transactions between system elements and controlflow attestation techniques for enhancing the operational correctness of such devices. In this frame, we consider the mutual verification of system components in distributed multi-operator environments. Our approach ensures a smooth transition and advancement beyond current strategies where security management services are considered in an isolated manner relying on traditional perimeter security and forensics in a “catch-and-patch” fashion without dwelling on the safety of the overall network as a whole, to holistic network security services capable of minimizing attack surfaces.

Duration 01.09.2020 - 31.08.2023, Funded by H2020

Contact person

Isabella2.0

Automobile logistics in sea and inland ports: Integrated and user-oriented control of device and load movements through artificial intelligence and a virtual training application

Show project description Hide project description

Motivation

The results from Isabella generate first improvements of the initial situation and show further starting points for additional improvement. Our motivation is to take up these points and further improve the logistic performance of the control algorithm and to optimize it according to the specific situations. Moreover, an extension of the applicability of the control algorithm to the transhipment processes at different transport modes offers great potential to further improve the overall performance. In addition, it must not be ignored that the introduction of the solution approaches will be accompanied by radical changes in the work situations for the employees. Therefore, we are furthermore motivated to integrate the employees into the development of the new solutions such that overall we gain better acceptance of the final solution.

Objective

The aim is to optimize the parameterization of the control algorithm and to extend the approach regarding multi-criteria optimization so that the optimization performance can be further improved taking into account the prevailing situation such as terminal filling level, vehicle mix, personnel availability, etc. A further goal is the systematic extension of the control algorithm to the processes for loading and unloading the modes of transport (ship, train and truck) and the creation of a virtual training application. It will take up the psychological aspects regarding work and organization that result from the process redesigns, facilitate the changeover for the employees and finally ensure the acceptance of the new solution.

Approach

By means of event-discrete simulation, we will investigate the performance of the control algorithm under different environmental conditions and parameter settings. To this end we will use methods of sensitivity analysis and artificial intelligence and aim to draw conclusions between performance, terminal situation and parameter settings. As a result, it will be possible to adjust the control algorithm to the respective terminal situation and to increase the predictability of the operative processes. In addition, new data analysis methods and artificial intelligence approaches will be applied to systematically derive relevant process parameters from operationally acquired data, such as the duration of individual process steps or track utilisation. For the extension of the applicability of the control system to the modes of transport (train, ship, truck), a concept for data reception in ships and railway wagons will be designed. To this end, we will consider ad-hoc and mesh networks in combination with suitable radio standards such as WLAN, Bluetooth or LoRa.

Duration 01.07.2020 - 30.06.2023, Funded by BMVI

Contact persons