Research Programme

Research programme

Integrated training and demonstration platform

Existing aerospace manufacturing demonstration cell

  • Testbed IT Infrastructure
  • Data Capture
  • Position Monitoring and Inspection Infrastructure
  • Tooling Set
  • Robotic Equipment

Enchancements from DiManD

  • Integration into Cyber-Physical System
  • Autonomous Context-Aware Operation
  • Agent-Based Control and Configuration
  • Cyber Security


DiManD aims to develop a high-quality multidisciplinary, multi-professional and cross-sectorial research and training framework for Europe with the purpose of improving Europe’s industrial competitiveness by designing and implementing an integrated programme in the area of intelligent informatics driven manufacturing that will form the benchmark for training future Industry 4.0 practitioners.

To achieve this, the consortium brings together a multidisciplinary and multi-sector, pan-European partnership drawing skills from world leading research centres across Europe with an established track record in multidisciplinary and internationally leading transformative research supported by a number of high value multinational manufacturing companies and small and medium size companies. The aim is supported by the following objectives:

  1. To provide a comprehensive and appropriate set of training and development activities for ESRs comprising network wide modules, courses and events, both technical and non-technical, and specific development activities, including the Integrated Training and Demonstration Platform as a legacy on which future developments can be built, to elevate the status of ESRs to become Digital Manufacturing Ambassadors (WP2).
  2. To create the system framework to standardised architectures and methodologies that facilitate the development of cyber-physical production resources and the necessary ICT infrastructure that enables the seamless integration of these into cyber-physical systems (WP3).
  3. To design and develop a control concept and underpinning data models for autonomous behaviour adaptation of distributed manufacturing systems based on context-aware autonomous systems (WP4).
  4. To analyse and apply new ICT trends, such as Big Data, Cyber Physical Systems and Data Mining, in manufacturing systems to enable more efficient processing of data for control and configuration and advanced diagnostics and monitoring purposes that at the same time provide security and privacy by design without compromising the need to share data between different organisations in the manufacturing chain (WP5), advancing technology from TRL 1 to 8.
  5. To ensure that the results of the DiManD programme are effectively communicated to European industry, associations, stakeholders (including universities, research and technology organisations), and the public domain. To provide effective academic dissemination for the ESR individual projects including major papers in high impact open access journals and presentations at leading national and internationally leading conferences (WP6).

The structure of DiManD comprises of 6 work-packages focused on addressing a series of key scientific challenges by a well-structured and complementary research project and unique integrated training programme to deliver future industrial and academic leaders in Digital Manufacturing. The strong multidisciplinary and inter-sectoral team combines the individual expertise of the universities, research institutes and industrial partners to deliver the required competencies to develop the proposed research projects and provide world leading training to the researchers. The ESR technical programme is organised into three research themes (WPs 3-5) supported by management (WP1), training (WP2) and  dissemination (WP6) activities. The research themes are described below:


Research themes
WP1: Project management, Governance and Coordination. (MGEP)
WP2: Network-Wide and Individual Training. (MGEP)

WP3: Integration of computation, networking and physical processes into cyber-physical systems. ESR 4, 5, 6, 7, 10. (KTH)

WP4: Autonomous, context-aware manufacturing platforms. ESR 1, 8, 9, 12, 13, 14. (UNOTT)

WP5: Informatics, big data, and agent based control and configuration. ESR 2, 3, 11. (UNI NOVA)

WP6: Dissemination and Exploitation. (ITIA)


  • WP 3: Integration of computation, networking, and physical processes into cyber-physical systems

Cyber-Physical Systems (CPSs) comprise of collaborating computational elements controlling physical entities. Recent developments have resulted in higher availability and affordability of sensors, data acquisition systems and computer networks which will support the transformation of existing manufacturing lines into CPSs, transforming today’s factories into an Industrie 4.0 factory.

ESR4 will examine the user interaction experience with CPSs based on a human driven innovation approach. An appropriate human centered design method will be developed, which will allow creating advanced CPS related product-services in Industrie 4.0 scenarios. ESR5 will develop methodology and tools for simulation-based design and testing of CPSs using digital twins. ESR6 will develop a cyber-physical framework based on IoT to handle the End-Of-Life cycle of mechatronic products for home automation. ESR7 will develop innovative and efficient methods and reconfigurable tools for handling miniaturized electrooptical components for the development of selective, flexible and efficient manufacturing and remanufacturing of PCBs and effective implementation of backplanes with embedded three dimensional optical parts. ESR10 will focus on the development of agent based cyber physical systems with a strong emphasis on self-learning, requiring learning, context and big data to implement it. Note: all the ESR will be backed up with a business model methodology to ensure that all stakeholders in the production of the given scenario are accounted for and supported in the value creation stages.

  • WP 4 Autonomous, context aware manufacturing platforms

Future manufacturing systems will require the ability to collect data, identify their own status and capability, and take autonomous decisions according to changes in the system and surrounding environment. Instead of programming instructions to passive machines and equipment, humans and control agents will continuously maintain a range of collaborative interactions forming dynamic and diverse manufacturing coalitions exhibiting collective emergent behaviours through a combination of selforganisation and dynamic  responsiveness. To realise this vision, a fundamental break with traditional manufacturing systems design and control methods is required by establishing the science needed to understand, build and apply future autonomous manufacturing systems.

ESR1 will consider the overall architecture of an autonomous, context aware manufacturing platform, developing a semantic model accessible to self-learning and self-adaptation. The remaining projects in this work package will consider the implementation of autonomous, context aware manufacturing platforms. The applications chosen are all industry relevant and will address different challenges in realising such manufacturing platforms. ESR8 will consider the development of a reconfigurable assembly line for an automotive alcohol-sensor. ESR9 will consider a door assembly station for the automotive industry, to enable full reconfigurability of the robot and its peripheral equipment for future variants and new products. ESR12 will specifically consider the automation of manufacturing robots, enabling them to quickly move between jobs while working alongside humans. ESR13 will focus on developing a cognitive robot for the inspection of healthcare products. ESR14 will develop an intelligent (test) instruments for application within assembly systems using, for example, plug-and-produce concepts, product-driven production, data collection and analytics through cloud-based services.

  • WP 5: Informatics, big data, and agent based control and configuration

Recent technological developments in and around networks, cloud-based solutions, machine performance, etc. have led to many new research opportunities and solutions. These new technologies and paradigms will be assessed for application in manufacturing environments at the different levels and the main benefits of applying these new informatics based trends and techniques to optimise and increase the overall  performance of the systems. Moreover their applicability to new market trends such as mass customization and quality requests will be investigated.

Agent based industrial systems have appeared as a promising technology to deal with the new requirements in manufacturing, such as flexibility, modularity, reduced ramp-up and plugability. However, as a novel technology and trend it is important to understand what are the main challenges and barriers in the penetration of various industries. An important aspect is to study methodologies and techniques to extract knowledge from big data arising at the shop floor. This extracted and generated knowledge can be important for the companies to optimise the process, giving to the manufacturing systems the capability to adapt and adjust according to the context.

The modular and pluggable CPSs are usually implemented as multi agent environments. The possibility of control and/or configure the manufacturing systems, constituted for different modules and abstracted for different informatics entities, which communicate and work in society, constituting a CPS will be explored. With the new modular and distributed CPS based manufacturing systems, the traditional and monolithic approach to perform diagnosis and monitoring are not capable to adapt and change frequently. In this sense, new distributed and adaptable diagnosis and monitoring solutions will be explored and studied, such as the usage of Artificial Immune Systems to perform diagnosis or distributed SCADA systems. ESR 2 will focus on developing machine learning techniques to allow self-learning within a regulated environment. ESR3 will consider appropriate design methods validated in different European manufacturing sectors in order to design advanced services
in Industrie 4.0 scenarios. ESR11 will focus on big-data techniques to implement energy saving solutions for industrial systems based on agent based cyber physical components. 


The research programme will deliver a dramatic step change by increasing manufacturing productivity and enhancing global competitiveness of the European manufacturing sector as well as contributing to job creation by offering for the first time a new holistic approach to both research and training in Manufacturing Informatics. It breaks with traditional approaches to research and is predicated on three key research challenges: (i) big data analytics, (ii) industrial Internet of Things and (iii) autonomous systems control which are at the core of the Industrie 4.0 vision. The research will ultimately enable a compressed product life cycle through the delivery of robust and compliant manufacturing systems that can be rapidly configured and optimised, thus reducing production ramp-up times and programme switchovers. This will be demonstrated through the development of the Integrated Training and Demonstration Platform, which is part of WP2. This platform will build on the already existing Aerospace Manufacturing Demonstration Cell at UNOTT by allowing the researchers to add their technical developments as part of DiManD into the existing cell which consists of Testbed IT Infrastructure, Data Capture, Position Monitoring and Inspection Infrastructure, Tooling Set and Robotic Equipment.