Specification of FAIRWork Use Case and DAI-DSS Prototype Report
Aleassandro Cisi, Roland Sitar, Wilfrid Utz, Christian Muck, Patrik Burzynski, Robert Woitsch, Magdalena Dienstl, Marlene Mayr, Remi Lanza, Rishyank Chevuri, Sylwia Olbrych, Johanna Werz, Alexander Nasuta, Stefan Böschen, Noushin Gheibi, Higor Rosse, Lucas Paletta
Deliverable D2.1 specifies the design requirements for the first relevant stage in the Horizon Europe project FAIRWork aiming at fair decision making within complex systems in the production domain. From the planned use cases of the industrial partners – FLEX “Automated Test Building”, “Worker Allocation”, “Machine Maintenance After Breakdown” and CRF “Workload Balance”, “Delay of Material” and “Quality Issues” – the report constitutes and specifies the basic design decisions for research and development directions in the project. A major contribution is the provision of the initial architecture of an innovative service framework for decision support systems.
The first part of the report is dedicated to the design thinking approach as an efficient choice for the analysis of user requirements. The planned use case scenarios were primarily examined from a user-driven perspective. In several workshops a participatory process was applied in order to deduce the most substantial design decisions from the results of the highly interactive sessions. A model-based approach of the design process was chosen in order to determine the user requirements that were consequently defined and described in detail. In this way, the knowledge about a use case was externalised in the form of conceptual representations, using domain-specific modelling languages that are suitable and provide the required construct for representation and processing. In a further step, the high-level scenarios were designed in a collaborative, interactive, and agile environment involving experts from different backgrounds. Processes are the outcome of this structured approach requiring support for: “finding similar projects”, “find relevant experts”, “simulate production process”, “allocate worker”, “map workers with profiles”, “find similar problems”, “reschedule production line”, “allocate order to production line”, “assess the impact”.
In the second part, we give an overview about the key challenges of FAIRWork. In the current production industry there is a need to make the current automated and hierarchical structured production processes more flexible. At the same time digitalization with AI support is seen as a key enabler for more energy efficient and resource efficient services, products or business models, by also enabling process optimization in the overall production process. Therefore, we describe in more detail the main challenges technical challenges such as configuration, resource allocation, and selection aspects. These three challenges are highly relevant for making the process more flexible, adaptive, and resource efficient by using the relevant AI-based decision strategies in our complex distributed decision-making. At the end, the trustworthy AI aspect is a further key challenge to get AI accepted by the involved humans and also utilize its potential.
In the third part, the overall methodology of making complex decision-making is outlined. Within this chapter, we describe the overall procedure for implementing complex decision-making processes. Therefore, this chapter gives an overview about relevant concepts for the research direction and implementation of such complex decision making by using AI services. In FAIRWork, AI is used in all our scenarios to automate processes or to make their processes more resource-efficient. Since humans are an important part of the overall decision process, trust in AI and human factors plays an essential role, therefore these aspects are explained. Finally, the technical concepts for a concrete implementation such as digital knowledge base, digital twin, digital shadow, will be discussed as well. Finally, it follows the explanation about the orchestration of decision-making processes by using Microservices.
In the fourth part, the initial architecture of the project is presented based on the overall project objectives and requirements. Key components of the FAIRWork service framework are motivated, described, and their relevant features are presented. A detailed description of these components is given in Deliverable D4.1 including the technical implementation of the basic core services or application specific services.
Finally, the initial design of the FAIRWork’s architecture is compared with most relevant technical architectures that are commonly used in the industry environment domain, such as, Gaia-X, FIWARE, International Data Space, and RAMI.
The first part of the report is dedicated to the design thinking approach as an efficient choice for the analysis of user requirements. The planned use case scenarios were primarily examined from a user-driven perspective. In several workshops a participatory process was applied in order to deduce the most substantial design decisions from the results of the highly interactive sessions. A model-based approach of the design process was chosen in order to determine the user requirements that were consequently defined and described in detail. In this way, the knowledge about a use case was externalised in the form of conceptual representations, using domain-specific modelling languages that are suitable and provide the required construct for representation and processing. In a further step, the high-level scenarios were designed in a collaborative, interactive, and agile environment involving experts from different backgrounds. Processes are the outcome of this structured approach requiring support for: “finding similar projects”, “find relevant experts”, “simulate production process”, “allocate worker”, “map workers with profiles”, “find similar problems”, “reschedule production line”, “allocate order to production line”, “assess the impact”.
In the second part, we give an overview about the key challenges of FAIRWork. In the current production industry there is a need to make the current automated and hierarchical structured production processes more flexible. At the same time digitalization with AI support is seen as a key enabler for more energy efficient and resource efficient services, products or business models, by also enabling process optimization in the overall production process. Therefore, we describe in more detail the main challenges technical challenges such as configuration, resource allocation, and selection aspects. These three challenges are highly relevant for making the process more flexible, adaptive, and resource efficient by using the relevant AI-based decision strategies in our complex distributed decision-making. At the end, the trustworthy AI aspect is a further key challenge to get AI accepted by the involved humans and also utilize its potential.
In the third part, the overall methodology of making complex decision-making is outlined. Within this chapter, we describe the overall procedure for implementing complex decision-making processes. Therefore, this chapter gives an overview about relevant concepts for the research direction and implementation of such complex decision making by using AI services. In FAIRWork, AI is used in all our scenarios to automate processes or to make their processes more resource-efficient. Since humans are an important part of the overall decision process, trust in AI and human factors plays an essential role, therefore these aspects are explained. Finally, the technical concepts for a concrete implementation such as digital knowledge base, digital twin, digital shadow, will be discussed as well. Finally, it follows the explanation about the orchestration of decision-making processes by using Microservices.
In the fourth part, the initial architecture of the project is presented based on the overall project objectives and requirements. Key components of the FAIRWork service framework are motivated, described, and their relevant features are presented. A detailed description of these components is given in Deliverable D4.1 including the technical implementation of the basic core services or application specific services.
Finally, the initial design of the FAIRWork’s architecture is compared with most relevant technical architectures that are commonly used in the industry environment domain, such as, Gaia-X, FIWARE, International Data Space, and RAMI.
Links
Cite as
BibTeX (Download)
@techreport{fairwork_d2.1,
title = {Specification of FAIRWork Use Case and DAI-DSS Prototype Report},
author = {Aleassandro Cisi, Roland Sitar, Wilfrid Utz, Christian Muck, Patrik Burzynski, Robert Woitsch, Magdalena Dienstl, Marlene Mayr, Remi Lanza, Rishyank Chevuri, Sylwia Olbrych, Johanna Werz, Alexander Nasuta, Stefan Böschen, Noushin Gheibi, Higor Rosse, Lucas Paletta},
editor = {Herwig Zeiner},
url = {https://fairwork-project.eu/deliverables/D2.1_Specification%20of%20FAIRWork-v1.0a-preliminary.pdf},
year = {2022},
date = {2022-02-28},
urldate = {2022-02-28},
abstract = {Deliverable D2.1 specifies the design requirements for the first relevant stage in the Horizon Europe project FAIRWork aiming at fair decision making within complex systems in the production domain. From the planned use cases of the industrial partners - FLEX “Automated Test Building”, “Worker Allocation”, “Machine Maintenance After Breakdown” and CRF “Workload Balance”, “Delay of Material” and “Quality Issues” - the report constitutes and specifies the basic design decisions for research and development directions in the project. A major contribution is the provision of the initial architecture of an innovative service framework for decision support systems.
The first part of the report is dedicated to the design thinking approach as an efficient choice for the analysis of user requirements. The planned use case scenarios were primarily examined from a user-driven perspective. In several workshops a participatory process was applied in order to deduce the most substantial design decisions from the results of the highly interactive sessions. A model-based approach of the design process was chosen in order to determine the user requirements that were consequently defined and described in detail. In this way, the knowledge about a use case was externalised in the form of conceptual representations, using domain-specific modelling languages that are suitable and provide the required construct for representation and processing. In a further step, the high-level scenarios were designed in a collaborative, interactive, and agile environment involving experts from different backgrounds. Processes are the outcome of this structured approach requiring support for: “finding similar projects”, “find relevant experts”, “simulate production process”, “allocate worker”, “map workers with profiles”, “find similar problems”, “reschedule production line”, “allocate order to production line”, “assess the impact”.
In the second part, we give an overview about the key challenges of FAIRWork. In the current production industry there is a need to make the current automated and hierarchical structured production processes more flexible. At the same time digitalization with AI support is seen as a key enabler for more energy efficient and resource efficient services, products or business models, by also enabling process optimization in the overall production process. Therefore, we describe in more detail the main challenges technical challenges such as configuration, resource allocation, and selection aspects. These three challenges are highly relevant for making the process more flexible, adaptive, and resource efficient by using the relevant AI-based decision strategies in our complex distributed decision-making. At the end, the trustworthy AI aspect is a further key challenge to get AI accepted by the involved humans and also utilize its potential.
In the third part, the overall methodology of making complex decision-making is outlined. Within this chapter, we describe the overall procedure for implementing complex decision-making processes. Therefore, this chapter gives an overview about relevant concepts for the research direction and implementation of such complex decision making by using AI services. In FAIRWork, AI is used in all our scenarios to automate processes or to make their processes more resource-efficient. Since humans are an important part of the overall decision process, trust in AI and human factors plays an essential role, therefore these aspects are explained. Finally, the technical concepts for a concrete implementation such as digital knowledge base, digital twin, digital shadow, will be discussed as well. Finally, it follows the explanation about the orchestration of decision-making processes by using Microservices.
In the fourth part, the initial architecture of the project is presented based on the overall project objectives and requirements. Key components of the FAIRWork service framework are motivated, described, and their relevant features are presented. A detailed description of these components is given in Deliverable D4.1 including the technical implementation of the basic core services or application specific services.
Finally, the initial design of the FAIRWork’s architecture is compared with most relevant technical architectures that are commonly used in the industry environment domain, such as, Gaia-X, FIWARE, International Data Space, and RAMI.
},
howpublished = {https://fairwork-project.eu/deliverables/D2.1_Specification%20of%20FAIRWork-v1.0a-preliminary.pdf},
keywords = {deliverable},
pubstate = {published},
tppubtype = {techreport}
}