Conception of a Reference Architecture for Machine Learning in the Process Industry

Wöstmann, René; Schlunder, P.; Klinkenberg, Ralf; Kimberger, Josef; Spichtinger, Andrea; Goldhacker, Markus; Deuse, Jochen

doi:10.1109/bigdata50022.2020.9378290

Cited by 7 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, none of the existing work adequately addresses competence development in an integrated role model. Therefore within the research project DaPro (Data-driven process optimisation based on machine learning in the beverage industry) (Wöstmann et al 2019), transdisciplinary role models were defined based on the preliminary work of the InDaS project and the DPDA (Data Preparation for Data Analytics) project group (Stark et al 2019) The basis for both the delimitation of the roles and the design of the competence profiles is formed by iterative workshops both in the prostep Group DPDA and within the DaPro project with practitioners from manufacturing industry, mechanical engineering companies, Data Scientists, IT companies and research institutes. The disciplines of the competences were expressed with different competence levels.…”

Section: Detailing Transdisciplinary Categories and Competencesmentioning

confidence: 99%

“…Citizen Data Scientist study on the use of ML to optimise malt yield at the Bitburger Braugruppe (Wöstmann et al 2020).…”

Section: Case Study In the Beverage Industrymentioning

confidence: 99%

“…Having also developed a brewery specific reference architecture (Figure 9) within the research project DaPro for developing ML-based use cases it is necessary to map the interface partners, which are actively involved in the use case, to key elements of the ML architecture. (Wöstmann et al 2020). value creation The key project handler in data science projects is the CDS.…”

Section: General Matching Of the Role Model And Project Organisationmentioning

confidence: 99%

“…Having implemented this use case several steps had to be solved along the project cycle. Beside finding and defining the use case itself it was also necessary to set up a ML-architecture (Figure 9), find all necessary data sources, built up a data pipeline for data understanding and preparation which was presented in more detail in (Wöstmann et al 2020). Enhancing a reliable standardized project management method to MLbased use cases has helped to find the common thread for both data science and ordinary project management.…”

Section: Exemplary Industrial Application Scenario Of Malt Yield Predictionmentioning

confidence: 99%

See 3 more Smart Citations

This is how we learn - A Best Practice Case of Qualification in SMEs for Work 4.0

Deuse¹,

Wöstmann²,

Schulte³

et al. 2021

Competence Development and Learning Assistance Systems for the Data-Driven Future

Self Cite

View full text Add to dashboard Cite

Increasing digitalisation is fundamentally changing the understanding and possi-bilities of value creation as well as labour organisation. The systematic collection, storage and analysis of data is becoming a decisive competitive factor and is the basis for intelligent products, processes and production technology. This results in new competence requirements and roles in mechanical and plant engineering and in the manufacturing industry in general. Machine Learning in particular, as the basis of Artificial Intelligence, poses great challenges for companies, as the demand for experts, so-called Data Scientists, significantly exceeds the offer and furthermore, these experts rarely have the required domain knowledge - the core competences of manufacturing companies. In this context, the new job descrip-tion of the Citizen Data Scientist as a link between the most important disci-plines of information technology, domain knowledge and data science enters the focus of attention. The article presents a role model as a basis for team building and systematic development of required competences in the manufacturing in-dustry and combines the results of various research projects and industrial im-plementations. For this purpose, competences of the future are derived in sec-tion 1 and transferred into a transdisciplinary role model in section 2. Section 3 addresses the exemplary practical application in an industrial use case, while section 4 gives an outlook on the possibilities of target-oriented competence development for the individual roles and actors.

show abstract

Section: Detailing Transdisciplinary Categories and Competencesmentioning

confidence: 99%

“…Citizen Data Scientist study on the use of ML to optimise malt yield at the Bitburger Braugruppe (Wöstmann et al 2020).…”

Section: Case Study In the Beverage Industrymentioning

confidence: 99%

Section: General Matching Of the Role Model And Project Organisationmentioning

confidence: 99%

Section: Exemplary Industrial Application Scenario Of Malt Yield Predictionmentioning

confidence: 99%

See 2 more Smart Citations

This is how we learn - A Best Practice Case of Qualification in SMEs for Work 4.0

Deuse¹,

Wöstmann²,

Schulte³

et al. 2021

Competence Development and Learning Assistance Systems for the Data-Driven Future

Self Cite

View full text Add to dashboard Cite

show abstract

“…The collection, integration, and analysis of such data enable companies to implement new types of services [1]. Examples documented in the literature include predictive maintenance services for machinery and equipment, process mining for determining bottlenecks in complex production environments, fine-tuning of recipes and sequences for process manufacturing [2], optimization of plant availability, energy management, monitoring and analysis of production and logistics processes [3], and new approaches to the management of packaging [4]. The context of most of these scenarios is not an isolated workplace or an individual asset but an environment with a variety of components embedded in large processes.…”

Section: Introductionmentioning

confidence: 99%

Cooperative Approaches to Data Sharing and Analysis for Industrial Internet of Things Ecosystems

et al. 2021

View full text Add to dashboard Cite

The collection and analysis of industrial Internet of Things (IIoT) data offer numerous opportunities for value creation, particularly in manufacturing industries. For small and medium-sized enterprises (SMEs), many of those opportunities are inaccessible without cooperation across enterprise borders and the sharing of data, personnel, finances, and IT resources. In this study, we suggest so-called data cooperatives as a novel approach to such settings. A data cooperative is understood as a legal unit owned by an ecosystem of cooperating SMEs and founded for supporting the members of the cooperative. In a series of 22 interviews, we developed a concept for cooperative IIoT ecosystems that we evaluated in four workshops, and we are currently implementing an IIoT ecosystem for the coolant management of a manufacturing environment. We discuss our findings and compare our approach with alternatives and its suitability for the manufacturing domain.

show abstract

Establishing a Machine Learning and Internet of Things Learning Infrastructure by Operating Transnational Cyber-Physical Brewing Labs

Deuse,

Wöstmann,

Syberg

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Conception of a Reference Architecture for Machine Learning in the Process Industry

Cited by 7 publications

References 30 publications

This is how we learn - A Best Practice Case of Qualification in SMEs for Work 4.0

This is how we learn - A Best Practice Case of Qualification in SMEs for Work 4.0

Cooperative Approaches to Data Sharing and Analysis for Industrial Internet of Things Ecosystems

Establishing a Machine Learning and Internet of Things Learning Infrastructure by Operating Transnational Cyber-Physical Brewing Labs

Contact Info

Product

Resources

About