Objective

In the manufacturing industry, the blasting process is an essential process step in the field of surface treatment with far-reaching effects on the quality of the end products, but it is subject to a number of problems. These problems are, for example, excessive equipment wear, inconsistent process results, and excessive abrasive consumption, and consequently lead not only to high monetary expenses for process users, but also to avoidable environmental impacts in the form of waste, scrap, power consumption, and emissions.

AI, in combination with a Digital Twin (DZ), can form a Smart Platform to enable real-time monitoring of blasting processes, detect equipment failures at an early stage and consequently enable more sustainable Manufacturing. AI as a new analytics component is instrumental in efficiently solving previous application limitations related to big data (e.g., limited, missing, or erroneous data), as small-data approaches can be used to extract information work relevant to the application context.

Overall, there is a lack of intelligent analysis capabilities in beam applications for evaluating the data basis. As a result, valuable optimization potential is wasted at the expense of process efficiency and the environment. Furthermore, there is a lack of user-friendly and customized processing of data and findings for the various parties involved (from the store floor to management) as well as the necessary competencies in dealing with the resulting blasting process data and their economic and ecological consequences.

Against the background of the challenges presented, the research partners aim to research and develop a Smart Platform for blasting processes. This platform is to use advanced analytics methods to evaluate and process a Digital Beam Process Twin based on Small Data and Big Data in real time and to integrate it into the system and process landscape of the users. Thus, for the first time, a cross-industry transparent, reproducible and resource-efficient blasting process shall be enabled.

Procedure

Recoveredthe SPIN:S data basis: Determination of the process and system architecture requirements at the application partners for the derivation of a Small and Big Data knowledge base for the digital mapping of the blasting process and a measurement and sensor system based on it.

Development of the SPIN:S platform: interface development for bidirectional data exchange with the existing process landscapes as well as labeling of the data base. Development of AI-based predictive analytics methods taking into account the specifics of the blasting process and their integration into existing processes.

Validation of the SPIN:S platform: design, development and testing of user-specific beam process and sustainability cockpits as well as evaluation of the SPIN:S user cockpits and derivation of lessons learned.

Project duration

October 2022 until September 2025

Project consortium

Supplier and consortium leader: Eisenwerk Würth GmbH

Technology expert: 3D Content Logistics GmbH

Research partner: Karlsruhe University of Applied Sciences (ILIN)

Collaborators

• Prof. Dr. Steffen Kinkel
• Sebastian Beiner
• Elena Stolz

This Research and Development Project is funded by the Federal Ministry of Education and Research (BMBF) in the program "Future of Value Creation - Research on Manufacturing, Services and Information Work" (funding code: 02L19C250) and supervised by the Project Management Agency Karlsruhe (PTKA). The responsibility for the content of this publication lies with the author.