The FLASH-COMP project – which is using AI to transform quality control in manufacturing – now has an up-and-running data space, which will form the cornerstone of the project’s novel Decision Support System (DSS). By housing databases, applications, and AI algorithms to support decision-making, the data space provides the fuel for the DSS that will eventually empower operators to manage production quality and make operational decisions that ensure products are manufactured right first time.

FLASH-COMP has successfully completed the initial phase of its systemic data management work, which lays the foundation for its novel Decision Support System (DSS) that will run off data gathered from defect estimation and inspection and monitoring tools.

At the laboratories of FLASH-COMP partner MSI, a data space has now been established conforming to specifications outlined by the International Data Space Association (IDSA). Within this space, simulations have been carried out of data derived from composite manufacturing processes monitored by partners, using inspection tools such as cameras and sensors.

In addition to hosting these various data sources, the data space also accommodates a range of applications, including AI algorithms, designed to support FLASH-COMP systems. Essentially, the data space serves as a central hub containing all necessary data, applications, algorithms, and AI systems for the FLASH-COMP solution, all of which will be integrated into the FLASH-COMP DSS.

Data governance rules for the space are also being developed and these will establish different user profiles and regulate access to sensitive data to ensure proper control over data usage and commercial exploitation.

The data space offers functionalities such as monitoring data flow and simulating the entire data processing pipeline, from collection to presentation, in the two FLASH-COMP use cases. Additionally, it incorporates an Asset Administration Shell (AAS) Registry Server for developing digital twins, enabling MSI to create digital replicas of real hardware and inspection tools. The data being collected by the partners’ various inspection and monitoring tools is being supplemented by synthetic data so that AI-generated simulations can be developed.

Presently, these efforts are based on a passive server, showcasing project elements without active connections. One of the topics for future discussion is whether to implement the next level of AAS in this project: reactive AAS, which obtains the status of the inspection and monitoring tools, and proactive AAS, which interacts with them and can directly change their properties.

An illustrative example of data flow as it is at this first phase involves the monitoring of composite material flow using cameras. By analysing data on bubble formation in the material, for example, quality standards can be quickly assessed and potential risks to product quality identified and corrected.

Moving forward, the plans are to integrate all components into a cohesive test bed for the inspection and monitoring tools and analysis of the data they collect. This integrated approach will enable comprehensive data collection and analysis, leading to the development of a robust DSS dashboard to support operators in managing production processes and ensuring product quality.

In essence, the data space serves as the cornerstone of the FLASH-COMP system and this development is a key milestone in the project. Providing a centralised platform for data aggregation, AI integration, and decision support facilitates data-driven decision-making. This will mean that process engineers and operators can now receive actionable insights in real time, ensuring the decisions they make throughout the production lifecycle will lead to better quality products that are delivered right first time, saving costs, energy, and material waste throughout the manufacturing process.
www.flashcomp.com

Tweet