Digital Industry

Digital Industry value chain vision: Digitised control systems with advanced sensing, automated defect classification, virtual metrology and the implementation of a digital tacit knowledge platform are the clear vision for semi- autonomous AI supported production environment for a sustainable and resilient European Digital Industry. The value chain integrates the edge AI technological developments into six demonstrators.

VCD 1.1: Smart Semiconductor Manufacturing Assistant (SSMA) demonstrator (lead: IFAT, SCUBE, TUWIEN) – aims to develop a decision support tool (SSMA) to establish AI-based causal links between the databases of the three pillars to quickly identify, predict, classify potential risks, and support the engineer in decision making.

VCD 1.2: Virtual Metrology demonstrator (lead: AMS-AT, SCUBE) – aims at implementation of a sophisticated use of tool sensor data with Machine Learning algorithms to predict the outcome and increase efficiency of the production line. Due to time critical decisions the process of prediction is required to deliver results virtually in real-time, which makes it necessary to make the data available accordingly.

VCD 1.3: Depth Computation at the Edge demonstrator (lead: AMS-CH, SYNS) – is aiming at establishing the possibility to use ML in an end-to-end manner to perform computations (to process the raw signal and create depth representations) efficiently as close as possible to the sensor.

VCD 1.4: Distributed sensing – Large-scale Object Recognition demonstrator (lead: COGNI, INTRA, GNT) – aims to demonstrate a Distributed Multisensory System with integrated AI-capabilities (including segmentation, feature extraction), capable of independent functioning and data processing. An edge-based approach offers the following advantages: it enables real-time use and decreases the dependence on cloud-based services, thus improving user-privacy and eliminating the necessity of a fast internet connection for transferring large amounts of data.

VCD 1.5: AI-based Quality Control for Woodwork Production Process demonstrator (lead: SCM, DEEPS, STM, UNIBO, UNICA, UMIL, XTE) – aims of developing a range of edge AI algorithms integrated into a custom edge AI-based application for identification of defects in furniture production processes.

VCD 1.6: AI-based Defect Detection in SoM Assembly Process demonstrator (lead: HTS, DEEPS, STM, UNIBO, UNICA, UMIL, XTE) – aims at demonstration the use of edge AI to automate industrial production control in System-on-Module (SoM) and to improve the responsiveness of the analysis, allowing for provision of prompt feedback to production chain control. The analysis will be based on HD images of the produced items, acquired with existing Automated Optical Inspection (AOI) machinery such as, the OMRON AOI station currently used at the HTS labs for manual quality control.

Share This