Name: An AutoML-powered Digital Twin Solution for Manufacturing Environments

Abstract: AuToWin aims to develop and deploy an advanced Digital Twin tool leveraging automated machine learning (AutoML) to optimize predictive maintenance for manufacturing partners. Led by Dakik Yazılım and IOTIQ, together with automotive part manufacturer ERMETAL as the industry partner, the project will build upon the AuToWin Digital Twin platform to integrate real-time sensor data streaming from ERMETAL’s presses and use AutoML pipelines to automatically train models for anomaly detection, lifetime estimation, and failure prediction. Over 9 months, the solution will be tested and validated on ERMETAL’s production lines to achieve TRL7. Key objectives include reducing equipment downtime and failures through optimized maintenance planning, and decreasing maintenance costs through condition-based monitoring. Upon project completion, AuToWin will provide a user-friendly and interoperable Digital Twin solution empowering data-driven decision-making for optimized production workflows and sustainable operational excellence in manufacturing environments.

Name: Machine Vision Solution for Product Customization and Process Optimization in Bakery Industry

Abstract: The project proposes solutions that affect the bakery industrial sector in 2 parallel ways. First, 3D Reconstruction and Photorealistic Rendering hardware and software solutions are implemented to give customers a completely new product experience for the sector of industrial bakery, thus enabling the possibility for higher customization. Second, it enables the digitalization of production with the aim of reducing waste and energy consumption by adopting automatic process optimization rules.

Name: Development of simulation-based cloud computing and machine learning technology for next-generation coating process setup towards net zero by 2050

Abstract: Thickness is one of the key features of any coating. This project aims to develop a digital twin solution for democratisation of high-speed coating simulations for end-users. Using coatML, end-users will be able to save time, HPC resources and man hours thereby lowering the costs of industrial coating-measurements for different applications. Thus, coatML will increase the digitalisation level of the coating sector and provide large material savings boosting tomorrow’s decarbonised systems.

Name: Measuring production KPIs and tracing textile materials in the textile industry using a Real-Time Locating System

Abstract: The CottonTracer project proposes the installation of a Real-Time Locating System at the industry partner’s premises for tracking moving assets, such as the bins that the company uses for semi-finished product transportation. Tracking bins and using data analytics tools on the positioning data could provide useful insights about the processes of the manufacturing line. The project aims to export critical key performance indicators (KPIs) connected with the manufacturing processes.

Name: Decision support tool for sustainable Choices About end of Life strategies of manufacturing equipment

Abstract: At the End of the First Lifetime (EO1L) of a machine tool the assessment of its exploitable life for reuse is of paramount importance to boost sustainable and effective circular manufacturing. Therefore, the overall objective of this project is to develop a hybrid (AI + physics-based) Decision Support platform able to assess the actual exploitable life of machine components at EO1L, identify component that need to be replace/remanufactured and assess the total cost of reuse (second life time).

Name: Development and testing a prototype of a digital microscopy solution, with robotics, computer vision and AI, to digitalize fungi-based production processes for the food manufacturing industry

Abstract: FungAI introduces a digital solution, based in automated microscope-image AI-analysis, acting as a Decision Support System for manufacturing companies with fungi-based bioprocesses. LIBRE Foods, fungi-based food producers, is the Industry Partner. FungAI will lead to maximize economic cost-effectiveness of their process and produce greener high-quality products, with maximum yields. The goal of this 9-months Innovation Support Project is evolving our MVP at TRL4 to a tested prototype at TRL7.

Name: Adaptive Laser Seam Tracking for Optimized Welding Process Control

Abstract: LASERTOP seeks to enhance welding process control by integrating advanced laser seam tracking, machine learning, and real-time adaptive control algorithms. The project will extend SkyBlue Laser tracker functionality with advanced adaptive control for welding processes. The solution will address issues at BRAIKO LTD, the industry partner, and offer a real test field for this Industry 4.0 solution designed for advanced welding processes.

Name: Enhancing Roll Forming Processes through Industry 4.0 and IoT-based Modernization

Abstract: Roll forming is a cost-effective metal shaping method extensively used in automotive, aircraft, construction industries to create unique profiles. PLC-based automation systems are employed in roll-forming machinery. However, operator mistakes can lead to production failures, material wastage, time and energy loss.

To overcome these issues and boost operational efficiency, we seek to integrate intelligent solutions. Our goal is to reduce errors, minimize waste, expenses and optimize energy usage.

Name: Optimizing Manufacturing with AI-powered Execution System

Abstract: The subject of the project; is the development of a software system and IoT hardware that will collect machine data and present executive reports digitally through Industry 4.0 applications such as Big Data, IOT, Artificial Intelligence and Smart-Flexible Automation Systems for the digitization and optimization of the manufacturing industry.

Name: Predictive Quality Models for Automotive

Abstract: Our proposal aims to overcome the limitations of traditional process control methods by integrating Cycle Analysis (CA), SPCi4.0, and ‘Adaptive Sampling’ AI models to detect, predict, and optimize quality defects. The solution relies on real-time analysis of machine sensors and inline quality control (IQCU) data. The collected data is then used to provide production insights through AI models and optimize the quality control activities of both the supplier and car makers.

Name: imProved RObot guidanCe by meanS of 2D viSion system

Abstract: EU industry, following the road to electrification, is developing many automation solutions for the production and disassembly of battery modules which require vision-guided robots suited to cover extended field of views minimizing the installation complexity and specialized personnel for their maintenance. To achieve these goals, PROCESS 2D aims to create a 3D robot guidance system based on 2D cameras, an iterative approach and one agnostic SW regarding camera brands, controllers, and robots.

Name: Customer Premises Microservices-Based Solution for Manufacturing Quality Control 

Abstract: Qual40 aims to enhance the digitalisation level of the industry by elevating the TRL of Customer Premises Microservices-Based Solution for Manufacturing Quality Control from TRL-4 to TRL-7 within a period of 9 months.

This goal will be collaboratively accomplished by BBRD creating a collection of microservices as an extensible on-site solution, PlusClouds centralising AI metrics via a secure cloud orchestrator, and Isuzu Automotive piloting & validating solution at its Quality Control Division.

Name: Indoor/Outdoor Autonomous Factory Carrier Robot for Material Transport

Abstract: RobiCarr project aims is to develop an innovative autonomous platform capable of towing and carrying cargo within manufacturing facilities.
RobiCarr with a capability of indoor and outdoor operations, integrates cutting-edge technologies, including LIDAR, cameras, GPS-INS devices, and HD maps, providing a smart solution for material handling and transportation in manufacturing facilities. It has advanced features like obstacle detection, traffic light recognition, lane-changing, and swerving.

Name: Autonomous Indoor Building Digitalisation for MEP Manufacturers

Abstract: Mechanical Electrical Plumbing (MEP) contractors/manufacturers are required to physically visit each site to get the asset’s structural dimensions and characteristics ensuring that the manufacturing of MEP system complies with the building’s ‘as-built’ physical specifications. The SITE2MACHINES solution autonomously digitalizes building assets, delivering structural data in a safe, accurate, and fast manner, connecting the physical building with the digital layouts of indoor application systems.

Name: Decentralized AI-based Predictive Maintenance System for Robotics Arms in Manufacturing Plants

Abstract: The project aims to implement the concept of Decentralised AI using federated learning to solve the problem of predictive maintenance without the need for any external cloud integration. This allows manufacturing companies to effectively utilise AI-based predictive maintenance with greater control of process data and eliminate losses due to unplanned downtime. Our project, SMARTARM adds the breakdown prediction capability to robotic arms to increase their OEE and minimize unplanned downtimes.

Name: Smart utilization of sensory tool systems via CAM-integration

Abstract: Sensory tool systems have been on the market for a few years now. This technology offers significant optimization potential, especially in the High-Mix Low-Volume segment by providing sensor-based insights about the process condition. However, large-scale adoption is hindered by not having established workflows for the use of sensory tools, especially between CAD/CAM and production. We want to address this by integrating the setup for the utilization of sensory tools already in the CAM process.

Name: Strengthening of logistics and sUpply chain management of maintenance services through PRocEss Mining powEred by AI

Abstract: Process mining techniques use event data to discover process models, to check the conformance of predefined process models, and to extend such models with information about bottlenecks, decisions, and resource usage. The final result of this project consists of a AI platform that enable process mining to support logistics/supply chain management of maintenance services in the manufacturing industry by providing novel insights that can be used to address their performance and compliance problems.

Name: Trusted Predictive Maintenance for the Textile Industry

Abstract: Unforeseen stops of machines in the textile industry can be solved with a maintenance plan that anticipates these situations. The aim of this proposal is to implement a trusted system in a Turkish textile plant based on the advanced analysis of secure data obtained from Industrial IoT devices and blockchain technology. This AI system will allow the design of a predictive maintenance plan to detect failure patterns and generate alerts to make well-informed decisions and minimize economic losses.