Miniaturization, advanced high performance materials and functional surface structures are all drivers behind key enabling technologies in high added value production. It is in such areas that ultrashort pulse lasers have enabled completely new machining concepts, where the big advantages of laser machining are combined with a quasi non-thermal and therefore mild process, which can be used to machine any material with high precision. An important obstacle however that hinders the full exploitation of the unique process characteristics, is the lack of a smart / adaptive machining technology. The laser process in principle is very accurate, but small deviations, e.g. in the materials to be processed, can compromise the accuracy to a very large extend. Therefore feedback systems are needed to keep the process accurate. Within this project the goal is to develop an adaptive laser micromachining system, based on ultrashort pulsed laser ablation and a novel depth measurement sensor, together with advanced data analysis software and automated system calibration routines. The sensor can be used inline with the laser ablation process, enabling adaptive processes by fast and accurate 3D surface measurements. The integrated sensor can be used to: • measure the surface topography while machining a part, in order to adapt the micromachining process, leading to highly increased machining accuracies and no defects, • measure the surface topography before machining, to scan for existing surface defects that can be removed in an automatically generated machining process, • measure complex shaped objects prior to machining, to precisely align the machining pattern to the workpiece, • quickly validate results after machining. Therefore, the main objective of this project is to develop a sensor based adaptive micro machining system using ultra short pulsed lasers for zero failure manufacturing.

There is a common saying in industry, and more generally in engineering "fast, cheap, reliable, choose two out of three". This saying captures the trade-off between resources, production time, quality and performance that are inherent in every manufacturing process. Conceptually, different points on this "Paretto front" correspond to different production choices and directly affect the competitiveness of an industry. OPTIMAI aims to redefine and optimize this Pareto front through integrating several enabling technologies in a common framework. The starting point for OPTIMAI is the smart instrumentation of production with AI-enabled sensors for quality inspection and monitoring, integrated on a secure middleware layer. To ensure data integrity and traceability, OPTIMAI foresees distributed ledger technology combined with a cyber-security module. Collected data are analysed using AI models for the early detection of defects and upstream causes of deficiencies. OPTIMAI also explores the virtualization of production using digital twins of processes and sensors that combined with AI models trained on production data, form a simulation engine for exploring production scenarios and optimizing production planning. Another innovative point is the rapid reconfiguration of production equipment via automated feedback from quality control results or via a context aware Augmented Reality ecosystem for fast and informed decision making. At the same time OPTIMAI put emphasis on establishing a comprehensive ethics and regulatory framework for the deployment of its technology realizing that a production line is a workplace and as such concerns related to privacy, protection of human rights and safety have to be carefully addressed before any kind of technology is adopted. OPTIMAI foresees an extended pilot phase on three industrial sites covering a representative sample of European industry in order to maximize its impact and facilitate commercial uptake.

Despite the indisputable benefits of AI, humans typically have little visibility and knowledge on how AI systems make any decisions or predictions due to the so-called “black-box effect” in which many of the machine learning/deep learning algorithms are not able to be examined after their execution to understand specifically how and why a decision has been made. The inner workings of machine learning and deep learning are not exactly transparent, and as algorithms become more complicated, fears of undetected bias, mistakes, and miscomprehensions creeping into decision making, naturally grow among manufacturers and practically any stakeholder In this context, Explainable AI (XAI) is today an emerging field that aims to address how black box decisions of AI systems are made, inspecting and attempting to understand the steps and models involved in decision making to increase human trust. XMANAI aims at placing the indisputable power of Explainable AI at the service of manufacturing and human progress, carving out a “human-centric”, trustful approach that is respectful of European values and principles, and adopting the mentality that “our AI is only as good as we are”. XMANAI, demonstrated in 4 real-life manufacturing cases, will help the manufacturing value chain to shift towards the amplifying AI era by coupling (hybrid and graph) AI "glass box" models that are explainable to a "human-in-the-loop" and produce value-based explanations, with complex AI assets (data and models) management-sharing-security technologies to multiply the latent data value in a trusted manner, and targeted manufacturing apps to solve concrete manufacturing problems with high impact.

QU4LITY will demonstrate, in a realistic, measurable, and replicable way an open, certifiable and highly standardised, SME-friendly and transformative shared data-driven ZDM product and service model for Factory 4.0 through 5 strategic ZDM plug & control lighthouse equipment pilots and 9 production lighthouse facility pilots. QU4LITY will also demonstrate how European industry can build unique and highly tailored ZDM strategies and competitive advantages (significantly increase operational efficiency, scrap reduction, prescriptive quality management, energy efficiency, defect propagation avoidance and improved smart product customer experience, and foster new digital business models; e.g. outcome-based and product servitisation) through an orchestrated open platforms ecosystem, ZDM atomized components and digital enablers (Industry 4.0 digital connectivity & edge computing package, plug & control autonomous manufacturing equipment, real-time data spaces for process monitoring & adaptation, simulation data spaces for digital process twin continuity, AI-powered analytic data spaces for cognitive digital control twin composable services, augmented worker interventions, European quality data marketplace) across all phases of product and process lifecycle (engineering, planning, operation and production) building upon the QU4LITY autonomous quality model to meet the Industry 4.0 ZDM challenges (cost and time effective brownfield ZDM deployment, flexible ZDM strategy design & adaptation, agile operation of zero defect processes & products, zero break down sustainable manufacturing process operation and human centred manufacturing).