Jérôme Pfeiffer, Nicolai Maisch, Sebastian Friedl
et al.
The growing adoption of federated data spaces, such as in the GAIA-X and the International Data Spaces (IDS) initiative, promises secure and sovereign data sharing across organizational boundaries in Industry 4.0. In manufacturing ecosystems, this enables use cases, such as cross-factory process optimization, predictive maintenance, and supplier integration. Frameworks and standards, such as the Asset Administration Shell (AAS), Eclipse Dataspace Connector (EDC), ID-Link and Open Platform Communications Unified Architecture (OPC UA) provide a strong foundation to realize this ecosystem. However, a major open challenge is the practical description and enforcement of context-dependent data usage policies using these base technologies - especially by domain experts without software engineering backgrounds. Therefore, this article proposes a method for leveraging domain-specific languages (DSLs) to enable declarative, human-readable, and machine-executable policy definitions for sovereign data sharing via data space connectors. The DSL empowers domain experts to specify fine-grained data governance requirements - such as restricting access to data from specific production batches or enforcing automatic deletion after a defined retention period - without writing imperative code.
Saurav Sharma, Satya K. Ammu, Prakash Thakolkaran
et al.
In the development of active animate materials, electromechanical coupling is highly attractive to realize mechanoresponsive functionality. Piezoelectricity is the most utilized electromechanical phenomenon due to the wide availability of materials that display precise and reliable coupling. However, the inherent directionality of these materials is constrained by the symmetry of their crystal structure, which limits the choice of available properties in natural piezoelectric materials. A solution to alleviate this limitation could be to leverage geometry or architecture at the mesoscale. Here, we present an integrated framework to design and 3D-print piezoelectric truss metamaterials with customizable anisotropic responses. To explore the vast design space of truss metamaterials, we employ generative machine learning to optimize the topology and geometry of truss lattices and achieve target piezoelectricity. Then, we develop an in-gel-3D printing method to fabricate polymer-ceramic piezoelectric truss metamaterial structures using a composite slurry of photo-curable resin and lead-free piezoelectric particles. The ML framework discovers designs exhibiting unconventional behaviors, including auxetic, unidirectional, and omnidirectional piezoelectricity, while the additive manufacturing technique ensures shaping freedom and precision in fabricating these metamaterials at small scales. Our results show an improvement of over 48% in the specific hydrostatic piezoelectric coefficient in optimized metamaterials over bulk lead zirconate titanate (PZT). We successfully achieved metamaterials with higher transverse piezoelectric coupling coefficient than its longitudinal coefficient, which is a phenomenon that is rare in bulk materials. Our approach enables customizable piezoelectric responses and paves the way towards the development of a new generation of electro-active animate materials.
A novel spatiotemporal framework using diverse econometric approaches is proposed in this research to analyze relationships among eight economy-wide variables in varying market conditions. Employing Vector Autoregression (VAR) and Granger causality, we explore trade policy effects on emerging manufacturing hubs in China, India, Malaysia, Singapore, and Vietnam. A Bayesian Global Vector Autoregression (BGVAR) model also assesses interaction of cross unit and perform Unconditional and Conditional Forecasts. Utilizing time-series data from the Asian Development Bank, our study reveals multi-way cointegration and dynamic connectedness relationships among key economy-wide variables. This innovative framework enhances investment decisions and policymaking through a data-driven approach.
Muhammad Tayyab Khan, Lequn Chen, Zane Yong
et al.
Efficient and accurate extraction of key information from 2D engineering drawings is essential for advancing digital manufacturing workflows. Such information includes geometric dimensioning and tolerancing (GD&T), measures, material specifications, and textual annotations. Manual extraction is slow and labor-intensive, while generic OCR models often fail due to complex layouts, engineering symbols, and rotated text, leading to incomplete and unreliable outputs. These limitations result in incomplete and unreliable outputs. To address these challenges, we propose a hybrid vision-language framework that integrates a rotation-aware object detection model (YOLOv11-obb) with a transformer-based vision-language parser. Our structured pipeline applies YOLOv11-OBB to localize annotations and extract oriented bounding box (OBB) patches, which are then parsed into structured outputs using a fine-tuned, lightweight vision-language model (VLM). We curate a dataset of 1,367 2D mechanical drawings annotated across nine key categories. YOLOv11-OBB is trained on this dataset to detect OBBs and extract annotation patches. These are parsed using two open-source VLMs: Donut and Florence-2. Both models are lightweight and well-suited for specialized industrial tasks under limited computational overhead. Following fine-tuning of both models on the curated dataset of image patches paired with structured annotation labels, a comparative experiment is conducted to evaluate parsing performance across four key metrics. Donut outperforms Florence-2, achieving 88.5% precision, 99.2% recall, and a 93.5% F1-score, with a hallucination rate of 11.5%. Finally, a case study demonstrates how the extracted structured information supports downstream manufacturing tasks such as process and tool selection, showcasing the practical utility of the proposed framework in modernizing 2D drawing interpretation.
Michael J. Abere, Hyein Choi, Levi Van Bastian
et al.
The additive manufacture of compositionally graded Al/Cu parts by laser engineered net shaping (LENS) is demonstrated. The use of a blue light build laser enabled deposition on a Cu substrate. The thermal gradient and rapid solidification inherent to selective laser melting enabled mass transport of Cu up to 4 mm away from a Cu substrate through a pure Al deposition, providing a means of producing gradients with finer step sizes than the printed layer thicknesses. Printing graded structures with pure Al, however, was prevented by the growth of Al$_2$Cu$_3$ dendrites and acicular grains amid a matrix of Al$_2$Cu. A combination of adding TiB$_2$ grain refining powder and actively varying print layer composition suppressed the dendritic growth mode and produced an equiaxed microstructure in a compositionally graded part. Material phase was characterized for crystal structure and nanoindentation hardness to enable a discussion of phase evolution in the rapidly solidifying melt pool of a LENS print.
Workplace accidents continue to pose significant risks for human safety, particularly in industries such as construction and manufacturing, and the necessity for effective Personal Protective Equipment (PPE) compliance has become increasingly paramount. Our research focuses on the development of non-invasive techniques based on the Object Detection (OD) and Convolutional Neural Network (CNN) to detect and verify the proper use of various types of PPE such as helmets, safety glasses, masks, and protective clothing. This study proposes the SH17 Dataset, consisting of 8,099 annotated images containing 75,994 instances of 17 classes collected from diverse industrial environments, to train and validate the OD models. We have trained state-of-the-art OD models for benchmarking, and initial results demonstrate promising accuracy levels with You Only Look Once (YOLO)v9-e model variant exceeding 70.9% in PPE detection. The performance of the model validation on cross-domain datasets suggests that integrating these technologies can significantly improve safety management systems, providing a scalable and efficient solution for industries striving to meet human safety regulations and protect their workforce. The dataset is available at https://github.com/ahmadmughees/sh17dataset.
Fatigue properties of additively manufactured (AM) materials depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluation inevitably requires these factors combined as many as possible, thus resulting in low efficiency and high cost. In recent years, their assessment by leveraging the power of machine learning (ML) has gained increasing attentions. Here, we present a comprehensive overview on the state-of-the-art progress of applying ML strategies to predict fatigue properties of AM materials, as well as their dependence on AM processing and post-processing parameters such as laser power, scanning speed, layer height, hatch distance, built direction, post-heat temperature, etc. A few attempts in employing feedforward neural network (FNN), convolutional neural network (CNN), adaptive network-based fuzzy system (ANFS), support vector machine (SVM) and random forest (RF) to predict fatigue life and RF to predict fatigue crack growth rate are summarized. The ML models for predicting AM materials' fatigue properties are found intrinsically similar to the commonly used ones, but are modified to involve AM features. Finally, an outlook for challenges (i.e., small dataset, multifarious features, overfitting, low interpretability, unable extension from AM material data to structure life) and potential solutions for the ML prediction of AM materials' fatigue properties is provided.
Philipp Schworm, Xiangquian Wu, Matthias Klar
et al.
Flexible Job Shop Scheduling (FJSSP) is a complex optimization problem crucial for real-world process scheduling in manufacturing. Efficiently solving such problems is vital for maintaining competitiveness. This paper introduces Quantum Annealing-based solving algorithm (QASA) to address FJSSP, utilizing quantum annealing and classical techniques. QASA optimizes multi-criterial FJSSP considering makespan, total workload, and job priority concurrently. It employs Hamiltonian formulation with Lagrange parameters to integrate constraints and objectives, allowing objective prioritization through weight assignment. To manage computational complexity, large instances are decomposed into subproblems, and a decision logic based on bottleneck factors is used. Experiments on benchmark problems show QASA, combining tabu search, simulated annealing, and Quantum Annealing, outperforms a classical solving algorithm (CSA) in solution quality (set coverage and hypervolume ratio metrics). Computational efficiency analysis indicates QASA achieves superior Pareto solutions with a reasonable increase in computation time compared to CSA.
Andrey Solano, Arne Sieverling, Robert Gieselmann
et al.
We present Fast-dRRT*, a sampling-based multi-robot planner, for real-time industrial automation scenarios. Fast-dRRT* builds upon the discrete rapidly-exploring random tree (dRRT*) planner, and extends dRRT* by using pre-computed swept volumes for efficient collision detection, deadlock avoidance for partial multi-robot problems, and a simplified rewiring strategy. We evaluate Fast-dRRT* on five challenging multi-robot scenarios using two to four industrial robot arms from various manufacturers. The scenarios comprise situations involving deadlocks, narrow passages, and close proximity tasks. The results are compared against dRRT*, and show Fast-dRRT* to outperform dRRT* by up to 94% in terms of finding solutions within given time limits, while only sacrificing up to 35% on initial solution cost. Furthermore, Fast-dRRT* demonstrates resilience against noise in target configurations, and is able to solve challenging welding, and pick and place tasks with reduced computational time. This makes Fast-dRRT* a promising option for real-time motion planning in industrial automation.
D. Tourret, J. Klemm-Toole, A. Eres Castellanos
et al.
Understanding rapid solidification behavior at velocities relevant to additive manufacturing (AM) is critical to controlling microstructure selection. Although in-situ visualization of solidification dynamics is now possible, systematic studies under AM conditions with microstructural outcomes compared to solidification theory remain lacking. Here we measure solid-liquid interface velocities of Ni-Mo-Al alloy single crystals under AM conditions with synchrotron X-ray imaging, characterize the microstructures, and show discrepancies with classical theories regarding the onset velocity for absolute stability of a planar solid-liquid interface. Experimental observations reveal cellular/dendritic microstructures can persist at velocities larger than the expected absolute stability limit, where banded structure formation should theoretically appear. We show that theory and experimental observations can be reconciled by properly accounting for the effect of solute trapping and kinetic undercooling on the velocity-dependent solidus and liquidus temperatures of the alloy. Further theoretical developments and accurate assessments of key thermophysical parameters - like liquid diffusivities, solid-liquid interface excess free energies, and kinetic coefficients - remain needed to quantitatively investigate such discrepancies and pave the way for the prediction and control of microstructure selection under rapid solidification conditions.
Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. It requires rigorous simulations of optical and chemical models that are computationally expensive. Recent developments in machine learning have provided alternative solutions in replacing the time-consuming lithography simulations with deep neural networks. However, the considerable accuracy drop still impedes its industrial adoption. Most importantly, the quality and quantity of the training dataset directly affect the model performance. To tackle this problem, we propose a litho-aware data augmentation (LADA) framework to resolve the dilemma of limited data and improve the machine learning model performance. First, we pretrain the neural networks for lithography modeling and a gradient-friendly StyleGAN2 generator. We then perform adversarial active sampling to generate informative and synthetic in-distribution mask designs. These synthetic mask images will augment the original limited training dataset used to finetune the lithography model for improved performance. Experimental results demonstrate that LADA can successfully exploits the neural network capacity by narrowing down the performance gap between the training and testing data instances.
Fusion-based metal additive manufacturing (AM) is a disruptive technology that can be employed to fabricate metallic component of near-net-shape with an unprecedented combination of superior properties. However, the interrelationship between AM processing and the resulting microstructures is still not well understood. This poses a grand challenge in controlling the development of microstructures during AM to achieve desired properties. Here we study the microstructure development of a single melt pool, the building block of AM-fabricated metallic component, using a phase-field model specifically developed for the rapid solidification of AM. It is found that during the rapid solidification of the melt pool, the solid-liquid interface is initially controlled by solute diffusion followed by a thermal diffusion-controlled stage with an undercooling larger than the freezing range. This switching of controlling mechanisms leads to the sudden changes in interfacial velocity, solute concentration, and temperature, which perfectly explains the formation of various heterogeneous microstructures observed in AM. By manipulating the processing conditions, the switching of controlling mechanisms can be controlled to form refined microstructures or layered structures for improved mechanical properties and resistance to cracking.
We provide an experimental evaluation of a wearable augmented reality (AR) system we have developed for human-robot teams working on tasks requiring collaboration in shared physical workspace. Recent advances in AR technology have facilitated the development of more intuitive user interfaces for many human-robot interaction applications. While it has been anticipated that AR can provided a more intuitive interface to robot assistants helping human workers in various manufacturing scenarios, existing studies in robotics have been largely limited to teleoperation and programming. Industry 5.0 envisions cooperation between human and robot working in teams. Indeed, there exist many industrial task that can benefit from human-robot collaboration. A prime example is high-value composite manufacturing. Working with our industry partner towards this example application, we evaluated our AR interface design for shared physical workspace collaboration in human-robot teams. We conducted a multi-dimensional analysis of our interface using establish metrics. Results from our user study (n=26) show that subjectively, the AR interface feels more novel and a standard joystick interface feels more dependable to users. However, the AR interface was found to reduce physical demand and task completion time, while increasing robot utilization. Furthermore, user's freedom of choice to collaborate with the robot may also affect the perceived usability of the system.
Mohammad Marvi-Mashhadi, Wahaaj Ali, Muzi Li
et al.
A simulation strategy based in the finite element model was developed to model the corrosion and mechanical properties of biodegradable Mg scaffolds manufactured by laser power bed fusion after immersion in simulated body fluid. Corrosion was simulated through a phenomenological, diffusion-based model which can take into account pitting. The elements in which the concentration of Mg was below a certain threshold (representative of the formation of Mg(OH)2) after the corrosion simulation were deleted for the mechanical simulations, in which Mg was assumed to behave as an isotropic, elastic-perfectly plastic solid and fracture was introduced through a ductile failure model. The parameters of the models were obtained from previous experimental results and the numerical predictions of the strength and fracture mechanisms of WE43 Mg alloy porous scaffolds in the as-printed condition and after immersion in simulated body fluid were in good agreement with the experimental results. Thus, the simulation strategy is able to assess the effect of corrosion on the mechanical behavior of biodegradable scaffolds, which is critical for design of biodegradable scaffolds for biomedical applications.
Emanuele Gabriel Margherita, Alessio Maria Braccini
In this position paper, we explore the socio-technical interplay of Industry 4.0. Industry 4.0 is an industrial plan that aims at automating the production process by the adoption of advanced leading-edge technologies down the assembly line. Most of the studies employ a technical perspective that is focused on studying how to integrate various technologies and the resulting benefits for organisations. In contrast, few studies use a socio-technical perspective of Industry 4.0. We close this gap employs the socio-technical lens on an in-depth single case study of a manufacturing organisation that effectively adopted Industry 4.0 technologies. The findings of our studies shed light both on the socio-technical interplay between workers and technologies and the novel role of workers. We conclude proposing a socio-technical framework for an Industry 4.0 context.
After more than five decades of research, the failure of bone implants is still an issue that becomes increasingly urgent to solve in our ageing population. Among the reasons for failure, catastrophic brittle fracture is one event that is directly related to the implant s material and fabrication and that deserves more attention. Indeed, clinically available implants pale at reproducing the hierarchical and heterogeneous microstructural organization of our natural bones, ultimately failing at reproducing their mechanical strength and toughness. Nevertheless, the recent advances in additive and advanced manufacturing open new horizons for the fabrication of biomimetic bone implants, challenging at the same time their characterization, testing and modelling. This critical review covers selected recent achievements in bone implant research from a materials standpoint and aims at deciphering some of the most urgent issues in this multidisciplinary field.
Powder Bed Fusion (PBF) is a type of Additive Manufacturing (AM) technology that builds parts in a layer-by-layer fashion out of a bed of metal powder via the selective melting action of a laser or electron beam heat source. The technology has become widespread, however the demand is growing for closed loop process monitoring and control in PBF systems to replace the open loop architectures that exist today. Controls-based models have potential to satisfy this demand by utilizing computationally tractable, simplified models while also decreasing the error associated with these models. This paper introduces a controls theoretic analysis of the PBF process, demonstrating models of PBF that are asymptotically stable, stabilizable, and detectable. We show that linear models of PBF are structurally controllable and structurally observable, provided that any portion of the build is exposed to the energy source and measurement, we provide conditions for which time-invariant PBF models are classically controllable/observable, and we demonstrate energy requirements for performing state estimation and control for time-invariant systems. This paper therefore presents the foundation for an effective means of realizing closed loop PBF quality control.
Many alloys made by Additive Manufacturing (AM) require careful design of post-heat treatment as an indispensable step of microstructure engineering to further enhance the performance. We developed a high-throughput approach by fabricating a long-bar sample heat-treated under a monitored gradient temperature zone for phase transformation study to accelerate the post-heat treatment development of AM alloys. This approach has been proven efficient in determining the aging temperature with peak hardness. We observed that the precipitation strengthening is predominant for the studied superalloy by laser powder bed fusion, and the grain size variation is insensitive on temperature between 605 and 825 Celcius. This new approach can be applied to post-heat treatment optimization of other materials made by AM, and further assist new alloy development.
Metamaterials exhibit materials response deviation from conventional elasticity. This phenomenon is captured by the generalized elasticity as a result of extending the theory at the expense of introducing additional parameters. These parameters are linked to internal length scales. Describing on a macroscopic level a material possessing a substructure at a microscopic length scale calls for introducing additional constitutive parameters. Therefore, in principle, an asymptotic homogenization is feasible to determine these parameters given an accurate knowledge on the substructure. Especially in additive manufacturing, known under the infill ratio, topology optimization introduces a substructure leading to higher order terms in mechanical response. Hence, weight reduction creates a metamaterial with an accurately known substructure. Herein, we develop a computational scheme using both scales for numerically identifying metamaterials parameters. As a specific example we apply it on a honeycomb substructure and discuss the infill ratio. Such a computational approach is applicable to a wide class substructures and makes use of open-source codes; we make it publicly available for a transparent scientific exchange.