155 results
Now showing1 - 10 of 155
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Embodied AI in industrial operations: A systematic literature reviewEmbodied Artificial Intelligence (EAI) is increasingly seen as a promising route toward flexible automation, also in industrial operations. Yet the term is used inconsistently, and existing surveys often address isolated components rather than the combined role of embodiment, learning, perception, action, data, and industrial deployment constraints. This paper presents a PRISMA-guided systematic literature review of recent EAI research in industrial operations. We first consolidate the terminology of EAI and define four guiding characteristics: embodiment, learning, perception-action coupling, and situated intelligence. Based on this framework, we introduce a manipulation-mobility matrix for classifying physical embodiments and analyze the reviewed literature across industrial applications, research focuses, hardware forms, input and output modalities, learning architectures, datasets, simulation environments, and training paradigms. The results show that current research is dominated by assembly and manufacturing scenarios, stationary robotic arms, vision- and language-based interfaces, and modular foundation model-centered architectures. However, tightly coupled sensorimotor learning, tactile and force feedback, situated intelligence, and validated real-world deployment remain limited. This review clarifies the current state of industrial EAI and identifies the key gaps that must be closed to enable scalable deployment in industrial operations. Conducts a PRISMA-guided review of 42 recent Embodied AI (EAI) industrial studies. Defines formal industrial EAI terminology via four key characteristics. Proposes a manipulation-mobility matrix classifying robotic embodiments. Finds a dominant focus on stationary cobots and vision/language inputs. Highlights key deployment bottlenecks: decoupled foundation models, precision limitsPublicationtype: Journal Article51 19 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Instant geodesic draping for optimization and path-planning and its application to incremental composite sheet formingTechnical textiles and their use in composites are crucial for many high-performance applications. Utilizing them in applications dominated by iteration and individualization requires flexible manufacturing processes. One such process is Incremental Sheet Forming (ISF), the 3D-Printing of forming processes, which is currently being adapted to composites. Enabling ISF, and other dieless processes, and leveraging their flexibility requires optimization and path-planning tools. Such tools must consider material behavior, which in turn necessitates the use of simulation. While highly sophisticated methods for increasingly accurate modeling have been developed, the speed requirements of CAM workflows and optimizations have kept simple yet efficient approximations relevant, the most prominent being kinematic draping algorithms. This work presents a novel heat-method based alternative that globally computes fabric draping under an assumption of uniform tow distances. This assumption makes it especially well-suited for the subsequently implemented drape-aware ISF paths. Additionally, the developed algorithm is highly computationally efficient, which is harnessed for visualization and optimization. While these are only explored computationally, the path-planning is employed to produce and compare a demonstrator part in a double sided ISF process. The initial results for the draping algorithm show an up to 80x speed increase compared to kinematic draping. This allows for real-time draping visualization and sub-minute optimization. The demonstrator part proves that the derived paths can counteract wrinkling, an important failure mode observed with conventional strategies. These results demonstrate the great potential of geodesic draping for ISF in particular and flexible manufacturing, optimization and visualization tasks in general.Publicationtype: Journal Article24 6 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Visual detection of flap tears on abrasive flap wheels using deep learningDuring abrasive flap wheel grinding, flaps may fail and tear prematurely. Such flap tears increase local tool flexibility and can impair the uniformity of material removal in automated grinding processes. To ensure process reliability, this paper proposes a novel computer vision approach for the automated detection and quantification of flap tears using deep learning. The processing pipeline is based on images showing the radial tool structure, followed by a geometric normalization that transforms the flap arrangement into a linear coordinate system. A YOLOv8-based object detection model is employed to localize abrasive flaps. To overcome class imbalances, a hybrid approach is implemented where the neural network performs a robust one-class detection, while the final distinction between intact flaps and stubs is achieved through deterministic, scale-invariant post-processing filters. The system was validated on a dataset including various tool diameters, grit sizes, and wear conditions. For tools within the trained distribution, the system achieved 96.5% classification accuracy and a Mean Absolute Error of 0.14 and 0.12 for flap and stub counts. However, performance is limited when encountering significant geometric domain shifts, such as larger tool diameters. The results demonstrate that the combination of deep learning and geometric heuristics provides a robust basis for automated flap tear detection in industrial flap wheel grinding applications.Publicationtype: Journal Article41 9 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Gradient-based viewpoint planning using approximated coverage computationA white light interferometer is a sensor suitable for automating inspections of components requiring high measurement accuracy. These sensors pose specific challenges for viewpoint planning that have not yet been addressed in the literature. This paper presents a novel approach to solving the view planning problem using gradient-based optimization. The goal is to determine a high-quality set of viewpoints for complete surface coverage. A surrogate optimization problem is formulated to maximize the coverage given a certain number of viewpoints. By iteratively increasing the number of viewpoints and re-optimizing all previous viewpoints together with the new one, a set of viewpoints achieving complete coverage is obtained. The proof of concept is demonstrated on representative test structures.Publicationtype: Conference Paper6 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Double-sided incremental forming of continuous fiber reinforced thermoplasticsContinuous fiber reinforced thermoplastics (CFRTP) combine excellent mechanical properties with recyclability, weldability, and reshapeability. However, their conventional processing requires part-specific tooling, imposing high initial cost and lead times. This limits their applicability to small lot sizes. A flexible alternative could be Incremental Sheet Forming (ISF), which creates parts by moving a small, part-agnostic tool along numerically controlled paths. While ISF is established for metals, its adoption for CFRTP started only recently. In particular, the Double-Sided Incremental Forming (DSIF) process, which employs a second forming tool to improve quality and flexibility, has not been investigated in detail for CFRTP. Therefore, this work presents the first extensive study into DSIF of CFRTP, with a focus on establishing a baseline process. The conducted process characterization includes temperature and force assessments. Forming strategies were compared by forming cone frusta, yielding a multi-stage strategy combining spiral and fiber-following toolpaths, which produced wrinkle-free parts with good accuracy. Micrographs indicate good consolidation for the tested material and process conditions. Furthermore, a preliminary process parameter analysis, including temperature, support force, and step size, was conducted. The results indicate that DSIF can become a viable, flexible manufacturing route for CFRTP components and provide a sound foundation for future research.Publicationtype: Journal Article53 19 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Tuning domain randomization for 3D-rendered synthetic training data for defect detection in aircraft engine borescope inspectionVisual surface defect detection in complex industrial inspection scenarios remains predominantly manual. Deep learning–based vision systems promise to automate this task but require large quantities of representative, annotated defect images, which are often unavailable due to the rarity and diversity of relevant defects. We address this challenge with a modular synthetic data generation pipeline leveraging physically based 3D rendering, which enables systematic domain randomization throughout the entire rendering chain. The pipeline comprises dedicated modules for scene composition, geometry-based defect generation, procedural material modeling, rendering, and automatic pixel-wise annotation, allowing users to expose and tune key parameters such as defect size, position, and penetration depth, object materials, camera poses, and lighting. We first provide a structured analysis of all process steps that influence image appearance in defect synthesis and then instantiate the pipeline for a case study on aircraft engine borescope inspection, targeting missing-material defects on high-pressure compressor blades. Using a two-stage experimental design, we employ a Plackett–Burman screening over 22 candidate factors followed by a one-factor-at-a-time optimization of the most influential parameters. Our results show that the material model, defect positioning, defect size, and penetration depth randomization dominate detection performance. Training an object detector solely on synthetic images generated with the optimized configuration yields a maximum of 0.89 mAP@0.5IoU on a real-world borescope validation set, with performance saturating at ∼500 rendered training images. These findings demonstrate that carefully structured domain randomization in a physically based rendering pipeline can provide practically useful synthetic training data for industrial defect detection.Publicationtype: Journal Article9 13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Hot double-sided incremental forming of fiber-reinforced thermoplastics: process capabilities and challengesFiber-reinforced thermoplastics (FRTP) offer high strength-to-weight ratios as well as weldability and recyclability, making them attractive for lightweight applications. Conventional thermoforming of continuous FRTP, however, requires part-specific molds, limiting economic viability for prototypes, individual parts, and small series. This study investigates a robotic hot double-sided incremental forming (DSIF) process developed for dieless, flexible forming of continuous FRTP sheets together with metal dummy sheets. Five different generic demonstrator parts with varying wall angles, degrees of symmetry, forming depths, and sizes were formed to assess process capability. Results demonstrate that typical defects such as fabric wrinkling and deconsolidation can be successfully avoided, and that the geometric accuracy achievable is comparable to that of metal DSIF. Challenges exist in forming larger parts due to the failure of the employed metal dummy sheets.Publicationtype: Journal Article12 14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Classifying parameters and target variables in incremental sheet forming of fiber reinforced polymers(Trans Tech Publications, 2026-04-16); ; ; Incremental Sheet Forming (ISF) enables the flexible creation of shell-shaped structures. Unlike conventional forming, ISF does not require a bespoke forming tool, greatly reducing upfront costs and lead times, especially for small lot sizes. Several parameter classifications for the ISF of metals and polymers have been proposed in the past. Such classifications increase awareness of possible levers for process optimization, guide experimental analysis, and enable a holistic understanding. Lately, fiber-reinforced polymers (FRP) are of increasing interest in ISF. In previous studies, ISF systems for various kinds of FRP have been developed, and several parameters and target variables have been investigated. However, there is currently no classification that addresses the specific parameters and target variables relevant to this material class. Therefore, the goal of this work is to develop such a classification to create a comprehensive foundation for future FRP ISF investigations. This effort is undertaken by building upon existing classifications and reviews independent of the material class and synthesizing these with a systematic literature review of FRP ISF investigations. The resulting classifications cover a broad range of parameters and target variables and reveal a structure that guides a systematic understanding and ensures future expandability.Publicationtype: Journal Article72 15 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , 3D printing of continuous Carbon fiber-reinforced polymer tee pipe: Strategy development and demonstrator fabrication(Trans Tech Publications, 2026-04-13); ; Conventional manufacturing techniques for continuous carbon fiber-reinforced polymers (CFRP) rely on costly, geometry-specific molds, which substantially limit design flexibility. To overcome these constraints, this paper proposes a robot-based, multi-axis Fused Filament Fabrication (FFF) approach for the production of CFRP components of complex geometries. The setup enables advanced material placement so that support structures and internal cores can be avoided, thereby reducing process preparation effort, post-processing requirements, and overall manufacturing cost. As a case study, a tee pipe geometry is investigated. A dedicated slicing strategy is developed in which the main pipe and the branching section are fabricated sequentially. This approach requires precise cutting and controlled re-adhesion of the CFRP material, a critical capability for extending conventional neat-polymer FFF processes to the additive manufacturing of CFRP. Experimental validation demonstrated the feasibility of the process, highlighting the critical role of an innovative technique called nozzle ironing for surface preparation, as well as the challenges associated with fiber cutting mechanisms. While the final component achieved structural coherence, leakage testing revealed porosity at specific interface regions, suggesting directions for future hardware refinement and process optimization.Publicationtype: Journal Article8 6 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Capabilities of robot-based double-sided incremental hot-forming of fiber-reinforced thermoplastics(Soc. for the Advancement of Material and Process Engineering, 2026-04); ; ; ; Thermoplastic composites are gaining interest for their good recyclability, in addition to their mechanical performance and light weight potential. However, conventional molding processes for thermoplastic composites, such as hot pressing, require full-surface, geometry-specific molding tools and are therefore associated with high investment costs and long lead times until production can start. This is a strong drawback for manufacturing of small series, prototypes or in case of geometry changes. A promising flexible alternative is incremental forming, where geometry-agnostic tool tips exert local force to successively form the part. This allows for the economical and quick production of small part quantities. This work investigates the capabilities of a novel double sided incremental hot-forming process that employs two cooperating robots to drape a heated organosheet into the targeted shape. The process is assessed regarding mechanical performance, geometric accuracy and economic efficiency. The analysis shows that the presented process is capable of producing a wide variety of geometries with viable accuracy and good mechanical performance. The economic assessment reveals a clear advantage in both lead time as well as per part cost for small lot sizes.Publicationtype: Conference Paper40