Automated Optical Inspection (AOI) is widely used across various industries, including surface mount technology in semiconductor manufacturing. One of the key challenges in AOI is optimising inspection tolerances. Traditionally, this process relies heavily on the expertise and intuition of engineers, making it subjective and prone to inconsistency. To address this, we are developing an intelligent, data-driven approach to optimise inspection tolerances in a more objective and consistent manner. Most existing research in this area focuses primarily on minimising false calls, often at the risk of allowing actual defects to go undetected. This oversight can compromise product quality, especially in critical sectors such as medical, defence, and automotive industries. Our approach introduces the use of percentile rank, amongst other logical strategies, to ensure that genuine defects are not overlooked. With continued refinement, our method aims to reach a point where every flagged item is a true defect, thereby eliminating the need for manual inspection. Our proof of concept achieved an 18% reduction in false calls at the 80th percentile rank, while maintaining a 100% recall rate. This makes the system both efficient and reliable, offering significant time and cost savings.
A topology optimization problem in a phase field setting is considered to obtain rigid structures, which are resilient to external forces and constructable with additive manufacturing. Hence, large deformations of overhangs due to gravity shall be avoided during construction. The deformations depend on the stage of the construction and are modelled by linear elasticity equations on growing domains with height-dependent stress tensors and forces. Herewith, possible hardening effects can be included. Analytical results concerning the existence of minimizers and the differentiability of the reduced cost functional are presented in case of a finite number of construction layers. By proving Korn's inequality with a constant independent of the height, it is shown that the cost functional, formulated continuously in height, is well-defined. The problem is numerically solved using a projected gradient type method in function space, for which applicability is shown. Second-order information can be included by adapting the underlying inner product in every iteration. Additional adjustments enhancing the solver's performance, such as a nested procedure and subsystem solver specifcations, are stated. Numerical evidence is provided that for all discretization level and also for any number of construction layers, the iteration numbers stay roughly constant. The benefits of the nested procedure as well as of the inclusion of second order information are illustrated. Furthermore, the choice of weights for the penalization of overhangs is discussed. For various problem settings, results are presented for one or two materials and void in two as well as in three dimensions.
Additive manufacturing (AM) is a rapidly evolving technology that has attracted applications across a wide range of fields due to its ability to fabricate complex geometries. However, one of the key challenges in AM is achieving consistent print quality. This inconsistency is often attributed to uncontrolled melt pool dynamics, partly caused by spatter which can lead to defects. Therefore, capturing and controlling the evolution of the melt pool is crucial for enhancing process stability and part quality. In this study, we developed a framework to support decision-making towards efficient AM process operations, capable of facilitating quality control and minimizing defects via machine learning (ML) and polynomial symbolic regression models. We implemented experimentally validated computational tools, specifically for laser powder bed fusion (LPBF) processes as a cost-effective approach to collect large datasets. For a dataset consisting of 281 varying process conditions, parameters such as melt pool dimensions (length, width, depth), melt pool geometry (area, volume), and volume indicated as spatter were extracted. Using machine learning (ML) and polynomial symbolic regression models, a high R2 of over 95 % was achieved in predicting the melt pool dimensions and geometry features on both the training and testing datasets, with either process conditions (power and velocity) or melt pool dimensions as the model inputs. In the case of volume indicated as spatter the value of the R2 improved after logarithmic transforming the model inputs, which were either the process conditions or the melt pool dimensions. Among the investigated ML models, the ExtraTree model achieved the highest R2 values of 96.7 % and 87.5 %.
Christina Schenk, Miguel Hernández-del-Valle, Luis Calero-Lumbreras
et al.
Device-to-device variability in experimental noise critically impacts reproducibility, especially in automated, high-throughput systems like additive manufacturing farms. While manageable in small labs, such variability can escalate into serious risks at larger scales, such as architectural 3D printing, where noise may cause structural or economic failures. This contribution presents a noise-aware decision-making algorithm that quantifies and models device-specific noise profiles to manage variability adaptively. It uses distributional analysis and pairwise divergence metrics with clustering to choose between single-device and robust multi-device Bayesian optimization strategies. Unlike conventional methods that assume homogeneous devices or generic robustness, this framework explicitly leverages inter-device differences to enhance performance, reproducibility, and efficiency. An experimental case study involving three nominally identical 3D printers (same brand, model, and close serial numbers) demonstrates reduced redundancy, lower resource usage, and improved reliability. Overall, this framework establishes a paradigm for precision- and resource-aware optimization in scalable, automated experimental platforms.
Emmanuel Akeweje, Conall Kirk, Chi-Wai Chan
et al.
Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing to capture the heterogeneity of industrial-scale batches. We present an automated, machine learning framework that couples high-throughput imaging with shape extraction and clustering to profile metallic powder morphology at scale. We develop and evaluate three clustering pipelines: an autoencoder pipeline, a shape-descriptor pipeline, and a functional-data pipeline. Across a dataset of approximately 126,000 powder images (0.5-102 micrometer diameter), internal validity metrics identify the Fourier-descriptor + k-means pipeline as the most effective, achieving the lowest Davies-Bouldin index and highest Calinski-Harabasz score while maintaining sub-millisecond runtime per particle on a standard desktop workstation. Although the present work focuses on establishing the morphological-clustering framework, the resulting shape groups form a basis for future studies examining their relationship to flowability, packing density, and SLM part quality. Overall, this unsupervised learning framework enables rapid, automated assessment of powder morphology and supports tracking of shape evolution across reuse cycles, offering a path toward real-time feedstock monitoring in SLM workflows.
The deployment of machine learning (ML)-based process monitoring systems has significantly advanced additive manufacturing (AM) by enabling real-time defect detection, quality assessment, and process optimization. However, redundancy is a critical yet often overlooked challenge in the deployment and operation of ML-based AM process monitoring systems. Excessive redundancy leads to increased equipment costs, compromised model performance, and high computational requirements, posing barriers to industrial adoption. However, existing research lacks a unified definition of redundancy and a systematic framework for its evaluation and mitigation. This paper defines redundancy in ML-based AM process monitoring and categorizes it into sample-level, feature-level, and model-level redundancy. A comprehensive multi-level redundancy mitigation (MLRM) framework is proposed, incorporating advanced methods such as data registration, downscaling, cross-modality knowledge transfer, and model pruning to systematically reduce redundancy while improving model performance. The framework is validated through an ML-based in-situ defect detection case study for directed energy deposition (DED), demonstrating a 91% reduction in latency, a 47% decrease in error rate, and a 99.4% reduction in storage requirements. Additionally, the proposed approach lowers sensor costs and energy consumption, enabling a lightweight, cost-effective, and scalable monitoring system. By defining redundancy and introducing a structured mitigation framework, this study establishes redundancy analysis and mitigation as a key enabler of efficient ML-based process monitoring in production environments.
Christopher Martin, Edward Kim, Enrique Velasquez
et al.
An almost periodic piecewise linear system (APPLS) is a type of piecewise linear system where the system cyclically switches between different modes, each with an uncertain but bounded dwell-time. Process regulation, especially disturbance rejection, is critical to the performance of these advanced systems. However, a method to guarantee disturbance rejection has not been developed. The objective of this study is to develop an $H_\infty$ performance analysis method for APPLSs, building on which an algorithm to synthesize practical $H_\infty$ controllers is proposed. As an application, the developed methods are demonstrated with an advanced manufacturing system -- roll-to-roll (R2R) dry transfer of two-dimensional materials and printed flexible electronics. Experimental results show that the proposed method enables a less conservative and much better performing $H_\infty$ controller compared with a baseline $H_\infty$ controller that does not account for the uncertain system switching structure.
As robotics advances toward integrating soft structures, anthropomorphic shapes, and complex tasks, soft and highly stretchable mechanotransducers are becoming essential. To reliably measure tactile and proprioceptive data while ensuring shape conformability, stretchability, and adaptability, researchers have explored diverse transduction principles alongside scalable and versatile manufacturing techniques. Nonetheless, many current methods for stretchable sensors are designed to produce a single sensor configuration, thereby limiting design flexibility. Here, we present an accessible, flexible, printing-based fabrication approach for customizable, stretchable sensors. Our method employs a custom-built printhead integrated with a commercial 3D printer to enable direct ink writing (DIW) of conductive ink onto cured silicone substrates. A layer-wise fabrication process, facilitated by stackable trays, allows for the deposition of multiple liquid conductive ink layers within a silicone matrix. To demonstrate the method's capacity for high design flexibility, we fabricate and evaluate both capacitive and resistive strain sensor morphologies. Experimental characterization showed that the capacitive strain sensor possesses high linearity (R^2 = 0.99), high sensitivity near the 1.0 theoretical limit (GF = 0.95), minimal hysteresis (DH = 1.36%), and large stretchability (550%), comparable to state-of-the-art stretchable strain sensors reported in the literature.
Accurate quality prediction in multi-process manufacturing is critical for industrial efficiency but hindered by three core challenges: time-lagged process interactions, overlapping operations with mixed periodicity, and inter-process dependencies in shared frequency bands. To address these, we propose PAF-Net, a frequency decoupled time series prediction framework with three key innovations: (1) A phase-correlation alignment method guided by frequency domain energy to synchronize time-lagged quality series, resolving temporal misalignment. (2) A frequency independent patch attention mechanism paired with Discrete Cosine Transform (DCT) decomposition to capture heterogeneous operational features within individual series. (3) A frequency decoupled cross attention module that suppresses noise from irrelevant frequencies, focusing exclusively on meaningful dependencies within shared bands. Experiments on 4 real-world datasets demonstrate PAF-Net's superiority. It outperforms 10 well-acknowledged baselines by 7.06% lower MSE and 3.88% lower MAE. Our code is available at https://github.com/StevenLuan904/PAF-Net-Official.
Leonel Rozo, Andras G. Kupcsik, Philipp Schillinger
et al.
Robotic manipulation is currently undergoing a profound paradigm shift due to the increasing needs for flexible manufacturing systems, and at the same time, because of the advances in enabling technologies such as sensing, learning, optimization, and hardware. This demands for robots that can observe and reason about their workspace, and that are skillfull enough to complete various assembly processes in weakly-structured settings. Moreover, it remains a great challenge to enable operators for teaching robots on-site, while managing the inherent complexity of perception, control, motion planning and reaction to unexpected situations. Motivated by real-world industrial applications, this paper demonstrates the potential of such a paradigm shift in robotics on the industrial case of an e-Bike motor assembly. The paper presents a concept for teaching and programming adaptive robots on-site and demonstrates their potential for the named applications. The framework includes: (i) a method to teach perception systems onsite in a self-supervised manner, (ii) a general representation of object-centric motion skills and force-sensitive assembly skills, both learned from demonstration, (iii) a sequencing approach that exploits a human-designed plan to perform complex tasks, and (iv) a system solution for adapting and optimizing skills online. The aforementioned components are interfaced through a four-layer software architecture that makes our framework a tangible industrial technology. To demonstrate the generality of the proposed framework, we provide, in addition to the motivating e-Bike motor assembly, a further case study on dense box packing for logistics automation.
To enable a mobile manipulator to perform human tasks from a single teaching demonstration is vital to flexible manufacturing. We call our proposed method MMPA (Mobile Manipulator Process Automation with One-shot Teaching). Currently, there is no effective and robust MMPA framework which is not influenced by harsh industrial environments and the mobile base's parking precision. The proposed MMPA framework consists of two stages: collecting data (mobile base's location, environment information, end-effector's path) in the teaching stage for robot learning; letting the end-effector repeat the nearly same path as the reference path in the world frame to reproduce the work in the automation stage. More specifically, in the automation stage, the robot navigates to the specified location without the need of a precise parking. Then, based on colored point cloud registration, the proposed IPE (Iterative Pose Estimation by Eye & Hand) algorithm could estimate the accurate 6D relative parking pose of the robot arm base without the need of any marker. Finally, the robot could learn the error compensation from the parking pose's bias to modify the end-effector's path to make it repeat a nearly same path in the world coordinate system as recorded in the teaching stage. Hundreds of trials have been conducted with a real mobile manipulator to show the superior robustness of the system and the accuracy of the process automation regardless of the harsh industrial conditions and parking precision. For the released code, please contact marketing@amigaga.com
Anushrut Jignasu, Kelly Marshall, Baskar Ganapathysubramanian
et al.
3D printing or additive manufacturing is a revolutionary technology that enables the creation of physical objects from digital models. However, the quality and accuracy of 3D printing depend on the correctness and efficiency of the G-code, a low-level numerical control programming language that instructs 3D printers how to move and extrude material. Debugging G-code is a challenging task that requires a syntactic and semantic understanding of the G-code format and the geometry of the part to be printed. In this paper, we present the first extensive evaluation of six state-of-the-art foundational large language models (LLMs) for comprehending and debugging G-code files for 3D printing. We design effective prompts to enable pre-trained LLMs to understand and manipulate G-code and test their performance on various aspects of G-code debugging and manipulation, including detection and correction of common errors and the ability to perform geometric transformations. We analyze their strengths and weaknesses for understanding complete G-code files. We also discuss the implications and limitations of using LLMs for G-code comprehension.
Early detection and correction of defects are critical in additive manufacturing (AM) to avoid build failures. In this paper, we present a multisensor fusion-based digital twin for in-situ quality monitoring and defect correction in a robotic laser direct energy deposition process. Multisensor fusion sources consist of an acoustic sensor, an infrared thermal camera, a coaxial vision camera, and a laser line scanner. The key novelty and contribution of this work are to develop a spatiotemporal data fusion method that synchronizes and registers the multisensor features within the part's 3D volume. The fused dataset can be used to predict location-specific quality using machine learning. On-the-fly identification of regions requiring material addition or removal is feasible. Robot toolpath and auto-tuned process parameters are generated for defecting correction. In contrast to traditional single-sensor-based monitoring, multisensor fusion allows for a more in-depth understanding of underlying process physics, such as pore formation and laser-material interactions. The proposed methods pave the way for self-adaptation AM with higher efficiency, less waste, and cleaner production.
As one of the important methods for surface modification of materials and life extension of key components, cemented carbide brazing coatings are widely used in agricultural machinery, oil drilling, aerospace and other fields, it has also attracted the attention of scholars in the field of surface modification at home and abroad. Based on the research reports of recent 20 years at home and abroad, the present research situation of cemented carbide brazed coating additive manufacturing technology are reviewed firstly. The research progress in preparation and performance control of cemented carbide/iron-base, cemented carbide/copper-base, cemented carbide/nickel-base, cemented carbide/silver-base heterogeneous brazing coatings are reviewed in detail. Then the practical applications of cemented carbide heterogenous brazing coatings in the fields of contact soil agricultural machinery parts life extension, aviation parts repair, surface function strengthening and so on are reviewed. In this review, the limitation of the research of cemented carbide heterogenous braze coating technology is discussed. The deficiencies in the research and development of cemented carbide heterogenous braze coating technology are summarized including cemented carbide heterogeneous additive materials and technology need to be expanded, the structure of cemented carbide heterogeneous brazing coatings need to be optimized, the mechanism of interface defects in cemented carbide heterogeneous brazing coatings need to be clarified. Finally, the future development direction of braze coating technology is prospected, too.
Mengkun Tian, Jahnavi Desai Choundraj, Thomas Voisin
et al.
Additive manufacturing (AM) by laser powder bed fusion (L-PBF) leads to the formation of a rich, hierarchical microstructure, including dislocation cell structures and elemental segregation. This structure has profound impacts on the corrosion behavior and mechanical properties of printed materials. In this study, we use in situ liquid cell scanning transmission electron microscope (STEM) to directly characterize the nanoscale origins of corrosion initiation in AM 316L stainless steel. Under applied anodic potentials, we found that the dislocation cellular boundaries were preferentially corroded and that pit-like features formed along the cellular boundaries. We directly observed the earliest stages of corrosion by controlling the biasing parameters to decelerate the corrosion processes. The results show that highly localized corrosion occurs via inclusion dissolution along dislocation cell boundaries. More widespread corrosion initiates at the dislocation cell boundaries and spreads throughout the dislocation networks.
Constructing precise micro-nano metal patterns on complex three-dimensional (3D) plastic parts allows the fabrication of functional devices for advanced applications. However, this patterning is currently expensive and requires complex processes with long manufacturing lead time. The present work demonstrates a process for the fabrication of micro-nano 3D metal-plastic composite structures with arbitrarily complex shapes. In this approach, a light-cured resin is modified to prepare an active precursor capable of allowing subsequent electroless plating (ELP). A multi-material digital light processing 3D printer was newly developed to enable the fabrication of parts containing regions made of either standard resin or active precursor resin nested within each other. Selective 3D ELP processing of such parts provided various metal-plastic composite parts having complicated hollow micro-nano structures with specific topological relationships on a size scale as small as 40 um. Using this technique, 3D metal topologies that cannot be manufactured by traditional methods are possible, and metal patterns can be produced inside plastic parts as a means of further miniaturizing electronic devices. The proposed method can also generate metal coatings exhibiting improved adhesion of metal to plastic substrate. Based on this technique, several sensors composed of different functional nonmetallic materials and specific metal patterns were designed and fabricated. The present results demonstrate the viability of the proposed method and suggest potential applications in the fields of smart 3D micro-nano electronics, 3D wearable devices, micro/nano-sensors, and health care.
Paraskevas Kontis, Edouard Chauvet, Zirong Peng
et al.
There are still debates regarding the mechanisms that lead to hot cracking in parts build by additive manufacturing (AM) of non-weldable Ni-based superalloys. This lack of in-depth understanding of the root causes of hot cracking is an impediment to designing engineering parts for safety-critical applications. Here, we deploy a near-atomic-scale approach to investigate the details of the compositional decoration of grain boundaries in the coarse-grained, columnar microstructure in parts built from a non-weldable Ni-based superalloy by selective electron-beam melting. The progressive enrichment in Cr, Mo and B at grain boundaries over the course of the AM-typical successive solidification and remelting events, accompanied by solid-state diffusion, causes grain boundary segregation induced liquation. This observation is consistent with thermodynamic calculations. We demonstrate that by adjusting build parameters to obtain a fine-grained equiaxed or a columnar microstructure with grain width smaller than 100 $μ$m enables to avoid cracking, despite strong grain boundary segregation. We find that the spread of critical solutes to a higher total interfacial area, combined with lower thermal stresses, helps to suppress interfacial liquation.
IoT is considered as one of the key enabling technologies for the fourth industrial revolution, that is known as Industry 4.0. In this paper, we consider the mechatronic component as the lowest level in the system composition hierarchy that tightly integrates mechanics with the electronics and software required to convert the mechanics to intelligent (smart) object offering well defined services to its environment. For this mechatronic component to be integrated in the IoT-based industrial automation environment, a software layer is required on top of it to convert its conventional interface to an IoT compliant one. This layer, that we call IoTwrapper, transforms the conventional mechatronic component to an Industrial Automation Thing (IAT). The IAT is the key element of an IoT model specifically developed in the context of this work for the manufacturing domain. The model is compared to existing IoT models and its main differences are discussed. A model-to-model transformer is presented to automatically transform the legacy mechatronic component to an IAT ready to be integrated in the IoT-based industrial automation environment. The UML4IoT profile is used in the form of a Domain Specific Modeling Language to automate this transformation. A prototype implementation of an Industrial Automation Thing using C and the Contiki operating system demonstrates the effectiveness of the proposed approach.
Among a variety of solution-based approaches to fabricate anisotropic films of aligned carbon nanotubes (CNTs), we focus on the dielectrophoretic assembly method using AC electric fields in DNA-stabilized CNT suspensions. We demonstrate that a one-stop manufacturing system using electrode needles can draw anisotropic DNA-CNT hybrid films of 10-100 $μ$m in size (i.e., free-standing DNA-CNT micro-cloths) from the remaining suspension into the atmosphere while maintaining structural order. It has been found that a maximal degree of polarization (ca. 40 \%) can be achieved by micro-cloths fabricated from a variety of DNA-CNT mixtures. Our results suggest that the one-stop method can impart biocompatibility to the downsized CNT films and that the DNA-stabilized CNT micro-cloths directly connected to an electrode could be useful for biofuel cells in terms of electron transfer and/or enzymatic activity.