Hasil untuk "Manufactures"

G. Bertin, D. Averbeck

Garrett W. Melenka, B. O. Cheung, Jonathon S. Schofield et al.

J. Eaton, Samuel Kortum, Brent Neiman et al.

Peter Pak, Amir Barati Farimani

This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.

Bazigu Alex, Mwebaze Johnson

The increasing demands for sustainable and efficient manufacturing systems have driven the integration of Internet of Things (IoT) technologies into smart manufacturing. This study investigates IoT-enabled systems designed to enhance energy efficiency and resource optimization in the manufacturing sector, focusing on a multi-layered architecture integrating sensors, edge computing, and cloud platforms. MATLAB Simulink was utilized for modeling and simulation, replicating typical manufacturing conditions to evaluate energy consumption, machine uptime, and resource usage. The results demonstrate an 18% reduction in energy consumption, a 22% decrease in machine downtime, and a 15% improvement in resource utilization. Comparative analyses highlight the superiority of the proposed framework in addressing operational inefficiencies and aligning with sustainability goals. The study underscores the potential of IoT in transforming traditional manufacturing into interconnected, intelligent systems, offering practical implications for industrial stakeholders aiming to optimize operations while adhering to global sustainability standards. Future work will focus on addressing identified challenges such as high deployment costs and data security concerns, aiming to facilitate the broader adoption of IoT in industrial applications. Keywords: IoT (Internet of Things), Smart Manufacturing, Energy Efficiency, Resource Optimization, Manufacturing

Artem B. Solomashenko, Olga L. Afanaseva, Maria V. Shishova et al.

This review considers the modern industrial applications of augmented reality headsets. It draws upon a synthesis of information from open sources and press releases of companies, as well as the first-hand experiences of industry representatives. Furthermore, the research incorporates insights from both profile events and in-depth discussions with skilled professionals. A specific focus is placed on the ergonomic characteristics of headsets: image quality, user-friendliness, etc. To provide an objective evaluation of the various headsets, a metric has been proposed which is dependent on the specific application case. This enables a comprehensive comparison of the various devices in terms of their quantitative characteristics, which is of particular importance for the formation of a rapidly developing industry.

Nazeer Bilal, Pradeep Carol Santhosh, Vargas Patricia A. et al.

This study presents a comprehensive study of a novel Contact-Based Pose Estimation Method (CBPEM) for enhancing precision in robotic assembly processes within digital twin frameworks. Conventional pose detection methods, such as laser and computer vision-based point cloud acquisition, are often hindered by limitations related to optical properties and occlusion when detecting small or intricate components. In contrast, CBPEM leverages contact-based detection using capacitive or load cell sensors, offering a high degree of position and orientation accuracy while mitigating the optical challenges posed by traditional methods. This study focuses on the precision assembly of a concentrator photovoltaic solar unit, which consists of primary and secondary lenses, a solar cell, and a tripod leg their small size, deformability, and unique optical properties, making pose estimation particularly challenging. Experimental evaluations were conducted to compare the effectiveness of capacitive and load cell sensors in detecting contact points, assessing their precision and accuracy on flexible and rigid components. CBPEM demonstrated commendable performance with position accuracies reaching 0.05 mm and orientation accuracies around 0.4 degrees, matching or surpassing traditional optical methods. While CBPEM provides enhanced accuracy, it requires sequential data acquisition, resulting in lower detection speeds compared to optical methods. Additionally, the method’s efficacy depends on the precision of robotic components and may be impacted by complex geometries or highly deformable surfaces. Overall, CBPEM offers a robust alternative for precision pose estimation in digital twin-driven robotic assembly, particularly when dealing with components unsuited to optical methods. Future research should explore hybrid approaches to optimize detection speed and adaptability across a broader range of robotic assembly scenarios.

Rahul Sharma, Maziar Raissi, Y. B. Guo

Compared to physics-based computational manufacturing, data-driven models such as machine learning (ML) are alternative approaches to achieve smart manufacturing. However, the data-driven ML's "black box" nature has presented a challenge to interpreting its outcomes. On the other hand, governing physical laws are not effectively utilized to develop data-efficient ML algorithms. To leverage the advantages of ML and physical laws of advanced manufacturing, this paper focuses on the development of a physics-informed machine learning (PIML) model by integrating neural networks and physical laws to improve model accuracy, transparency, and generalization with case studies in laser metal deposition (LMD).

Guojin Chen, Haoyu Yang, Bei Yu et al.

Advancements in chip design and manufacturing have enabled the processing of complex tasks such as deep learning and natural language processing, paving the way for the development of artificial general intelligence (AGI). AI, on the other hand, can be leveraged to innovate and streamline semiconductor technology from planning and implementation to manufacturing. In this paper, we present \textit{Intelligent OPC Engineer Assistant}, an AI/LLM-powered methodology designed to solve the core manufacturing-aware optimization problem known as optical proximity correction (OPC). The methodology involves a reinforcement learning-based OPC recipe search and a customized multi-modal agent system for recipe summarization. Experiments demonstrate that our methodology can efficiently build OPC recipes on various chip designs with specially handled design topologies, a task that typically requires the full-time effort of OPC engineers with years of experience.

Abdulla Almesmari, Imad Barsoum, Rashid K. Abu Al-Rub

This study evaluates topologically optimized lattice structures for high strain rate loading, crucial for impact resistance. Using the BESO (Bidirectional Evolution Structural Optimisation) topology optimisation algorithm, CompIED and ShRIED topologies are developed for enhanced energy absorption and impact resistance. Micromechanical simulations reveal CompIED surpasses theoretical elasticity limits for isotropic cellular materials, while the hybrid design ShRComp achieves theoretical maximum across all relative densities. Compared to TPMS, truss, and plate lattices, the proposed structures exhibit higher uniaxial modulus. Manufactured via fused deposition modeling with ABS thermoplastic, their energy absorption capabilities are assessed through compression tests and impact simulations. The ShRComp lattice demonstrates superior energy absorption under compression compared to CompIED. Impact analyses of CompIED and ShRComp sandwich structures at varying velocities show exceptional resistance to perforation and higher impact absorption efficiency, outperforming other classes of sandwich structures at similar densities. These findings position these new and novel topologies as promising candidates for impact absorption applications.

Yu Song, Zhenyu Chen, Tongzheng Wei et al.

Drawing upon the intricacies of nature, bionics has significantly bolstered the engineering structure performance by providing innovative solutions and novel design principles. This study presented a tapered hollow strut lattice structure design that is inspired by the unique structural attributes of bamboo. The relative density, mechanical responses and Zenner’s anisotropy of the developed BCC, RD and OCTET unit cells with tapered hollow struts were simulated, while the corresponding geometric configurations that deliver the best combinations of physical and mechanical properties were optimized. The selected unit cells were then fabricated into 3 × 3 × 3 type lattice structures by laser powder bed fusion (LPBF) for experimental analysis. The compression results confirmed that the tapered hollow strut design obviously improved the deformation stability as compared with the straight hollow strut and solid strut design counterparts. Deformation modes analysis suggested that the tapered hollow strut design enhanced the strength and shear resistance, which contributed to the deformation stability improvement of the designed lattice structure. The current study is envisaged to provide useful guidance for future bio-inspired lattice structure design, with the final aim of enhancing the mechanical properties of the lightweight components.

Andrew Weng, Jason B. Siegel, Anna Stefanopoulou

Voltage-based battery metrics are ubiquitous and essential in battery manufacturing diagnostics. They enable electrochemical "fingerprinting" of batteries at the end of the manufacturing line and are naturally scalable, since voltage data is already collected as part of the formation process which is the last step in battery manufacturing. Yet, despite their prevalence, interpretations of voltage-based metrics are often ambiguous and require expert judgment. In this work, we present a method for collecting and analyzing full cell near-equilibrium voltage curves for end-of-line manufacturing process control. The method builds on existing literature on differential voltage analysis (DVA or dV/dQ) by expanding the method formalism through the lens of reproducibility, interpretability, and automation. Our model revisions introduce several new derived metrics relevant to manufacturing process control, including lithium consumed during formation and the practical negative-to-positive ratio, which complement standard metrics such as positive and negative electrode capacities. To facilitate method reproducibility, we reformulate the model to account for the "inaccessible lithium problem" which quantifies the numerical differences between modeled versus true values for electrode capacities and stoichiometries. We finally outline key data collection considerations, including C-rate and charging direction for both full cell and half cell datasets, which may impact method reproducibility. This work highlights the opportunities for leveraging voltage-based electrochemical metrics for online battery manufacturing process control.

Harshit Gupta, Ashok Kumar Madan

This article provides an overview of the evolution of the product quality and measurement inspection procedure with emphasis on the Reconfigurable Inspection System and Machine. The major components of a reconfigurable manufacturing system have been examined, and the evolution of manufacturing processes has been briefly discussed. Different Reconfigurable Inspection Machines (RIMs) and their arrangement in an assembly line as an inspection system have been carefully studied and the modern inspection system equipped in RMS has been compared to the traditional techniques commonly used in inspection of product quality. A survey of evolving inspection techniques is offered from the standpoint of technological challenges and advancement affecting manufacturing over time. As per authors' knowledge, the review on Reconfigurable Inspection in Manufacturing and taxonomy of reconfigurable inspection systems is rare. Considering the studies done in this domain, there is still resourceful taxonomy for this paradigm. Therefore, different types of inspection procedures have been discussed, their features and applications have been compared to arrive at the taxonomy of the RIS based on the understanding of the nature of a RIS after a critical review.

Margarita Ntousia, Ioannis Fudos, Spyridon Moschopoulos et al.

Additive manufacturing is a process that has facilitated the cost effective production of complicated designs. Objects fabricated via additive manufacturing technologies often suffer from dimensional accuracy issues and other part specific problems such as thin part robustness, overhang geometries that may collapse, support structures that cannot be removed, engraved and embossed details that are indistinguishable. In this work we present an approach to predict the dimensional accuracy per vertex and per part. Furthermore, we provide a framework for estimating the probability that a model is fabricated correctly via an additive manufacturing technology for a specific application. This framework can be applied to several 3D printing technologies and applications. In the context of this paper, a thorough experimental evaluation is presented for binder jetting technology and applications.

Ali Ahmad Malik

The thrust for increased rating capacity of wind turbines has resulted into larger generators, longer blades, and taller towers. Presently, up to 16 MW wind turbines are being offered by wind turbines manufacturers which is nearly a 60 percent increase in the design capacity over the last five years. Manufacturing of these turbines involves assembling of gigantic sized components. Due to the frequent design changes and the variety of tasks involved, conventional automation is not possible making it a labor-intensive activity. However the handling and assembling of large components are challenging the human capabilities. The article proposes the use of mobile robotic assistants for partial automation of wind turbines manufacturing. The robotic assistant can result into reducing production costs, and better work conditions. The article presents development of a robot assistant for human operators to effectively perform assembly of wind turbines. The case is from a leading wind turbines manufacturer. The developed system is also applicable to other cases of large component manufacturing involving intensive manual effort.

Shahzad Khalil, Mirza Ameen ul Haq

This study is evaluating the customer-based retail brand equity by the effect of consumption value and brand experience. Considering Holbrook’s value typology, this study is investigating the value dimensions of efficiency, entertainment, excellence, and aesthetics of retail setup. The purpose of the study is to examine the impact of retail value i.e. efficiency, entertainment, excellence, aesthetics on retail brand equity by intervention of brand experience. This study would be applied on sample population who purchase products from various retail supermarket in Karachi and Lahore.  This study employed Partial Least Squares Structural Equation Modelling (PLS-SEM) by using the SmartPLS 3.0 software. The study revealed that there was a significantly positive impact of efficiency, service, entertainment and aesthetic value on brand experience, but the impact of product excellence on brand experience was insignificant. Similarly, brand experience fully mediated the relationships of efficiency, service, entertainment and aesthetic value with retail brand equity but brand experience didn’t mediated between product excellence and retail brand equity. Although, there was a positively direct relationship between product excellence and retail brand equity. This study gives very important suggestions to retail marketing strategists in order to give customers memorable retail brand experience and creating retail brand equity.

Georgios Sofianidis, Jože M. Rožanec, Dunja Mladenić et al.

The implementation of Artificial Intelligence (AI) systems in the manufacturing domain enables higher production efficiency, outstanding performance, and safer operations, leveraging powerful tools such as deep learning and reinforcement learning techniques. Despite the high accuracy of these models, they are mostly considered black boxes: they are unintelligible to the human. Opaqueness affects trust in the system, a factor that is critical in the context of decision-making. We present an overview of Explainable Artificial Intelligence (XAI) techniques as a means of boosting the transparency of models. We analyze different metrics to evaluate these techniques and describe several application scenarios in the manufacturing domain.

Amir M. Mirzendehdel, Morad Behandish, Saigopal Nelaturi

Metal additive manufacturing (AM) processes often fabricate a near-net shape that includes the as-designed part as well as the sacrificial support structures that need to be machined away by subtractive manufacturing (SM), for instance multi-axis machining. Thus, although AM is capable of generating highly complex parts, the limitations of SM due to possible collision between the milling tool and the workpiece can render an optimized part non-manufacturable. We present a systematic approach to topology optimization (TO) of parts for AM followed by SM to ensure removability of support structures, while optimizing the part's performance. A central idea is to express the producibility of the part from the near-net shape in terms of accessibility of every support structure point using a given set of cutting tool assemblies and fixturing orientations. Our approach does not impose any artificial constraints on geometric complexity of the part, support structures, machining tools, and fixturing devices. We extend the notion of inaccessibility measure field (IMF) to support structures to identify the inaccessible points and capture their contributions to non-manufacturability by a continuous spatial field. IMF is then augmented to the sensitivity field to guide the TO towards a manufacturable design. The approach enables efficient and effective design space exploration by finding nontrivial complex designs whose near-net shape can be 3D printed and post-processed for support removal by machining with a custom set of tools and fixtures. We demonstrate the efficacy of our approach on nontrivial examples in 2D and 3D.

Trier Mortlock, Deepan Muthirayan, Shih-Yuan Yu et al.

Future manufacturing requires complex systems that connect simulation platforms and virtualization with physical data from industrial processes. Digital twins incorporate a physical twin, a digital twin, and the connection between the two. Benefits of using digital twins, especially in manufacturing, are abundant as they can increase efficiency across an entire manufacturing life-cycle. The digital twin concept has become increasingly sophisticated and capable over time, enabled by rises in many technologies. In this paper, we detail the cognitive digital twin as the next stage of advancement of a digital twin that will help realize the vision of Industry 4.0. Cognitive digital twins will allow enterprises to creatively, effectively, and efficiently exploit implicit knowledge drawn from the experience of existing manufacturing systems. They also enable more autonomous decisions and control, while improving the performance across the enterprise (at scale). This paper presents graph learning as one potential pathway towards enabling cognitive functionalities in manufacturing digital twins. A novel approach to realize cognitive digital twins in the product design stage of manufacturing that utilizes graph learning is presented.

Tianyu Zhang, Xiangjia Chen, Guoxin Fang et al.

Multi-axis additive manufacturing enables high flexibility of material deposition along dynamically varied directions. The Cartesian motion platforms of these machines include three parallel axes and two rotational axes. Singularity on rotational axes is a critical issue to be tackled in motion planning for ensuring high quality of manufacturing results. The highly nonlinear mapping in the singular region can convert a smooth toolpath with uniformly sampled waypoints defined in the model coordinate system into a highly discontinuous motion in the machine coordinate system, which leads to over-extrusion / under-extrusion of materials in filament-based additive manufacturing. The problem is challenging as both the maximal and the minimal speeds at the tip of a printer head must be controlled in motion. Moreover, collision may occur when sampling-based collision avoidance is employed. In this paper, we present a motion planning method to support the manufacturing realization of designed toolpaths for multi-axis additive manufacturing. Problems of singularity and collision are considered in an integrated manner to improve the motion therefore the quality of fabrication.