articles+ search results

штучний інтелект, fpga, ші як сервіс, гетерогенні проєкти ші систем, апаратні прискорювачі ші, dpu, інструментальні засоби розробки ші, xrt, Motor vehicles. Aeronautics. Astronautics, and TL1-4050

The subject of study in this article is modern technologies, tools and methods of building AI systems as a service using FPGA as a platform. The goal is to analyze modern technologies and tools used to develop FPGA-based projects for systems that implement artificial intelligence as a service and to prepare a practical AI service prototype. Task: to analyze the evolution of changes in the products of leading manufacturers of programmable logic devices and experimental and practical examples of the implementation of the paradigm of continuous reprogramming of programmable logic; analyze the dynamics of changes in the development environment of programmable logic systems for AI; analyze the essential elements of building projects for AI systems using programmable logic. According to the tasks, the following results were obtained. The area of application of hardware implementation of artificial intelligence for on-board and embedded systems including airspace industry, smart cars and medical systems is analyzed. The process of programming FPGA accelerators for AI projects is analyzed. The analysis of the capabilities of FPGA with HBM for building projects that require enough of high speed memory is performed. Description languages, frameworks, the hierarchy of tools for building of hardware accelerators for AI projects are analyzed in detail. The stages of prototyping of AI projects using new FPGA development tools and basic DPU blocks are analyzed. The parameters of the DPU blocks were analyzed. Practical steps for building such systems are offered. The practical recommendations for optimizing the neural network for FPGA implementation are given. The stages of neural network optimization are provided. The proposed steps include pruning of branches with low priority and the use of fixed point computations with custom range based on the requirements of an exact neural network. Based on these solutions, a practical case of AI service was prepared, trained and tested. Conclusions. The main contribution of this study is that, based on the proposed ideas and solutions, the next steps to create heterogeneous systems based on the combination of three elements are clear: AI as a service, FPGA accelerators as a technology for improving performance, reliability and security, and cloud or Edge resources to create FPGA infrastructure and AI as service. The development of this methodological and technological basis is the direction of further R&D.

Directed energy deposition, entropy, grain refinement, alloy design, Industrial engineering. Management engineering, and T55.4-60.8

Additive manufacturing (AM) is a tool for rapid prototyping with complex geometry. However, the cyclic heating and cooling in laser melting processes often cause large columnar grains that dominate the as-printed microstructure, resulting in a strong texture and anisotropic properties that limit the application of AM. In this work, we apply powder-based directed energy deposition to discover new alloys using mixtures of Inconel 718 (IN718) and Stainless Steel 316L (SS316L). We discovered that the 77 wt.% IN718 alloy mixture, with the highest configurational entropy, demonstrated an intriguingly fine grain structure in the as-built condition and after homogenization at 1180°C. Residual stress from the laser melting process was identified as the primary cause of the observed grain refinement phenomenon. Although, a quantitative analysis of the changes in grain size after homogenization in the alloy mixtures of IN718 and SS316L requires further research. The discovery of this unique microstructural behavior shows how in-situ mixing of commercially available powders can be used to develop next-generation feedstock materials for AM and improve the understanding of fundamental process-microstructure-property relationships.

3D printing, Zinc submicron particles, Osteoinductivity, Anti-inflammatory, Bone defect repair, Materials of engineering and construction. Mechanics of materials, TA401-492, Biology (General), and QH301-705.5

Long-term nonunion of bone defects has always been a major problem in orthopedic treatment. Artificial bone graft materials such as Poly (lactic-co-glycolic acid)/β-tricalcium phosphate (PLGA/β-TCP) scaffolds are expected to solve this problem due to their suitable degradation rate and good osteoconductivity. However, insufficient mechanical properties, lack of osteoinductivity and infections after implanted limit its large-scale clinical application. Hence, we proposed a novel bone repair bioscaffold by adding zinc submicron particles to PLGA/β-TCP using low temperature rapid prototyping 3D printing technology. We first screened the scaffolds with 1 wt% Zn that had good biocompatibility and could stably release a safe dose of zinc ions within 16 weeks to ensure long-term non-toxicity. As designed, the scaffold had a multi-level porous structure of biomimetic cancellous bone, and the Young's modulus (63.41 ± 1.89 MPa) and compressive strength (2.887 ± 0.025 MPa) of the scaffold were close to those of cancellous bone. In addition, after a series of in vitro and in vivo experiments, the scaffolds proved to have no adverse effects on the viability of BMSCs and promoted their adhesion and osteogenic differentiation, as well as exhibiting higher osteogenic and anti-inflammatory properties than PLGA/β-TCP scaffold without zinc particles. We also found that this osteogenic and anti-inflammatory effect might be related to Wnt/β-catenin, P38 MAPK and NFkB pathways. This study lay a foundation for the follow-up study of bone regeneration mechanism of Zn-containing biomaterials. We envision that this scaffold may become a new strategy for clinical treatment of bone defects.

Power electronics, Inverters, Rapid control prototyping, Experimental setups, Science (General), and Q1-390

A flexible power electronic converter embedding a rapid control prototyping platform suitable to be applied in research test setups and teaching laboratories is proposed and described in this paper. The electronic system is composed of three subsystems, namely, i) three half-bridge power boards, ii) a dc-link capacitor bank with a half-bridge power module for active dc-link control, iii) an interfacing board, called motherboard, to couple the power modules with a control unit, iv) a digital control unit with rapid control prototyping functionalities for controlling power electronic circuits. Power modules integrate sensors with related conditioning circuits, driving circuits for power switches, and protection circuits. Conversion circuits exploit GaN electronic switches for optimal performance. The architecture and implementation of the system are described in detail in this manuscript. Main applications are in the implementation of conversion circuits for supplying arbitrary ac or dc voltages or currents, testing of new control algorithms for power electronic converters, testing of systems of electronic converters in, for example, smart nanogrids or renewable energy applications, training of undergraduate and graduate students.

jaw defect, functional reconstruction, digital technology, computer-aided design, 3d printing, personalized surgical instruments, preoperative virtual surgery, immediate implantation, and Medicine

With the development of computer-aided surgery and rapid prototyping via 3D printing technology, digital surgery has rapidly advanced in clinical practice, especially in the field of oral and maxillofacial surgery. 3D printing technology has been applied to the functional restoration and reconstruction of the jawbone. Before surgery, a 3D digital model is constructed through software to plan the scope of the osteotomy, shape the bone graft and plan the placement of the implant. Additionally, 3D models of personalized surgical instrument guides are printed prior to surgery. With these 3D-printed models and guides, accurate excision of the jaw tumor, accurate placement of the grafted bone and precise placement of implants can be achieved during surgery. Postoperative evaluation of accuracy and function shows that 3D printing technology can aid in achieving the biomechanical goals of simultaneous implant placement in jaw reconstruction, and in combination with dental implant restoration, the technology can improve patients' postoperative occlusal and masticatory functions. Nevertheless, 3D printing technology still has limitations, such as time-consuming preparation before surgery. In the future, further development of 3D printing technology, optimization of surgical plans, and alternative biological materials are needed. Based on domestic and foreign literature and our research results, we have reviewed the process and clinical application prospects of jaw reconstruction via 3D printing technology to provide a reference for oral and maxillofacial surgeons.

Artificial intelligence, Machine learning, AutoML, Business analytics, Data-driven decision making, Digital transformation, Cybernetics, Q300-390, Electronic computers. Computer science, and QA75.5-76.95

The realization that AI-driven decision-making is indispensable in today's fast-paced and ultra-competitive marketplace has raised interest in industrial machine learning (ML) applications significantly. The current demand for analytics experts vastly exceeds the supply. One solution to this problem is to increase the user-friendliness of ML frameworks to make them more accessible for the non-expert. Automated machine learning (AutoML) is an attempt to solve the problem of expertise by providing fully automated off-the-shelf solutions for model choice and hyperparameter tuning. This paper analyzed the potential of AutoML for applications within business analytics, which could help to increase the adoption rate of ML across all industries. The H2O AutoML framework was benchmarked against a manually tuned stacked ML model on three real-world datasets. The manually tuned ML model could reach a performance advantage in all three case studies used in the experiment. Nevertheless, the H2O AutoML package proved to be quite potent. It is fast, easy to use, and delivers reliable results, which come close to a professionally tuned ML model. The H2O AutoML framework in its current capacity is a valuable tool to support fast prototyping with the potential to shorten development and deployment cycles. It can also bridge the existing gap between supply and demand for ML experts and is a big step towards automated decisions in business analytics. Finally, AutoML has the potential to foster human empowerment in a world that is rapidly becoming more automated and digital.

Upscaling, Scaling up, Climate services, Prototyping, Pilot projects, Meteorology. Climatology, QC851-999, Social sciences (General), and H1-99

Translating climate data and information for use in real-world applications often involves the development of climate service prototypes within the constraints of pilot or demonstration projects. However, these services rarely make the transition from prototype to fully-fledged, transferrable and/or repeatable climate services – that is, there are problems with upscaling them beyond the pilot/demonstrator phase.In this paper we are using the mainstream understanding of the three main types of upscaling: reaching many (horizontal), enhancing the enabling environment (vertical), and expanding the product or service’s features (functional). Through a review of the general upscaling literature, coupled with focused interviews with weather/climate services experts, we found that there are common barriers to, and enablers for, successful upscaling – many of which apply to the specific case of upscaling climate services. Barriers include problems with leadership (e.g. the absence of a long-term vision and/or strategy for upscaling); limited funding or lack of a business model for the service at scale; issues with the enabling environment for upscaling (e.g. poor policy context, inadequate governance systems); and poor user engagement.Lessons learned from the literature in the context of upscaling climate services include planning for it as early as possible in the prototyping process; including a monitoring, evaluation and learning approach to inform upscaling progress; taking actions to foster and enhance the enabling environment; and searching for a balance between generic solutions and fit-for-purpose products.

additive manufacturing, 3d printing, materials mechanics, manufacturing engineering, industrial engineering, Science, Manufactures, and TS1-2301