48 research outputs found
A novel method for high-volume manufacturing of self-protective plastic surfaces to ensure durable anti-counterfeiting functionality
No full textEnhancing weld line visibility prediction in injection molding using physics-informed neural networks
No full textThis study introduces a novel approach using Physics-Informed Neural Networks (PINN) to predict weld line visibility in injection-molded components based on process parameters. Leveraging PINNs, the research aims to minimize experimental tests and numerical simulations, thus reducing computational efforts, to make the classification models for surface defects more easily implementable in an industrial environment. By correlating weld line visibility with the Frozen Layer Ratio (FLR) threshold, identified through limited experimental data and simulations, the study generates synthetic datasets for pre-training neural networks. This study demonstrates that a quality classification model pre-trained with PINN-generated datasets achieves comparable performance to a randomly initialized network in terms of Recall and Area Under the Curve (AUC) metrics, with a substantial reduction of 78% in the need for experimental points. Furthermore, it achieves similar accuracy levels with 74% fewer experimental points. The results demonstrate the robustness and accuracy of neural networks pre-trained with PINNs in predicting weld line visibility, offering a promising approach to minimizing experimental efforts and computational resources
Transfer Learning-Based Artificial Neural Network for Predicting Weld Line Occurrence through Process Simulations and Molding Trials
No full textOptimizing process parameters to minimize defects remains an important challenge in injection molding (IM). Machine learning (ML) techniques offer promise in this regard, but their application often requires extensive datasets. Transfer learning (TL) emerges as a solution to this problem, leveraging knowledge from related tasks to enhance model training and performance. This study explores TL's viability in predicting weld line visibility in injection-molded components using artificial neural networks (ANNs). TL techniques are employed to transfer knowledge between datasets related to different components. Furthermore, both source datasets obtained from simulations and experimental tests are used during the study. In order to use process simulations to obtain data regarding the presence of surface defects, it was necessary to correlate an output variable of the simulations with the experimental observations. The results demonstrate TL's efficacy in reducing the data required for training predictive models, with simulations proving to be a cost-effective alternative to experimental data. TL from simulations achieves comparable predictive metric values to those of the non-pre-trained network, but with an 83% reduction in the required data for the target dataset. Overall, transfer learning shows promise in streamlining injection molding optimization and reducing manufacturing costs
A Multi-Standard Reconfigurable Viterbi Decoder using Embedded FPGA Blocks
No full textThis paper presents a Viterbi Decoder (VD) architecture for a reprogrammable data transmission system, implemented using a Field Programmable Gate Array (FPGA) device. This VD has been conceived as a building block of a Software Defined
Radio (SDR) mobile transceiver, reconfigurable on user request and capable to provide agility in choosing between different standards. UMTS and GPRS standards decoding is achieved by choosing different coding rates and constraint lengths, and the possibility to switch, at run time, between them guarantees a high degree of reconfigurability. The architecture has been tested and verified with a Xilinx XC2V2000 FPGA, to provide a generalized co-simulation/co-design testbed. The results show that this decoder can sustain an uncoded data rate of about 2 Mbps, with an area
occupation of 45%, due to the efficient resource reuse
Real-Time Generation of Standard-Compliant DVB-T Signals
No full textThis paper proposes and discusses two software implementations of the DVB-T modulator, using C++ and MATLAB, respectively. All the key features of the DVB-T standard are included. The C++ DVB-T modulator, incorporated into the Iris framework developed by Trinity College of Dublin, works in real time on an Intel Core i7 2.4 GHz CPU with the Iris testbed. The MATLAB-based DVB-T modulator is coupled with a receiver implementation with channel estimation, equalization, soft-output demapping and channel decoding. The validation step demonstrates that the proposed DVB-T software implementations generate standard-compliant DVB-T signals that are correctly received by commercially available TV sets and USB dongles. The software code for the Iris-based C++ modulator, and for the MATLAB-based modulator and receiver, has been made publicly available under the GNU license
Heterozygosis drives maize hybrids to select elite probiotic Pseudomonas strains among resident soil populations.
No full textBy comparing the distribution of genomic and phenotypic markers among rhizospheric Pseudomonas strains recovered from two maize hybrids, with those of strains recovered from their four respective parental lines, we evidenced that both hybrids supported more elite probiotic strains than parents. Elite Pseudomonas strains showed potential for an appropriate in vitro 2,4-diacetylphloroglucinol (DAPG) and auxin (AIA) productivity, and a superior root-colonization ability. The actual biocontrol, root-stimulation and root-colonization abilities of these strains were confirmed by bioassays on five fungal strains and on axenic maize plants. Finally, results on the abundance and genetic diversity of resident probiotic Pseudomonas strains indicated that each hybrid was able to select its own specific probiotic population, while the four parental lines were not. The evidence that heterozygosis can drive maize plants to select elite probiotic rhizospheric DAPG+ -AIA+ Pseudomonas strains opens the way to a new strategy in the set up of plant breeding for low-input and organic agriculture
AI-driven ground robots: mobile edge computing and mmWave communications at work
No full textThe seamless integration of multiple radio access technologies (multi-RAT) and cloud/edge resources is pivotal for advancing future networks, which seek to unify distributed and heterogeneous computing and communication resources into a cohesive continuum system, tailored for mobile applications. Many research projects and focused studies are proposing solutions in this area, the impact of which is undoubtedly increased by moving from theoretical and simulation studies to experimental validations. To this aim, this paper proposes a testbed architecture that combines contemporary communication and cloud technologies to provide microservice-based mobile applications with the ability to offload part of their tasks to cloud/edge data centers connected by multi-RAT cellular networks. The testbed leverages Kubernetes, Istio service mesh, OpenFlow, public 5G networks, and IEEE 802.11ad mmWave (60 GHz) Wi-Fi access points. The architecture is validated through a use case in which a ground robot autonomously follows a moving object by using an artificial intelligence-driven computer vision application. Computationally intensive navigation tasks are offloaded by the robot to microservice instances, which are executed on demand within cloud and edge data centers that the robot can exploit during its journey. The proposed testbed is flexible and can be reused to assess communication and cloud innovations focusing on multi-RAT cloud continuum scenarios
Organic breeding should select for plant genotypes able to efficiently exploit indigenous Probiotic Rhizobacteria
No full textIn order to rapidly achieve crop varieties adapted to organic crop production systems, it is of crucial importance to know plant genotype potential for positive interactions with soil indigenous microflora. In this frame, European research efforts are now considering beneficial non-symbiotic (probiotic) rhizobacteria as an essential factor for sustainable plant breeding. Published findings are beginning to elucidate how probiotic rhizobacteria contribute to plant nutrient assimilation and disease resistance. Future efforts for crop breeding in organic agriculture should take into the right account the capacity of plants to efficiently exploit indigenous probiotic rhizobacteria in low-input cultural conditions
An Improved Algorithm for On-Chip Clustering and Lossless Data Compression of HL-LHC Pixel Hits
No full textA prototype chip, called RD53A, has been designed by the RD53 collaboration to face the very high hit and trigger rate requirements (up to 3 GHz/cm2 and 1 MHz, respectively) of the High Luminosity LHC experiment upgrades. In this paper, an improved algorithm for data compression, capable of sustaining the very high data volume and proposed to be implemented in the periphery of the chip, is presented: it exploits Run Length Encoding (RLE) and Variable Length Coding (VLC) to compact chip pixel hit patterns. The compression and decompression algorithms are implemented with MATLAB, and the performance is calculated taking into account the RD53A data readout implementation and its chip simulation and verification framework (called VEPIX53). In all considered cases, the results show that the RLE and VLC combination achieves a data compression ratio between 1.57 and 1.62, resulting in a bitstream size reduction between 36.2% and 38.4% with respect to the rate of the current data transmission format
