- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Data-driven and probabilistic learning of the process-structure-property relationship in solution-grown tellurene for optimized nanomanufacturing of high-performance nanoelectronics
摘要： Two-dimensional (2-D) semiconductors have been intensely explored as alternative channel materials for future generation ultra-scaled transistor technology [1–8]. However, significant roadblocks (e.g., poor carrier mobilities [9–11], instability [4,5,10], and vague potential in scaling-up [10,12–15]) exist that prevent the realization of the current state-of-the-art 2-D materials’ potential for energy-efficient electronics. The emergent solution-grown tellurene exhibits attractive attributes, e.g., high room-temperature mobility, large on-state current density, air-stability, and tunable material properties through a low-cost, scalable process, to tackle these challenges [16]. Nevertheless, the fundamental manufacturing science of the hydrothermal processing for tellurene remains elusive. Here, we report on the first systematic, data-driven learning of the process-structure-property relationship in solution-grown tellurene, revealing the process factors’ effects on tellurene’s production yield, dimensions, and transistor-relevant properties, through a holistic approach integrating both the experimental explorations and data analytics. We further demonstrate the application of such fundamental knowledge for developing tellurene transistors with optimized and reliable performance, which can enable the cost-effective realization of high-speed, energy-efficient electronics.
关键词： Process-structure-property relationship,2-D materials,Energy-efficient electronics,Nanomanufacturing,Tellurene,Data-driven learning
更新于2025-09-23 15:23:52
-
A data-driven model for weld bead monitoring during the laser welding assisted by magnetic field
摘要： In this research, a data-driven model is developed to monitor the seam during the laser beam welding under the influence of an external magnetic field (LBW-AMF). Firstly, a visible LBW-AMF system is built for tracking the laser melting pool and keyhole. Then, the features of the laser melting pool and keyhole are extracted with image processing techniques. The approach for an ensemble of different neural networks which includes radial basis function neural network, back-propagation neural network, and generalized regression neural network is proposed to establish the correlations of the characteristics of the laser melting pool and keyhole and the welding seam. Finally, LBW-AMF experimental results are obtained to validate the performance of the proposed data-driven model. Results illustrate that the developed model can provide a reliable result for monitoring the weld bead, which could give guidance for controlling the processing parameters in real time to improve the weld quality for practical LBW-AMF.
关键词： Image processing,Laser beam welding,Neural networks,Online monitoring,Data-driven model
更新于2025-09-23 15:21:01
-
Data-driven uncertainty analysis of distribution networks including photovoltaic generation
摘要： This paper investigates residential distribution networks with uncertain loads and photovoltaic distributed generation. An original probabilistic modeling of consumer demand and photovoltaic generation is presented that is based on the analysis of large set of data measurements. It is shown how photovoltaic generation is described by complex non-standard distributions that can be described only numerically. Probabilistic analysis is performed using an enhanced version of the Polynomial Chaos technique that exploits a proper set of polynomial basis functions. It is described how such functions can be generated from the numerically available data. Compared to other approximate methods for probabilistic analysis, the novel technique has the advantages of modeling accurately truly nonlinear problems and of directly providing the detailed Probability Density Function of relevant observable quantities affecting the quality of service. Compared to standard Monte Carlo method, the proposed technique introduces a simulation speedup that depends on the number of random parameters. Numerical applications to radial and weakly meshed networks are presented where the method is employed to explore overvoltage, unbalance factor and power loss, as a function of photovoltaic penetration and/or network configuration.
关键词： Photovoltaic generation,Data-driven models,Polynomial chaos,Unbalanced distribution networks,Probabilistic load flow,Uncertainty Analysis
更新于2025-09-23 15:21:01
-
Power Management in Active Distribution Systems Penetrated by Photovoltaic Inverters: A Data–Driven Robust Approach
摘要： Under the smart grid paradigm, distribution systems with large penetrations of photovoltaic–based power generation are called to optimize their operational resources to achieve a more ef?cient and reliable performance. In this context, this paper proposes a multiperiod mixed integer second order cone formulation to optimize distribution feeders operation. The model takes into account the feeder physical behavior; discrete control equipment (tap changers and capacitors banks) with a maximum allowable daily switching operation number; photovoltaic inverters operation; and the uncertain nature of solar energy and loads. A two–stage robust optimization framework is used to include the uncertainty into the model, where discrete and continuous control actions are assumed to be part of the ?rst and second stage of this model, respectively. The conservativeness level of the robust model is controlled by an polyhedral uncertainty set whose vertexes are adaptively adjusted in a data–driven fashion in order to better capture complex spatiotemporal dependencies among uncertain parameters. Extensive computational experiments are performed utilizing modi?ed versions of various IEEE test feeders. The performance of the proposed data–driven model is contrasted against traditional deterministic and robust budget–constrained models, using a rolling horizon out–of–sample evaluation methodology. When compared to the deterministic model, the data–driven approach yields a reduction in power losses of approximately 15% and a reduction up to 98% in hourly voltage violations. Results also suggests that the proposed approach exhibits better performance in terms of both average and conditional–value–at–risk metrics in comparison to budget–constrained models.
关键词： Distribution Systems,Data-Driven Optimization,Optimal Power Flow,Robust Optimization,Volt/VAR Control
更新于2025-09-12 10:27:22
-
A Novel Spline Model Guided Maximum Power Point Tracking Method for Photovoltaic Systems
摘要： This paper develops a novel data-driven maximum power point tracking (MPPT) method, which is of two-fold, to benefit the power generation of photovoltaics (PV) systems facing variable partial shading conditions (PSCs). Under each PSC, the proposed MPPT utilizes a compact data-driven modelling process to develop the power-voltage (P-V) curve model via the natural cubic spline. Next, the proposed MPPT method develops a novel natural cubic spline guided iterative search process to update the P-V curve model having multiple peaks and to promptly obtain the global maximum power point (GMPP) under the considered PSC. This is a pioneer study which discusses a GMPPT algorithm using a natural cubic spline based P-V curve model. The convergence of the MPP tracked by the proposed algorithm to the GMPP is theoretically ensured by the property of the natural cubic spline. The effectiveness and robustness of the proposed algorithm have been comprehensively evaluated via extensive simulation studies and experiments. Computational results demonstrate that the proposed algorithm is more efficient and effective to attain GMPPs under variable PSCs by comparing with recent MPPT methods using heuristic techniques, which are easily trapped into local MPP under variable PSCs.
关键词： photovoltaics systems,maximum power point tracking,Heuristic search,partial shading conditions,data-driven
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Discovering Temporal Patterns of Air Quality in Different Parts of Europe with Data Driven Feature Extraction
摘要： Air quality is strongly affecting human lifestyle all over the world, and its impact is apparent on healthcare, sustainable development, welfare and public administration policies. Accurate understanding of the polluting processes requires to analyze huge volumes of records, so that significant patterns and regularities can be detected. In this paper, we introduce a framework to explore the air pollution dynamics over all Europe by means of a data driven feature extraction approach. Taking advantage of MODIS records, we are able to investigate daily trends of air quality from 2003 to 2016. By means of an automatic learning scheme based on mutual information maximization, we extract the most significant patterns in the dataset. Experimental results show that the proposed approach is able to identify relevant air pollution trends that can be associated with specific physical phenomena on ground.
关键词： mutual information maximization,MODIS,data driven feature extraction,Europe,air quality
更新于2025-09-10 09:29:36
-
[Handbook of Numerical Analysis] Processing, Analyzing and Learning of Images, Shapes, and Forms: Part 1 Volume 19 || Factoring Scene Layout From Monocular Images in Presence of Occlusion
摘要： Discovering 3D arrangements of objects from single indoor monocular images is important given its many applications such as scene understanding, interior design, and content creation for AR and VR applications. The extracted information (e.g., arrangement of typical objects expressed as distributions) can provide valuable cues as to how our surrounding indoor environments are organized and how we interact with such objects. Although heavily researched in the recent years, existing approaches quickly break down under medium to heavy occlusion as the core image-space region detection module (e.g., RCNN or its variants) fails in absence of directly visible cues. Instead, we explore using holistic contextual 3D information and exploit the fact that objects in indoor scenes cooccur mostly in typical configurations. First, we use a neural network trained on real indoor annotated images to extract 2D image-space keypoints and feed them to a 3D candidate object generation stage. Then, we solve a global selection problem among these candidates using pairwise cooccurrence statistics discovered from a large 3D scene database. We iterate the process allowing for candidates with low keypoint response to be incrementally detected based on the location of the already discovered nearby objects. We demonstrate how combining deep features with shape optimization leads to performance improvement over combinations of state-of-the-art methods, especially for scenes with moderate/severe occlusion.
关键词： Keypoint detection,Data-driven modelling,Occlusion handling,Layout estimation
更新于2025-09-10 09:29:36
-
A Modeling Method of Electromagnetic Micromirror in Random Noisy Environment
摘要： In this paper, a data-driven modeling method for electromagnetically actuated micromirror in random noisy environment is proposed. In this method, the electromagnetic micromirror is considered as a dynamic system with preceded hysteresis. Then, a linear dynamic submodel is used to describe the angular deflection mechanism, while a preceded rate-dependent hysteresis submodel is used to depict the hysteresis phenomenon inherent in the electromagnetic driver. By considering the influence of random noise on the micromirror, an on-line modeling scheme with varying weighting factors is studied to handle the data contaminated by random noises. Subsequently, the convergence of proposed modeling method is analyzed. Finally, the experimental results of the proposed modeling scheme for an electromagnetically actuated micromirror are presented.
关键词： Data-driven model,modeling,micromirror,martingale convergence theorem,hysteresis
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Conference on 3D Vision (3DV) - Verona (2018.9.5-2018.9.8)] 2018 International Conference on 3D Vision (3DV) - Learning to Reconstruct Texture-Less Deformable Surfaces from a Single View
摘要： Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, and essentially relates to Shape-from-Shading. In this paper, we introduce a data-driven approach to this problem. We introduce a general framework that can predict diverse 3D representations, such as meshes, normals, and depth maps. Our experiments show that meshes are ill-suited to handle texture-less 3D reconstruction in our context. Furthermore, we demonstrate that our approach generalizes well to unseen objects, and that it yields higher-quality reconstructions than a state-of-the-art SfS technique, particularly in terms of normal estimates. Our reconstructions accurately model the fine details of the surfaces, such as the creases of a T-Shirt worn by a person.
关键词： deformable surfaces,data-driven approach,Shape-from-Shading,texture-less surfaces,3D reconstruction
更新于2025-09-04 15:30:14