1|INTRODUCTION In Linyi,Shandong,China,researchers used 100%grid-forming(GFM)photovoltaics(PVs)to power the microgrid without the conventional synchronous *** microgrid operates independently and stably supporting the...
详细信息
1|INTRODUCTION In Linyi,Shandong,China,researchers used 100%grid-forming(GFM)photovoltaics(PVs)to power the microgrid without the conventional synchronous *** microgrid operates independently and stably supporting the seamless transition between islanded and grid-connected *** to the grid-following(GFL)method,GFM enables renewable sources to behave like voltage sources with the transient frequency and voltage *** is the key technology for the renewable generations to replace the con-ventional generations to maintain the synchronous stability of the ***,most GFM methods are developed for the battery energy storage system(BESS)and focus on the single-machine level to emulate the conventional synchronous machine,such as virtual synchronous machine(VSM)1 and droop control.2 These methods tend to lose the synchronous stability in response to the large disturbances under the multi-machine conditions.
This paper presents PSS (Power system stabilizer) design based on fractional order fuzzy PID (FOFPID). The proposed PSS architecture design is considered for single-machine infinite bus power system. The primary goal ...
详细信息
With more inverter-based resources (IBRs), our power systems have lower frequency nadirs following N-1 contingencies, and undesired under-frequency load shedding (UFLS) can occur. To address this challenge, IBRs can b...
详细信息
We propose the lattice design that allows multiple topologically protected edge modes. The scattering between these modes, which is linear, energy preserving, and robust against local disorders, is discussed in terms ...
详细信息
ISBN:
(数字)9798350372076
ISBN:
(纸本)9798350372083
We propose the lattice design that allows multiple topologically protected edge modes. The scattering between these modes, which is linear, energy preserving, and robust against local disorders, is discussed in terms of signal processing capacity.
Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional ...
详细信息
Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.
Cyber-physical distribution systems (CPDS) have emerged from the integration of information technology into distribution systems. While offering substantial benefits, this integration also introduces vulnerabilities. ...
详细信息
Very recently,intensive discussions and studies on Industry 5.0 have sprung up and caused the attention of researchers,entrepreneurs,and policymakers from various sectors around the ***,there is no consensus on why an...
详细信息
Very recently,intensive discussions and studies on Industry 5.0 have sprung up and caused the attention of researchers,entrepreneurs,and policymakers from various sectors around the ***,there is no consensus on why and what is Industry 5.0 *** this paper,we define Industry 5.0from its philosophical and historical origin and evolution,emphasize its new thinking on virtual-real duality and human-machine interaction,and introduce its new theory and technology based on parallel intelligence(PI),artificial societies,computational experiments,and parallel execution(the ACP method),and cyber-physical-social systems(CPSS).Case studies and applications of Industry 5.0 over the last decade have been briefly summarized and analyzed with suggestions for its future *** believe that Industry 5.0 of virtual-real interactive parallel industries has great potentials and is critical for building smart *** are outlined to ensure a roadmap that would lead to a smooth transition from CPS-based Industry 4.0 to CPSS-based Industry 5.0 for a better world which is Safe in physical spaces,S ecure in cyberspaces,Sustainable in ecology,Sensitive in individual privacy and rights,Service for all,and Smartness of all.
Recently, Transformer has achieved great success in computer vision. However, it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection ...
Recently, Transformer has achieved great success in computer vision. However, it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection applications from point clouds. Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points. To address these limitations, we propose the cosh-attention, which reduces the computation complexity of space and time from the quadratic order to linear order with respect to the number of points. In the cosh-attention, the traditional softmax operator is replaced by non-negative ReLU activation and hyperbolic-cosine-based operator with re-weighting mechanism. Then based on the key component, cosh-attention, we present a two-stage hyperbolic cosine transformer (ChTR3D) for 3D object detection from point clouds. It refines proposals by applying cosh-attention in linear computation complexity to encode rich contextual relationships among points. Extensive experiments on the widely used KITTI dataset and Waymo Open Dataset demonstrate that, compared with vanilla attention, the cosh-attention significantly improves the inference speed with competitive performance. Experiment results show that, among two-stage state-of-the-art methods using point-level features to refine proposals, the proposed ChTR3D is the fastest one.
暂无评论