Current magnetic anomaly detection (MAD) methods prioritize signal-to-noise ratio (SNR) over signal features and edge information, leading to signal distortion. To address this issue, a new MAD approach utilizes struc...
详细信息
ISBN:
(数字)9798331529192
ISBN:
(纸本)9798331529208
Current magnetic anomaly detection (MAD) methods prioritize signal-to-noise ratio (SNR) over signal features and edge information, leading to signal distortion. To address this issue, a new MAD approach utilizes structured lowrank approximation and block singular value decomposition based on the spatial frequency domain, dubbed FL-BSVD is proposed. First, the low-rankness structure of the magnetic anomaly signal is obtained through 2D Discrete Fourier Transform (2D-DFT) and structured Hankel transformation. Then, block singular value decomposition is applied to the Hankel matrix to reduce noise while preserving more signal edge features and enhancing detection accuracy. Finally, a field experiment comparing FL-BSVD with four commonly used methods is conducted. The experiment confirms that FL-BSVD can effectively recover magnetic anomaly signal features and edge information in a strong noisy environment.
In practical applications of multi-agent systems, agents are often heterogeneous, and each type of them typically has different task objectives. For heterogeneous multi-agent reinforcement learning (HMARL), the divers...
详细信息
The widespread application of unmanned aerial vehicle (UAV) has made the coverage path planning problem for multiple UAV systems a research hotspot. In this paper, we propose a multi-UAV solution to achieve complete c...
详细信息
ISBN:
(数字)9798350368604
ISBN:
(纸本)9798350368611
The widespread application of unmanned aerial vehicle (UAV) has made the coverage path planning problem for multiple UAV systems a research hotspot. In this paper, we propose a multi-UAV solution to achieve complete coverage of multi-region. Based on this solution, we present an improved particle swarm optimization (PSO) algorithm that combines PSO algorithm, greedy strategy, and back-and-forth (BAF) algorithm. Its purpose is to plan the optimal paths for multi-UAV while achieving the shortest total distance and the highest UAV cooperation efficiency with the minimum number of UAVs, thereby enhancing the multi-UAV coverage cooperation and path optimization capabilities. Simulation results demonstrate the feasibility and superiority of this algorithm.
作者：
Junqi MuXiaofeng ZongYiyang WeiXuping HouSchool of Automation
China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China
The actuator, serving as the fundamental power source of a soft robot, functions as its central component. The field of soft robotics has garnered increasing research attention since its inception. Pneumatic crawling ...
详细信息
ISBN:
(数字)9798350355642
ISBN:
(纸本)9798350355659
The actuator, serving as the fundamental power source of a soft robot, functions as its central component. The field of soft robotics has garnered increasing research attention since its inception. Pneumatic crawling robots, being an essential branch within the realm of soft robotics, possess notable characteristics such as rapid response time, cost-effectiveness, and human-computer interaction safety. Consequently, they hold significant research value. Among various types of crawling robots that have garnered considerable interest from researchers is the inchworm crawling robot. This paper aims to address the design and development aspects pertaining to inchworm actuators. By utilizing ABAQUS simulation software and taking displacement as the reference parameter, an analysis was conducted to investigate the impact of various geometric parameters on actuator displacement. Additionally, optimization of these geometric parameters was performed. The values of aspect ratio, length-to-width ratio, vertex angle and gap depth suitable for inchworm-like actuator are obtained. These findings are presented for the first time in the field of crawling soft robots and provide a theoretical basis for the development of pneumatic inchworm-like actuators.
The key to face recognition lies in how to improve the model’s ability to extract facial features. To this end, numerous loss functions based on different metrics have been proposed to increase the margin of feature ...
详细信息
ISBN:
(数字)9798350349399
ISBN:
(纸本)9798350349405
The key to face recognition lies in how to improve the model’s ability to extract facial features. To this end, numerous loss functions based on different metrics have been proposed to increase the margin of feature distinction between different classes. Methods based on Cosine distance significantly enhance face recognition performance by focusing on angular constraints between samples and classes, demonstrating their superiority over those based on Euclidean distance. However, a significant oversight in these methods is the neglect of feature magnitude’s importance in representing facial features. To address this gap, our study introduces the NormIntegrated Softmax loss (NIface loss), a novel loss function that amalgamates feature norms with angular information. This integration offers a comprehensive perspective for feature classification, augmenting the compactness of intra-class features. Extensive evaluations on large-scale public datasets have demonstrated the efficacy of NIface loss in enhancing recognition accuracy and stability.
In this paper, aiming at the planar magnetic sensor, the model of the planar magnetic sensor probe is constructed from the principle of magnetic line orbit transfer. The planar magnetic sensor probe is simulated and a...
详细信息
ISBN:
(数字)9798350350326
ISBN:
(纸本)9798350350333
In this paper, aiming at the planar magnetic sensor, the model of the planar magnetic sensor probe is constructed from the principle of magnetic line orbit transfer. The planar magnetic sensor probe is simulated and analyzed by COMSOL Multiphysics software. The influence of the horizontal width, height, length, and relative permeability parameters of the magnetic line orbit transfer structure on the orbit transfer coefficient of the magnetic line orbit transfer structure is studied. The simulation results analyze the influence of the structural parameters of the magnetic line transfer on the transfer coefficient, and the optimal parameter conditions are obtained. In order to verify the simulation results, an experimental test platform was built to test the planar magnetic sensor, and the magnetic line of force rail structure with the best experimental effect was obtained. The magnetic line of the force rail structure selects soft magnetic material with relative permeability greater than 5000, the horizontal width is 3mm, the height is 14mm, and the length of the magnetic line of the force rail structure in the experiment is determined to be 5mm according to the actual demand and the production process. Finally, the conversion efficiency of the planar magnetic sensor to the Z-axis magnetic field can reach 39.9 %. This study provides a research idea for promoting the planar design of magnetic sensors.
作者：
Jianrong ZhangHang XuHongzhang WangChuanke ZhangSchool of Automation
China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China
In the power system, due to the instability of the external environment, safe and stable operation cannot always be guaranteed, as it frequently encounters varying degrees of external disturbances. In order to mitigat...
详细信息
ISBN:
(数字)9798350389012
ISBN:
(纸本)9798350389029
In the power system, due to the instability of the external environment, safe and stable operation cannot always be guaranteed, as it frequently encounters varying degrees of external disturbances. In order to mitigate the effects of these disturbances on the system, the power system can operate safely and stably, In this paper, a power system load frequency control (LFC) based on Equivalent Input Disturbance (EID) method is proposed from the perspective of active disturbance suppression. Firstly, the disturbances present in the environment are unified as external disturbances, and then a single area the electric power system model with external disturbance was constructed. Then, a controller algorithm based on EID was designed using EID equivalent processing method and linear matrix inequality method to address the issue of external interference in the power system. Finally, a numerical example is used to validate the effectiveness and accuracy of the controller by simulating with two aspects, fixed perturbation and random perturbation, respectively.
Physics-Informed Neural Network(PINN)represents a new approach to solve Partial Differential Equations(PDEs).PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions(I/BCs)into a ...
详细信息
Physics-Informed Neural Network(PINN)represents a new approach to solve Partial Differential Equations(PDEs).PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions(I/BCs)into a loss ***,the imbalance of the loss function caused by parameter settings usually makes it difficult for PINNs to converge,*** they fall into local *** other words,the presence of balanced PDE loss,initial loss and boundary loss may be critical for the *** addition,existing PINNs are not able to reveal the hidden errors caused by non-convergent boundaries and conduction errors caused by the PDE near the ***,these problems have made PINN-based methods of limited use on practical *** this paper,we propose a novel physics-informed neural network,*** adaptive physics-informed neural network with a two-stage training *** algorithm adds spatio-temporal coefficient and PDE balance parameter to the loss function,and solve PDEs using a two-stage training process:pre-training and formal *** pre-training step ensures the convergence of boundary loss,whereas the formal training process completes the solution of PDE by balancing various loss *** order to verify the performance of our method,we consider the imbalanced heat conduction and Helmholtz equations often appearing in practical *** Klein-Gordon equation,which is widely used to compare performance,reveals that our method is able to reduce the hidden *** results confirm that our algorithm can effectively and accurately solve models with unbalanced loss function,hidden errors and conduction *** codes developed in this manuscript are publicy available at https://***/callmedrcom/ATPINN.
The issue of H∞ state estimation for neural networks with time-varying delays is investigated in this study. Firstly, an augmented Lyapunov-Krasovskii functional (LKF) with two delay-product-type terms is constructed...
详细信息
Recent advancements in Novel View Synthesis using neural radiance fields and 3D Gaussian splatting have demon-strated promising results. However, these methods conventionally rely on accurate initial poses and point c...
详细信息
ISBN:
(数字)9798350368604
ISBN:
(纸本)9798350368611
Recent advancements in Novel View Synthesis using neural radiance fields and 3D Gaussian splatting have demon-strated promising results. However, these methods conventionally rely on accurate initial poses and point clouds from the model of structure from motion, which poses challenges in sparse input views. To addressing these drawbacks, we introduces an novel method for view synthesis based on 3D Gaussian splatting. Our approach operates on sparse input views without the prerequisite of pose priors, achieving reconstruction and real-time rendering of novel perspectives. For the deficiency of camera poses and point cloud, we employ an end- to-end deep learning model to recover the 3D structure from a few of 2D images to initialize the 3D Gaussian point cloud. In addressing the issue with few-shot, we utilize the differentiable rasterization module to render depth map and apply regulation on it. Additionally, we incorporate supervision between input views by interpolating to generate novel perspectives during training. Experimental results demonstrate that our proposed method significantly enhances the capabilities of 3D Gaussian splatting for novel view synthesis in sparse views and without the necessity of camera pose priors.
暂无评论