T-spline surfaces play important role in the integration of CAD and CAE, the quality of the surface infects not only the design of applications but also the analysis in simulations. So fairing is a necessary connectio...
详细信息
Reinforcement Learning(RL)has emerged as a promising data-driven solution for wargaming ***,two domain challenges still exist:(1)dealing with discrete-continuous hybrid wargaming control and(2)accelerating RL deployme...
详细信息
Reinforcement Learning(RL)has emerged as a promising data-driven solution for wargaming ***,two domain challenges still exist:(1)dealing with discrete-continuous hybrid wargaming control and(2)accelerating RL deployment with rich offline *** RL methods fail to handle these two issues simultaneously,thereby we propose a novel offline RL method targeting hybrid action space.A new constrained action representation technique is developed to build a bidirectional mapping between the original hybrid action space and a latent space in a semantically consistent *** allows learning a continuous latent policy with offline RL with better exploration feasibility and scalability and reconstructing it back to a needed hybrid ***,a novel offline RL optimization objective with adaptively adjusted constraints is designed to balance the alleviation and generalization of out-of-distribution *** method demonstrates superior performance and generality across different tasks,particularly in typical realistic wargaming scenarios.
In the monitoring area, nodes collaboratively collect various types of critical information about the target object, including temperature, humidity, and stress, and relay this data to users. This study evaluates a sc...
详细信息
The last decade has witnessed a surge of interest in artificial neural network in many different areas of scientific *** the rapid expansion in the application of neural networks,few efforts have been carried out to i...
详细信息
The last decade has witnessed a surge of interest in artificial neural network in many different areas of scientific *** the rapid expansion in the application of neural networks,few efforts have been carried out to introduce such a powerful tool into lubrication ***,this work aims to apply the physics-informed neural network(PINN)to the hydrodynamic lubrication *** 2D Reynolds equation is *** PINN is a meshless method and does not require big data for network training compared with classical *** results are consistent with those obtained by experiments and the finite element ***,we envision that the PINN method will have great application potential in lubrication and bearing research.
The ocular lubrication,where the eyelid constantly slides on the curved corneal surface,is considered as one of primary lubrication systems in *** reliable lubrication conditions,sensitive ocular tissues remain intact...
详细信息
The ocular lubrication,where the eyelid constantly slides on the curved corneal surface,is considered as one of primary lubrication systems in *** reliable lubrication conditions,sensitive ocular tissues remain intact from fatigue damage during spontaneous blink *** tear film,evenly filled between cornea and conjunctiva,is a biological fluid with dynamic adjustment ability,which provides superior lubrication with the friction coefficient of below ***,the lubrication failure may result in a variety of uncomfortable symptoms such as inflammatory reactions,tissue damage and neurological ***,it is essential to clarify the fundamental mechanism of ocular lubrication,which helps to alleviate and even recover from various ocular *** review firstly demonstrates that the ocular components,containing lipids and mucins,contribute to maintaining the lubrication stability of tear ***,the ocular lubrication state in various physiological environments and the physical effect on tear film dynamics are further *** typical applications,the therapeutic agents of dry eye syndrome and contact lens with superior lubrication effects are introduced and their lubrication mechanisms are ***,this review summarizes a series of the latest research inspired by ocular ***,this work will provide a valuable guidance on the theoretical research and extensive applications in the field of biological lubrication.
In the evolving landscape of robotics and visual navigation,event cameras have gained important traction,notably for their exceptional dynamic range,efficient power consumption,and low *** these advantages,conventiona...
详细信息
In the evolving landscape of robotics and visual navigation,event cameras have gained important traction,notably for their exceptional dynamic range,efficient power consumption,and low *** these advantages,conventional processing methods oversimplify the data into 2 dimensions,neglecting critical temporal *** overcome this limitation,we propose a novel method that treats events as 3D time-discrete *** inspiration from the intricate biological filtering systems inherent to the human visual apparatus,we have developed a 3D spatiotemporal filter based on unsupervised machine learning *** filter effectively reduces noise levels and performs data size reduction,with its parameters being dynamically adjusted based on population *** ensures adaptability and precision under various conditions,like changes in motion velocity and ambient *** our novel validation approach,we first identify the noise type and determine its power spectral density in the event *** then apply a one-dimensional discrete fast Fourier transform to assess the filtered event data within the frequency domain,ensuring that the targeted noise frequencies are adequately *** research also delved into the impact of indoor lighting on event stream ***,our method led to a 37%decrease in the data point cloud,improving data quality in diverse outdoor settings.
Digital holography has emerged as a powerful tool for investigating dynamic particle behaviors in the spatiotemporal domain. However, the performance of this technique is fundamentally limited by the system’s space–...
详细信息
Extensive penetration of distribution energy resources(DERs)brings increasing uncertainties to distribution *** topology identification is a critical basis to guarantee robust distribution network *** algorithms that ...
详细信息
Extensive penetration of distribution energy resources(DERs)brings increasing uncertainties to distribution *** topology identification is a critical basis to guarantee robust distribution network *** algorithms that estimate distribution network topology have already been ***,most are based on data-driven alone method and are hard to deal with ever-changing distribution network physical *** these backgrounds,this paper proposes a data-model hybrid driven topology identification scheme for distribution ***,a data-driven method based on a deep belief network(DBN)and random forest(RF)algorithm is used to realize the distribution network topology rough ***,the rough identification results in the previous step are used to make a model of distribution network *** model transforms the topology identification problem into a mixed integer programming problem to correct the rough topology *** of the proposed method is verified in an IEEE 33-bus test system and modified 292-bus system.
To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Marko...
详细信息
To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Markov Transition Field(MTF)image encoding combined with a lightweight convolutional neural network that integrates a Convolutional Block Attention Module(CBAM-LCNN).Specifically,we first use the Markov Transition Field to convert the original one-dimensional vibration signals of rolling bearings into two-dimensional ***,we construct a lightweight convolutional neural network incorporating the convolutional attention module(CBAM-LCNN).Finally,the two-dimensional images obtained from MTF mapping are fed into the CBAM-LCNN network for image feature extraction and fault *** validate the effectiveness of the proposed method on the bearing fault datasets from Guangdong University of Petrochemical Technology’s multi-stage centrifugal fan and Case Western Reserve *** results show that,compared to other advanced baseline methods,the proposed rolling bearing fault diagnosis method offers faster diagnostic speed and higher diagnostic *** addition,we conducted experiments on the Xi’an Jiaotong University rolling bearing dataset,achieving excellent results in bearing fault *** results validate the strong generalization performance of the proposed *** method presented in this paper not only effectively diagnoses faults in rolling bearings but also serves as a reference for fault diagnosis in other equipment.
Unmanned Surface Vehicle (USV) face challenges in underwater survey tasks, considering both environmental and self-performance constraints. In complex marine environments with obstacles, optimal route planning is cruc...
详细信息
暂无评论