In recent years,research on the state of health(SOH)and remaining useful life(RUL)estimation methods for lithium-ion batteries has garnered significant attention in the new energy *** the substantial volume of annual ...
详细信息
In recent years,research on the state of health(SOH)and remaining useful life(RUL)estimation methods for lithium-ion batteries has garnered significant attention in the new energy *** the substantial volume of annual publications,a systematic approach to quantifying and analyzing these contributions is *** study focuses on selecting pertinent literature related to lithium-ion battery SOH and RUL estimation from CNKI and WOS databases,spanning January 2010 to December *** bibliometric tools such as VOSviewer and CiteSpace,we conduct visual analyses to elucidate the current state,development trends,and research frontiers in this *** examination encompasses scholarly activity,year-wise literature distribution,international collaboration networks,structural dissemination,and journal *** findings indicate an upward trend in annual publication output,with China,the United States,the United Kingdom,and Canada at the forefront of collaborative research *** is increasingly recognized as a pivotal hub for global scholarly ***,Harbin Institute of Technology,Beijing Institute of Technology,Chongqing University,Chinese Academy of Sciences,and Beijing Jiaotong University are the top institutions in China and the world in terms of *** Journal of Energy Storage emerges as a prominent periodical,acclaimed both domestically and internationally for its rigorous standards and high-quality *** on the research content from CNKI and WOS,VOSviewer clusters the main research directions into three themes:aging mechanisms,SOH estimation methods,and RUL prediction *** such as‘online estimation’,‘hybrid models’,and‘artificial neural networks’feature prominently,signaling a strong emphasis on artificial intelligence *** study concludes with a prospective outlook on imminent research trajectories regarding the health and longevity estimations of lithium-ion batteries,high
In this paper, a novel adaptive fuzzy controller based on deep reinforcement learning (DRL) is introduced for electro-hydraulic servo systems. The controller combines the strengths of fuzzy proportional–integral (PI)...
详细信息
Understanding the spin-configuration of excited states in a luminescent material is essential for tailoring its properties for many applications such as light-emitting diodes and spin-optoelectronic ***-dimensional or...
详细信息
Understanding the spin-configuration of excited states in a luminescent material is essential for tailoring its properties for many applications such as light-emitting diodes and spin-optoelectronic ***-dimensional organic-inorganic metal halide（0D-OIMH） materials have demonstrated remarkable potential in diverse applications owing to their captivating optoelectronic characteristics. However, the electronic structure and spin-configuration of the frequently observed dual-peak emission in these materials remains a subject of intensive debate. In this study, we employ low-temperature magneto-optical measurements to investigate the excited state structure of a representative 0D-OIMH, namely（Bmpip）2SnBr4. The spin-configurations of the dark and bright states are clearly elucidated by measuring the magneto-polarization of the emissions. Our results reveal that the high-energy peak arises from bright excited states within a higher energy band, whilst the low-energy peak originates from a combination of triplet-bright states and singlet-dark states. These findings provide an unambiguous understanding of the exciton structures of the distinctive 0D-OIMHs.
This study presents the development of sliding mode control (SMC) using the diagonal recurrent neural network (DRNN) for nonlinear systems. Firstly, the SMC for linear systems is developed for nonlinear coupled tank s...
详细信息
This paper investigates the resilient control problem of vehicle platoons under false data injection (FDI) attack. Considering the FDI attacks in vehicle internal communication links， the adaptive radial basis functi...
详细信息
This paper investigates the resilient control problem of vehicle platoons under false data injection (FDI) attack. Considering the FDI attacks in vehicle internal communication links， the adaptive radial basis function neural network (RBF NN) is applied to estimate the lumped nonlinear term and FDI attacks in the sensor-actuator (S-C) channel. Based on this， a neuro-adaptive observer is developed for state reconstruction under FDI attack in the controller-actuator (C-A) channel. Then， for the FDI attack in the vehicle-vehicle (V-V) communication link， an observer-based resilient control algorithm is designed to guarantee the safety of platoon by employing the asymmetric barrier Lyapunov function (ABLF)， which is proved to be capable of restricting the position of vehicles in the collision avoidance region. Finally， simulation results demonstrate the effectiveness of the proposed algorithms.
With the development of sensors,the application of multi-source remote sensing data has been widely *** hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains ...
详细信息
With the development of sensors,the application of multi-source remote sensing data has been widely *** hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep ***-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network *** this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR ***,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and *** addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI ***,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the *** verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento *** experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.
An intelligent endo-atmospheric penetration strategy based on generative adversarialreinforcement learning is proposed in this ***,attack and defense adversarial mod-els are established,and missile maneuver penetratio...
详细信息
An intelligent endo-atmospheric penetration strategy based on generative adversarialreinforcement learning is proposed in this ***,attack and defense adversarial mod-els are established,and missile maneuver penetration problem is transformed into an optimal con-trol problem,considering penetration,handover position and mid-terminal guidance ***,Radau Pseudospectral method is adopted to generate data samples consideringrandom ***,Generative Adversarial Imitation Learning Combined withDeep Deterministic Policy Gradient method(GAIL-DDPG)is designed,with internal processreward signals constructed to tackle long-term sparse reward in missile manuver penetration ***,penetration strategy is trained and *** shows that using generativeadversarial reinforcement learning,with sample library to learn expert experience in training earlystage,the proposed method can quickly ***,performance is further optimized with rein-forcement learning exploration strategy in the later stage of *** shows that the pro-posed method has better engineering application ability compared with traditional reinforcementlearning method.
The paper proposes a novel checkpoint management method for a real-time system with a quintuple modular redundancy (QMR) structure wherein multiple fault detections are performed between checkpoints. If the detected f...
详细信息
For remote sensing scene classification (RSSC), exemplar-based class-incremental learning uses all the training data of the new classes and a small number of exemplars of the old classes to train the model in each inc...
详细信息
This paper addresses a cooperative/non-cooperative game based lane-changing decision-making method for intelligent and connected vehicles (ICVs) for reducing traffic congestion and accident in the lane-changing proces...
详细信息
暂无评论