Effective management of lithium-ion batteries is pivotal for energy supply systems. However, the significance of battery early prognostics is often overlooked and conventional data-driven approaches frequently fall sh...
详细信息
Effective management of lithium-ion batteries is pivotal for energy supply systems. However, the significance of battery early prognostics is often overlooked and conventional data-driven approaches frequently fall short in precisely predicting lifespan or reconstructing degradation trajectories during the initial stages of battery life. To address these challenges, this article proposes a pseudo meta-learning (PML) neural network integrating hybrid cyclic-based and physical-informed features for battery early lifespan estimation and capacity reconstruction. A convolutional variational autoencoder is initially employed to train a robustness encoder using sufficient battery early aging data. Furthermore, PML combines features of batteries with different lifespans for checkpoint prediction from full-life battery aging data. To mitigate overfitting concerns, multiple PMLs are interconnected through a gating network, and a joint-learning strategy is introduced to fine-tune hyperparameters. In the experimental validation, comparative experiments on other battery prognostic methods are conducted, and a detailed discussion on enhancing prediction performance, considering both computational complexity and accuracy, is presented.
In vehicular Ad Hoc networks (VANETs), vehicle platoons share state information through vehicle-to-vehicle (V2V) communication. However, in an open network environment, cyber-attacks may be suffered, threatening the n...
详细信息
The paper presents a novel curriculum reinforcement learning (CRL) approach for real-time entry trajectory planning in uncertain environments and diverse tasks. The trajectory planning problem is divided into two stag...
详细信息
This paper designs optimal control polices for networked multiagent pursuit-evasion game (MPEG) problems based on reinforcement learning (RL) technique. Depending on the number of evaders, MPEG is formulated into seve...
详细信息
This paper designs optimal control polices for networked multiagent pursuit-evasion game (MPEG) problems based on reinforcement learning (RL) technique. Depending on the number of evaders, MPEG is formulated into several simpler multiple-pursuer single-evader games (MPSEGs) by a divide and conquer approach. Then we propose optimal control policies for all the agents in each MPSEG, which constitute a distributed Nash equilibrium, and provide the capturability and Nash equilibrium analysis. Finally, a data-driven RL algorithm is developed to online learn optimal control polices using measurable behavior data. A simulation example is given to verify the effectiveness of the proposed approach.
In response to the issue of low accuracy in speech emotion recognition, this paper proposes an improved classification model that utilizes the Energy Valley Optimizer (EVO) to enhance the Multi-kernel Extreme learning...
详细信息
People with unilateral transtibial amputation generally exhibit asymmetric gait, likely due to inadequate prosthetic ankle function. This results in compensatory behavior, leading to long-term musculoskeletal impairme...
详细信息
People with unilateral transtibial amputation generally exhibit asymmetric gait, likely due to inadequate prosthetic ankle function. This results in compensatory behavior, leading to long-term musculoskeletal impairments (e.g., osteoarthritis in the joints of the intact limb). Powered prostheses can better emulate biological ankles, however, control methods are over-reliant on non-disabled data, require extensive amounts of tuning by experts, and cannot adapt to each user's unique gait patterns. This work directly addresses all these limitations with a personalized and data-drivencontrol strategy. Our controller uses a virtual setpoint trajectory within an impedance-inspired formula to adjust the dynamics of the robotic ankle-foot prosthesis as a function of stance phase. A single sensor measuring thigh motion is used to estimate the gait phase in real time. The virtual setpoint trajectory is modified via a data-driven iterative learning strategy aimed at optimizing ankle angle symmetry. The controller was experimentally evaluated on two people with transtibial amputation. The control scheme successfully increased ankle angle symmetry about the two limbs by 24.4% when compared to the passive condition. In addition, the symmetry controller significantly increased peak prosthetic ankle power output at push-off by 0.52 W/kg and significantly reduced biomechanical risk factors associated with osteoarthritis (i.e., knee and hip abduction moments) in the intact limb. This research demonstrates the benefits of personalized and data-driven symmetry controllers for robotic ankle-foot prostheses.
This letter devises Neural Dynamic Equivalence (NeuDyE), which explores physics-aware machine learning and neural-ordinary-differential-equations (ODE-Net) to discover a dynamic equivalence of external power grids whi...
详细信息
This letter devises Neural Dynamic Equivalence (NeuDyE), which explores physics-aware machine learning and neural-ordinary-differential-equations (ODE-Net) to discover a dynamic equivalence of external power grids while preserving its dynamic behaviors after disturbances. The contributions are threefold: 1) an ODE-Net-enabled NeuDyE formulation to enable a continuous-time, data-driven dynamic equivalence of power systems;2) a physics-informed NeuDyE learning method (PI-NeuDyE) to actively control the closed-loop accuracy of NeuDyE without an additional verification module;3) a physics-guided NeuDyE (PG-NeuDyE) to enhance the method's applicability even in the absence of analytical physics models. Extensive case studies in the NPCC system validate the efficacy of NeuDyE, and, in particular, its capability under various contingencies.
Due to the characteristics of large inertia, significant lag, and model uncertainty in the Selective Catalytic Reduction (SCR) denitrification system, traditional control schemes encounter challenges in achieving prec...
详细信息
Two data-driven strategies for value iteration in linear quadratic optimal control problems over an infinite horizon are proposed. The two architectures share common features, since they both consist of a purely conti...
详细信息
Two data-driven strategies for value iteration in linear quadratic optimal control problems over an infinite horizon are proposed. The two architectures share common features, since they both consist of a purely continuous-time control architecture and are based on the forward integration of the differential Riccati equation (DRE). They profoundly differ, instead, in the estimation mechanism of the vector field of the underlying DRE from collected data: The first relies on a characterization of properties of the advantage function associated to the problem, whereas the second is inspired by tools from adaptive control theory and ensures semi-global exponential convergence to the optimal solution. Advantages and drawbacks of the architectures are discussed, while the performance is validated via a benchmark numerical example.
This paper offers a formal data-driven scheme for constructing control barrier certificates (CBC) and synthesizing safety controllers for discrete-time controlsystems. Our framework accommodates scenarios where the m...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
This paper offers a formal data-driven scheme for constructing control barrier certificates (CBC) and synthesizing safety controllers for discrete-time controlsystems. Our framework accommodates scenarios where the mathematical model is unknown, while also considering the presence of wireless communication networks between sensor-controller and controller-actuator links. While existing literature extensively addresses the design of CBC, there has been a notable lack of attention in incorporating wireless communication networks to tackle potential packet losses. This gap poses a greater challenge when considering the absence of knowledge about the system's model, a crucial aspect in real-world applications. Given a particular rank condition for unknown wirelessly-connected systems, our method provides a linear matrix inequality, constructed based on two input-output trajectories of the system, offering a probabilistic safety assurance across an infinite time horizon. We showcase the efficacy of our data-driven approach over a wirelessly-connected synchronous motor with an unknown model.
暂无评论