Deep reinforcement learning (DRL) has demonstrated strong potential for energy management systems. However, existing approaches struggle with the complex nonlinear dynamics of hybrid energy storage systems (HESS), especially due to gradient attenuation under extreme conditions, which undermines control stability. This paper proposes a Residual-enhanced Proximal Policy Optimization (ResPPO) algorithm, which integrates residual connections into the policy network. This design enhances gradient flow propagation and mitigates vanishing gradients, leading to better training stability and optimization performance. Simulation experiment results under UDDS conditions show that ResPPO achieves a 31.7% reduction in battery degradation costs compared to standard PPO while delivering superior supercapacitor state-of-charge (SOC) regulation.

While the application fields of li-ion batteries becoming more and more extensive, the risk of thermal runaway caused by overcharging, over-discharging, internal short circuit and other faults, mainly due to the complex operating environment, can no longer be ignored. Predicting the risk of thermal runaway and ensuring the safety of drivers are the first problems to be solved. On the other hand, how to reduce the false alarm rate and realize more robust fault detection is still a common challenge for researchers. To address the above problems, this paper combines Wasserstein GAN and autoencoder to realize robust and effective fault detection. The autoencoder’s discriminative ability is enhanced by the adversarial network and the training stability of Wasserstein GAN is utilized to significantly reduce the false alarm rate. Experimental results on a real electric vehicle dataset experiencing thermal runaway show that the proposed method reduces the false alarm rate to 0.71% while ensuring accurate detection capability.

Microgrids based on distributed control are susceptible to cyber attacks during operation, which can result in system anomalies, crashes, and even equipment damage. To ensure a secure collaborative environment, this paper proposes an attack detection mechanism based on extended cell similarity. First, a DC microgrid model and a network attack model were established. Secondly, a microgrid state interval prediction mechanism based on QRLSTM is proposed. The output of the load prediction model is used as the input of the mechanism model, and the expected state range of the terminal equipment voltage and current is obtained through simulation. Then, the cell similarity algorithm is improved to relate the similarity between the actual measured data and the expected period to the probability of cyber attacks occurring. Finally, the effectiveness and feasibility of the detection method were verified through experiments.

To mitigate the impact of model uncertainties and the nonlinear dynamic characteristics of actuators on the control of heterogeneous vehicle platoon, this study proposes a distributed data-enabled predictive control (DeePC) strategy. This strategy can effectively guide unknown dynamic systems to move along expected trajectories while satisfying system constraints. Firstly, a non-parametric model of the vehicle system, which takes into account the nonlinear dynamic characteristics of the actuator, is established using input-output (I/O) vehicle trajectories. Then, the regularized DeePC and the distributed control are integrated and applied to the data-driven control of vehicle platoon based on the non-parametric model. Furthermore, a local cost function, considering other vehicles information and constraints, is designed to optimize the control problem of vehicle platoon. Finally, the simulation results verify the effectiveness of the distributed data-enabled predictive control strategy in vehicle platoon control. Compared with distributed nonlinear model predictive control, the proposed distributed data-enabled predictive control exhibits stronger robustness.

The rapid and accurate detection of faults for lithium-ion batteries plays a critical role in ensuring the safe operation of electric vehicle systems. This paper proposes a fault detection method for electric vehicle batteries by exploiting the temporal smoothness and spatial similarity of battery pack data. Firstly, a temporal convolutional network (TCN) is utilized to learn the latent spatial and temporal features of the data. Then, a self-attention mechanism is employed to capture the correlations and importance between different features. Furthermore, an autoencoder is employed to reconstruct input data based on the extracted spatial-temporal features. This encoder-structured approach is trained only using normal data and the anomalies are detected as conspicuous differences between the input data and the reconstructed data. The detection performance of the proposed method is validated by utilizing real-world electric vehicle operational datasets.

Grid operation state estimation of power grid operating states and power system analysis largely relies on physical layer measurements of the power system. However, the introduction of information and communication technologies in smart grids has greatly improved operational efficiency while also increasing the system’s vulnerability to attack. This can compromise data integrity and reliability, leading to data missing and then affecting subsequent steps. Additionally, data collection and transmission can encounter various issues, resulting in partial data loss or errors. Therefore, it is crucial to recover and complete the missing data.This paper proposes a solution for missing data recovery in power systems based on generative adversarial network (GAN). The approach utilizes graph convolutional network (GCN) to extract features from data, taking into account the topological connectivity between nodes. To improve the quality of data imputation and enhance the authenticity of recovered data, incomplete data containing nodes with missing data and observable nodes is used as input for the generator, and a local feature extractor is added to the existing discriminator network. This structure allows the generator to estimate unknown information by observing known data, while the discriminator focuses more on the local areas containing the recovered data when determining the authenticity, thereby helping the generator to improve its data completion capability. Correspondingly, we design context loss constraints considering both local and global ranges to ensure accurate recovery of non-missing node data while completing the missing data portions.The experimental results demonstrate that employing GCN and incorporating local features can significantly enhance recovery performance on grid data. For voltage magnitude, the mean absolute error decreased by 10.4335%. Additionally, high-precision recovery results can still be achieved even with up to half data missing, which is validated on the IEEE-14 system.

In the current era, a Li-ion battery pack, typically comprised of multiple cells, can offer higher voltage and output power. This plays a crucial role in various applications, including electric vehicles and energy storage. Accurate estimating the battery pack's state of charge (SOC) is crucial to offer users a clearer understanding of the battery status and to alleviate range anxiety. In the industry, it's common practice to precisely estimate the SOC for each cell, enabling an accurate assessment of the battery pack's overall SOC. However, most current methods for estimating the SOC in battery packs are centralized. In such cases, a problem with estimating the SOC of a single cell can greatly impact the overall SOC estimation of the entire battery pack. Likewise, if centralized equipment encounters issues, the SOC estimation for the entire battery pack is likely to be interrupted. This paper presents a distributed method for estimating battery pack SOC, utilizing a digital twin-based simulation platform. In the following, the each node that measures the SOC of cell is regarded as an agent that can communicate. Through communication among agents, each agent can converge to a reliable battery pack SOC estimation. In the event of a sudden issue arising in the SOC estimation of a cell, the proposed method can still uphold a dependable estimate of the battery pack's SOC, thereby bolstering the overall robustness of the SOC estimation system for the entire battery pack.

To ensure optimal functionality of the super-capacitor management system in practical applications, the accurate and robust state of charge (SOC) estimation is crucial, particularly to account for aging effects and varying operating conditions. This paper proposes a switched system-based approach for the co-estimation of SOC and parameters of supercapacitors coupled with balancing resistor circuits. A switched model incorporating an equivalent circuit model is developed to accommodate the activation of equalization within a series-connected supercapacitor pack. The method combines a modified recursive least squares (RLS) algorithm with a switching sliding mode observer (SMO) for real-time parameter adaptation and SOC estimation. The experimental verification under a multi-balancing charging scenario demonstrates sig-nificant enhancements in accuracy and robustness compared to traditional methods employing fixed model configurations and parameters.

This paper explores the estimation of the State of Charge (SoC) of lithium-ion batteries. Currently, the majority of research efforts focus on the SoC estimation of individual lithium-ion batteries. However, in practical scenarios, lithium-ion batteries are commonly connected with balancing circuits to address battery imbalances. Upon activation of the equalization circuit, the battery's system dynamics transition to a new mode. Therefore, it is difficult f o r c l assical S o C estimation algorithms to accurately estimate the real SoC value. In this paper, we employ a switched system methodology to estimate the battery's SoC. We describe the switched system of the Thevenin equivalent circuit model of a lithium-ion battery using a switched resistance balance circuit. Then we use the method of nonlinear switching observer to analyze the convergence and divergence. Finally, we set up an experimental platform and verify the performance of the observer through several sets of experiments.

Supercapacitors, leveraging their distinctive characteristics and advantages, have evolved into efficient energy storage solutions. State of Charge (SOC) is a crucial parameter for supercapacitors, and the estimation of SOC for individual supercapacitor cells has been extensively researched. In practical applications, it is common to assemble hundreds or even thousands of cells to form a supercapacitor pack, particularly in fields like electric vehicles a nd electric b uses. Therefore, estimating the SOC for the supercapacitor pack becomes imperative. In response to the demands for supercapacitor pack SOC$(SOC_{pack})$estimation and wireless management, this paper proposes a distributed method. After modeling the supercapacitor cells, the definition of$SOC_{pack}$is introduced. The SOC of a cell in the definition is estimated based on Kalman filter. The proposed distributed method relies on wireless communication and computational updates between cells. Through iterative processes, it ultimately converges to the estimated$SOC_{pack}$. Finally, we conducted simulation experiments to analyze the performance of the proposed method under various communication conditions, thereby validating its effectiveness and robustness.

The integration of advanced communication and information technologies in smart grids has led to enhanced efficiency and reliability but also introduced security vulnera-bilities, prompting the need for robust cyber attack detection methods. Traditional approaches struggle to capture evolving attack patterns and handle high-dimensional data, highlighting the necessity for more sophisticated approaches. A neighbor-hood reconstruction-based smart grid attack detection scheme based on subgraphs is proposed. By leveraging Graph Neural Networks (GNNs), the challenge of capturing complex inter-dependencies among grid nodes is addressed. This approach employs unsupervised learning principles, training the model solely on normal data and utilizing the reconstruction error of node features to detect attacks. Additionally, by subgraph sampling and feature suppression, the model's ability to utilize neighborhood information is enhanced, thereby further improving detection effectiveness. Simulation results on IEEE 30-bus and IEEE 118-bus power system demonstrate the feasibility of the method, achieving a detection accuracy of 96.67% and 97.46%, respectively.

Faults in braking actuators can compromise the safety and stability of urban rail train operations. Existing fault-tolerant control methods for trains struggle to guarantee both transient and steady-state braking performance quantitatively. In this paper, we propose a cooperative fault-tolerant braking control with prescribed performance for urban rail trains. A coupled multi-agent braking model is first developed, where each vehicle is treated as an independent and controllable agent subject to various uncertainties, input saturation and different levels of actuator faults. Further, incorporating a prescribed tracking performance function, a distributive adaptive terminal sliding mode controller is developed to ensure safe and reliable train braking control. The control input saturation nonlinearity is addressed by employing a smooth hyperbolic tangent function for approximation. Adaptation laws are introduced to mitigate the effects of parameter uncertainties and external disturbances. The efficacy of the proposed control scheme is validated through comprehensive numerical simulations.

The prediction of driving range is very important for electric bus, but there is usually a difficulty: battery aging affects the accuracy of driving range prediction. In order to solve this problem, this paper proposes a driving range prediction method for electric bus, which is robust to the battery aging effect. Firstly, we extract the features that affect the driving range from the real-world dataset, quantify the correlation between them and the driving range by grey correlation analysis. Then through the feature enhancement technology, the time window processing is used to mitigate the influence of battery aging, and the time information hidden in the historical period sequence is deeply excavated. On this basis, we establish the driving range prediction model based on k-nearest neighbors regression, where the key parameters are optimized with the particle swarm optimization algorithm. Numerous experimental results show that compared with the classical methods, the method proposed in this paper has higher prediction accuracy especially when the batteries undergo significant aging effects.

The accurate estimation of adhesion force between wheels and rails is an important task as it helps to the wheel-slip prevention (WSP) system preventing the wheels from locking and reducing the stopping distance. Influenced by a changing external environment, the adhesion force estimation process is complex. Thus, an extended state observer (ESO) is proposed to accurately estimate the adhesion force of railway vehicles with the modeling deviation and measurement noise. With the estimated modeling error information, an auxiliary compensation part is designed to eliminate the steady-state estimation error causing by the modeling deviation. Further, a Fal function filter is added to the ESO to deal with the effect of measurement noise. The convergence of the proposed estimation method is analyzed theoretically. The effectiveness of the designed algorithm is corroborated by simulation comparisons to other standard approaches.

Precision stopping of trains requires special attention to brake control because a pneumatic brake system of a train is highly nonlinear, hybrid and uncertain. Existing solutions to automatic train stop control ignore the pneumatic brake system or simply treat it as a system delay, which is quite far apart from the real train stopping dynamics. Moreover, the service life of pneumatic brake systems decreases fast due to the frequent changes in output of existing controllers. Thus, an adaptive nonlinear sliding mode control method is developed in this paper, which has strong applicability to nonlinear and hybrid system control synthesis due to its natural variable structure characteristic. A nonlinear integral sliding surface with adaptive updating parameters is proposed to improve the control precision and the robustness. Extensive simulations are performed to validate the effectiveness of the proposed method. The results show that the proposed algorithm outperforms a PID control algorithm in terms of stopping error and expected lifetime of pneumatic brake systems.

Currently, the robot is playing an increasingly significant role in managing a warehouse. This paper proposes an optimal method to help a warehouse robot make task decisions, which aims at minimizing the whole cost of completing multiple tasks. Firstly, Abstract Transition System (ATS) is used to model the warehouse environment, and Linear Temporal Logic (LTL) formula is used to formulate the tasks of warehouse robot. Then based on the ATS and the Büchi automaton translated from the LTL formula, a Min-cost Task Decision Algorithm is proposed to obtain the task decision for the warehouse robot. The decision points out the optimal order and path for the robot to do its tasks. The effectiveness of the proposed method is validated through case studies with two kinds of tasks.

With the rapid development of inspection techniques, more emphases should be placed on the improvement of the reliability, safety and intelligence of the robot system. In this paper, a framework for the patrol robot that automatically finishes complex task and motion planning in the indoor substation is proposed. To realize real-time response to the environmental changes, the proposed framework keeps an ongoing interaction with the environment as a Reactive System (RS). The RS employs the Transition System (TS) and Nondeterministic Biichi Automaton (NBA) to create a discrete controller that bounds the acts of the patrol robot in the safe and reasonable specifications. What's more, the environment signals are treated as the trigger condition of task switching. If a new environment information is detected, our approach can automatically give a feasible plan. Then, the sensor-based mechanism of continuous controllers is guided by the discrete controller, which results in a hybrid system satisfying the high-level specification. The experiment within the LTLMoP toolkit verifies the proposed framework.