Cell balancing is used in battery systems to guarantee uniform charge and discharge of their cells during operations, and aims at improving the performance of the whole battery pack. Onboard battery performance and lifespan are particularly important in Electric Vehicles (EVs), since they have a direct impact on their autonomy. This paper proposes a Deep Reinforcement Learning (DRL)-based framework for Dynamic Reconfigurable Batteries (DRBs), where the capability of dynamically reconfiguring their cell topology can be exploited to attain cell balancing in EV applications. Thanks to the model-free nature and the robustness/adaptability properties of DRL-based solutions, the resulting trained agent is able to reach DRB cell balancing, while also taking into account both operational and modelling aspects of the combined EV-DRB system (e.g., all the events included in a typical driving cycle, the EV regenerative braking, and the heterogeneity of the DRB cells). The training process is carried out by using standard driving cycles, while the resulting trained agent is validated with a dataset based on real driving profiles. Finally, the performance achieved by the DRL policies is compared with some heuristic/rule-based approaches inspired from the literature.

Optimal management of the electrical power system (EPS) in low Earth orbit satellites requires the design of dedicated algorithms. A power flow supervisor is here proposed by defining decision strategies based on a dynamic model of the EPS that discriminates between different operating modes satisfying the primary constraint of load service while efficiently managing battery charging/discharging and tracking the maximum power point from photovoltaic panels. The transitions among different modes are governed by exogenous inputs, load power demands, and battery state of charge, providing flexibility and adaptability to varying conditions. In each mode the supervisor determines the duty cycle of the DC-DC buck converter used as the interface between the photovoltaic panels and the battery on the unregulated bus and the current to be absorbed by a bleeder circuit connected in parallel to the battery. The overall design of the EPS supervisor was obtained as the solution of a two-level optimization procedure. Indeed, fine-tuning of the parameters are obtained as the solution of a mathematical problem and then an optimization approach was used to determine the optimal sizing of the battery and photovoltaic panels. The simulation results demonstrated the effectiveness of the optimization strategy.

In the widely adopted description of seismic occurrence, earthquakes are categorized as either background or triggered events. In this work, we present a fully automated, non‐parametric algorithm for distinguishing between these two categories, a process known as seismic declustering, based on the widely used nearest‐neighbor (NN) metric. We introduce a new measure, the susceptibility index, which identifies an optimal threshold to discriminate between background and triggered events within the NN metric. Through statistical testing on simulated epidemic type aftershock sequence catalogs, we demonstrate that our method yields classification metrics exceeding 90%, outperforming state‐of‐the art algorithms. Notably, we show that a single threshold is sufficient for reliable discrimination within a given data set. The identification of this threshold requires memory capacity and computational time that scale linearly and quadratically with the data set size, respectively, making the method particurarly suited for large earthquake catalogs. We also apply our method to the relocated Southern California catalog and the GeoNet catalog of New Zealand (NZ). Our method effectively adapts across the different tectonic settings, capturing the variability of background seismicity rates between the shallow crustal events of Southern California and the tectonically diverse seismicity of NZ.

Effective energy management in Low Earth Orbit satellites is critical, as inefficient energy management can significantly affect mission objectives. The dynamic and harsh space environment further complicates the development of effective energy management strategies. To address these challenges, we propose a Deep Reinforcement Learning approach using Deep-Q Network to develop an adaptive energy management framework for Low Earth Orbit satellites. Compared to traditional techniques, the proposed solution autonomously learns from environmental interaction, offering robustness to uncertainty and online adaptability. It adjusts to changing conditions without manual retraining, making it well-suited for handling modeling uncertainties and non-stationary dynamics typical of space operations. Training is conducted using a realistic satellite electric power system model with accurate component parameters and single-orbit power profiles derived from real space missions. Numerical simulations validate the controller performance across diverse scenarios, including multi-orbit settings, demonstrating superior adaptability and efficiency compared to conventional Maximum Power Point Tracking methods.

The increasing complexity of modern ground vehicles is making crucial the role of control for improving energetic efficiency, comfort and performance. At the same time, the control software must be frequently updated in order to let the vehicle respond safely and efficiently within more sophisticated environments and to optimize the operations when new vehicle components are integrated. In this framework real-time hardware-in-the-loop simulations represent a fundamental tool for supporting the verification and validation processes of the control software and hardware. In this chapter a railway case study will be presented. The mathematical models of the most relevant electromechanical components of the vehicle powertrain are presented: the pantograph connected to an ideal overhead line with continuous voltage; the electrical components of a pre-charge circuit, the line filter and the braking chopper; the three-phase voltage source inverter and the induction motor; and, finally, the mechanical transmission system, including its interactions with the rail. Then the issues related to the real-time simulation of the locomotive components models are discussed, concentrating on challenges related to the stiff nature of the dynamic equations and on their numerical integration by combining field programmable gate array (FPGA) and central processing unit (CPU) boards. The usefulness of the real-time hardware-in-the-loop simulations for the analysis of railway control software will be demonstrated by considering the powertrains of two real metropolitan trains under complex scenarios, i.e., stator winding disconnection of the induction motor, pantograph missing contact, wheel-rail slipping phenomenon.