Roberts Grants

With the development of scientific machine learning (SciML), the proposal of physics-informed neural networks (PINNs) has provided a powerful paradigm for solving partial differential equations (PDEs). While PINNs perform well in solving high-dimensional PDEs, they perform worse than traditional numerical methods for low-dimensional problems. This discrepancy arose from potential convergence conflicts induced by distinct physical magnitude of loss terms. To decouple the convergence conflicts, we propose a partial derivative guided multi-branch physics-informed neural network (PDGM-PINN). Inspired by SciML, we treat both the solution and partial derivatives as dependent variables to be predicted. The partial derivatives are directly predicted by sub-branches, while the main branch approximates the PDE solution, and all branches share error backpropagation information. Furthermore, we redesign the loss function. The loss of the governing equation is computed with the solution and partial derivatives predicted by the main and sub-branches. Schwarz’s theorem and Kullback–Leibler divergence are incorporated into the loss terms as soft constraints of partial derivatives continuity and residual distributions consistency for the governing equations. We conducted comprehensive experimental evaluations on seven PDEs, and ablation experiments, sensitivity analyses, and complexity analyses were carried out to investigate the rationality of PDGM-PINN. The results demonstrate that PDGM-PINN achieves the best performance among PINN variants with the fewest trainable parameters, effectively avoiding architectural redundancy.

Rapid expansion of electric vehicle adoption has led to increased dependence on a charging infrastructure that is tightly integrated with energy distribution systems and digital communication networks. As electric vehicle charging stations evolve into complex cyber–physical systems, cybersecurity risks pose a growing threat to grid reliability and user trust. This paper presents a hybrid decision-support framework for cybersecurity risk assessment in EV charging infrastructure that advances beyond prior multi-criteria decision-making approaches by combining interpretability with data-driven validation. Specifically, the framework integrates the Analytic Hierarchy Process (AHP) for expert-driven weighting of cybersecurity attributes with PROMETHEE for flexible threat prioritization, enabling transparent and auditable risk rankings. The framework categorizes cybersecurity criteria across four infrastructure layers—transmission, distribution, consumer, and electric vehicle charging stations—and assigns relative weights through expert-driven pairwise comparisons. PROMETHEE is then applied to rank potential cyber threats based on these weights, allowing for flexible prioritization of cybersecurity interventions. The methodology is validated using the real-world WUSTL-IIoT-2018 SCADA dataset, which includes simulated reconnaissance (network scanning), device identification, and exploitation attacks. While this dataset does not natively include OCPP 2.0 or ISO 15118 protocols, the experimental results demonstrate strong discrimination power (AUC = 0.99, recall = 95%) and provide a basis for extension to modern EVSE communication standards. The results identify critical metrics such as anomalous source packet behavior and encryption reliability as key vulnerability markers, aligning with documented EV charging attack scenarios. By bridging expert judgment with empirical traffic data, the proposed framework offers both technical robustness and explainability, supporting grid operators, SOC teams, and infrastructure planners in systematically assessing risks, allocating resources, and enhancing the resilience of EV charging ecosystems against evolving cyber threats.

Physics-informed neural networks (PINNs) solve partial differential equations (PDEs) by embedding physical conditions as soft penalties into the loss function. However, the coexistence of multiple loss components often leads to gradient conflicts, degrading convergence and solution accuracy. To address this issue, we propose a dynamic domain–gradient loss reweighting PINN (DDR-PINN). The proposed method introduces a dual-residual reweighting mechanism based on gradient variations, where adaptive weights are derived from the L2 norm of the dot product between loss gradients and residuals. These weights are further normalized through a nonlinear hyperbolic tangent transformation, enabling dynamic and balanced reweighting of interior, initial, and boundary domain losses throughout training. Extensive numerical experiments on PDEs with both Dirichlet and Neumann boundary conditions demonstrate that the DDR-PINN consistently outperforms the standard PINN, APINN, and VI-PINN with the fewest trainable parameters.

This paper proposes a design and optimization scheme for an Internet of Things (IoT)-based cloud platform aimed at enhancing the communication efficiency and operational performance of autonomous agricultural machinery. The platform integrates the dual communication capabilities of Narrowband Internet of Things (NB-IoT) and 5G, where NB-IoT is utilized for low-power, reliable data transmission from environmental sensors, such as soil information and weather monitoring, while 5G supports high-bandwidth, low-latency tasks like task scheduling and path tracking to effectively address the diverse communication requirements of modern complex agricultural scenarios. The cloud platform improves operational efficiency and resource utilization through real-time task scheduling, dynamic optimization, and seamless coordination between devices. To accommodate the diverse operational demands of agricultural environments, the system incorporates a real-time data feedback mechanism leveraging sensor data for path tracking and adjustment, enhancing adaptability and stability. Furthermore, a multi-machine collaborative scheduling strategy combining Dijkstra’s algorithm and an improved Harris hawk optimization (IHHO) algorithm, along with a multi-objective optimized path tracking method, is introduced to further improve scheduling efficiency and resource utilization while improving path tracking accuracy and smoothness and reducing external interferences, including environmental fluctuations and sensor inaccuracies. Experimental results demonstrate that the IoT-based cloud platform excels in data transmission reliability, path tracking accuracy, and resource optimization, validating its feasibility in smart agriculture and providing an efficient and scalable solution for large-scale agricultural operations.

With the global shift to electric vehicles, countries face unique challenges and opportunities shaped by their geographical and economic contexts. This paper presents a system that leverages smart transport technologies, the Internet of Things, and decision-making algorithms, such as PROMETHEE, to optimize charging stations and their positioning in diverse urban and rural settings. The system addresses key obstacles, including managing charging infrastructure, balancing energy consumption, and enhancing transport accessibility. By analyzing local conditions, the proposed solution incorporates innovative algorithms for electricity demand forecasting, charging station management, and integration with urban transport systems. This approach ensures a flexible, scalable, and sustainable electric vehicle management system that aligns with international standards and evolving technological trends.

This study presents a novel methodology for evaluating the quality of life in urban areas of Kazakhstan through the development of tailored sustainability indicators. While urban livability and sustainability are global concerns, few studies have focused on developing comprehensive, region-specific metrics for assessing these factors in Kazakhstan, a country with diverse urban environments and newly established administrative divisions. This research fills a critical gap by creating aggregated indicators that address economic, social, environmental, and infrastructural dimensions in a uniquely Kazakhstan context. The study goes beyond the existing literature by integrating local dynamics and challenges, offering a nuanced understanding of urban sustainability that reflects the country’s regional characteristics. The findings provide policymakers and urban planners with actionable insights to improve quality of life and make informed decisions. Moreover, the methodology is designed for ongoing application, allowing for continuous monitoring and adaptation to evolving urban development strategies across Kazakhstan. This research advances the field by offering a replicable framework that can be adapted to other regions with similar complexities.

This article represents and compares two control systems for a vertical takeoff and landing (VTOL) unmanned aerial vehicle (UAV): a sliding proportional–integral–derivative (PID) controller and an adaptive L1 controller. The goal is to design a high-performing and stable control system for a specific VTOL drone. The mathematical model of the unique VTOL drone is presented as a control object. The sliding PID and adaptive L1 controllers are then developed and simulated, and their performance is compared. Simulation results demonstrate that both control systems achieve stable and accurate flight of the VTOL drone, but the adaptive L1 controller outperforms the sliding PID controller in terms of robustness and adaptation to changing conditions. This research contributes to ongoing work on adaptive control systems for VTOL UAVs and highlights the potential benefits of using L1 adaptive control for this application.

The paper is devoted to the digital transformation of the core engineering maintenance processes involved in medium-voltage overhead distribution network infrastructure inspection. The study presents an analysis of digital twin utilization for inspection of the infrastructure of medium-voltage overhead distribution networks. At present, the infrastructure monitoring process is still manual, and its automatization is a challenging task due to the large distances between and small dimensions of the elements involved. The proposed digital twin is employed for 3D infrastructure modeling and complex analysis based on photogrammetry and aerial scanning data processing methods. The paper describes practical use cases for these data-driven methods for specific infrastructure management processes, e.g., scheduled inspection processes, including geometrical parameter measurements and visual infrastructure element defect identification, unplanned inspection processes (state of emergency, post-storm, etc.), and vegetation management processes. The proposed method allows operations to be performed remotely without physical presence in the field. At the same time, data-driven solutions provide objective results and potential automation via machine learning algorithms, which are more profitable economically. As the proposed method allows processes to be performed remotely, these data-driven solutions offer cost-effective results for automation. The digital twin concept is applied to the Latvian medium-voltage overhead distribution network with the support of the Latvian distribution system operator “Sadales tīkls” JSC.

Electric vehicles are coming into our daily lives. In relevant future, battery charged vehicles with high probability will replace fuel internal combustion engines entirely. New transport systems must be flexible, provide new solutions, and must be reliable in future demand. Transport systems needed new solutions to expand and offer to end customers more flexibility and possibilities at lower costs as possible.