This paper presents a novel approach to dynamic pricing and distributed energy management in virtual power plant (VPP) networks using multi-agent reinforcement learning (MARL). As the energy landscape evolves towards greater decentralization and renewable integration, traditional optimization methods struggle to address the inherent complexities and uncertainties. Our proposed MARL framework enables adaptive, decentralized decision-making for both the distribution system operator and individual VPPs, optimizing economic efficiency while maintaining grid stability. We formulate the problem as a Markov decision process and develop a custom MARL algorithm that leverages actor-critic architectures and experience replay. Extensive simulations across diverse scenarios demonstrate that our approach consistently outperforms baseline methods, including Stackelberg game models and model predictive control, achieving an 18.73% reduction in costs and a 22.46% increase in VPP profits. The MARL framework shows particular strength in scenarios with high renewable energy penetration, where it improves system performance by 11.95% compared with traditional methods. Furthermore, our approach demonstrates superior adaptability to unexpected events and mis-predictions, highlighting its potential for real-world implementation.
The performance of Organic Solar Cells (OSCs) is intrinsically linked to the molecular, electronic, and structural properties of donor and acceptor materials. This study employs various machine learning techniques, namely the Generalized Regression Neural Network (GRNN), Support Vector Machine (SVM), and Tree Boost, to predict key performance metrics of OSCs, including power conversion efficiency (PCE), short-circuit current density (JSC), open-circuit voltage (VOC), and fill factor (FF). The models are trained and evaluated using an experimentally reported dataset compiled by Sahu et al. Correlation analysis demonstrates that material characteristics such as polarizability, bandgap, dipole moment, and charge transfer are statistically associated with OSC performance. The predictive performance of the GRNN model is compared with that of the SVM and Tree Boost models, showing consistently lower prediction errors within the considered dataset. In addition, sensitivity analysis is performed to assess the relative importance of the predictor variables and to examine the influence of kernel functions on GRNN performance. The results indicate that machine learning models, particularly GRNN, can serve as effective data-driven tools for predicting the performance of organic solar cells and for supporting computational screening studies.
Fabio Mendonca, Sheikh Shanawaz Mostafa, Fernando Morgado-Dias
et al.
Uncertainty analysis of classification or regression models is a key feature of probabilistic approaches to supervised learning, allowing the assessment of how trustworthy predictions are. Just as boosting algorithms aim at obtaining accurate ensembles of simple classifiers, using a process guided by the accuracy of each of these classifiers, the method proposed in this paper builds an ensemble guided by the uncertainty of each of its individual models. The proposed method, named ProBoost (probabilistic boosting), uses the epistemic uncertainty of each training sample to determine those about which each model is most uncertain; the importance of these samples is then increased for the next learner, producing a sequence that progressively focuses on samples found to have the highest uncertainty. In the end, the learned models are combined into an ensemble. Thus, the approach goes beyond standard boosting methods, which usually focus on deterministic error correction, by quantifying predictive uncertainty to guide sequential training through dataset manipulation. Three methods are proposed to update the importance of the samples according to the uncertainty estimates at each stage: undersampling, oversampling, and weighting. Furthermore, two approaches are studied regarding the final ensemble combination. The learners herein considered are standard convolutional neural networks, and the probabilistic models underlying the uncertainty estimation use either variational inference or Monte Carlo dropout. The experimental evaluation carried out on MNIST and CIFAR 10 benchmark datasets shows that ProBoost yields significant performance improvement, compared to not using ProBoost, and outperforms a wider single model with a similar number of parameters.
Christopher Knievel, Alexander Bernhardt, Christian Bernhardt
Intelligent tutoring systems combined with large language models offer a promising approach to address students' diverse needs and promote self-efficacious learning. While large language models possess good foundational knowledge of electrical engineering basics, they remain insufficiently capable of addressing specific questions about electrical circuits. In this paper, we present AITEE, an agent-based tutoring system for electrical engineering designed to accompany students throughout their learning process, offer individualized support, and promote self-directed learning. AITEE supports both hand-drawn and digital circuits through an adapted circuit reconstruction process, enabling natural interaction with students. Our novel graph-based similarity measure identifies relevant context from lecture materials through a retrieval augmented generation approach, while parallel Spice simulation further enhances accuracy in applying solution methodologies. The system implements a Socratic dialogue to foster learner autonomy through guided questioning. Experimental evaluations demonstrate that AITEE significantly outperforms baseline approaches in domain-specific knowledge application, with even medium-sized LLM models showing acceptable performance. Our results highlight the potential of agentic tutors to deliver scalable, personalized, and effective learning environments for electrical engineering education.
Abstract Metallic phthalocyanines are promising electrocatalysts for CO2 reduction reaction (CO2RR). However, their catalytic activity and stability (especially under high potential) are still unsatisfactory. Herein, we synthesized a covalent organic polymer (COP‐CoPc) by introducing charge‐switchable viologen ligands into cobalt phthalocyanine (CoPc). The COP‐CoPc exhibits great activity for CO2RR, including a high Faradaic efficiency over a wide potential window and the highest CO partial current density among all ligand‐tuned phthalocyanine catalysts reported in the H‐type cell. Particularly, COP‐CoPc also shows great potential for practical applications, for example, a FECO of >95% is realized at a large current density of 150 mA/cm2 in a two‐electrode membrane electrode assembly reactor. Ex situ and in situ X‐ray absorption fine structure spectroscopy measurements and theory calculations reveal that when the charge‐switchable viologen ligands switch to neutral‐state ones, they can act as electron donors to enrich the electron density of Co centers in COP‐CoPc and enhance the desorption of *CO, thus improving the CO selectivity. Moreover, the excellent reversible redox capability of viologen ligands and the increased Co–N bonding strength in the Co–N4 sites enable COP‐CoPc to possess outstanding stability under elevated potentials and currents, enriching the knowledge of charge‐switchable ligands tailored CO2RR performance.
Materials of engineering and construction. Mechanics of materials
Soham Das, Soumya Kanti Biswas, Abhishek Kundu
et al.
In this experimental investigation, a Physical Vapor Deposition (PVD) process was employed to deposit TiAlN coating onto a Si substrate. The nitrogen flow rate, bias voltage, and substrate-to-target distance were selected as input parameters, each with three different levels. The design of these input parameters was structured according to Taguchi's L9 Orthogonal Array (OA). Following deposition, the mechanical, microstructural, structural, and electrochemical properties of the TiAlN coating were meticulously characterized and analyzed to discern the influence of the selected parameters on its various properties. Microstructural analysis revealed a homogeneous structure throughout the film. Additionally, the mechanical properties of the film exhibited notable performance under the specified parameters. However, it was observed that no consistent trend could be identified across different properties concerning the applied parameters. To elucidate the complex relationships among these variables, the Least Squares Method (LSM) regression analysis technique was employed. This analytical approach facilitated the establishment of correlations among the diverse parameters, enhancing the understanding of their collective impact on the TiAlN coating properties. The understanding of analytical results will be useful for predicting the values between the two extremities to measure the performance parameters where the experimental results are not available.
Materials of engineering and construction. Mechanics of materials, Industrial electrochemistry
This article deals with the issue of assembling conventional SMD components on textile substrates using UV-curable non-conductive adhesives. This technology is easily applicable in the textile industry. It thus enables the easy and fast production of e-textiles that are equipped with conventional electronic components or even entire electronic modules. The article describes the principle of this innovative technology. Furthermore, comprehensive results of testing the effect of mechanical stress, chemical cleaning, and climatic changes on e-textiles with assembled SMD components on the change in contact resistance are presented here. The results show that this technology can be used for assembling and encapsulating SMD components on a textile substrate in the realization of e-textiles.
Electric apparatus and materials. Electric circuits. Electric networks
Preferential Bayesian optimization (PBO) is a framework for human-in-the-loop optimization to maximize black-box human preference functions such as seeking perceptually good visual designs. It is advantageous when consistently providing a degree of preference is challenging, but selecting the best option among multiple choices is relatively more straightforward. However, similar to conventional BO methods, PBO suffers from high dimensional problems, that is, finding a good solution becomes increasingly difficult as the dimensionality of the search space increases. In this paper, we focus on slider-based PBO (S-PBO), which is a variant of PBO generating a set of candidates aligned on a one-dimesional line segment, and propose novel acquisition strategies for high dimensional problems. Specifically, we propose two acquisition functions that have a different balance of local/global search abilities. In addition, we propose a simple yet effective randomized strategy that balances the local/global search abilities provided by the two proposed acquisition functions. Through empirical evaluation, we assess the effectiveness of our proposed strategy in improving high-dimensional problems.
Rakesh Chaudhari, Rushikesh Bhatt, Vatsal Vaghasia
et al.
In the present study, the Gas metal arc welding (GMAW) based Wire-arc additive manufacturing (WAAM) process was preferred for the fabrication of multi-layered structures and their investigations of mechanical properties on metal core wire. Based on literature work, preliminary trials, machine limits, travel speed (TS), voltage (V), and gas mixture ratio (GMR) were identified as machining parameters along with output factors of bead width (BW), bead height (BH), and depth-of-penetration (DOP). Experiments were conducted by following the Box-Behnken design. The feasibility of the generated non-linear regression models has been validated through the statistical analysis of variance and residual plots. The multi-layered structure has been successfully fabricated at the optimized parametric settings of TS at 24 mm/s; the voltage at 24 V, and GMR at 1 which was obtained through the heat transfer search (HTS) algorithm. The fabricated structure was observed to be uniform. The structure exhibited uniform bead-on-bead deposition for the deposited layers. The fabricated multi-layered structure underwent a detailed microstructural and mechanical examinations. Microstructural examination revealed dense needles at the bottom section of the structure as compared to the top section, as the bottom section undergoes multiple heating and cooling cycles. When comparing the multilayer structure to the metal core wire, all the properties exhibited favorable tensile characteristics. The obtained strength from the impact test results highlights the impressive ductility of the multi-layer deposition. Fractography of tensile and impact test specimens has shown the occurrences of larger dimples and suggested a ductile fracture. Lastly, the hardness value in all the sections of the built structure was observed to be uniform, suggesting uniform deposition across the built multi-layer structure. The authors consider the current work will be highly beneficial for users in fabricating multi-layer structures at optimized parametric settings and their investigations for mechanical properties for metal core wire.
Materials of engineering and construction. Mechanics of materials
Emilio Vital Brazil, Eduardo Soares, Lucas Villa Real
et al.
Data is a critical element in any discovery process. In the last decades, we observed exponential growth in the volume of available data and the technology to manipulate it. However, data is only practical when one can structure it for a well-defined task. For instance, we need a corpus of text broken into sentences to train a natural language machine-learning model. In this work, we will use the token \textit{dataset} to designate a structured set of data built to perform a well-defined task. Moreover, the dataset will be used in most cases as a blueprint of an entity that at any moment can be stored as a table. Specifically, in science, each area has unique forms to organize, gather and handle its datasets. We believe that datasets must be a first-class entity in any knowledge-intensive process, and all workflows should have exceptional attention to datasets' lifecycle, from their gathering to uses and evolution. We advocate that science and engineering discovery processes are extreme instances of the need for such organization on datasets, claiming for new approaches and tooling. Furthermore, these requirements are more evident when the discovery workflow uses artificial intelligence methods to empower the subject-matter expert. In this work, we discuss an approach to bringing datasets as a critical entity in the discovery process in science. We illustrate some concepts using material discovery as a use case. We chose this domain because it leverages many significant problems that can be generalized to other science fields.
This paper presents findings on dynamic cell modeling for state-of-charge (SOC) estimation in an autonomous electric vehicle (AEV). The studied cells are Lithium-Ion Polymer-based with a nominal capacity of around 8Ah, optimized for power-needy applications. The AEV operates in a harsh environment with rate requirements up to +/-25C and highly dynamic rate profiles, unlike portable-electronic applications with constant power output and fractional C rates. SOC estimation methods effective in portable electronics may not suffice for the AEV. Accurate SOC estimation necessitates a precise cell model. The proposed SOC estimation method utilizes a detailed Kalman-filtering approach. The cell model must include SOC as a state in the model state vector. Multiple cell models are presented, starting with a simple one employing "Coulomb counting" as the state equation and Shepherd's rule as the output equation, lacking prediction of cell relaxation dynamics. An improved model incorporates filter states to account for relaxation and other dynamics in closed-circuit cell voltage, yielding better performance. The best overall results are achieved with a method combining nonlinear autoregressive filtering and dynamic radial basis function networks. The paper includes lab test results comparing physical cells with model predictions. The most accurate models obtained have an RMS estimation error lower than the quantization noise floor expected in the battery-management-system design. Importantly, these models enable precise SOC estimation, allowing the vehicle controller to utilize the battery pack's full operating range without overcharging or undercharging concerns.
Douglas Beck, Joseph Carlson, Zohreh Davoudi
et al.
In preparation for the 2023 NSAC Long Range Plan (LRP), members of the Nuclear Science community gathered to discuss the current state of, and plans for further leveraging opportunities in, QIST in NP research at the Quantum Information Science for U.S. Nuclear Physics Long Range Planning workshop, held in Santa Fe, New Mexico on January 31 - February 1, 2023. The workshop included 45 in-person participants and 53 remote attendees. The outcome of the workshop identified strategic plans and requirements for the next 5-10 years to advance quantum sensing and quantum simulations within NP, and to develop a diverse quantum-ready workforce. The plans include resolutions endorsed by the participants to address the compelling scientific opportunities at the intersections of NP and QIST. These endorsements are aligned with similar affirmations by the LRP Computational Nuclear Physics and AI/ML Workshop, the Nuclear Structure, Reactions, and Astrophysics LRP Town Hall, and the Fundamental Symmetries, Neutrons, and Neutrinos LRP Town Hall communities.
Registered reports are scientific publications which begin the publication process by first having the detailed research protocol, including key research questions, reviewed and approved by peers. Subsequent analysis and results are published with minimal additional review, even if there was no clear support for the underlying hypothesis, as long as the approved protocol is followed. Registered reports can prevent several questionable research practices and give early feedback on research designs. In software engineering research, registered reports were first introduced in the International Conference on Mining Software Repositories (MSR) in 2020. They are now established in three conferences and two pre-eminent journals, including Empirical Software Engineering. We explain the motivation for registered reports, outline the way they have been implemented in software engineering, and outline some ongoing challenges for addressing high quality software engineering research.
In the present work, we have done a systematic shell model study of $N=82$ and $N=126$ isotones. For the $N=82$ isotones, we have performed calculations using SN100PN interaction, while for $N=126$ isotones, we have used KHPE interaction. Similarities between these two isotonic chains have been reported, using the strong resemblance between the high-$j$ orbitals. Apart from the nuclear spectroscopic properties, we have also explained different isomeric states in these two regions. In the $N$ =82 region, we have mainly discussed the properties of the $6^+$ and $17/2^+$ isomers, while in the $N=126$ region for $8^+$, $11^-$, $21/2^-$ and $29/2^+$ isomers. We have reported $B(E2)$, $B(E3)$, $g$-factor, and quadrupole moments of the isomeric states for comparison in these two isotonic chains.
In the last decade, Single-Board Computers (SBCs) have been employed more frequently in engineering and computer science both to technical and educational levels. Several factors such as the versatility, the low-cost, and the possibility to enhance the learning process through technology have contributed to the educators and students usually employ these devices. However, the implications, possibilities, and constraints of these devices in engineering and Computer Science (CS) education have not been explored in detail. In this systematic literature review, we explore how the SBCs are employed in engineering and computer science and what educational results are derived from their usage in the period 2010-2020 at tertiary education. For that, 154 studies were selected out of n=605 collected from the academic databases Ei Compendex, ERIC, and Inspec. The analysis was carried-out in two phases, identifying, e.g., areas of application, learning outcomes, and students and researchers' perceptions. The results mainly indicate the following aspects: (1) The areas of laboratories and e-learning, computing education, robotics, Internet of Things (IoT), and persons with disabilities gather the studies in the review. (2) Researchers highlight the importance of the SBCs to transform the curricula in engineering and CS for the students to learn complex topics through experimentation in hands-on activities. (3) The typical cognitive learning outcomes reported by the authors are the improvement of the students' grades and the technical skills regarding the topics in the courses. Concerning the affective learning outcomes, the increase of interest, motivation, and engagement are commonly reported by the authors.
In the emerging world of metaverses, it is essential for speech communication systems to be aware of context to interact with virtual assets in the 3D world. This paper proposes the metaverse for aircraft maintenance training and education of Boeing-737, supplied with legacy manuals, 3D models, 3D simulators, and aircraft maintenance knowledge. Furthermore, to navigate and control operational flow in the metaverse, which is strictly followed by maintenance manuals, the context-aware speech understanding module Neuro-Symbolic Speech Executor (NSSE) is presented. Unlike conventional speech recognition methods, NSSE applies Neuro-Symbolic AI, which combines neural networks and traditional symbolic reasoning, to understand users’ requests and reply based on context and aircraft-specific knowledge. NSSE is developed with an industrially flexible approach by applying only synthetic data for training. Nevertheless, the evaluation process performed with various automatic speech recognition metrics on real users’ data showed sustainable results with an average accuracy of 94.7%, Word Error Rate (WER) of 7.5%, and the generalization ability to handle speech requests of users with the non-native pronunciation. The proposed Aircraft Maintenance Metaverse is a cheap and scalable solution for aviation colleges since it replaces expensive physical aircraft with virtual one that can be easily modified and updated. Moreover, the Neuro-Symbolic Speech Executor, playing the role of field expert, provides technical guidance and all the resources to facilitate effective training and education of aircraft maintenance.