Search Results (195)

This study presents TeS v.3, a thermodynamic equilibrium simulator integrated with an artificial intelligence agent (AI), ThermoAgent, to enhance the analysis of complex chemical systems. Developed in Python, the simulator employs Gibbs energy minimization for isothermal reactors and entropy maximization for adiabatic reactors. ThermoAgent leverages the LangChain framework to interpret natural language commands, autonomously execute simulations, and query a scientific knowledge base through a Retrieval-Augmented Generation (RAG) approach. The validation of TeS v.3 demonstrated high accuracy, with coefficients of determination (R² > 0.95) compared to reference simulation data and strong correlation (R² > 0.88) with experimental data from the steam methane reforming (SMR) process. The SMR analysis correctly distinguished the high conversions in isothermal reactors from the limited conversions in adiabatic reactors, due to the reaction temperature drop. ThermoAgent successfully executed simulations and provided justified analyses, combining generated data with information from reference publications. The successful integration of the simulator with the AI agent represents a significant advancement, offering a powerful tool that accurately calculates equilibrium and accelerates knowledge extraction through intuitive interaction. Full article

Accurate carbon price forecasting is essential for market stability, risk management, and policy-making. To address the nonlinear, non-stationary, and multiscale nature of carbon prices, this paper proposes a forecasting framework integrating secondary decomposition, two-stage feature selection, and dynamic ensemble learning. Firstly, the original price series is decomposed into intrinsic mode functions (IMFs), using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). The IMFs are then grouped into low- and high-frequency components based on multiscale entropy (MSE) and K-Means clustering. To further alleviate mode mixing in the high-frequency components, an improved variational mode decomposition (VMD) optimized by particle swarm optimization (PSO) is applied for secondary decomposition. Secondly, a two-stage feature-selection method is employed, in which the partial autocorrelation function (PACF) is used to select relevant lagged features, while the maximal information coefficient (MIC) is applied to identify key variables from both historical and external data. Finally, this paper introduces a dynamic integration module based on sliding windows and sequential least squares programming (SLSQP), which can not only adaptively adjust the weights of four base learners but can also effectively leverage the complementary advantages of each model and track the dynamic trends of carbon prices. The empirical results of the carbon markets in Hubei and Guangdong indicate that the proposed method outperforms the benchmark model in terms of prediction accuracy and robustness, and the method has been tested by Diebold Mariano (DM). The main contributions are the improved feature-extraction process and the innovative use of a sliding window-based SLSQP method for dynamic ensemble weight optimization. Full article

During the steam reforming of methane (SRM) process, elevated CH₄ levels after the reaction often signify inadequate heat supply or incomplete reactions within the reformer, jeopardizing process stability. In this paper, a novel multi-step forecasting method using a Trans-GRU network was proposed for predicting the methane content outlet of the SRM reformer. First, a novel feature selection based on the maximal information coefficient (MIC) was applied to identify critical input variables and determine their optimal input order. Additionally, the Trans-GRU network enables the simultaneous capture of multivariate correlations and the learning of global sequence representations. The experimental results based on time-series data from a real SRM process demonstrate that the proposed approach significantly improves the accuracy of multi-step methane content prediction. Compared to benchmark models, including the TCN, Transformer, GRU, and CNN-LSTM, the Trans-GRU consistently achieves the lowest root mean squared error (RMSE) and mean absolute error (MAE) values across all prediction steps (1–6). Specifically, at the one-step horizon, it yields an RMSE of 0.0120 and an MAE of 0.0094. This high performance remains robust across the 2–6-step predictions. The improved predictive capability supports the stable operation and predictive optimization strategies of the steam reforming process in hydrogen production. Full article

Sluices play a critical role in flood control, power generation, water supply, etc. With decades of service, sluice safety assurance becomes a structural engineering imperative. Previous investigations have revealed that failures of sluices are often associated with seepage damage. To gain further insight into sluice seepage and ensure the safety of sluice structures, proposing an effective prediction method for sluice seepage nevertheless remains a challenging fundamental and practical perspective. Therefore, in this paper, a novel prediction model for sluice seepage based on impact factor screening methods, the improved Kepler optimization algorithm (IKOA) and the bidirectional gated recurrent unit (BiGRU), is presented. Primarily, the maximal information coefficient and the correlation-based feature selection (MIC–CFS) are introduced to screen the impact factors of the model, aiming to reduce redundant information and the complexity of the model. Subsequently, the Kepler optimization algorithm (KOA) is enhanced using three strategies: chaotic mapping-based initialization, Runge–Kutta-based position updating, and the enhanced solution quality (ESQ) strategy to optimize the hyperparameters of the BiGRU network. On this basis, the prediction model is established, which is applied in the Bengbu sluice to verify its fitting and prediction performance. Eventually, comparison analyses with a traditional stepwise regression model, IKOA–LSTM, and IKOA–GRU, were conducted based on monitoring sequences of three monitoring points. The coefficients of determination of the proposed model were located in the range of 0.974 to 0.988. Correspondingly, the mean absolute error values of the proposed model were the lowest, ranging from 0.074 to 0.064. The results of six evaluation metrics confirm that the proposed model consistently exhibits superior interpretability and is able to serve as a promising tool for sluice seepage prediction. Full article

High-voltage direct current (HVDC) systems, with their advantages of large capacity, long distance, high efficiency, and low loss, are becoming the core support of new power systems. However, in conventional droop control, the fixed droop coefficient causes output power disproportionate to the available capacities among converters, as well as a relatively large deviation of DC voltage in HVDC systems. Therefore, in this paper, a two-objective optimization model for droop control is developed and then it is integrated to a cooperative control, which achieves the co-optimization of voltage deviation and power sharing among multiple converters. In the optimization model, there are two objectives, the minimization of voltage deviation and maximization of the capacity utilization rates of converters. Further, a cooperative control method based on the optimization model is proposed, where information on voltage and power in droop-controlled converters is acquired and the co-optimization of voltage deviation and power sharing is performed to obtain the optimal droop coefficients for these converters, which minimizes voltage deviation, and at the same time, makes power mismatches proportional to their available capacities among converters. Finally, a testbed is built in PSCAD/EMTDC and four cases are designed to verify the proposed method under different settings. The simulation results show that compared with conventional droop control, the voltage deviation is reduced by 71.74% and 67.67% under the cases that a converter is out of service and the three-phase ground fault of a converter occurs. Additionally, when large power fluctuations occur twice, the power mismatches are shared proportionally to their available capacities, which results in the capacity utilization rates of the droop-controlled converters increasing by 24.46% and 18.75%, respectively. Full article

The development of ultrahigh-concentration photovoltaic (UHCPV) systems plays a pivotal role in advancing sustainable solar energy technologies. As the demand for clean energy grows, the need to align concentrated photovoltaic (CPV) system design with high-efficiency solar cell production becomes critical for maximizing energy yield while minimizing resource use. Despite some experimental efforts in UHCPV development, there remains a gap in integrating Fresnel lens-based systems with the comprehensive thermal modeling of key components in improving system sustainability and performance. To bridge this gap and promote more energy-efficient designs, a detailed numerical model was established to evaluate both the thermal and optical performance of a UHCPV system. This model contributes to the sustainable design process by enabling informed decisions on system efficiency, thermal management, and material optimization before physical prototyping. Through COMSOL Multiphysics simulations, the system was assessed under direct normal irradiance (DNI) ranging from 400 to 1000 W/m². Optical simulations indicated a high theoretical optical efficiency of ~93% and a concentration ratio of 1361 suns, underscoring the system’s potential to deliver high solar energy conversion with minimal land and material footprint. Moreover, the integration of thermal and optical modeling ensures a holistic understanding of system behavior under varying ambient temperatures (20–50 °C) and convective cooling conditions (heat transfer coefficients between 4 and 22 W/m².K). The results showed that critical optical components remain within safe temperature thresholds (<54 °C), while the receiver stage operates between 78.5 °C and 157.4 °C. These findings highlight the necessity of an effective cooling mechanism—not only to preserve system longevity and safety but also to maintain high conversion efficiency, thereby supporting the broader goals of sustainable and reliable solar energy generation. Full article

In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking the time needed for training and detection. Moreover, they may not fully leverage the combined utilization of CAN bus IDs and the data field with external network data. Consequently, these systems frequently struggle to meet the real-time demands and broader attack scenarios inherent in in-vehicle systems. To overcome these challenges, we propose a stacked-model IDS architecture deployed across the CAN bus and central gateway, capable of detecting both internal and external vehicular network attacks. The system extracts key features from in-vehicle and external network data, builds base learners (CART, LightGBM, XGBoost), and integrates them through stacking with a meta-learner. Feature selection and training efficiency are enhanced using information gain and maximal information coefficient algorithms. Experiments show that the proposed IDS achieves an average detection accuracy of 99.99% for internal CAN bus attacks and 99.81% for external network attacks, with fast detection times of 0.018 ms and 0.088 ms, respectively. These results highlight the system’s real-time capability, high accuracy, and adaptability to complex attack scenarios. Full article

Narrative mapping, an advanced geographic information visualization technology, presents spatial information episodically, enhancing readers’ spatial understanding and event cognition. However, during 3D scene construction, viewpoint selection is heavily reliant on the cartographer’s subjective interpretation of the event. Even with fixed-angle settings, the task of ensuring that selected viewpoints align with the narrative theme remains challenging. To address this, an automated viewpoint selection method constrained by narrative relevance and visual information is proposed. Narrative relevance is determined by calculating spatial distances between each element and the thematic element within the scene. Visual information is quantified by assessing the visual salience of elements as the ratio of their projected area on the view window to their total area. Pearson’s correlation coefficient is used to evaluate the relationship between visual salience and narrative relevance, serving as a constraint to construct a viewpoint fitness function that integrates the visual salience of the convex polyhedron enclosing the scene. The chaotic particle swarm optimization (CPSO) algorithm is utilized to locate the viewpoint position while maximizing the fitness function, identifying a viewpoint meeting narrative and visual salience requirements. Experimental results indicate that, compared to the maximum projected area method and fixed-value method, a higher viewpoint fitness is achieved by this approach. The narrative views generated by this method were positively recognized by approximately two-thirds of invited professionals. This process aligns effectively with narrative visualization needs, enhances 3D narrative map creation efficiency, and offers a robust strategy for viewpoint selection in 3D scene-based narrative mapping. Full article

Lidar has been used for many years to study the optical properties of aerosols, but estimating the boundary values requires solving the lidar elastic scattering equation, which remains a challenge. The boundary values are often determined by fitting to uniform regions of the atmosphere. This method typically excludes low signal-to-noise ratio (SNR) signals because it classifies them as non-uniform, reducing the effective detection range of the lidar. On the other hand, directly fitting low SNR signals to estimate the boundary values can introduce significant errors. The method is based on maximizing the lidar detection distance and determines the boundary value using a new estimation algorithm with the averaging of multiple fitted results in the low SNR region to reduce the impact of noise. Simulations demonstrate that the new method reduces the relative error in the boundary value estimation by approximately 5% and improves the accuracy of the extinction coefficient profile inversion compared with the method of directly fitting all-sample signals. Field comparison experiments with forward-scattering sensors further verify that the algorithm improves the retrieval accuracy by 17.3% under extremely low signal-to-noise ratio (SNR) conditions, while performing comparably to the traditional method in high SNR homogeneous atmospheres. Additionally, based on the scanned lidar signals, the algorithm can provide detailed information on the spatial distribution of sea fog and offer valuable insights for an in-depth understanding of the physical evolution of sea fog. Full article

The construction sector is swiftly evolving toward more sustainable practices. Life cycle assessment (LCA) is essential for assessing the environmental impact of construction materials. A crucial factor in this context is the wear-out coefficient (WOC), which indicates a material’s reusability and directly affects the amount of material used during a project’s life cycle. This study contrasts conventional timber formwork with alternative materials, including aluminum, steel, plywood, plastic, and various hybrid systems. The environmental consequences are assessed throughout several life cycle stages—manufacturing, transportation, usage, and disposal—utilizing a 3D building information modeling (BIM)-integrated life cycle assessment (LCA) framework. This method facilitates adherence to green building standards and corresponds with the Sustainable Development Goals (SDGs). Hybrid Option 2 (timber–aluminum–steel) and Hybrid Option 4 (steel–plastic–aluminum) distinguish themselves as superior choices, integrating environmental efficacy with resilience. Aluminum exhibits the lowest WOC (0.13), signifying its exceptional reusability and lack of environmental impact. The results highlight the need to incorporate BIM and LCA in formwork material planning to improve sustainability, prolong the service life, and maximize resource efficiency in construction. Full article

Daily reference crop evapotranspiration (ET₀) is crucial for precision irrigation management, yet traditional prediction methods struggle to capture its dynamic variations due to the complexity and nonlinearity of meteorological conditions. To address this, we propose an Improved Informer model to enhance ET₀ prediction accuracy, providing a scientific basis for agricultural water management. Using meteorological and soil data from the Yingde region, we employed the Maximal Information Coefficient (MIC) to identify key influencing factors and integrated Residual Cycle Forecasting (RCF), Star Aggregate Redistribute (STAR), and Fully Adaptive Normalization (FAN) techniques into the Informer model. MIC analysis identified total shortwave radiation, sunshine duration, maximum temperature at 2 m, soil temperature at 28–100 cm depth, and surface pressure as optimal features. Under the five-feature scenario (S3), the improved model achieved superior performance compared to Long Short-Term Memory (LSTM) and the original Informer models, with MAE reduced to 0.065 (LSTM: 0.637, Informer: 0.171) and MSE to 0.007 (LSTM: 0.678, Informer: 0.060). The inference time was also reduced by 31%, highlighting the enhanced computational efficiency. The Improved Informer model effectively captures the periodic and nonlinear characteristics of ET₀, offering a novel solution for precision irrigation management with significant practical implications. Full article

The enthalpy of mixing, a critical thermodynamic property in the liquid phase reflecting element interaction strength and pivotal for studying phase equilibria, can now be predicted efficiently using machine learning. This study proposes a model combining machine learning with the Calculation of Phase Diagram (CALPHAD) to predict the enthalpy of mixing. We obtained data for 583 binary alloy systems from the SGTE database, ensuring experimental constraints for accuracy. Using pure element properties and Miedema’s model parameters as descriptors, we trained and evaluated four machine learning algorithms, finding LightGBM to perform best (R² = 92.2%, MAE = 3.5 kJ/mol). The model performance was further optimized through Recursive Feature Elimination (RFE) and Maximal Information Coefficient (MIC) feature selection methods. Shapley Additive Explanations reveals that the primary factors affecting the mixing enthalpy, such as atomic radius and electronegativity, align with the key parameters of the Miedema model, thereby confirming the physical interpretability of our data-driven approach. This work offers an accelerated method for predicting complex multi-component system thermodynamics. Future research will focus on collecting more high-quality data to enhance model accuracy and generalization. Full article

Magnetoencephalography (MEG) is a non-invasive neuroimaging technique that measures weak magnetic fields generated by neural electrical activity in the brain. Traditional MEG systems use superconducting quantum interference device (SQUID) sensors, which require cryogenic cooling and employ a dense array of sensors to capture magnetic field maps (MFMs) around the head. Recent advancements have introduced optically pumped magnetometers (OPMs) as a promising alternative. Unlike SQUIDs, OPMs do not require cooling and can be placed closer to regions of interest (ROIs). This study aims to optimize the layout of OPM-MEG sensors, maximizing information capture with a limited number of sensors. We applied a sequential selection algorithm (SSA), originally developed for body surface potential mapping in electrocardiography, which requires a large database of full-head MFMs. While modern OPM-MEG systems offer full-head coverage, expected future clinical use will benefit from simplified procedures, where handling a lower number of sensors is easier and more efficient. To explore this, we converted full-head SQUID-MEG measurements of auditory-evoked fields (AEFs) into OPM-MEG layouts with 80 sensor sites. System conversion was done by calculating a current distribution on the brain surface using minimum norm estimation (MNE). We evaluated the SSA’s performance under different protocols, for example, using measurements of single or combined OPM components. We assessed the quality of estimated MFMs using metrics, such as the correlation coefficient (CC), root-mean-square error, and relative error. Additionally, we performed source localization for the highest auditory response (M100) by fitting equivalent current dipoles. Our results show that the first 15 to 20 optimally selected sensors (CC > 0.95, localization error < 1 mm) capture most of the information contained in full-head MFMs. Our main finding is that for event-related fields, such as AEFs, which primarily originate from focal sources, a significantly smaller number of sensors than currently used in conventional MEG systems is sufficient to extract relevant information. Full article

The dynamic mode decomposition serves as a useful tool for the coherent structure extraction of the complex flow fields with characteristic frequency identification, but the phase information of the flow modes is paid less attention to. In this study, phase information around the locally flexible membrane airfoil is quantitatively studied using dynamic mode decomposition (DMD) to unveil the physical mechanism of the lift improvement of the membrane airfoil. The flow over the airfoil at a low Reynolds number (Re = 5500) is computed parametrically across a range of angles of attack (AOA = 4°–14°) and membrane lengths (LM = 0.55c–0.70c) using a verified fluid–structure coupling framework. The lift enhancement is analyzed by the dynamic coherent patterns of the membrane airfoil flow fields, which are quantified by the DMD modal phase propagation. A downstream propagation pressure speed (DPP) on the upper surface is defined to quantify the propagation speed of the lagged maximal pressure in the flow separation zone. It is found that a faster DPP speed can induce more vortices. The correlation coefficient between the DPP speed and lift enhancement is above 0.85 at most cases, indicating the significant contribution of vortex evolution to aerodynamic performance. The DPP speed greatly impacts the retention time of dominant vortices on the upper surface, resulting in the lift enhancement. Full article

We propose a vertiport location-allocation methodology for urban air mobility (UAM) from the perspective of transportation network topology. The location allocation of vertiports within a transportation network is a crucial factor in determining the unique characteristics of UAM compared to existing transportation modes. However, as UAM is still in the pre-commercialization phase, with significant uncertainties, there are limitations in applying location-allocation models that optimize objective functions such as maximizing service coverage or minimizing travel distance. Instead, vertiport location allocation should be approached from a strategic perspective, taking into account public capital investments aimed at improving the transportation network by leveraging UAM’s distinct characteristics compared to existing urban transportation modes. Therefore, we present a methodology for evaluating the impact of vertiport location-allocation strategies on changes in transportation network topology. To analyze network topology, we use the Seoul Metropolitan railway network as the base network and construct scenarios where vertiports are allocated based on highly connected nodes and those prioritizing structurally vulnerable nodes. We then compare and analyze global network efficiency, algebraic connectivity, average shortest path length, local clustering coefficient, transitivity, degree assortativity and modularity. We confirm that while allocating vertiports based on network centrality improves connectivity compared to vulnerability-based allocation, the latter approach is superior in terms of network efficiency. Additionally, as the proportion of vertiports increases, the small-world property of the network rapidly increases, indicating that the vertiport network can fundamentally alter the structure of multimodal transportation systems. Regardless of whether centrality or vulnerability is prioritized, we observe that connectivity increase exponentially, while network efficiency changes linearly with the increase in vertiport proportion. Our findings highlight the necessity of a network-based approach to vertiport location allocation in the early stages of UAM commercialization, and we expect our results to inform future research directions on vertiport allocation in multimodal transportation networks. Full article