Search Results (2,539)

The global atmospheric concentration of carbon dioxide (CO₂) has exceeded 420 ppm. Adsorption-based carbon capture technologies, offer energy-efficient, sustainable solutions. Relying on classical adsorption models like Langmuir to predict CO₂ uptake presents limitations due to the need for case-specific parameter fitting. To address this, the present study introduces a universal machine learning (ML) framework using multiple algorithms—Generalized Linear Model (GLM), Feed-forward Multilayer Perceptron (DL), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosted Trees (GBT)—to reliably predict CO₂ adsorption capacities across diverse zeolite structures and conditions. By compiling over 5700 experimentally measured adsorption data points from 71 independent studies, this approach systematically incorporates critical factors including pore size, Si/Al ratio, cation type, temperature, and pressure. Rigorous Cross-Validation confirmed superior performance of the GBT model (R² = 0.936, RMSE = 0.806 mmol/g), outperforming other ML models and providing comparable performance with classical Langmuir model predictions without separate parameter calibration. Feature importance analysis identified pressure, Si/Al ratio, and cation type as dominant influences on adsorption performance. Overall, this ML-driven methodology demonstrates substantial promise for accelerating material discovery, optimization, and practical deployment of zeolite-based CO₂ capture technologies. Full article

This paper proposes a novel Twin Delayed Deep Deterministic Policy Gradient (TDDPG)-based joint optimization algorithm for hybrid reconfigurable intelligent surface (RIS)-assisted integrated sensing and communication (ISAC) systems in Internet of Vehicles (IoV) scenarios. The proposed system model achieves deep integration of sensing and communication by superimposing the communication and sensing signals within the same waveform. To decouple the complex joint design problem, a dual-DDPG architecture is introduced, in which one agent optimizes the transmit beamforming vector and the other adjusts the RIS phase shift matrix. Both agents share a unified reward function that comprehensively considers multi-user interference (MUI), total transmit power, RIS noise power, and sensing accuracy via the CRLB constraint. Simulation results demonstrate that the proposed TDDPG algorithm significantly outperforms conventional DDPG in terms of sum rate and interference suppression. Moreover, the adoption of a hybrid RIS enables an effective trade-off between communication performance and system energy efficiency, highlighting its practical deployment potential in dynamic IoV environments. Full article

Underwater acoustic (UWA) communication supports many critical applications but still faces several physical-layer signal processing challenges. In response, recent advances in machine learning (ML) and deep learning (DL) offer promising solutions to improve signal detection, modulation adaptability, and classification accuracy. These developments highlight the need for a systematic evaluation to compare various ML/DL models and assess their performance across diverse underwater conditions. However, most existing reviews on ML/DL-based UWA communication focus on isolated approaches rather than integrated system-level perspectives, which limits cross-domain insights and reduces their relevance to practical underwater deployments. Consequently, this systematic literature review (SLR) synthesizes 43 studies (2020–2025) on ML and DL approaches for UWA communication, covering channel estimation, adaptive modulation, and modulation recognition across both single- and multi-carrier systems. The findings reveal that models such as convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and generative adversarial networks (GANs) enhance channel estimation performance, achieving error reductions and bit error rate (BER) gains ranging from ${10}^{-3}$ to ${10}^{-6}$. Adaptive modulation techniques incorporating support vector machines (SVMs), CNNs, and reinforcement learning (RL) attain classification accuracies exceeding 98% and throughput improvements of up to 25%. For modulation recognition, architectures like sequence CNNs, residual networks, and hybrid convolutional–recurrent models achieve up to 99.38% accuracy with latency below 10 ms. These performance metrics underscore the viability of ML/DL-based solutions in optimizing physical-layer tasks for real-world UWA deployments. Finally, the SLR identifies key challenges in UWA communication, including high complexity, limited data, fragmented performance metrics, deployment realities, energy constraints and poor scalability. It also outlines future directions like lightweight models, physics-informed learning, advanced RL strategies, intelligent resource allocation, and robust feature fusion to build reliable and intelligent underwater systems. Full article

As critical components of planetary gearboxes, gears directly affect mechanical system reliability when faults occur. Traditional feature extraction methods exhibit limitations in accurately identifying fault characteristics and achieving satisfactory diagnostic accuracy. This research is concerned with the gear of the planetary gearbox and proposes a new approach termed multi-scale wavelet packet energy entropy (MSWPEE) for extracting gear fault features. The signal is split into sub-signals at three different scale factors. Following decomposition and reconstruction using the wavelet packet algorithm, the wavelet packet energy entropy for each node is computed under different operating conditions. A feature vector is formed by combining the wavelet packet energy entropy at different scale factors. Furthermore, this study proposes a method combining multi-scale wavelet packet energy entropy with extreme learning machine (MSWPEE-ELM). The experimental findings validate the precision of this approach in extracting features and diagnosing faults in sun gears with varying degrees of tooth breakage severity. Full article

The identification of structural damage types remains a key challenge in electromechanical impedance/admittance (EMI/EMA)-based structural health monitoring realm. This paper proposed a damage classification approach for concrete structures by using integrating discrete wavelet transform (DWT) decomposition of EMA signatures with supervised machine learning. In this approach, the EMA signals of arranged piezoelectric ceramic (PZT) patches were successively measured at initial undamaged and post-damaged states, and the signals were decomposed and processed using the DWT technique to derive indicators including the wavelet energy, the variance, the mean, and the entropy. Then these indicators, incorporated with traditional ones including root mean square deviation (RMSD), baseline-changeable RMSD named RMSDk, correlation coefficient (CC), and mean absolute percentage deviation (MAPD), were processed by a support vector machine (SVM) model, and finally damage type could be automatically classified and identified. To validate the approach, experiments on a full-scale reinforced concrete (RC) slab and application to a practical tunnel segment RC slab structure instrumented with multiple PZT patches were conducted to classify severe transverse cracking and minor crack/impact damages. Experimental and application results cogently demonstrated that the proposed DWT-based approach can precisely classify different types of damage on concrete structures with higher accuracy than traditional ones, highlighting the potential of the DWT-decomposed EMA signatures for damage characterization in concrete infrastructure. Full article

Early and accurate detection of mechanical damage in prunes is crucial for preserving postharvest quality and enabling automated sorting. This study proposes a practical and reproducible method for identifying cumulative bruising in prunes using visible–near-infrared (Vis–NIR) reflectance spectroscopy coupled with machine learning techniques. A self-developed impact simulation device was designed to induce progressive damage under controlled energy levels, simulating realistic postharvest handling conditions. Spectral data were collected from the equatorial region of each fruit and processed using a hybrid modeling framework comprising continuous wavelet transform (CWT) for spectral enhancement, uninformative variable elimination (UVE) for optimal wavelength selection, and support vector machine (SVM) for classification. The proposed CWT-UVE-SVM model achieved an overall classification accuracy of 93.22%, successfully distinguishing intact, mildly bruised, and cumulatively damaged samples. Notably, the results revealed nonlinear reflectance variations in the near-infrared region associated with repeated low-energy impacts, highlighting the capacity of spectral response patterns to capture progressive physiological changes. This research not only advances nondestructive detection methods for prune grading but also provides a scalable modeling strategy for cumulative mechanical damage assessment in soft horticultural products. Full article

This study aims to address the challenges posed by uneven energy amplitude and a low signal-to-noise ratio (SNR) in the total focus imaging of coarse-crystalline elastic anisotropic materials. A novel method for acoustic field correction vector-coherent total focus imaging, based on the materials’ properties, is proposed. To demonstrate the effectiveness of this method, a test specimen, an austenitic stainless steel nozzle weld, was employed. Seven side-drilled hole defects located at varying positions and depths, each with a diameter of 2 mm, were examined. An ultrasound simulation model was developed based on material backscatter diffraction results, and the scattering attenuation compensation factor was optimized. The acoustic field correction function was derived by combining acoustic field directivity with diffusion attenuation compensation. The phase coherence weighting coefficients were calculated, followed by image reconstruction. The results show that the proposed method significantly improves imaging amplitude uniformity and reduces the structural noise caused by the coarse crystal structure of austenitic stainless steel. Compared to conventional total focus imaging, the detection SNR of the seven defects increased by 2.34 dB to 10.95 dB. Additionally, the defect localization error was reduced from 0.1 mm to 0.05 mm, with a range of 0.70 mm to 0.88 mm. Full article

This article presents the development, integration, and experimental validation of a modular microgrid for sustainable hydrogen production, addressing global electricity demand and environmental challenges. The system was designed for initial validation in a thermoelectric power plant environment, with scalability to other applications. Centered on a six-compartment skid, it integrates photovoltaic generation, battery storage, and a liquefied petroleum gas generator to emulate typical cogeneration conditions, together with a high-purity proton exchange membrane electrolyzer. A supervisory control module ensures real-time monitoring and energy flow management, following international safety standards. The study also explores the incorporation of blockchain technology to certify the renewable origin of hydrogen, enhancing traceability and transparency in the green hydrogen market. The experimental results confirm the system’s technical feasibility, demonstrating stable hydrogen production, efficient energy management, and islanded-mode operation with preserved grid stability. These findings highlight the strategic role of hydrogen as an energy vector in the transition to a cleaner energy matrix and support the proposed architecture as a replicable model for industrial facilities seeking to combine hydrogen production with advanced microgrid technologies. Future work will address large-scale validation and performance optimization, including advanced energy management algorithms to ensure economic viability and sustainability in diverse industrial contexts. Full article

Traditional approaches in tunnel lighting have been directed toward the installation of appropriate luminaires in the intermediate and transitional sections with the simple objective of diminishing the effect of delayed visual accommodation during daylight hours. Such efforts run in parallel with the target of keeping the huge electrical use at the lowest level. Nevertheless, inadequate attention has been conceded to the interior areas, whose noticeable longitude in several instances, and subsequently the duration of occupancy of the users, can produce discomfort in the majority of the tunnel or underground passageway. It is in this region where the flicker effect presents a more remarkable impact. Although such effect is in fact uncomfortable, the strategies to eliminate it efficiently have not been developed in depth and the result is still deserving, especially in terms of sustainability. The reasons for this neglect, as well as some particularities and solutions, are exposed and discussed in the present article. Specifically, it is proved that the use of sunlight can be an adequate initiative and a positive energy input into design and retrofit tunnels capable of hampering or totally avoiding such unwanted effect. The innovative tunnel geometry explained in this manuscript is not cylindrical, and it is not based in revolution forms. Thus, it prevents the appearance of such unnerving visual effects, which compromise sustainability and endanger security. We are in the position to explain how the vector field generated by the normal to the points of the novel surface displayed remains non-parallel, ensuring appropriate diffusivity and, consequently, an even distribution of radiated energy. In the same manner, the notion of the tunnel is extended from a linear system to a veritable network of galleries, which can traverse in space bi- or even three-dimensionally. Accordingly, we will offer diverse instances of junctions and splices that further enhance the permeability into the terrain, augmenting the resilience capabilities of this disruptive technology. With all the former, a net reduction of costs reaching 25% can be easily expected with revenues. Full article

Agrivoltaic (Agri-PV) systems face the critical challenge of balancing photovoltaic energy generation with crop productivity, yet systematic approaches to quantifying the trade-offs between these objectives remain scarce. In this study, we identify nine essential design indicators: panel tilt angle, elevation, photovoltaic coverage ratio, shading factor, land equivalent ratio, photosynthetically active radiation (PAR) utilization, crop yield stability index, water use efficiency, and return on investment. We introduce a novel dual matrix Analytic Hierarchy Process (AHP) to evaluate their relative significance. An international panel of eighteen Agri-PV experts, encompassing academia, industry, and policy, provided pairwise comparisons of these indicators under two objectives: maximizing annual energy yield and sustaining crop output. The high consistency observed in expert responses allowed for the derivation of normalized weight vectors, which form the basis of two Weighted Influence Matrices. Analysis of Total Weighted Influence scores from these matrices reveal distinct priority sets: panel tilt, coverage ratio, and elevation are most influential for energy optimization, while PAR utilization, yield stability, and elevation are prioritized for crop productivity. This methodology translates qualitative expert knowledge into quantitative, actionable guidance, clearly delineating both synergies, such as the mutual benefit of increased elevation for energy and crop outcomes, and trade-offs, exemplified by the negative impact of high photovoltaic coverage on crop yield despite gains in energy output. By offering a transparent, expert-driven decision-support tool, this framework enables practitioners to customize Agri-PV system configurations according to local climatic, agronomic, and economic contexts. Ultimately, this approach advances the optimization of the food energy nexus and supports integrated sustainability outcomes in Agri-PV deployment. Full article

To circumvent the computational bottlenecks associated with the intermediate steps (e.g., least squares fitting) in conventional sine wave similarity principles and directly acquire the energy metrics required for stabilized sinusoidal waveform characterization, this study leverages time domain probability distribution theory. From a complementary advantage perspective, a novel transformer inrush current identification criterion is developed using the Wasserstein distance metric. The methodology employs feature discretization to extract target/template signals, transforming them into state vectors for sample labelling. By quantifying inter-signal energy distribution disparities through this framework, it achieves a precise waveform similarity assessment in sinusoidal regimes. The theoretical analysis and simulations demonstrate that the approach eliminates frequency domain computations while maintaining implementation simplicity. Compared with conventional sine wave similarity methods, the solution streamlines protection logic and significantly enhances practical applicability with accelerated response times. Furthermore, tests conducted on field-recorded circuit breaker closing waveforms using MATLAB R2022a confirm the effectiveness of the proposed method in improving transformer protection performance. Full article

The four-level nested neutral point clamped (4L-NNPC) inverter has recently become a promising solution for renewable energy generation, e.g., wind and photovoltaic power. The NNPC inverter can stabilize the flying capacitor (FC) voltages of each bridge through redundant switch states (RSSs). This paper presents an improved three-layer sequential model predictive control (3LS-MPC) method for 4L-NNPCs. This method eliminates weighting factors and removes the switch states that generate high common-mode voltage (CMV). Before selecting the optimal vector, we disable certain switch states which affect the FC voltages, continuing to deviate from the desired value. Then, adopting a two-stage optimal vector selection method, we select the optimal sector based on six specific vectors and choose the optimal vector from the seven vectors in the optimal sector. The feasibility of this method was verified in Matlab/Simulink and the prototype. The experimental results show that compared with classical FCS-MPC, the proposed 3LS-MPC method reduces the common-mode voltage and has better harmonic quality and more stable FCs voltages. Full article

As a pivotal economic province in China, Jiangsu’s efforts in civil building energy conservation are critical to achieving the national “dual carbon” goals. This paper proposes a hybrid model that integrates wavelet transform, support vector regression (SVR), and extreme learning machine (ELM) to predict the civil building energy consumption of Jiangsu Province. Based on data from statistical yearbooks, the historical energy consumption of civil buildings is calculated. Through a grey relational analysis (GRA), the key factors influencing the civil building energy consumption are identified. The wavelet transform technique is then applied to decompose the energy consumption data into a trend component and a fluctuation component. The SVR model predicts the trend component, while the ELM model captures the fluctuation patterns. The final prediction results are generated by combining these two predictions. The results demonstrate that the hybrid model achieves superior performance with a Mean Absolute Percentage Error (MAPE) of merely 1.37%, outperforming both individual prediction methods and alternative hybrid approaches. Furthermore, we develop three prospective scenarios to analyze civil building energy consumption trends from 2023 to 2030. The analysis reveals that the observed patterns align with the Environmental Kuznets Curve (EKC). These findings provide valuable insights for provincial governments in future policy-making and energy planning. Full article

Conventional space vector pulse width modulation (CSVPWM) with the fixed switching frequency generates significant sideband harmonics in the three-phase voltage. Discrete random switching frequency SVPWM (DRSF-SVPWM) methods have been widely applied in motor control systems for the suppression of tone harmonic energy. To further reduce the amplitude of the high-frequency harmonic with a limited switching frequency variation range, this paper proposes a time-division subbands beta distribution random SVPWM (TSBDR-SVPWM) method. The overall frequency band of the switching frequency is equally divided into N subbands, and each fundamental cycle of the line voltage is segmented into 2*(N-1) equal time intervals. Additionally, within each time segment, the switching frequency is randomly selected from the corresponding subband and follows the optimal discrete beta distribution. The switching frequency harmonic energy in the line voltage spectrum spreads across multiple frequency subbands and discrete frequency components, thereby forming a more uniform power spectrum of the line voltage. Both simulation and experimental results validate that, compared with CSVPWM, the sideband harmonic amplitude is reduced by more than 8.5 dB across the entire range of speed and torque conditions in the TSBDR-SVPWM. Furthermore, with the same variation range of the switching frequency, the proposed method achieves the lowest switching frequency harmonic amplitude and flattest line voltage spectrum compared with several state-of-the-art random modulation methods. Full article

Modern energy storage systems for both power and transportation are highly related to lithium-ion batteries (LIBs). However, their safety depends on a potentially hazardous failure mode known as thermal runaway (TR). Predicting and classifying TR causes can widely enhance the safety of power and transportation systems. This paper presents an advanced machine learning method for forecasting and classifying the causes of TR. A generative model for synthetic data generation was used to handle class imbalance in the dataset. Hyperparameter optimization was conducted using Optuna for four classifiers: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), tabular network (TabNet), and Extreme Gradient Boosting (XGBoost). A three-fold cross-validation approach was used to guarantee a robust evaluation. An open-source database of LIB failure events is used for model training and testing. The XGBoost model outperforms the other models across all TR categories by achieving 100% accuracy and a high recall (1.00). Model results were interpreted using SHapley Additive exPlanations analysis to investigate the most significant factors in TR predictors. The findings show that important TR indicators include energy adjusted for heat and weight loss, heater power, average cell temperature upon activation, and heater duration. These findings guide the design of safer battery systems and preventive monitoring systems for real applications. They can help experts develop more efficient battery management systems, thereby improving the performance and longevity of battery-operated devices. By enhancing the predictive knowledge of temperature-driven failure mechanisms in LIBs, the study directly advances thermal analysis and energy storage safety domains. Full article