Search Results (42)

To address the challenge that traditional dam model materials are difficult to simultaneously meet the requirements of microstructural similarity, dynamic damage simulation, and environmental friendliness, a novel microparticle mortar simulated concrete was developed. This new material consists of cement, sand, gypsum, mineral oil, water, and baryte sand. Through systematic material mechanical tests, the effects of each component on the material’s strength, density, and elastic modulus were revealed, and the optimal mix ratio was determined. This enabled precise control of low elastic modulus and had a high density, while the material is environmentally friendly, non-toxic, and compatible with direct contact with natural water. Its mechanical properties are highly similar to those of the prototype concrete. Based on a 1:70 geometric scale, a shaking table model test of the concrete gravity dam-reservoir system was conducted. The dynamic response and damage evolution under empty and full reservoir conditions were compared and analyzed. The study shows that this material can accurately simulate the stress-strain relationship and failure mode of prototype concrete. Under the full reservoir condition, the dam’s fundamental frequency showed only a 2.72% deviation from the numerical simulation, and as the seismic excitation amplitude increased, the changes in the fundamental frequency effectively reflected the accumulation of damage. Under the design seismic motion, the measured accelerations and stress responses for both empty and full reservoir conditions were in good agreement with numerical calculations. Under overload conditions, the acceleration amplification factor at the dam crest decreased with damage accumulation, and the dam neck was identified as the seismic weak zone. As the peak ground acceleration (PGA) increased from 0.15 g to 0.70 g, the fundamental frequency changes effectively reflected the damage accumulation process in the dam, while the hydrodynamic pressure at the dam heel showed a linear increase (457% increase). The experimentally measured hydrodynamic pressure distribution was between the rigid dam and elastic dam hydrodynamic pressures, reflecting the real fluid-structure interaction effect. This study provides a reliable material solution and data support for dam seismic physical model testing. Full article

In photovoltaic (PV) power generation, the intermittency and uncertainty caused by meteorological factors pose challenges to grid operations. Accurate PV power prediction is crucial for optimizing power dispatching and balancing supply and demand. This paper proposes a PV power prediction model based on Density Peak Clustering Algorithm (DPCA)–Crested Porcupine Optimizer (CPO)–Random Forest (RF)–Gated Recurrent Unit (GRU)–Kolmogorov–Arnold Network (KAN). First, the DPCA is used to accurately classify weather conditions according to meteorological data such as solar radiation, temperature, and humidity. Then, the CPO algorithm is established to optimize the factor screening characteristic variables of the RF. Subsequently, a hybrid GRU model with a KAN layer is introduced for short-term PV power prediction. The Shapley Additive Explanation (SHAP) method values evaluating feature importance and the impact of causal features. Compared with other contrast models, the DPCA-CPO-RF-KAN-GRU model demonstrates better error reduction capabilities under three weather types, with an average fitting accuracy R² reaching 97%. SHAP analysis indicates that the combined average SHAP value of total solar radiation and direct solar radiation contributes more than 70%. Finally, the Kernel Density Estimation (KDE) is utilized to verify that the KAN-GRU model has high robustness in interval prediction, providing strong technical support for ensuring the stability of the power grid and precise decision-making in the electricity market. Full article

Rolling element bearing fault diagnosis (BFD) is fundamental to Predictive Maintenance (PdM) strategies for rotating machinery, as early anomaly detection prevents catastrophic failures, reduces unplanned downtime, and optimizes operational costs. This study introduces an interpretable Deep Learning (DL) framework that rigorously compares the performance of an Artificial Neural Network–Multilayer Perceptron (ANN-MLP), a one-dimensional Convolutional Neural Network (1D-CNN), and a ResNet-1D architecture for classifying seven bearing health states using a compact vector of 15 statistical features extracted from vibration signals. Both baseline models (ANN-MLP and 1D-CNN) failed to detect the critical Abrasive Particles fault (F1 = 0.0000). In contrast, the ResNet-1D architecture achieved statistically superior diagnostic performance, successfully resolving the most challenging class with a perfect F1-score of 1.0000 and an overall macro F1-score of 0.9913. This superiority was confirmed by a paired t-test on 100 bootstrap samples, establishing a highly significant difference in performance against the 1D-CNN ($t=592.702$, $p=0.00000$). To boost transparency and trust, the SHapley Additive exPlanations (SHAP) method was applied to interpret the ResNet-1D’s decisions. The SHAP analysis revealed that the Crest Factor from Sensor 1 (Crest_1) exerts the strongest influence on the critical Abrasive Particles fault predictions, physically validating the model’s intelligence against established domain knowledge of impulsive wear events. These findings support transparent, highly reliable, and evidence-based decision-making in industrial PdM applications within Industry 4.0 environments. Full article

Accurate prediction of photovoltaic power generation is a pivotal factor for enhancing the operational efficiency of electrical grids and facilitating the stable integration of solar energy. This study introduces a holistic forecasting framework that achieves seamless integration of dual-stage decomposition, deep learning architectures, and an advanced metaheuristic algorithm, thereby significantly improving the prediction precision of PV power generation. Initially, the raw PV power sequences are processed using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) to capture multi-scale temporal characteristics. The derived components are subsequently categorized into high-, medium-, and low-frequency groups through K-means clustering to manage complexity. To address residual noise and non-stationary behaviors, the high-frequency constituents are further decomposed via Variational Mode Decomposition (VMD). The refined subsequences are then input into a TCN_BiGRU_Attention network, which employs temporal convolutional operations for hierarchical feature extraction, bidirectional gated recurrent units to model temporal correlations, and a multi-head attention mechanism to prioritize influential time steps. For hyperparameter optimization of the forecasting model, an Improved Crested Porcupine Optimizer (ICPO) is developed, integrating Chebyshev chaotic mapping for initialization, a triangular wandering strategy for local search, and Lévy flight to strengthen global exploration and accelerate convergence. Validation on real-world PV datasets indicates that the proposed model attains a Mean Squared Error (MSE) of 0.3456, Root Mean Squared Error (RMSE) of 0.5879, Mean Absolute Error (MAE) of 0.3396, and a determination coefficient (R²) of 99.59%, surpassing all benchmark models by a significant margin. This research empirically demonstrates the efficacy of the dual decomposition methodology coupled with the optimized hybrid deep learning network in elevating both the accuracy and stability of predictions, thereby offering a reliable and stable forecasting framework for PV power systems. Full article

The complex nonlinear interplay between preparation parameters and macroscopic properties poses challenges for predicting the performance of anti-aging rubber asphalt. To address this, two bio-inspired algorithms—Crested Porcupine Optimizer (CPO) and Dung Beetle Optimizer (DBO)—were integrated with a backpropagation (BP) neural network, forming CPO-BP and DBO-BP hybrid models for multi-target prediction. The CPO-BP model demonstrated superior predictive accuracy, significantly outperforming both the standard BP and DBO-BP models, which is attributed to its adaptive global-local optimization mechanism. Shapley additive explanations (SHAP) analysis identified mixing temperature as the most influential factor, with elevated values enhancing rutting resistance but compromising ductility, while moderate temperatures improved aging resistance. Feature interactions indicated synergistic effects between mixing temperature and shear time, and a strong coupling effect between rubber content and temperature on low-temperature performance. Parameter optimization via Non-dominated Sorting Genetic Algorithm II (NSGA-II) further enhanced high–low temperature stability and aging resistance, confirmed by Atomic Force Microscopy (AFM)-based microstructural characterization. The proposed approach provides a robust framework that integrates data-driven prediction and multi-objective optimization for the rational design of high-performance anti-aging rubber asphalt. Full article

Due to the susceptibility of LiDAR echo signals to various noise interferences, which severely affect their detection quality and accuracy, this paper proposes a joint denoising method combining Variational Mode Decomposition (VMD), Crested Porcupine Optimizer (CPO), and Improved Wavelet Thresholding (IWT), named VMD-CPO-IWT. The parameter-adaptive CPO optimization algorithm is employed to optimize the key parameters of VMD (decomposition level k, quadratic penalty factor α), effectively solving the challenge of determining the optimal parameter combination in the VMD algorithm. Based on the probability density function (PDF), the Wasserstein distance is used as a similarity metric to screen intrinsic mode functions. Subsequently, the IWT is applied to obtain the optimal wavelet threshold, which compensates for the shortcomings of traditional threshold methods while further suppressing both low-frequency and high-frequency noise in the signal, ultimately yielding the denoising result. Experimental results demonstrate that for both simulated signals and actual LiDAR echo signals, the VMD-CPO-IWT method outperforms Neighcoeff-db4 wavelet denoising (WT-db4), EMD combined with detrended fluctuation analysis denoising (EMD-DFA), and VMD combined with Whale Optimization Algorithm (VMD-WOA) in terms of improving the Signal-to-Noise Ratio (SNR) and reducing the Root Mean Square Error (RMSE). For the actual LiDAR echo signal at a detection range of 25 m, the SNR is improved by 13.64 dB, and the RMSE is reduced by 62.6%. This method provides an efficient and practical solution for denoising LiDAR echo signals. Full article

The increasing reliance on renewable energy sources, such as photovoltaic (PV) systems, is pivotal for achieving sustainable development and addressing global energy challenges. However, short-term power forecasting for distributed PV systems often faces accuracy limitations, hindering their efficient grid integration. To address this, a novel hybrid prediction model is proposed, combining multivariate variational mode decomposition (MVMD) with a gated recurrent unit (GRU) network, an attention mechanism (ATT), and an enhanced vector weighted average algorithm (cINFO). The MVMD first decomposes historical data to reduce volatility. The INFO algorithm is then improved by integrating the crested porcupine optimizer (CPO), forming the cINFO algorithm to optimize GRU-ATT hyperparameters. An attention mechanism is incorporated to accentuate key influencing factors. The model was evaluated using the DKASC Alice Springs dataset. Results demonstrate high predictive accuracy, with mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) values of 0.0249, 0.0693, and 99.79%, respectively, under sunny conditions, significantly outperforming benchmark models. This confirms the model’s feasibility and superiority for short-term PV power forecasting. Full article

Spatiotemporal modeling and prediction of road network traffic flow are essential components of intelligent transport systems (ITS), aimed at effectively enhancing road service levels. Sustainable and reliable traffic management in smart cities requires the use of modern algorithms based on a comprehensive analysis of a significant number of dynamically changing factors. This paper designs a Crested Porcupine Optimizer (CPO)-CNN-LSTM-Attention time series prediction model, which integrates machine learning and deep learning to improve the efficiency of traffic flow forecasting in the condition of urban roads. Based on historical traffic patterns observed on Paris’s roads, a traffic flow prediction model was formulated and subsequently verified for effectiveness. The CPO algorithm combined with multiple neural network models performed well in predicting traffic flow, surpassing other models with a root-mean-square error (RMSE) of 17.35–19.83, a mean absolute error (MAE) of 13.98–14.04, and a mean absolute percentage error (MAPE) of 5.97–6.62%. Therefore, the model proposed in this paper can predict traffic flow more accurately, providing a solution for enhancing urban traffic management in intelligent transportation systems, and thus offering a research direction for the future development of smart city construction. Full article

With the transition of the energy structure and the continuous development of smart grids, short-term user-side load forecasting plays a key role in fine power dispatch and efficient system operation. However, existing parameter optimization methods lack multi-dimensional and physically interpretable fitness evaluation. They also fail to fully exploit frequency-domain features of decomposed modal components. These limitations reduce model accuracy and robustness in complex scenarios. To address this issue, this paper proposes a short-term user-side load forecasting method based on the MCPO-VMD-FDFE decomposition-enhanced framework. Firstly, a multi-dimensional fitness function is designed using indicators such as modal energy entropy and energy concentration. The Crested Porcupine Optimizer with Multidimensional Fitness Function (MCPO) algorithm is applied in VMD (Variational Mode Decomposition) to optimize the number of decomposition modes (K) and the penalty factor (α), thereby improving decomposition quality. Secondly, each IMF component obtained from VMD is analyzed by FFT. Key frequency components are selectively enhanced based on adaptive thresholds and weight coefficients to improve feature expression. Finally, a multi-scale convolution module is added to the PatchTST model to enhance its ability to capture local and multi-scale temporal features. The enhanced IMF components are fed into the improved model for prediction, and the final output is obtained by aggregating the results of all components. Experimental results show that the proposed method achieves the best performance on user-side load datasets for weekdays, Saturdays, and Sundays. The RMSE is reduced by 45.65% overall, confirming the effectiveness of the proposed approach in short-term user-side load forecasting tasks. Full article

A bioresorbable cannulated bone screw was developed using PLA/PCL-based composites reinforced with hydroxyapatite (HA) and titanium dioxide (TiO₂), two additives previously reported to enhance mechanical compliance, biocompatibility, and molding feasibility in biodegradable polymer systems. The design incorporated a crest-trimmed thread and a strategically positioned gate in the thin-wall zone opposite the hexagonal socket to preserve torque-transmitting geometry during micromolding. To investigate shrinkage behavior, a Taguchi orthogonal array was employed to systematically vary micromolding parameters, generating a structured dataset for training a back-propagation neural network (BPNN). Analysis of variance (ANOVA) identified melt temperature as the most influential factor affecting shrinkage quality, defined by a combination of shrinkage rate and dimensional variation. A hybrid AI framework integrating the BPNN with genetic algorithms and particle swarm optimization (GA–PSO) was applied to predict the optimal shrinkage conditions. This is the first use of BPNN–GA–PSO for cannulated bone screw molding, with the shrinkage rate as a targeted output. The AI-predicted solution, interpolated within the Taguchi design space, achieved improved shrinkage quality over all nine experimental groups. Beyond the specific PLA/PCL-based systems studied, the modeling framework—which combines geometry-specific gate design and normalized shrinkage prediction—offers broader applicability to other bioresorbable polymers and hollow implant geometries requiring high-dimensional fidelity. This study integrates composite formulation, geometric design, and data-driven modeling to advance the precision micromolding of biodegradable orthopedic devices. Full article

The reinforcement effect of single-reinforced soil support under external loading has limitations, and it is difficult for it to meet engineering stability requirements. Therefore, the stability analysis of slopes supported by a combination of anti-slip piles and reinforced soil under the seismic loading effect needs an in-depth study. Based on the upper-bound theorem of limit analysis and the strength-reduction technique, this study establishes an upper-bound stability model for high–steep slopes that simultaneously considers seismic action and the combined reinforcement of anti-slide piles and reinforced soil. A closed-form safety factor is derived. The theoretical results are validated against published data, demonstrating satisfactory agreement. Finally, the MATLAB R2022a sequential quadratic programming method is used to optimize the objective function, and the Optum G2 2023 software is employed to analyze the factors influencing slope stability due to the interaction between anti-slide piles and geogrids. The research indicates that the horizontal seismic acceleration coefficient k_h exhibits a significant negative correlation with the safety factor F_s. Increases in the tensile strength T of the reinforcing materials, the number of layers n, and the length l all significantly improve the safety factor F_s of the reinforced-soil slope. Additionally, as l increases, the potential slip plane of the slope shifts backward. For slope support systems combining anti-slide piles and reinforced soil, when the length of the geogrid is the same, adding anti-slide piles can significantly improve the slope’s safety factor. As anti-slide piles move from the toe to the crest of the slope, the safety factor first decreases and then increases, indicating that the optimal reinforcement position for anti-slide piles should be in the middle to lower part of the slope body. The length of the anti-slip piles should exceed the lowest layer of the geogrid to more effectively utilize the blocking effect of the pile ends on the slip surface. The research findings can provide a theoretical basis and practical guidance for parameter optimization in high–steep slope support engineering. Full article

Coastal areas are increasingly vulnerable to erosion, a process that can lead to severe consequences such as flooding and land loss. This study investigates strategies for preventing and mitigating coastal erosion, with a particular focus on nature-based solutions, notably artificial sand nourishment. Artificial nourishment has proven to be an effective method for erosion control. However, its success depends on factors such as the placement location, sediment volume, and frequency of operations. To optimize these interventions, simulations were conducted using both a numerical model (CS-Model) and a physical flume model, based on the same cross-section beach/dune profile, to compare cross-shore nourishment performance across different scenarios. The numerical modeling approach is presented first, including a description of the reference prototype-scale scenario. This is followed by an overview of the physical modeling, detailing the experimental 2D cross-section flume setup and tested scenarios. These scenarios simulate nourishment interventions with variations in beach profile, aiming to assess the influence of water level, berm width, bar volume, and bar geometry. The results from both numerical and physical simulations are presented, focusing on the cross-shore morphological response of the beach profile under wave action, particularly the effects on profile shape, water level, bar volume, and the position and depth of the bar crest. The main conclusion highlights that a wider initial berm leads to greater wave energy dissipation, thereby contributing to the mitigation of dune erosion. Full article

This study investigates the structural and energetic properties of hydrogen-bonded complexes between indole and a range of aliphatic, cyclic, and aromatic ketones using a combined vibrational spectroscopic and quantum-chemical approach. FTIR measurements in CCl₄ revealed redshifts in the N-H stretching vibration of indole upon complexation, with formation constants (K_a) ranging from 0.3 to 6.6 M⁻¹. Cyclohexanone displayed the strongest binding, while benzophenone exhibited the weakest interaction. Quantum-chemical calculations, employing CREST and MMFF94 conformational sampling, along with M06-2X/6-311++G(d,p) optimizations, confirmed the formation of hydrogen bonds and additional weak interactions that govern the stability of the complex. QTAIM analysis revealed moderate closed-shell hydrogen bonds with electron densities at the bond critical points (ρ) ranging from 0.010 to 0.019 a.u. and potential energy densities (V) from −18.4 to −36.4 kJ mol⁻¹. Multivariate regression analysis established strong correlations (R² = 0.928 and 0.957) between experimental binding constants and theoretical descriptors, including binding energy, NBO charge on oxygen atom, ionization potential, and electrophilicity index, highlighting the interplay between geometric, electronic, and global reactivity factors. This comprehensive study underlines the predictive power of spectroscopic and quantum descriptors for assessing hydrogen bonding in biologically relevant systems. Full article

The battery management system (BMS) is crucial for the efficient operation of batteries, with state of health (SOH) prediction being one of its core functions. Accurate SOH prediction can optimize battery management, enhance utilization and range, and extend battery lifespan. This study proposes an SOH estimation model for lithium-ion batteries that integrates the Crested Porcupine Optimizer (CPO) for parameter optimization, Extreme Learning Machine (ELM) for prediction, and Adaptive Bandwidth Kernel Function Density Estimation (ABKDE) for uncertainty quantification, aiming to enhance the long-term reliability and sustainability of energy storage systems. Health factors (HFs) are extracted by analyzing the charging voltage curves and capacity increment curves of lithium-ion batteries, and their correlation with battery capacity is validated using Pearson and Spearman correlation coefficients. The ELM model is optimized using the CPO algorithm to fine-tune input weights (IWs) and biases (Bs), thereby enhancing prediction performance. Additionally, ABKDE-based probability density estimation is introduced to construct confidence intervals for uncertainty quantification, further improving prediction accuracy and stability. Experiments using the NASA battery aging dataset validate the proposed model. Comparative analysis with different models demonstrates that the CPO-ELM-ABKDE model achieves SOH estimation with a mean absolute error (MAE) and root-mean-square error (RMSE) within 0.65% and 1.08%, respectively, significantly outperforming other approaches. Full article

In actual operation, the output power of distributed marine photovoltaic monitoring faces challenges from wind, waves, and other dynamic motion factors. To address these challenges, this paper proposes a novel maximum power point inference method for distributed marine photovoltaic monitoring. First, a digital fusion model has been constructed to obtain a comprehensive dataset of the distributed marine photovoltaic monitoring system. Second, Multilayer Convolutional Neural Networks (CNN) are constructed to extract the local high-frequency motion characteristics, Squeeze and Excitation Attention (SE-Attention) is employed to capture the global low-frequency motion characteristics, and Long Short-Term Memory (LSTM) is utilized to perform temporal modeling of the motion characteristics. Subsequently, the Crested Porcupine Optimizer (CPO) algorithm is used to achieve high-precision recognition of the maximum power point in distributed marine photovoltaic monitoring. Finally, the effectiveness of the method is verified through experiments and simulations. The results indicate that the maximum power point of distributed marine photovoltaic monitoring exhibits multi-spectral motion characteristics, with the highest frequency at 335.2 Hz and the lowest frequency at 12.9 Hz. The proposed method enables efficient inference of the maximum power point for distributed marine photovoltaic monitoring under motion conditions, with an accuracy of 98.63%. Full article