Search Results (207)

This paper presents the flow field reconstruction and prediction of powder fuel transport systems based on representative feature extraction from scattering images using deep learning techniques. A laboratory-built powder fuel supply system was used to conduct scattering spectroscopy experiments on boron-based fuel under various flow rate conditions. Based on the acquired scattering images, a prediction and reconstruction method was developed using a deep network framework composed of a Stacked Autoencoder (SAE), a Backpropagation Neural Network (BP), and a Long Short-Term Memory (LSTM) model. The proposed framework enables accurate classification and prediction of the dynamic evolution of flow structures based on learned representations from scattering images. Experimental results show that the feature vectors extracted by the SAE form clearly separable clusters in the latent space, leading to high classification accuracy under varying flow conditions. In the prediction task, the feature vectors predicted by the LSTM exhibit strong agreement with ground truth, with average mean square error, mean absolute error, and r-square values of 0.0027, 0.0398, and 0.9897, respectively. Furthermore, the reconstructed images offer a visual representation of the changing flow field, validating the model’s effectiveness in structure-level recovery. These results suggest that the proposed method provides reliable support for future real-time prediction of powder fuel mass flow rates based on optical sensing and imaging techniques. Full article

As hydraulic buildings are constantly subjected to complex interactions with water, particularly variations in hydrostatic pressure and temperature, deformation structural behavior is inherently sensitive to environmental fluctuations. Monitoring dam deformation with high accuracy and robustness is critical for ensuring the long-term safety and operational integrity of hydraulic structures. However, traditional physics-based models often struggle to fully capture the nonlinear and time-dependent deformation responses in hydraulic structures driven by such coupled environmental influences. To address these limitations, this study presents an advanced deep learning (DL)-based deformation monitoring for hydraulic buildings using long-sequence monitoring data of hydrostatic pressure and temperature. Specifically, the Bidirectional Stacked Long Short-Term Memory (Bi-Stacked-LSTM) is proposed to capture intricate temporal dependencies and directional dynamics within long-sequence hydrostatic and thermal time series. Then, hyperparameters, including the number of LSTM layers, neuron counts in each layer, dropout rate, and time steps, are efficiently fine-tuned using the Gaussian Process-based surrogate model optimization (GP-SMO) algorithm. Multiple deformation monitoring points from hydraulic buildings and a variety of advanced machine-learning methods are utilized for analysis. Experimental results indicate that the developed GP-SMO-optimized Bi-Stacked-LSTM dam deformation monitoring model shows better comprehensive representation capability of both past and future deformation-related sequences compared with benchmark methods. By approximating the behavior of the target function, the GP-SMO algorithms allow for the optimization of critical parameters in DL models while minimizing the high computational costs typically associated with direct evaluations. This novel DL-based approach significantly improves the extraction of deformation-relevant features from long-term monitoring data, enabling more accurate modeling of temporal dynamics. As a result, the developed method offers a promising new tool for safety monitoring and intelligent management of large-scale hydraulic structures. Full article

The transformation of traditional energy systems into smart energy systems has ushered in an era of efficiency, sustainability and technological growth. In this paper, we propose a new definition for “Quality of Energy Service” that focuses on ensuring optimal power-supply quality, encompassing factors such as availability, speed (i.e., the time to restore or adjust supply following interruptions or load changes) and reliability of supply. We explore the integration of advanced algorithms specifically tailored to enhance the Quality of Energy Services. By concentrating on key aspects—reliability, availability and operational efficiency—the study reviews how various algorithmic approaches, from machine learning models to classical optimisation techniques, can significantly improve power grid management. These algorithms are evaluated for their potential to optimise load distribution, predict system failures and manage real-time adjustments in power supply, thereby ensuring higher service quality and grid stability. The findings aim to provide actionable insights for policymakers, engineers and industry stakeholders seeking to advance smart grid technologies and meet global energy standards. Furthermore, we present a case study to demonstrate how these models can be integrated to optimise grid management, forecast energy demand and enhance operational efficiency. We employ multiple machine learning models—including Random Forest, XGBoost version 1.6.1 and Long Short-Term Memory (LSTM) networks—to predict future energy demand. These models are then combined within an ensemble learning framework to improve both the accuracy and robustness of the forecasts. Our ensemble framework not only predicts energy consumption but also optimises battery storage utilisation, ensuring continuous energy availability and reducing reliance on external energy sources. The proposed stacking ensemble achieved a forecasting accuracy of 99.06%, with a Mean Absolute Percentage Error (MAPE) of 0.9364% and a Coefficient of Determination (R²) of 0.998345, highlighting its superior performance compared to each individual base model. Full article

Accurate building energy consumption prediction is essential for efficient energy management and energy optimization. This study utilizes bidirectional long short-term memory (BiLSTM) to automatically extract deep time series features. The nonlinear fitting and high-precision prediction capabilities of Random Forest (RF) and XGBoost models are then utilized to develop a BiLSTM-RF-XGBoost stacked hybrid model. To enhance model generalization and reduce overfitting, a Bayesian algorithm with an early stopping mechanism is utilized to fine-tune hyperparameters, and strict K-fold time series cross-validation (TSCV) is implemented for performance evaluation. The hybrid model achieves a high TSCV average R² value of 0.989 during cross-validation. When evaluated on an independent test set, it yields a mean square error (MSE) of 0.00003, a root mean square error (RMSE) of 0.00548, a mean absolute error (MAE) of 0.00130, and a mean absolute percentage error (MAPE) of 0.26%. These values are significantly lower than those of comparison models, indicating a significant improvement in predictive performance. The study offers insights into the internal decision-making of the model through SHAP (SHapley Additive exPlanations) feature significance analysis, revealing the key roles of temperature and power lag features, and validating that the stacked model effectively utilizes the outputs of base models as meta-features. This study makes contributions by proposing a novel hybrid model trained with Bayesian optimization, analyzing the influence of various feature factors, and providing innovative technological solutions for building energy consumption prediction. It also provides theoretical value and guidance for low-carbon building energy management and application. Full article

Sodium batteries have emerged as a competitive energy storage candidate due to their low cost and abundant resources. The accurate estimation of the state of health (SOH) of sodium batteries is essential for their practical utilization. However, limited cycling data and rapid capacity decay pose significant challenges for SOH prediction. This study proposes a data-driven approach for SOH estimation in sodium batteries. By analyzing first-cycle data, the method determines battery health factor ranges and extracts comprehensive features from limited charging data segments. A predictive model is then established using deep learning techniques, specifically a stacked, bidirectional, long short-term memory (SB-LSTM) network. Unlike conventional methodologies relying on filtering or curve smoothing, the proposed approach demonstrates exceptional robustness, particularly at high discharge rates of up to 5C. Moreover, it applies to a wider range of current rates and consumes fewer computational resources. The method’s effectiveness is validated on three different battery sets, achieving high accuracy with an average absolute error in SOH estimation below 0.86% and a root mean square error under 1.07%. These results highlight the potential of this data-driven approach for reliable SOH estimation in sodium batteries, contributing to their practical implementation in energy storage systems. Full article

To improve the robustness of intrusion detection systems constructed using deep learning models, a method based on an auxiliary adversarial training WGAN (AuxAtWGAN) is proposed from the defender’s perspective. First, one-dimensional traffic data are downscaled and processed into two-dimensional image data via a stacked autoencoder (SAE), and mixed adversarial samples are generated using the fast gradient sign method (FGSM), Projected Gradient Descent (PGD) and Carlini and Wagner (C&W) adversarial attacks. Second, the improved WGAN with an integrated perceptual network module is trained with mixed training samples composed of mixed adversarial samples and normal samples. Finally, the adversary-trained AuxAtWGAN model is attached to the original model for adversary sample detection, and the detected adversary samples are removed and input into the original model to improve the robustness of the original model. The average attack success rate of the original convolutional neural network (CNN) model against multiple adversarial samples is 75.17%, and after using AuxAtWGAN, the average attack success rate of the adversarial attacks decreases to 27.56%; moreover, the detection accuracy of the original CNN model against normal samples is still 93.57%. The experiment proves that AuxAtWGAN improves the robustness of the original model. In addition, validation experiments are conducted by attaching the AuxAtWGAN model to the Long Short-Term Memory Network (LSTM) and Residual Network34 (ResNet) models, which prove that the proposed method has high generalization performance. Full article

The increasing sophistication of web-based services has intensified the risk of zero-day attacks, exposing critical vulnerabilities in user information security. Traditional detection systems often rely on labeled attack data and struggle to identify novel threats without prior knowledge. This paper introduces a novel one-class ensemble method for detecting zero-day web attacks, combining the strengths of Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and stacked autoencoders through latent representation concatenation and compression. Additionally, a structured tokenization strategy based on character-level analysis is employed to enhance input consistency and reduce feature dimensionality. The proposed method was evaluated using the CSIC 2012 dataset, achieving 97.58% accuracy, 97.52% recall, 99.76% specificity, and 99.99% precision, with a false positive rate of just 0.2%. Compared to conventional ensemble techniques like majority voting, our approach demonstrates superior anomaly detection performance by fusing diverse feature representations at the latent level rather than the output level. These results highlight the model’s effectiveness in accurately detecting unknown web attacks with low false positives, addressing major limitations of existing detection frameworks. Full article

The capacity of Lithium-ion batteries degrades over the time, making accurate prediction of their Remaining Useful Life (RUL) crucial for maintenance and product lifespan design. However, diverse aging mechanisms, changing working conditions and cell-to-cell variation lead to the inhomogeneous cell lifespan and complicated life prediction. In this work, a data-driven algorithm based on stacked Long Short Term Memory (LSTM) encoder–decoders is proposed for RUL prediction. The encoder and upstream decoder form an autoencoder framework for feature extraction. The encoder and the downstream decoder form the encoder–decoder framework for RUL prediction. To enhance generalization during training, the Maximum Mean Discrepancy (MMD) loss is included in the autoencoder framework. The similarity of aging patterns is analyzed during splitting source and target datasets through k-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The Euclidean metric with accumulated Equivalent Cycle Number (ECN) sequence during aging shows better performance for similarity-based data splitting than the Dynamic Time Wrapping (DTW) distance metric based on capacity fading trajectory. The experimental results indicate that the proposed algorithm can provide accurate RUL prediction using 5% fading data and shows good generalization with Coefficient of Determination (R²) score of 0.98. Full article

Due to the rapid proliferation of social media and online reviews, the accurate identification and classification of controversial texts has emerged as a significant challenge in the field of natural language processing. However, traditional text-classification methodologies frequently encounter critical limitations, such as feature sensitivity and inadequate generalization capabilities. This results in a notably suboptimal performance when confronted with diverse controversial content. To address these substantial limitations, this paper proposes a novel controversial text-detection framework based on stacked ensemble learning to enhance the accuracy and robustness of text classification. Firstly, considering the multidimensional complexity of textual features, we integrate comprehensive feature engineering, i.e., encompassing word frequency, statistical metrics, sentiment analysis, and comment tree structure features, as well as advanced feature selection methodologies, particularly lassonet, i.e., a neural network with feature sparsity, to effectively address dimensionality challenges while enhancing model interpretability and computational efficiency. Secondly, we design a two-tier stacked ensemble architecture, which not only combines the strengths of multiple machine learning algorithms, e.g., gradient-boosted decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGBoost), with deep learning models, e.g., gated recurrent unit (GRU) and long short-term memory (LSTM), but also implements the support vector machine (SVM) for efficient meta-learning. Furthermore, we systematically compare three hyperparameter optimization algorithms, including the sparrow search algorithm (SSA), particle swarm optimization (PSO), and Bayesian optimization (BO). The experimental results demonstrate that the SSA exhibits a superior performance in exploring high-dimensional parameter spaces. Extensive experimentation across diverse topics and domains also confirms that our proposed methodology significantly outperforms the state-of-the-art approaches. Full article

To address the limitations of the conventional low-strain reflected wave method for pile foundation testing, this study proposes an intelligent multi-point vibration acquisition testing model based on machine learning to evaluate the integrity of in-service, high-cap pile foundations. The model’s performance was assessed using statistical error metrics, including the correlation coefficient R², mean absolute error (MAE), and variance accounted for (VAF), with comparative evaluations conducted across different model frameworks. Results show that both the convolutional neural network (CNN) and the long short-term memory neural network (LSTM) consistently achieved high accuracy in identifying the location of the first reflection point in the pile shaft, with R² values greater than 0.98, MAE below 0.41 (m), and VAF greater than 98%. These findings demonstrate the model’s strong predictive capability, test stability, and practical utility in supporting operator decision-making. Among the evaluated models, CNN is recommended for analyzing the integrity of in-service pile foundation based on the multi-point vibration pickup signals and multi-sensor fusion signal preprocessed by the time series stacking method. Full article

This work explores the classification of driving behaviors using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks (ConvLSTM). Sensor data are collected from a smartphone application and undergo a preprocessing pipeline, including data normalization, labeling, and feature extraction, to enhance the model’s performance. By capturing temporal and spatial dependencies within driving patterns, the proposed ConvLSTM model effectively differentiates between normal and aggressive driving behaviors. The model is trained and evaluated against traditional stacked LSTM and Bidirectional LSTM (BiLSTM) architectures, demonstrating superior accuracy and robustness. Experimental results confirm that the preprocessing techniques improve classification performance, ensuring high reliability in driving behavior recognition. The novelty of this work lies in a simple data preprocessing methodology combined with the specific application scenario. By enhancing data quality before feeding it into the AI model, we improve classification accuracy and robustness. The proposed framework not only optimizes model performance but also demonstrates practical feasibility, making it a strong candidate for real-world deployment. Full article

To address the performance degradation in existing PM_2.5 prediction models caused by excessive complexity, poor spatiotemporal efficiency, and suboptimal parameter optimization, we employ stacking ensemble learning for feature weighting analysis and integrate the ant colony optimization (ACO) algorithm for model parameter optimization. Combining meteorological and collaborative pollutant data, a model (namely the stacking-ACO-LSTM model) with a much shorter consuming time than that of only long short-term memory (LSTM) networks suitable for PM_2.5 concentration prediction is established. It can effectively filter out feature variables with higher weights, thereby reducing the predictive power of the model. The prediction of hourly PM_2.5 concentration of the model is trained and tested using real-time monitoring data in Nanchang City from 2017 to 2019. The results show that the established stacking-ACO-LSTM model has high accuracy in predicting PM_2.5 concentration, and compared to the same model without considering time and space efficiency and defective parameter optimization, the mean square error (MSE) decreases by about 99.88%, and the coefficient of determination (R²) increases by about 2.39%. This study provides a new idea for predicting PM_2.5 concentration in cities. Full article

This paper presents a new deep learning model called the stranded Long Short-Term Memory. The model utilizes arbitrary LSTM recurrent neural networks of variable cell depths organized in classes. The proposed model can adapt to classifying emergencies at different intervals or provide measurement predictions using class-annotated or time-shifted series of sensory data inputs. In order to outperform the ordinary LSTM model’s classifications or forecasts by minimizing losses, stranded LSTM maintains three different weight-based strategies that can be arbitrarily selected prior to model training, as follows: least loss, weighted least loss, and fuzzy least loss in the LSTM model selection and inference process. The model has been tested against LSTM models for forecasting and classification, using a time series of temperature and humidity measurements taken from meteorological stations and class-annotated temperature measurements from Industrial compressors accordingly. From the experimental classification results, the stranded LSTM model outperformed 0.9–2.3% of the LSTM models carrying dual-stacked LSTM cells in terms of accuracy. Regarding the forecasting experimental results, the forecast aggregation weighted and fuzzy least loss strategies performed 5–7% better, with less loss, using the selected LSTM model strands supported by the model’s least loss strategy. Full article

Atmospheric water vapor plays a significant impact on the climate system, radiative transfer models, and optoelectronic engineering applications. Fast and accurate calculation of its optical depth and transmittance is a crucial step to studying the radiation characteristics of water vapor. Although the traditional physics-based, line-by-line radiative transfer model (LBLRTM) meets the accuracy requirements, it is too slow and computationally expensive for practical applications. In this study, to facilitate the accuracy and efficiency requirements of atmospheric water vapor optical depth and transmittance calculation, we propose a Stack LSTM-AT model that combines a double-layer Long Short-Term Memory (LSTM) network and a self-attention mechanism method, and different configurations of the hybrid model are extensively examined. The results show that, compared to the LBLRTM model, the Stack LSTM-AT model significantly improves computational efficiency while maintaining accuracy. Overall, the R-squared, mean absolute error (MAE), and root mean square error (RMSE) of optical depth is 0.9999945, 0.00568, and 0.02033, respectively, while the R-squared, MAE, and RMSE of atmospheric transmittance is 0.9999964, 5.5586 × 10⁻⁴, and 9.4 × 10⁻⁴, respectively. Moreover, the difference in optical depths and transmittance between the prediction results of the Stack LSTM-AT model and the calculation results of the LBLRTM are no greater than 0.3 and 0.008, respectively, across various pressures, temperatures, and water vapor amounts. The computation time for calculating the transmittance of a single spectrum (1–5000 cm⁻¹) is about 9.784 × 10⁻² s, with a spectrum resolution of 1 cm⁻¹, which is about 1000 times faster than that of LBLRTM. The proposed Stack LSTM-AT model could significantly enhance the efficiency and accuracy of atmospheric radiative transfer simulations, demonstrating its broad potential in real-time meteorological monitoring and atmospheric component inversion. This study may provide new insights and technical support for the study of radiative transfer, climate change, and atmospheric environmental monitoring. Full article

This study explores the efficacy of advanced machine learning models, including various Long Short-Term Memory (LSTM) architectures and traditional time series approaches, for forecasting cotton futures prices. This analysis is motivated by the importance of accurate price forecasting to aid U.S. cotton producers in hedging and marketing decisions, particularly in the Texas Gulf region. The models evaluated included ARIMA, basic feedforward neural networks, basic LSTM, bidirectional LSTM, stacked LSTM, CNN LSTM, and 2D convolutional LSTM models. The forecasts were generated for five-, ten-, and fifteen-day periods using historical data spanning 2009 to 2023. The results demonstrated that advanced LSTM architectures outperformed other models across all forecast horizons, particularly during periods of significant price volatility, due to their enhanced ability to capture complex temporal and spatial dependencies. The findings suggest that incorporating advanced LSTM architectures can significantly improve forecasting accuracy, providing a robust tool for producers and market analysts to better navigate price risks. Future research could explore integrating additional contextual variables to enhance model performance further. Full article