Search Results (264)

The growing demand for agile and reliable Unmanned Aerial Vehicles (UAVs) has spurred the advancement of advanced control strategies capable of ensuring stability and precision under nonlinear and uncertain flight conditions. This work addresses the challenge of accurately tracking UAV position by proposing a neural-network-based approach designed to replicate the behavior of classical control systems. A complete nonlinear model of the quadcopter was derived and linearized around a hovering point to design a traditional proportional derivative (PD) controller, which served as a baseline for training a nonlinear autoregressive exogenous (NARX) artificial neural network. The NARX model, selected for its feedback structure and ability to capture temporal dynamics, was trained to emulate the control signals of the PD controller under varied reference trajectories, including step, sinusoidal, and triangular inputs. The trained networks demonstrated performance comparable to the PD controller, particularly in the vertical axis, where the NARX model achieved a minimal Mean Squared Error (MSE) of $7.78\times {10}^{-5}$ and an $R^2$ value of 0.9852. These results confirm that the NARX neural network, trained via supervised learning to emulate a PD controller, can replicate and even improve classical control strategies in nonlinear scenarios, thereby enhancing robustness against dynamic changes and modeling uncertainties. This research contributes a scalable approach for integrating neural models into UAV control systems, offering a promising path toward adaptive and autonomous flight control architectures that maintain stability and accuracy in complex environments. Full article

Accurate precipitation forecasting remains a critical challenge due to the nonlinear and multifactorial nature of rainfall dynamics. This is particularly important in arid regions like Tamanghasset, where precipitation is the primary driver of agricultural viability and water resource management. This study evaluates the performance of several time series models for monthly rainfall prediction, including the autoregressive integrated moving average (ARIMA), Exponential Smoothing State Space Model (ETS), Seasonal and Trend decomposition using Loess with ETS (STL-ETS), Trigonometric Box–Cox transform with ARMA errors, Trend and Seasonal components (TBATS), and neural network autoregressive (NNAR) models. Historical monthly precipitation data from 1953 to 2020 were used to train and test the models, with lagged observations serving as input features. Among the approaches considered, the NNAR model exhibited superior performance, as indicated by uncorrelated residuals and enhanced forecast accuracy. This suggests that NNAR effectively captures the nonlinear temporal patterns inherent in the precipitation series. Based on the best-performing model, rainfall was projected for the year 2021, providing actionable insights for regional hydrological and agricultural planning. The results highlight the relevance of neural network-based time series models for climate forecasting in data-scarce, climate-sensitive regions. Full article

This paper proposes a hybrid methodology for one-step-ahead torsional torque estimation in an electric drive with an elastic connection. The approach integrates Nonlinear Autoregressive Neural Networks with Exogenous Inputs (NARX NNs) and model-based feedback. The NARX model uses real-time and historical motor speed and torque signals as inputs while leveraging physics-derived torsional torque as a feedback input to refine estimation accuracy and robustness. While model-based methods provide insight into system dynamics, they lack predictive capability—an essential feature for proactive control. Conversely, standalone NARX NNs often suffer from error accumulation and overfitting. The proposed hybrid architecture synergises the adaptive learning of NARX NNs with the fidelity of physics-based feedback, enabling proactive vibration damping. The method was implemented and evaluated on a two-mass drive system using an IP controller and additional torsional torque feedback. Results demonstrate high accuracy and reliability in one-step-ahead torsional torque estimation, enabling effective proactive vibration damping. MATLAB 2024a/Simulink and dSPACE 1103 were used for simulation and hardware-in-the-loop testing. Full article

Accurate gas consumption forecasting is critical for modern energy systems due to complex consumer behavior and regulatory requirements. Deep neural networks (DNNs), such as Seq2Seq with attention, TiDE, and Temporal Fusion Transformers, are promising for modeling complex temporal relationships and non-linear dependencies. This study compares state-of-the-art architectures using real-world data from over 100,000 consumers to determine their practical viability for forecasting gas consumption under operational and regulatory conditions. Particular attention is paid to the impact of data quality, feature attribution, and model reliability on performance. The main use cases for natural gas consumption forecasting are tariff setting by regulators and system balancing for suppliers and operators. The study used monthly natural gas consumption data from 105,527 households in the Volyn region of Ukraine from January 2019 to April 2023 and meteorological data on average monthly air temperature. Missing values were replaced with zeros or imputed using seasonal imputation and the K-nearest neighbors. The results showed that previous consumption is the dominant feature for all models, confirming their autoregressive origin and the high importance of historical data. Temperature and category were identified as supporting features. Improvised data consistently improved the performance of all models. Seq2SeqPlus showed high accuracy, TiDE was the most stable, and TFT offered flexibility and interpretability. Implementing these models requires careful integration with data management, regulatory frameworks, and operational workflows. Full article

This study presents a hybrid intelligent model for predicting Olympic medal distribution at the 2028 Los Angeles Games, based on data-intelligence fusion (DIF). By integrating historical medal records, athlete performance metrics, debut medal-winning countries, and coaching resources, the model aims to provide accurate national medal forecasts. The model introduces a Performance Score (PS) system combining a Traditional Advantage Index (TAI) via K-means clustering, an Athlete Strength Index (ASI) using a backpropagation neural network, and a Host effect factor. Sub-models include an autoregressive integrated moving average model for time-series forecasting, logistic regression for predicting debut medal-winning countries, and random forest regression to quantify the “Great Coach” effect. The results project America winning 44 gold and 124 total medals, and China 44 gold and 94 total medals. The model demonstrates strong accuracy with root mean square errors of 3.21 (gold) and 4.32 (total medals), and mean-relative errors of 17.6% and 8.04%. Compared to the 2024 Paris Olympics, the model projects a notable reshuffling in 2028, with the United States expected to strengthen its overall lead as host while countries like France are predicted to experience significant declines in medal counts. Findings highlight the nonlinear impact of coaching and event expansion’s role in medal growth. This model offers a strategic tool for Olympic planning, advancing medal prediction from simple extrapolation to intelligent decision support. Full article

This study aims to optimize daily forecasts of the PM2.5 concentrations in Dakar, Senegal using a long short-term memory (LSTM) neural network model. Particulate matter, aggravated by factors such as dust, traffic, and industrialization, poses a serious threat to public health, especially in developing countries. Existing models such as the Autoregressive integrated moving average (ARIMA) have limitations in capturing nonlinear relationships and complex dynamics in environmental data. Using four years of daily data collected at the Bel Air station, this study shows that the LSTM neural network model provides more accurate forecasts with a root mean square error (RMSE) of 3.2 μg/m³, whereas the RMSE for ARIMA is about 6.8 μg/m³. The LSTM model predicts reliably up to 7 days in advance, accurately reproducing extreme values, especially during dust event outbreaks and peak travel periods. Computational analysis shows that using Graphical Processing Unit and Tensor Processing Unit processors significantly reduce the execution time, improving the model efficiency while maintaining high accuracy. Overall, these results highlight the usefulness of the LSTM network for air quality prediction and its potential for public health management in Dakar. Full article

The accurate forecasting of financial flow data in power-grid operations is critical for improving operational efficiency. To tackle the challenges of low forecasting accuracy and high error rates caused by the long sequences, nonlinearity, and multi-scale and non-stationary characteristics of financial flow data, a forecasting model based on multi-verse expansion evolution (MVE²) and spatial–temporal fusion network (STFN) is proposed. Firstly, preprocess data for power-grid financial flow data based on the autoregressive integrated moving average (ARIMA) model. Secondly, establish a financial flow data forecasting framework using MVE²-STFN. Then, a feature extraction model is developed by integrating convolutional neural networks (CNN) for spatial feature extraction and bidirectional long short-term memory networks (BiLSTM) for temporal feature extraction. Next, a hybrid fine-tuning method based on MVE² is proposed, exploiting its global optimization capability and fast convergence speed to optimize the STFN parameters. Finally, the experimental results demonstrate that our approach significantly reduces forecasting errors. It reduces RMSE by 5.75% and 13.37%, MAPE by 22.28% and 41.76%, and increases R² by 1.25% and 6.04% compared to CNN-BiLSTM and BiLSTM models, respectively. These results confirm the model’s effectiveness in improving both accuracy and efficiency in financial flow data forecasting for power grids. Full article

This study proposes a hybrid forecasting model that integrates the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model with a Long Short-Term Memory (LSTM) neural network to estimate Value at Risk (VaR) in the Rwandan foreign exchange market. The model is designed to capture both volatility clustering and temporal dependencies in daily exchange rate returns. Using daily data on USD, EUR, and GBP from 2012 to 2024, we evaluate the model’s performance relative to standalone GARCH(1,1) and LSTM models. Empirical results show that the hybrid model improves VaR estimation accuracy by up to 10%, especially during periods of elevated market volatility. These improvements are validated through MSE, MAE, and backtesting statistics. The enhanced accuracy is particularly relevant in emerging markets, where exchange rate dynamics are highly nonlinear and sensitive to external shocks. The proposed approach offers practical insights for financial institutions and regulators seeking to improve market risk assessment in emerging economies. Full article

This research presents an advanced autonomous HVAC control system tailored for a chemical fiber factory, emphasizing the human-centric principles and collaborative potential of Industry 5.0. The system architecture employs several functional levels—actuator and sensor, process, model, critic, fault detection, and specification—to effectively monitor and predict indoor air pressure differences, which are critical for maintaining consistent product quality. Central to the system’s innovation is the integration of digital twins and physical AI, enhancing real-time monitoring and predictive capabilities. A virtual representation runs in parallel with the physical system, enabling sophisticated simulation and optimization. Development involved custom sensor kit design, embedded systems, IoT integration leveraging Node-RED for data streaming, and InfluxDB for time-series data storage. AI-driven system identification using Nonlinear Autoregressive with eXogenous inputs (NARX) neural network models significantly improved accuracy. Crucially, incorporating airflow velocity data alongside AHU output and past pressure differences boosted the NARX model’s predictive performance (R² up to 0.9648 on test data). Digital twins facilitate scenario testing and optimization, while physical AI allows the system to learn from real-time data and simulations, ensuring adaptive control and continuous improvement for enhanced operational stability in complex industrial settings. Full article

Accurately forecasting sinusoidal time series is essential in various scientific and engineering applications. However, traditional models such as the seasonal autoregressive integrated moving average (SARIMA) rely on assumptions of linearity and stationarity, which may not adequately capture the complex periodic behaviors of sinusoidal data, including varying amplitudes, phase shifts, and nonlinear trends. This study investigates Monte Carlo dropout neural networks (MCDO NNs) as an alternative approach for both forecasting and uncertainty quantification. The performance of MCDO NNs is evaluated across six sinusoidal time series models, each exhibiting different dynamic characteristics. Results indicate that MCDO NNs consistently outperform SARIMA in terms of root mean square error, mean absolute percentage error, and the coefficient of determination, while also producing more reliable prediction intervals. To assess real-world applicability, the airline passenger dataset is used, demonstrating MCDO’s ability to effectively capture periodic structures. These findings suggest that MCDO NNs provide a robust alternative to SARIMA for sinusoidal time series forecasting, offering both improved accuracy and well-calibrated uncertainty estimates. Full article

Weather forecasting is essential for various applications such as agriculture and transportation, and relies heavily on meteorological sequential data such as multivariate time series collected from weather stations. Traditional numerical weather prediction (NWP) methods applied to multivariate time series forecasting are grounded in statistical principles such as Autoregressive Integrated Moving Average (ARIMA); however, they often struggle with capturing complex nonlinear patterns among meteorological variables and temporal variances. Currently, existing deep learning approaches such as Recurrent Neural Networks (RNNs) and transformers offer remarkable performance in handling complex patterns among meteorological multivariate time series, yet frequently fail to maintain weather-specific physical properties such as strict values constraints, while also incurring the significant computational costs of large parameter scales. In this paper, we present a novel deep learning plug-and-play framework named Post Constraint and Correction (PCC) to address these challenges by incorporating additional constraints and corrections based on weather-specific properties such as multivariant correlations and physical-based strict value constraints into the prediction process. Our method demonstrates notable computational efficiency, delivering significant improvements over existing deep learning time series models and helping to achieve better performance with far fewer parameters. Extensive experiments demonstrate the effectiveness, efficiency, and robustness of our method, highlighting its potential for real-world applications. Full article

In self-consumption (SC) configurations, energy management systems (EMSs) are increasingly being implemented to maximise the self-consumption ratio (SCR). Recent studies have demonstrated that prediction-based EMSs significantly enhance decision-making capabilities compared to non-predictive EMSs. This paper presents the design, implementation, and testing on a real system of two machine learning (ML)-type predictive models capable of forecasting the electricity consumption of an individual building using a small dataset. A nonlinear autoregressive with exogenous input (NARX) neural network model and a support vector regression (SVR) model were designed and compared. These models predict day-ahead hourly electricity consumption using forecasted meteorological data from Meteo Galicia (MG) and building occupancy data, both automatically obtained and pre-processed. In order to compensate for the lack of recurrence of the SVR model, the effect of introducing an additional input, a time vector, was analysed. It is proved that both ML models trained with a small dataset are able to predict the next day’s average hourly power with a mean MAPE below 13.96% and a determination coefficient (R²) greater than 0.78. The model that most accurately predicts the hourly average power of a week is the SVR, which achieves a mean MAPE and R² of 10.73% and 0.85, respectively. Full article

Accurately forecasting CO₂ emissions in the transportation sector is essential for developing effective mitigation strategies. This study uses an annually spanning dataset from 1993 to 2022 to evaluate the predictive performance of three methods: NAR, NARX, and GA-T2FIS. Among these, NARX-VK, which incorporates vehicle kilometers (VK) and economic variables, demonstrated the highest predictive accuracy, achieving a MAPE of 2.2%, MAE of 1621.449 × 10³ tons, and RMSE of 1853.799 × 10³ tons. This performance surpasses that of NARX-RG, which relies on registered vehicle data and achieved a MAPE of 3.7%. While GA-T2FIS exhibited slightly lower accuracy than NARX-VK, it demonstrated robust performance in handling uncertainties and nonlinear relationships, achieving a MAPE of 2.6%. Sensitivity analysis indicated that changes in VK significantly influence CO₂ emissions. The Green Transition Scenario, assuming a 10% reduction in VK, led to a 4.4% decrease in peak CO₂ emissions and a 4.1% reduction in total emissions. Conversely, the High Growth Scenario, modeling a 10% increase in VK, resulted in a 7.2% rise in peak emissions and a 4.1% increase in total emissions. Full article

The global demand for clean and sustainable energy has driven the rapid growth of wind power. However, wind farm managers face the challenge of forecasting wind power for efficient power generation and management. Accurate wind speed forecasting (WSF) is vital for predicting wind power; yet, the variability and intermittency of the wind make forecasting wind speeds difficult. Consequently, WSF remains a challenging area of wind research, driving continuous improvement in the field. This study aimed to enhance the optimization of multifeature-driven short multistep WSF. The primary contributions of this research include the integration of ReliefF feature selection (RFFS), a novel approach to variational mode decomposition for multifeature decomposition (NAMD), and a recursive non-linear autoregressive with exogenous inputs (NARXR) neural network. In particular, RFFS aids in identifying meteorological features that significantly influence wind speed variations, thus ensuring the selection of the most impactful features; NAMD improves the accuracy of neural network training on historical data; and NARXR enhances the overall robustness and stability of the wind speed forecasting results. The experimental results demonstrate that the predictive accuracy of the proposed NAMD–NARXR hybrid model surpasses that of the models used for comparison, as evidenced by the forecasting error and statistical metrics. Integrating the strengths of RFFS, NAMD, and NARXR enhanced the forecasting performance of the proposed NAMD–NARXR model, highlighting its potential suitability for applications requiring multifeature-driven short-term multistep WSF. Full article

To address the nonlinearity and control problems of the Maglev system caused by external disturbances and internal factors of the system, this study first established a kinematic model of a single-point levitation system. Secondly, based on the nonlinear characteristics of the kinematic model, Gaussian noise was introduced into the model as input disturbance, and a neural network was used to train the constructed model. A nonlinear autoregressive model with exogenous inputs was constructed, and the Recursive Least Squares method with Forgetting Factor (RLS-FF) was used to perform parameter identification on the levitation system by combining the training data, further constructing an accurate model of the levitation system. Then, based on the accurate model of the levitation system, the backstepping method was adopted to design an adaptive controller for the levitation system, and its stability was verified. Simulation analysis was conducted on the MATLAB/Simulink platform, and comparisons were made with the LQR control method and the Fuzzy-PID control method that verified that the designed controller had a faster response speed and better self-regulation ability. At the same time, interference signals were introduced into the simulation to simulate the actual scene, and the good anti-interference ability and adaptive performance of the designed controller were further verified. Full article