Search Results (4,309)

In the mission scenario of On-Orbit Assembly (OOA), servicing spacecraft are frequently tasked with towing large-scale, flexible truss structures to designated assembly sites. This process involves complex coupled dynamics between the spacecraft and the flexible payload, which are often unmodeled or unknown, posing significant challenges to control precision. Furthermore, the proximity of other assembled structures in the construction area necessitates strict collision avoidance. To address these challenges, this paper proposes a novel adaptive robust controller for spacecraft thruster-based orbital control that integrates Prescribed Performance Control (PPC) with a Radial Basis Function Neural Network (RBFNN). The PPC framework ensures that the position tracking errors remain within user-predefined, time-varying boundaries, providing an intrinsic mechanism for collision avoidance during the towing of large flexible structures. Concurrently, the RBFNN is employed to approximate the entire unknown nonlinear dynamics of the combined spacecraft-truss system online, effectively compensating for uncertainties arising from the flexibility of the truss and external disturbances. The performance of the proposed controller is validated through both numerical simulations and hardware experiments on a ground-based air-bearing satellite simulator. Simulation results demonstrate the controller’s superior tracking accuracy compared to a conventional PID controller, while strictly adhering to the prescribed error constraints. Experimental results further confirm its effectiveness, showing that the simulator can track a desired trajectory with high precision, with tracking errors converging to approximately 5 mm while consistently remaining within the predefined safety boundaries. The proposed approach provides a robust and safe control solution for complex proximity operations in on-orbit construction, eliminating the need for precise dynamic modeling of flexible payloads. Full article

Intelligent ventilation is positioned as a key axis for reconciling energy efficiency and indoor air quality (IAQ) in residential and non-residential buildings. This review synthesizes 51 recent publications covering control strategies (DCV, MPC, reinforcement learning), IoT architectures and sensor validation, energy recovery (HRV/ERV, anti-frost strategies, low-loss exchangers, PCM-air), active envelope solutions (thermochromic windows) and passive solutions (EAHE), as well as evaluation methodologies (uncertainty, LCA, LCC, digital twin) and smart readiness indicator (SRI) frameworks. Evidence shows ventilation energy savings of up to 60% without degrading IAQ when control is well-designed, but also possible overconsumption when poorly parameterized or contextualized. Performance uncertainty is strongly influenced by occupant emissions and pollutant sources (bioeffluents, formaldehyde, PM2.5). The integration of predictive control, scalable IoT networks, and robust energy recovery, together with life-cycle evaluation and uncertainty analysis, enables more reliable IAQ-energy balances. Gaps are identified in VOC exposure under DCV, robustness to sensor failures, generalization of ML/RL models, and standardization of ventilation effectiveness metrics in natural/mixed modes. Full article

The uncertainty of baseline load forecasting critically influences both the assessment of load reduction potential and demand response (DR) settlement. Therefore, this paper focuses on assessing load reduction potential based on probabilistic predictions of the baseline load. First, the uncertainty of the baseline load prediction is analyzed through calculating the conditional probability density function (PDF) and interval estimation of baseline load prediction errors from the convolutional neural network (CNN) model. Then, the probabilistic model of load reduction potential is proposed based on the results from the probabilistic prediction of baseline load and the terms about the interruptible load in DR contracts. Finally, the Monte Carlo simulation method is used to assess the load reduction potential, and probability distributions of the load reduction states, the lower and upper limits of the load reduction potential, are analyzed. Case studies demonstrate that the proposed method effectively characterizes the uncertainty of prediction results, with the prediction interval normalized average width (PINAW) decreased by 10.97%, thereby enabling the effective assessment of load reduction potential from the probabilistic perspective, helping decision makers take better choices. Full article

Energy storage systems enhance grid efficiency by mitigating peak demand and balancing generation variability. This work addresses the challenge of achieving optimal peak shaving without prior knowledge of the actual load profile. To this end, we introduce the Forecast-Integrated Shortest Path (FISP) framework, which integrates load forecasting with the shortest-path optimization algorithm to determine optimal generation and storage strategies under forecast uncertainty. A penalty-based metric is proposed to quantify the deviation between forecast-driven and ideal operation, providing a unified measure of forecast-to-optimization performance. The proposed approach is validated using real load data from the European Network of Transmission System Operators for Electricity (ENTSO-E) and evaluated with two forecasting techniques—Long Short-Term Memory (LSTM) networks and Autoregressive Moving Average (ARMA) models. The results show that LSTM-based forecasts yield substantially lower penalties than ARMA, demonstrating that accurate prediction combined with intelligent storage control can significantly enhance operational reliability and peak-shaving performance. Full article

Accurate forecasting of groundwater level dynamics poses a critical challenge for sustainable water management in arid regions. However, the strong spatiotemporal heterogeneity inherent in groundwater systems and their complex interactions between natural processes and human activities often limit the effectiveness of conventional prediction methods. To address this, a hybrid CNN-LSTM deep learning model is constructed. This model is designed to extract multivariate coupled features and capture temporal dependencies from multi-variable time series data, while simultaneously simulating the nonlinear and delayed responses of aquifers to groundwater abstraction. Specifically, the convolutional neural network (CNN) component extracts the multivariate coupled features of hydro-meteorological driving factors, and the long short-term memory (LSTM) network component models the temporal dependencies in groundwater level fluctuations. This integrated architecture comprehensively represents the combined effects of natural recharge–discharge processes and anthropogenic pumping on the groundwater system. Utilizing monitoring data from 2021 to 2024, the model was trained and tested using a rolling time-series validation strategy. Its performance was benchmarked against traditional models, including the autoregressive integrated moving average (ARIMA) model, recurrent neural network (RNN), and standalone LSTM. The results show that the CNN-LSTM model delivers superior performance across diverse hydrogeological conditions: at the upstream well AJC-7, which is dominated by natural recharge and discharge, the Nash–Sutcliffe efficiency (NSE) coefficient reached 0.922; at the downstream well AJC-21, which is subject to intensive pumping, the model maintained a robust NSE of 0.787, significantly outperforming the benchmark models. Further sensitivity analysis reveals an asymmetric response of the model’s predictions to uncertainties in pumping data, highlighting the role of key hydrogeological processes such as delayed drainage from the vadose zone. This study not only confirms the strong applicability of the hybrid deep learning model for groundwater level prediction in data-scarce arid regions but also provides a novel analytical pathway and mechanistic insight into the nonlinear behavior of aquifer systems under significant human influence. Full article

Reliable detection of unknown signals is essential for ensuring the robustness of underwater acoustic sensing systems, particularly in maritime security and autonomous navigation. However, Conventional deep learning models often exhibit overconfidence when encountering unknown signals and are unable to quantify predictive uncertainty due to their deterministic inference process. To address these limitations, this study proposes a novelty detection framework that integrates an out-of-distribution detector for neural networks (ODIN) with Monte Carlo (MC) dropout. ODIN mitigates model overconfidence and enhances the separability between known and unknown signals through softmax probability calibration, while MC dropout introduces stochasticity via multiple forward passes to estimate predictive uncertainty—an element critical for stable sensing in real-world underwater environments. The resulting probabilistic outputs are modeled using Gaussian mixture models fitted to ODIN-calibrated softmax distributions of known classes. The Kullback–Leibler divergence is then employed to quantify deviations of test samples from known class behavior. Experimental evaluations on the DeepShip dataset demonstrate that the proposed method achieves, on average, a 9.5% and 5.39% increase in area under the receiver operating characteristic curve, and a 7.82% and 2.63% reduction in false positive rate at 95% true positive rate, compared to the MC dropout and ODIN baseline, respectively. These results confirm that integrating stochastic inference with ODIN significantly enhances the stability and reliability of novelty detection in underwater acoustic environments. Full article

This study presents a novel hybrid intelligent framework integrating fuzzy logic and artificial neural networks (ANN) to model the erosion-corrosion behavior of glass-fiber-reinforced pipes (GRP) under harsh operating conditions. Experimental data encompassing multiple operational parameters—including abrasive sand concentrations (250 g, 400 g, 500 g), flow rates (0.0067 m³/min, 0.01 m³/min, 0.015 m³/min), chlorine content (0–10 wt.%), and exposure times (1–5 h)—were utilized to develop the computational models. The fuzzy logic system effectively captured qualitative expert knowledge and uncertainty in material degradation processes, while ANN models provided quantitative predictions of erosion and corrosion rates. Results demonstrated good prediction accuracy, with R² values of 0.81 for corrosion rate and moderate prediction accuracy 0.56 for erosion rate. The analysis revealed that flow rate (correlation: 0.6) and fuzzy severity (0.6) were the most influential parameters, followed by chlorine content (0.41) and sand concentration (0.32). The hybrid model identified optimal operating conditions to minimize material degradation: low sand concentration (250 g), low flow rate (0.0067 m³/min), absence of chlorine, and shorter exposure times. This intelligent modeling approach provides a powerful tool for predictive maintenance, operational optimization, and service life prediction of GRP systems in aggressive environments, bridging the gap between experimental data and computational intelligence for enhanced material performance assessment. Full article

The dual imperative of mitigating carbon emissions and maximizing hydrocarbon recovery has amplified global interest in carbon capture, utilization, and storage (CCUS) technologies. These integrated processes hold significant promise for achieving net-zero targets while extending the productive life of mature oil reservoirs. However, their effectiveness hinges on a nuanced understanding of the complex interactions between geological formations, reservoir characteristics, and injection strategies. In this study, a comprehensive machine learning-based framework is presented for estimating CO₂ storage capacity and enhanced oil recovery (EOR) performance simultaneously in subsurface reservoirs. The methodology combines simulation-driven uncertainty quantification with supervised machine learning to develop predictive surrogate models. Simulation results were used to generate a diverse dataset of reservoir and operational parameters, which served as inputs for training and testing three machine learning models: Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN). The models were trained to predict three key performance indicators (KPIs): cumulative oil production (bbl), oil recovery factor (%), and CO₂ sequestration volume (SCF). All three models exhibited exceptional predictive accuracy, achieving coefficients of determination (R²) greater than 0.999 across both training and testing datasets for all KPIs. Specifically, the Random Forest and XGBoost models consistently outperformed the ANN model in terms of generalization, particularly for CO₂ sequestration volume predictions. These results underscore the robustness and reliability of machine learning models for evaluating and forecasting the performance of CO₂-EOR and sequestration strategies. To enhance model interpretability and support decision-making, SHapley Additive exPlanations (SHAP) analysis was applied. SHAP, grounded in cooperative game theory, offers a model-agnostic approach to feature attribution by assigning an importance value to each input parameter for a given prediction. The SHAP results provided transparent and quantifiable insights into how geological and operational features such as porosity, injection rate, water production rate, pressure, etc., affect key output metrics. Overall, this study demonstrates that integrating machine learning with domain-specific simulation data offers a scalable approach for optimizing CCUS operations. The insights derived from the predictive models and SHAP analysis can inform strategic planning, reduce operational uncertainty, and support more sustainable oilfield development practices. Full article

This research develops and implements a novel reinforcement learning (RL) architecture to address the trajectory-tracking problem in bipedal robotic systems under articulated-joint constraints. The proposed RL framework extends previously designed adaptive controllers characterized by state-dependent gain structures. The learning mechanism comprises two hierarchical adaptation layers: the first employs an adaptive dynamic programming (ADP) formulation to approximate the Bellman value function using a class of continuous-time dynamic neural networks. In contrast, the second uses an iterative optimization scheme based on the deep deterministic policy gradient (DDPG) algorithm. The resulting control strategy minimizes a robust performance index defined over the tracking trajectories of a system with uncertain and nonlinear dynamics representative of bipedal locomotion. The dynamic programming formulation ensures robustness to bounded parametric uncertainties and external perturbations. By approximating the Hamilton–Jacobi–Bellman (HJB) value function using neural network structures, a closed-loop controller design is systematically established. Numerical simulations demonstrate the convergence of the tracking error to a region centered at the origin with a size that depends on the approximation quality of the selected neural network. To assess the effectiveness of the proposed approach, a conventional state-feedback control design is adopted as a benchmark, revealing that the suggested method produces a lower cumulative tracking error norm (0.023 vs. 0.037 rad·s) in the trajectory-tracking control problem for all robotic joints while simultaneously reducing the control effort required to complete motion tasks. Full article

Semi-supervised learning (SSL) is critical for medical image segmentation but often struggles with network dependency and pseudo-label error accumulation. To address these issues, we propose a fractal-dimension-guided hierarchical contrastive learning dual-student framework(FD-HCL). We extend the Mean Teacher architecture with a dual-student design and introduce an independence-aware exponential moving average (I-EMA) update mechanism to mitigate model coupling. For enhanced feature learning, we devise a hierarchical contrastive learning (HCL) mechanism guided by voxel uncertainty, spanning global, high-confidence, and low-confidence regions. We further improve structural integrity by incorporating a fractal-dimension (FD)-weighted consistency loss and integrating a novel uncertainty-aware bidirectional copy–paste (UB-CP) augmentation. Extensive experiments on the LA and BraTS 2019 datasets demonstrate the state-of-the-art performance of our framework across 10% and 20% labeled data settings. On the LA dataset with 10% labeled data, our method achieved a Dice score that outperformed the best existing approach by 0.68%. Similarly, under the 10% labeling setting on the BraTS 2019 dataset, we surpassed the state-of-the-art Dice score by 0.55%. Full article

The strong uncertainty of renewable energy poses significant reliability and safety challenges for the coordinated operation of multi-integrated energy systems (MIES). To address this, a data-driven two-stage distributed robust collaborative optimization scheduling model for MIES is proposed, based on a spatiotemporal fusion conditional diffusion model (STF-CDM). First, to more accurately capture the uncertainty in renewable energy output, the model utilizes a scenario set generated by the STF-CDM model and reduced via the K-means clustering algorithm as the initial renewable energy scenarios for the distributed robust optimization set. The STF-CDM model employs a Temporal module component (TMC) unit composed of Transformer time-series modules and a Spatial module component (SMC) unit composed of CNN neural networks for feature extraction and fusion of time-series and spatial-series data. Second, a benefit allocation method based on multi-energy trading contribution rates is proposed to achieve equitable distribution of cooperative gains. Finally, to protect participant privacy and enhance computational efficiency, an alternating direction multiplier method (ADMM) coupled with parallelizable column and constraint generation (C&CG) is employed to solve the energy trading problem. The case analysis results demonstrate that the STF-CDM model proposed in this study exhibits superior performance in addressing the uncertainty of renewable energy output. Concurrently, the asymmetric Nash game mechanism and the ADMM-C&CG solution algorithm proposed in this study achieve a fair and reasonable distribution of benefits among all participants when handling energy transactions and cooperative gains. This is accomplished while ensuring system robustness, economic efficiency, and privacy. Full article

Hybrid microgrids struggle to manage electricity due to renewable source, storage, and load demand variability. This paper proposes a centralized controller employing hybrid deep learning and evolutionary optimization to overcome these issues. Solar panels, BESS, EVs, dynamic loads, steady loads, and a switching main grid make up the hybrid microgrid. To capture spatial and temporal patterns, a centralized controller uses a deep learning model with a CNN–LSTM architecture. The imperialist competitive algorithm (ICA) optimizes neural network hyperparameters for more accurate controller outputs. The controller controls grid switching, voltage source converter power, and EV reference current. R² values of 0.9602, 0.9512, and 0.9618 show reliable controller output predictions. A typical test case, low sunshine, and no EV or BESS initial charging are validation situations. Its constant power flow, uncertainty management, and adaptability make this controller better than others. Even with intermittent energy and limited storage capacity, the ICA-optimized hybrid deep learning controller stabilized smart-grids. Full article

Accurately predicting the peak impact force exerted by landslides on bridge piers is crucial for evaluating structural safety. However, the reliability of such predictions is frequently undermined by the spatial variability and uncertainty inherent in soil and rock strength parameters. To quantify the influence of this uncertainty, in this study, a three-dimensional numerical model of a landslide impacting bridge piers was developed using LS-DYNA software (version R11.0.0). A neural network was then trained on the peak impact forces simulated by the numerical model. Based on the neural network predictions, the impact mechanisms were categorized into two distinct modes, namely, a low-impact mode and a high-impact mode, for a comparative analysis. The results revealed statistically significant differences in soil parameters between these modes. Specifically, low-impact forces (F < 467 kN) were found to correlate with higher cohesion (18.5–24.9 kPa) and lower internal friction angles (15–22.4°). Conversely, high-impact forces (F ≥ 467 kN) were associated with lower cohesion (14.0–21.6 kPa) and higher internal friction angles (18.1–25.3°). This negative correlation highlights the decisive role that the combined uncertainty of strength parameters plays in predicting the peak impact force. Moreover, the surrogate model developed in this study effectively addresses the computational inefficiencies commonly associated with Monte Carlo simulations. This methodology provides a valuable tool for evaluating the vulnerability of infrastructure systems exposed to landslide hazards. Full article

In this paper, we propose a Bayesian Deep Learning (BDL) framework to model uncertainty and predict the performance of terahertz (THz) biosensors with a graphene and molybdenum disulfide (MoS₂) coating for AML biomarker detection. Although there have been studies on the individual advantage of these 2D materials for biosensing, a comparative analysis taking into account predictive uncertainty is still insufficient. To this end, we have generated a high-fidelity simulation dataset from full-wave EM simulations of DSSRR structures over the 0.1–2.5 THz frequency range. Realistic geometrical and dielectric modifications have been incorporated to mimic bio-sensing conditions. An approach based on a Bayesian Neural Network (BNN) with Monte Carlo dropout was employed for predicting sensitivity, Q-factor, resonance shift, and absorption, along with the estimation of aleatoric, as well as epistemic, uncertainty. Our results demonstrated a trade-off between material types: MoS₂ sensors showed higher sensitivity (3548 GHz/RIU) but with a larger prediction uncertainty range of ±118 GHz/RIU; on the other hand, graphene-based sensors exhibited a better spectral resolution (Q = 48.5) and a more reliable QV prediction range of ±42 GHz/RIU. The uncertainty study further revealed that graphene demonstrated a predominance for aleatoric uncertainty (68%), classifying them as predictable physical characteristics, while MoS₂ presents a higher epistemic one (55%), indicating sensitivity towards underrepresented design cases. We present a material selection algorithm based on utility that balances sensitivity, resolution, and uncertainty, demonstrating that MoS₂ is the best choice for early screening, while graphene is more suitable for high-precision diagnostics. This study offers a scalable and reliable AI framework for quick, uncertainty-aware optimization of THz biosensors, which is directly applicable to clinical diagnostics and 2D-material-based photonic design. Full article

Open-channel irrigation systems often face constraints due to water supply uncertainty and insufficient gate control precision. This study proposes an integrated framework for canal water allocation and gate control that combines interval-based uncertainty analysis with intelligent optimization to address these challenges. First, we predict the inflow process using an Auto-Regressive Integrated Moving Average (ARIMA) model and quantify the range of water supply uncertainty through Maximum Likelihood Estimation (MLE). Based on these results, we formulate a bi-objective optimization model to minimize both main canal flow fluctuations and canal network seepage losses. We solve the model using the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to obtain Pareto-optimal water allocation schemes under uncertain inflow conditions. This study also designs a Fuzzy Proportional–Integral–Derivative (Fuzzy PID) controller. We adaptively tune its parameters using the Particle Swarm Optimization (PSO) algorithm, which enhances the dynamic response and operational stability of open-channel gate control. We apply this framework to the Chahayang irrigation district. The results show that total canal seepage decreases by 1.21 × 10⁷ m³, accounting for 3.9% of the district’s annual water supply, and the irrigation cycle is shortened from 45 days to 40.54 days, improving efficiency by 9.91%. Compared with conventional PID control, the PSO-optimized Fuzzy PID controller reduces overshoot by 4.84%, and shortens regulation time by 39.51%. These findings indicate that the proposed method can significantly improve irrigation water allocation efficiency and gate control performance under uncertain and variable water supply conditions. Full article