Search Results (269)

Electric pump-fed liquid rocket engines require coordinated propellant delivery under coupled hydraulic, electrical, actuator, and thermal constraints. This study develops an integrated reduced-order model of a dual-channel electric pump-fed propellant system, including the battery and DC bus, power converters, two independently driven motor–pump units, hydraulic feed lines, control valves, combustion chamber, and thermal states. A hierarchical constrained multi-criteria supervisory controller is formulated to regulate chamber pressure, oxidizer-to-fuel mixture ratio, feed-channel coordination, electrical loading, and thermal response. Performance is compared with a conventional PI controller and an enhanced PI configuration incorporating feedforward and disturbance compensation under nominal, degraded, long-duration, and constraint-active scenarios. Relative to the baseline PI controller, the proposed controller reduced the startup pressure peak from 2.64 to 2.32 MPa, pressure RMSE from 0.016 to 0.006 MPa, and mean branch synchronization error from 0.112 to 0.028 MPa. The minimum battery voltage increased from 87.0 to 90.4 V, while the peak motor current decreased from approximately 88 to 65 A. In the 1800 s thermal case, the maximum fuel-drive temperature decreased from approximately 104 to 74 °C. Numerical verification and comparison with published experimental benchmarks supported the physical plausibility and equilibrium-scale behavior of the reduced-order model, while differences in absolute transient time scales limit its use for quantitative prediction of hardware transient dynamics. The results indicate improved coordinated control within the investigated operating envelope and support the use of the framework for comparative system-level assessment and preliminary design of small-class electric-pump propulsion systems. Full article

Digital health commodity networks process billions of transactions annually, yet European health systems exhibit diagnostic lags of 30–180 days between anomalous events and institutional detection. Existing governance architectures are retrospective by design, and no existing framework combines pre-emptive predictive control with a principled human–AI cognitive-boundary taxonomy for this setting. This study introduces Deep Business Analytics (DBA), a pre-emptive management control system extending Simons’ four levers of control with a fifth—Predictive Feedforward Control—implemented via Long Short-Term Memory (LSTM) neural networks integrated with a Balanced Scorecard KPI layer. DBA is governed by Artificial Complementary Intelligence (ACI), a four-domain cognitive boundary taxonomy specifying where algorithmic governance is appropriate and where human clinical judgment must retain sovereignty, operationalised within a four-layer Predictive Governance Architecture (PGA). Empirical grounding draws on two deployments: a longitudinal case study at Royal Liverpool Hospital NHS Trust conducted over 28 consecutive days in 2023 (>10 million timestep records; RMSE = 0.00436) and a practitioner case study of 15 million GKV prescriptions processed in 2023 (VisionXY7; approximately 95% anomaly detection accuracy; Governance Velocity Improvement Ratio≈180:1). The ACI boundary taxonomy identifies two governance domains structurally unsuitable for autonomous AI decision-making. DBA and ACI together constitute an integrated, EU AI Act Annex III-compliant architecture that transforms health network AI governance from retrospective detection to pre-emptive control with principled human–AI boundaries. Full article

Water treatment plants are essential urban infrastructure with direct implications for public health and everyday life. Data-driven management has received growing attention in drinking water treatment, particularly for optimizing chemical dosing to improve operational efficiency, reduce costs, and ease operator workload. AI-based prediction of coagulant dosage has therefore become an active research topic. Existing studies, however, have focused mainly on model architecture, with less attention to data validity and cost control. In practice, many plants face data-quality problems, including inconsistent dosing records under similar water-quality conditions. Conventional data cleaning may also remove large portions of the dataset, which can weaken model reliability. This study proposes an artificial intelligence (AI) modeling framework for coagulation dosing that handles anomalous data, emphasizes data quality assurance, and combines cost-oriented feedforward prediction with feedback control. A genetic algorithm-optimized backpropagation (GA-BP) neural network was first evaluated on controlled laboratory data and full-scale plant data using the same core model architecture, allowing the effects of model configuration to be separated from those of data quality. Historical plant records were subsequently cleaned through expert-guided validation, approximate time-delay alignment, and turbidity-based classification of operating conditions. Settled-water turbidity was then used as a feedback signal to dynamically adjust subsequent coagulant dosage and assess the resulting chemical savings. Changes in the input structure produced only modest improvements in full-scale prediction performance (R² = 0.53–0.72). In contrast, data cleaning and process-based data organization markedly improved predictive performance, with R² values increasing to 0.927–0.969. Standalone AI models achieved only moderate dosage reductions, while their integration with real-time turbidity feedback provided the best cost-control performance. The model-based control strategy reduced average coagulant consumption by 10.37%, with a maximum reduction of 21.33% at a settled-water turbidity target of 1.9 nephelometric turbidity units (NTU). Across the evaluated feedback-control scenarios, manual dosing was up to 32.83% higher than the corresponding feedback-controlled dosage. Overall, AI models can fit coagulation-dosing data and predict coagulant dosage with sufficient accuracy, but data quality assurance remains the main factor determining model performance. Effective cost control also requires real-time turbidity-based feedback regulation rather than model outputs alone. Full article

The solar–air source heat pump (S-ASHP) system is used to prepare domestic hot water and is an important form of hot water preparation in many colleges and universities in China. However, the traditional design specifications and operation control strategies can cause excessive design capacity for the hot water system and energy waste. To address these issues, in this study, we integrate the S-ASHP hot water system with predictive modeling of user demand, proposing two distinct control strategies for the hot water supply system. Scheme I: The traditional hot water demand specification is used for design, and the feedback control strategy of the end hot water demand is set according to a fixed mode. Scheme II: A feedforward–feedback combined control strategy based on the ANN-LSTM-STA model is used to predict water consumption and set the end hot water demand. Compared with Scheme I, Scheme II shows significant advantages in heat supply, total energy consumption, and coefficient of performance (COP). The heat supply of the solar collector (SC) supply system is increased by 9.47%, the heat supply of the ASHP supply system is significantly reduced by 57.52%, the running time is reduced by 33.45%, the pump’s energy usage decreases by 16.65%, and the overall system energy consumption drops by 43.85%. Additionally, the coefficient of performance (COP) improves by 6.42%, and the coefficient of performance of the system (COPsys) sees a significant increase of 18.39%. Full article

Reliable finite-horizon forecasting of chaotic dynamics is challenging because small approximation errors grow rapidly during recursive prediction. This study presents a controlled comparison of data-driven and physics-regularized forecasting methods for the Lorenz and Rössler systems. The proposed Hybrid Physics-Informed Feedforward Neural Network (Hybrid PI-FNN) learns a discrete state-transition map from a ten-state observation window through a five-step recursive rollout. Unlike conventional continuous-coordinate physics-informed neural networks, physical consistency is imposed using fourth-order Runge–Kutta transition targets derived from the known governing equations. The physics weight is selected using chronological recursive validation and evaluated against an architecturally identical multi-step FNN with $\lambda =0$. Conventional FNN, LSTM, Echo State Network (ESN), Autoregressive AR(10), and Dynamic Mode Decomposition baselines are also evaluated using untouched test trajectories. For the 1000-step Lorenz test rollout, the ESN achieved the lowest mean squared error (MSE) of 0.1701, followed by the LSTM with 22.9962. The Hybrid PI-FNN produced an MSE of 95.8157, compared with 87.9260 for its $\lambda =0$ ablation; therefore, physics regularization did not improve Lorenz test MSE, although their forecast horizons at a 10% normalized-error threshold were similar (273 and 272 steps, respectively). For the Rössler system, the Hybrid PI-FNN reduced recursive MSE from 0.2202 for the $\lambda =0$ ablation to 0.0834, corresponding to a 62.11% reduction, while both models completed the maximum evaluated 1000-step forecast horizon. Nevertheless, the ESN again achieved the lowest Rössler MSE of approximately $8.04\times {10}^{-5}$. Finite-horizon correlation-dimension analysis, exact governing-equation Lyapunov spectra, computational-cost comparisons, and five-seed paired experiments were additionally conducted. The exact spectra confirmed one positive, one approximately neutral, and one negative exponent for each system, indicating chaotic but not hyperchaotic behavior. The paired multi-seed analysis did not establish a statistically significant forecasting advantage from physics regularization. These findings show that higher-order physics consistency can benefit particular systems and configurations, but it does not guarantee universal superiority in recursive chaotic forecasting. Full article

High gas–oil ratio (GOR) well streams challenge the stable operation of oilfield gathering systems because positive-displacement multiphase pumps lose volumetric efficiency, amplify pressure pulsation, and suffer seal degradation as the inlet gas fraction rises. Targeting GOR = 100–300 Nm³/t (≈480–1450 scf/STB), this study proposes a jet pump-based oil–gas multiphase transportation system together with an evaluation framework that couples localized computational fluid dynamics (CFD) with a one-dimensional (1D) transient pipeline network model. The methodological novelty is a GOR-dependent source-term closure embedded in the 1D momentum equation: the pump pressure rise is evaluated at every time step as $\mathsf{\Delta }{p}_{\mathrm{p}\mathrm{u}\mathrm{m}\mathrm{p}}\left(t\right)=k_g\left(\mathrm{G}\mathrm{O}\mathrm{R}\right)·{\Pi }_p\left(\mathrm{G}\mathrm{O}\mathrm{R},p_w\right)·\left(p_w-p_s\right)$ from CFD-derived maps of entrainment ratio, pressure recovery, and high-gas correction, so that the jet pump enters the network simulation as a dynamic source rather than a steady boundary condition, a capability that neither pump-level transient CFD nor conventional 1D codes provide. Transient simulations under slug disturbances give three main results. (i) At GOR = 200 Nm³/t and constant working-fluid pressure, slug arrivals drive the outlet pressure transiently below the ±5% band (0.76–0.84 MPa), and it returns to the band of the 0.80 MPa set point within ≈150 s. (ii) As GOR increases from 100 to 300 Nm³/t, ${\displaystyle \frac{{\sigma }_p}{p_{\mathrm{s}\mathrm{e}\mathrm{t}}}}$ rises from 0.031 to 0.089 and the peak-to-peak ratio from 0.18 to 0.50, with stability criterion C1 violated beyond ≈275 Nm³/t. (iii) Three applicability zones are delineated: preferred (100–200), controllable (200–260), and marginal (260–300 Nm³/t), where the marginal zone requires inlet peak-shaving, ≥30% working-fluid pressure margin, and feedforward–feedback control. Mesh independence (${\mathrm{G}\mathrm{C}\mathrm{I}}_{\mathrm{f}\mathrm{i}\mathrm{n}\mathrm{e}}=0.23–0.35$%) and a CFD–1D transfer mismatch ≤3% support internal consistency; the delineated boundaries remain model predictions pending experimental and field validation. Full article

Aiming at the problems of strong model uncertainty, unmodeled perturbation disturbances and unknown maneuvering of space non-cooperative targets in orbital rendezvous missions, an orbit prediction and control method combining active disturbance rejection and model predictive control (ADRC-MPC) is proposed in this paper. Firstly, the relative motion dynamic equations of chaser–target are established under a geocentric inertial coordinate system, and the lumped disturbance including space perturbation and unknown evasive maneuvers of the target is expanded into extended state variable. Secondly, an extended state observer (ESO) is designed to achieve real-time accurate estimation and feedforward compensation of time-varying lumped disturbances, which mitigates adverse influences induced by J2 zonal harmonics, atmospheric drag, solar radiation pressure, and target evasive maneuvers. Thirdly, a constrained MPC strategy incorporating thrust saturation, approach corridor, and collision safety zone constraints is developed. Sufficient conditions for closed-loop input-to-state stability (ISS) are theoretically derived via the small-gain theorem under the given assumptions, which ensures the uniform ultimate boundedness (UUB) of tracking errors. Finally, numerical simulations, comparative benchmarks against conventional MPC and proportional-derivative (PD) control, and Monte Carlo robustness tests are performed. Simulation results demonstrate that the proposed ADRC-MPC framework delivers superior rendezvous precision, stronger disturbance rejection, reduced propellant consumption, and improved robustness against initial state offsets and measurement noises, laying solid theoretical and technical foundations for autonomous orbital rendezvous with space non-cooperative targets. Full article

Unmanned Surface Vehicles (USVs) increasingly require on-board policies capable of engagement-level tactical decisions under discrete mission-system constraints. Most existing systems, however, remain rule-based and predictable, and many maritime reinforcement learning studies still focus on low-level continuous control. This paper proposes TAP-DDQN, a GRU-enhanced dueling deep Q-network trained with a multiplicative Tactical Approach Potential (TAP) and a dynamic target curriculum for discrete tactical decision-making in adversarial maritime engagements. The proposed TAP couples a desired engagement-range ring with an aspect-aware tactical term so that angular shaping becomes active mainly inside the tactical band, providing dense guidance without encouraging irrelevant long-range aspect optimization. The method is implemented through the non-invasive TRNLE wrapper, which enables learning and deployment without modifying the legacy combat-management software stack. In a 1-vs-1 surface-engagement scenario, the proposed agent achieves a DGAR of $54.87\pm 4.19\%$ and consistently outperforms feedforward and non-TAP baselines on reward-aligned diagnostics and maneuver consistency; relative to the strongest learning baseline (DQN+MLP without TAP), the improvement is $8.13$ percentage points. Qualitative analyses further show that the learned policy approaches the desired engagement ring, stabilizes a favorable stern-quarter geometry, and exhibits more coherent maneuver behavior than rule-based or additive-reward baselines. These results support multiplicative TAP shaping as an effective and deployment-compatible approach for USV tactical autonomy and intelligent adversary generation in naval training environments. Full article

Material conveying and collection are critical to harvesting efficiency, crop quality, energy consumption, and operational continuity in combine harvesters. However, existing studies mainly focus on individual technologies, while systematic criteria for technology comparison and selection remain insufficient. This review critically analyzes major conveying and collection technologies, mechanism-based simulation methods, and intelligent sensing and control strategies. Screw, clamping-flexible, chain/vibrating, and pneumatic conveying systems are compared in terms of conveying efficiency, crop damage and material loss, energy consumption, reliability, and adaptability. DEM, dynamic/vibro-acoustic analysis, and CFD–DEM are further evaluated according to their applicable mechanisms, physical fidelity, and computational cost. Recent advances in multi-source sensing, data-driven prediction, and feedforward–feedback control are summarized. Based on these comparisons, a system-level optimization framework is proposed, emphasizing efficiency, quality preservation, and energy efficiency while maintaining operational reliability and adaptability. The review indicates that no single technology is universally optimal; technology selection should be matched to crop properties, operating conditions, and dominant performance objectives. Future research should focus on material-property-informed technology selection, mechanism–data hybrid modeling, and adaptive closed-loop control for intelligent harvesting systems. Full article

Portable sensor-based assessment of human motion is important for monitoring motor development and informing the design of rehabilitation applications. This study investigated upper limb motor characteristics during two-dimensional circular target tracking across different age groups and speeds. Fifty-one participants were divided into three groups: lower-elementary children, upper-elementary children, and adults. Using a tablet- and stylus-based input device suitable for human–computer interaction systems, participants performed the tracking task at three speeds. Each trial included relatively feedback-dominant target-visible segments and relatively feedforward-dominant temporarily target-invisible segments. The latter imposed greater demands on predictive tracking because current target-related visual information was unavailable. A participant-level Tracer Error Ratio was calculated as the target-invisible positional error divided by the target-visible positional error. The two child groups showed similar ratios across all speeds, whereas adults showed lower ratios than either child group. As tracking speed increased, the ratio decreased in all groups, with the adult mean falling below 1 only in the high-speed condition. These findings indicate an adult-child difference in predictive tracking during temporary target disappearance but do not directly identify a specific cerebellar mechanism. This portable tablet-stylus approach may be useful for research on age group differences in upper limb target tracking performance. Full article

Traditional grid-forming converter (GFC) control faces fundamental challenges in maintaining DC bus stability during rapid power transients, primarily due to the limited dynamic response capability of source-side energy storage devices. To address this, this paper proposes a hybrid control strategy integrating long short-term memory (LSTM) networks with a joint GFC and storage converter (SC) control scheme. The LSTM detects short-term voltage trends from historical DC bus data to generate a feedforward compensation signal, while the joint SC-GFC control dynamically incorporates the GFC’s inertial power demand into the SC’s power reference. Hardware-in-the-loop experiments show that, compared to traditional independent control under the same step transient conditions, the proposed method can reduce power overshoot by approximately 79.2%. The LSTM-enhanced joint control maintains stable power flow and significantly suppresses low-frequency oscillations, validating the necessity of data-driven trend prediction for achieving superior inertial support in practical constrained environments. This work provides a communication-free, practical solution for enhancing GFC performance. Full article

Freeform machining of impellers involves extended cycle times, leading to high energy consumption and costs necessitating efficient process optimization. This study develops a CAD/CAM-integrated hybrid Taguchi-Artificial Neural Network (ANN) model to optimize machining parameters for a freeform impeller. Four controllable factors, namely cutting feed ($C_f$), feed Z ($F_z$), retract feed ($R_f$), and cutter diameter ($C_D$), were investigated at five levels using an L25 orthogonal array, with machining time as the response. Taguchi analysis identified cutting feed as the most dominant factor, while retract feed was insignificant, and a first-order regression model yielded an R² of 95.88%. A two-layer feedforward neural network with six hidden neurons achieved an R² of 0.9999 and a mean absolute error of 0.0976 min. To rigorously validate generalization, leave-one-out cross-validation was employed, identifying three hidden neurons as optimal with a cross-validated R² of 0.9823, RMSE of 0.5350 min, and MAE of 0.3429 min. The final model trained on all samples achieved an R² of 0.9996. Comparison with a quadratic regression model on the same test set confirmed the superior predictive capability of the ANN ($R^2=0.9992$ vs. $0.9983$). Optimal parameters ($C_f=\mathrm{12,000} \mathrm{m}\mathrm{m}/\mathrm{m}\mathrm{i}\mathrm{n}$, $F_z=600 \mathrm{m}\mathrm{m}/\mathrm{m}\mathrm{i}\mathrm{n}$, $R_f=4000 \mathrm{m}\mathrm{m}/\mathrm{m}\mathrm{i}\mathrm{n}$, $C_D=6 \mathrm{m}\mathrm{m}$) were validated through simulation, yielding a machining time of 11.05 min, representing a 52.6% reduction from 23.32 min. The hybrid Taguchi–ANN framework effectively optimizes freeform impeller machining, significantly enhancing productivity while maintaining process reliability. Full article

This work presents a novel method known as the Red Deer Algorithm-Based Artificial Neural Network (RDA-ANN) for managing real-time voltage and harmonic control in a cascade H-bridge multilevel inverter (CHB-MLI) that is fed by photovoltaic (PV) panels. The RDA-ANN technique proposed here computes the switching angles in real-time for selective harmonic elimination (SHE) on the output voltage of a multilevel inverter (MLI). In the proposed approach, a comprehensive lookup table containing 7776 permutations of switching angles was first generated offline using RDA optimization for a three-phase, 11-level CHB-MLI with five PV panels operating across a voltage range of 30 V to 35 V. This dataset was subsequently used to train a feed-forward ANN model capable of predicting optimal switching angles corresponding to any real-time voltage measurements from the panels. The SHE-PWM approach based on RDA-ANN targets the elimination of the 5th, 7th, 11th, and 13th order harmonics. This algorithm guarantees that the intended fundamental voltage is achieved, even during fluctuations in the voltages of the panels caused by varying irradiation and temperature conditions, while effectively removing the unwanted harmonics. The findings, validated under multiple environmental scenarios, illustrate that the RDA-ANN-based SHE-PWM technique successfully eliminates the selected harmonics from the load voltage with a fundamental voltage error not exceeding 0.18%, and results in a low total harmonic distortion (THD) value that complies with the IEEE 519-2022 standard across all tested conditions. Full article

To address junction-temperature fluctuations and thermal-fatigue degradation of IGBT modules in EV traction inverters under CLTC conditions, this study develops a hierarchical active thermal-management framework. A temperature-dependent loss model coupled with a fourth-order Foster thermal network is first established and evaluated against experimentally derived temperature references. The prediction errors are mainly within ±5 °C over approximately 30–145 °C, with a small number of larger deviations during rapid thermal transients. Speed-based feedforward scheduling, single-variable fuzzy feedback, and dual-variable fuzzy control coordinating switching frequency and cooling intensity are then evaluated in simulation. Rainflow counting and the Miner rule show cumulative-damage reductions of 57.09%, 66.70%, and 81.90%, respectively, while the dual-variable strategy increases the model-based equivalent lifetime from 5.32 to 31.99 years. The results demonstrate the benefit of coordinated heat-generation and heat-dissipation control for inverter thermal reliability. Full article

Lane keeping under degraded visual confidence remains challenging because most existing approaches focus either on improving lane-feature extraction or on estimating vehicle motion, while giving less attention to how unreliable visual measurements should modify the estimator–controller interaction in a physical closed-loop system. This paper presents a confidence-gated Kalman lane-keeping architecture for a 1:10-scale autonomous vehicle. The methodological contribution lies in the direct coupling of visual confidence, state estimation, and steering control: unreliable lane measurements are down-weighted through confidence-dependent measurement noise, while the propagated lane-relative state remains available to the controller. The primary experimental unit is the run, defined as one logged lap under one control configuration; frame-level summaries are retained only as historical reproducibility material. In the run-level comparison, the autonomous vision, inertial measurement unit (IMU)-feedforward, and Kalman filter (KF) group KF_G1—the first inferential KF generation—had lower mean absolute error than the human baseline, while vision and KF_G1 had overlapping run-level confidence intervals for absolute error. KF_G1 shifted the mean signed bias closer to the lane reference than the vision and IMU groups, but with higher run-level spread than vision. KF_G2, the second observational KF generation, is reported only as an observational generation comparison, so no causal claim is made for its estimator–controller correction weight $K_s=0.15$ setting. KF_G3, the single descriptive adverse-condition KF run, is reported without an estimable confidence interval or population-level adverse-illumination inference. A further limitation is that the inertial prediction pathway was inactive in the logged Kalman-filter runs because the inertial coupling coefficient $\alpha =0$. The main contribution is a reproducible run-level evaluation of confidence-gated estimator–controller coupling that distinguishes supported evidence from observational and descriptive cases. Full article