Search Results (1,952)

Ultra-low-phosphorus high-purity iron (ULP-HPFe) is essential for advanced electromagnetic, aerospace, and defense systems, yet stabilizing basic-oxygen-furnace (BOF) dephosphorization remains challenging. To address this instability, we present an intelligent partition-and-prediction framework (iDePP) that first auto-classifies 5102 industrial data records into medium-phosphorus (iDePP-MP), low-phosphorus (iDePP-LP), and ultra-low-phosphorus (iDePP-ULP) subsets, and dedicated ensemble prediction models are then developed for each subset based on representative machine learning algorithms, including random forest (RF), extreme gradient boosting (XGBoost), and neural networks (NNs). Compared with a single global predictor, iDePP reduces the mean absolute error from 0.0018% to 0.0011%, 0.0007%, and 0.0004% for the three classes, respectively, and increases the iDePP-ULP hit rate (HR) to 82.7% within ±6 ppm. Shapley additive explanations (SHAP) and quantitative feature coupling analysis reveal two critical mechanisms governing extreme dephosphorization: limestone-induced thermal penalties and furnace-age effects. Guided by these insights, three consecutive 200-ton BOF industrial trials preliminarily verified the practical feasibility of producing ULP-HPFe, with model plant deviations of approximately 4 ppm, 1 ppm, and 1.5 ppm, respectively. Notably, this work demonstrates the value of automatic domain partitioning combined with subset-specific ensemble learning for complex BOF control, highlighting the potential applicability of iDePP to other data-sparse industrial processes. Full article

In long-endurance and high-precision navigation scenarios, gravity disturbances have become the core bottleneck limiting the performance improvement of high-precision Inertial Navigation Systems (INSs). This paper aims to investigate the compensation efficacy of gravity field spherical harmonic models of different degrees for high-precision INS. The influence mechanisms of gravity disturbances on INS error propagation are derived, and corresponding simulation analyses are performed. The gravity compensation mechanism based on gravity field spherical harmonic models is elaborated, and the performance differences in gravity disturbance compensation among spherical harmonic models of different orders are comparatively analyzed. Based on long-endurance ship trial experiments using high-precision inertial navigation equipment, the compensation efficacy of the 360-order and 2159-order compensation schemes on multiple navigation performance indicators is quantitatively evaluated across sea areas with different gravity characteristics. The experimental results demonstrate that the widely held consensus within the field—that a higher model degree yields better compensation efficacy when improving high-precision INS accuracy based on gravity field spherical harmonic model compensation—does not hold universal applicability. The research findings can provide theoretical support for the engineering implementation of gravity compensation schemes and the selection of model degrees for high-precision INS. Full article

Accurate short-term power forecasting is essential for enhancing the efficiency and reliability of energy systems. Nonetheless, conventional techniques for forecasting struggle to detect nonlinear patterns in power time series, as maintaining both stability and accuracy in predictions is tough. This research presents a unique prediction framework that integrates a Multilayer Perceptron (MLP) with survivor-based evolutionary selection strategies. The proposed neural network architecture comprises three hidden layers containing 32, 16, and 8 neurons, respectively. This enables the network to extract features while preserving essential information progressively. A Survivor selection process is employed to enhance the model’s efficacy. This approach retains the optimal training models for subsequent training phases. This technique enhances both predictive accuracy and training efficiency. The amalgamation of Survivor-based selection methodologies with MLP architectures for short-term power generation forecasting is overlooked in the existing literature, although it holds promise. Thus, the proposed model is evaluated against established baselines, including Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR). The results from 30 distinct trials indicate that the proposed MLP (32-16-8) combined with the Survivor approach exhibits the minimal prediction errors, with a mean absolute error (MAE) of 5.3588 and a root mean square error (RMSE) of 10.0216. This strategy is superior in minimizing errors compared to alternative methods. Furthermore, statistical analyses utilizing the Wilcoxon signed-rank test and paired t-test indicate that the proposed method significantly outperforms SVR and RF, while displaying performance comparable to LR. The findings indicate that including a Survivor-based selection mechanism in the MLP training process is an effective and reliable method for forecasting short-term generation power. Full article

Reliable indoor localization is required for automated guided vehicles (AGVs), robot validation, and industrial digital-twin applications, but ultrasonic positioning can degrade sharply when acoustic visibility changes. This paper evaluates Marvelmind Super-Beacon localization in controlled laboratory experiments involving both AGV tracking and UR10 robot-arm positioning. The non-inverse architecture (NIA) and inverse architecture (IA) configurations are included as parallel validation scenarios to assess the robustness of the proposed mitigation framework across different Marvelmind deployment modes. The baseline analysis identifies the dominant acoustic failure modes, including multipath-induced scatter, crossover-zone handover jumps, update-rate degradation, complete non-line-of-sight (NLoS) outages, and height-dependent 3D jitter. To mitigate these effects, an embedded ultrasonic–inertial pipeline is implemented on an ESP32-S3-WROOM-1 module. The system combines UART packet validation, interrupt-driven ICM-20948 inertial acquisition at 500 Hz, sliding-window kinematic outlier rejection, and a 15-state error-state Kalman filter (ESKF). The embedded estimator logic is designed to maintain motion continuity during intermittent or corrupted acoustic positioning while reintroducing validated ultrasonic absolute corrections. Using recorded AGV and UR10 datasets, mitigation performance was quantitatively assessed through a firmware-consistent replay of the recorded measurements, using the same gating, inertial propagation, and measurement-update logic as the real-time ESP32-S3 implementation. Across ten trials per configuration, the replay-based trial-mean RMSE in the 2D AGV scenarios decreased from 101.2–104.1 mm for raw ultrasonic data to 47.2–48.7 mm after fusion, while peak failure-interval errors were reduced by 64.2–65.7%. In the 3D UR10 scenarios, replay-based trial-mean RMSE decreased from 157.6–158.4 mm to 80.2–80.5 mm, and peak height-sensitive 3D errors were reduced by 58.8–60.0%. The results demonstrate the feasibility of embedded ultrasonic–inertial robustness enhancement for localization in controlled laboratory AGV and robot-arm scenarios. While the proposed approach shows promising performance under the investigated conditions, further validation is required before extending the conclusions to larger-scale and dynamically changing industrial environments. Full closed-loop online robot localization and control based directly on the fused localization output remain subjects for future investigation. Full article

Low-cost bipolar-junction-transistor (BJT) thermal pixel arrays provide robust, force-free contact sensing for tactile skins, but their slow frame rate confines contact-timing resolution to the inter-frame interval—252 ms at the 4 Hz rate of the 16 × 16 array studied here—well below the needs of contact-aware control. We propose a four-frame complementary-error-function (erfc) template, derived from one-dimensional semi-infinite heat conduction, that jointly estimates the contact amplitude, the thermal-diffusion parameter, and the sub-frame contact-onset offset (τ₁), solved by a grid-initialized semi-analytic Levenberg–Marquardt scheme (Path A) at deterministic single-pass cost. On 42 contacts from five subjects, the per-contact Cramér–Rao lower bound for τ₁ is 16.2 ms, and the empirical cross-contact dispersion is 83.5 ms; both are internal, model-derived quantities, since no synchronised external timing reference was available. A two-layer rejection pipeline separates 19/19 valid contacts from 2/2 hardware faults; transfers to four held-out subjects (23/23) without retuning; attains an overall AUC of 0.878 on a five-class synthetic disturbance library—ramp and saturating-exponential remain acknowledged failure modes; and rejects 5/6 disturbance trials in a real-airflow stress session. Larger independent cohorts and externally synchronised timing validation remain parameters for future work. Full article

Laser powder bed fusion (LPBF) is a widely utilized metal additive manufacturing (AM) process for fabricating intricate geometries with high mechanical strength. However, achieving defect-free parts remains challenging due to complex thermodynamics and process variability. Component quality is primarily determined by mel-pool morphology, which depends on key process parameters such as laser power, scan speed, and layer thickness. Improper parameter selection causes defects like porosity (keyhole and lack of fusion), balling, and residual stresses, compromising structural integrity. Optimizing these parameters is crucial but difficult due to the multi-scale, multi-physics nature of the process, which traditionally relies on costly, time-intensive experimental trials. We present results from a data-driven approach using machine learning (ML) models to predict and optimize LPBF melt-pool characteristics, reducing reliance on trial-and-error experimentation. We find that laser power and scan speed predominantly influence the melt-pool formation. Higher scan speeds produce more favorable melt pools, whereas excessive laser power at low scan speeds leads to deep keyhole defects. To predict and classify melt pools efficiently, several ML models are deployed, including logistic regression, decision trees, ensemble learning, and fully connected neural networks. The standard neural network achieved the highest cross-validated macro-F1 score of 0.978 ± 0.014, while the weighted neural network achieved the highest recall for the rare optimal melt-pool class, 0.967 ± 0.050. These findings show that class-weighted learning provides a recall-oriented strategy for identifying suitable LPBF process windows, while avoiding overreliance on single train-test split performance. The findings underscore the effectiveness of ML in accurately classifying LPBF melt pools to rapidly identify optimal process parameters. Full article

Behavior change technologies are increasingly deployed in everyday contexts where perception errors are difficult to avoid. Such errors can undermine user trust and long-term engagement, while purely technical approaches to error elimination are often impractical in open-world environments. This study proposes a fault-tolerant design that translates algorithmic uncertainty into anthropomorphic expressions of vulnerability. By decoupling task-outcome feedback from internal confidence states, an embodied agent communicates uncertainty through a five-level nonverbal framework comprising posture, facial expression, and motion intensity. The approach was implemented in an interactive waste-sorting system and examined through a three-week field study in a semi-public university corridor. Three feedback strategies were compared: an outcome-only baseline, a persistently confident agent, and an adaptive agent whose vulnerability expression varied according to a transformed confidence signal. The findings suggest differences in user behavior across conditions. Under the adaptive condition, user sorting accuracy exhibited a fluctuation–recovery pattern during the final deployment phase, whereas accuracy under the confident-agent condition showed a declining trend. Correct-trial stay durations were shorter under the adaptive condition, consistent with the formation of a more streamlined interaction routine. In contrast, observations from error cases were limited by the small number of misclassification events. Due to the exploratory nature of the study, the small sample size of the questionnaire and the sequential deployment structure, the results should be considered preliminary evidence. Nevertheless, the findings suggest that expressing vulnerability in an anthropomorphic way may be a promising approach for communicating uncertainty in behavior change systems. Full article

Oil-in-water nanoemulsions (NE) can increase the water solubility of plant-derived bioactive molecules as drug candidates. Machine learning-guided NE design can prevent the expensive, time-consuming trial-and-error process. NE composition data was aggregated into a dataset; a predictive machine learning model identified improved self-nanoemulsifying system formulations (olive oil and combinations of Tween 20, Tween 80, glycerol, and soy lecithin). Predictive power was assessed by estimating successful self-nanoemulsification through transmittance and Dynamic Light Scattering. NEs were loaded with an organic extract containing anacardic acid. Encapsulation efficiency was measured by UHPLC. Antiproliferative activity was evaluated on human hepatic cancer (Hep G2) and normal-like human embryonic kidney (HEK-293) cell lines. The model showed an accuracy of 81%. The best-performing formulation, consisting of 10% olive oil, 60% Tween 20, and 30% glycerol, exhibited an average particle size of 162.8 ± 26 nm, a polydispersity index of 0.234 ± 0.03, and high encapsulation efficiency. While HEK-293 cells remained unaffected, naked NE exhibited a selective growth inhibitory effect on the Hep G2 cell line. Loaded NE increased the cytotoxic effect on Hep G2 (IC50: 5.9 ± 1.27 µM). Machine learning-guided NE formulation was a successful carrier for the plant extract and the molecule of interest, providing a proof of concept for how artificial intelligence can shorten the development pipeline for NE drug delivery systems. Full article

Accurate discrete element method (DEM) modelling of mature peanut plants is essential for simulating peanut harvesting, pod detachment, and harvest-loss formation. However, existing peanut DEM models are usually simplified as isolated pods, rigid cylindrical particles, or partial stem–pod structures, which limits their ability to represent the flexible deformation of vines and pod stalks and the fracture behaviors at the pod–pod stalk junction. In this study, a DEM-based flexible plant model was developed for mature peanut plants. The geometric dimensions, contact parameters, and mechanical properties of peanut pods, pod stalks, and stems were measured through physical experiments. The Hertz–Mindlin model was used for non-bonded contacts, whereas the Hertz–Mindlin with Bonding model was adopted to represent the flexible connections among plant organs and the fracture behaviors of the pod–pod stalk junction. The main DEM parameters were calibrated using Plackett–Burman screening, steepest ascent experiments, and central composite design. The results showed that the tangential stiffness per unit area and tangential critical stress at the pod–pod stalk junction were the dominant factors affecting pod detachment force. The optimized parameter combination was a tangential stiffness per unit area of 4.738 × 10⁵ N/m³ and a tangential critical stress of 9.350 × 10⁵ Pa, corresponding to a simulated tensile force of 6.73 N. Model validation was performed by comparing peanut harvesting simulations with field trials. The relative error of pod loss rate between simulation and field measurement was less than 7.55%, and the t-test result indicated no significant difference between the two datasets (p > 0.05). These results demonstrate that the proposed flexible peanut plant model can effectively characterize pod–pod stalk separation and can provide a reliable DEM modelling basis for peanut harvesting process analysis and equipment optimization. Full article

Friction stir welding (FSW) began as a fairly specialized joining method, but over the past three decades it has evolved into something considerably more versatile, a manufacturing platform that now handles complex multi-material assemblies and solid-state additive processes with reasonable reliability. This review follows this evolution, paying particular attention to friction stir additive manufacturing (FSAM) and the persistent difficulties that arise when joining dissimilar systems, such as aluminum to steel or metals to polymers, where the fate of the joint is largely decided by how well the intermetallic compounds are kept under control. Machine learning, artificial intelligence, and high-fidelity numerical models are reducing the reliance on trial-and-error that once dominated parameter selection and defect prediction, bringing FSW closer to the operating principles of Industry 4.0. Hybrid variants, including ultrasonically assisted and underwater FSW, also receive attention here, as they offer researchers finer control over heat generation and plastic flow than the standard process allows. Throughout the study, microstructural observations are directly connected to mechanical results, with the aim of analyzing the current state of solid-state manufacturing and identifying the questions that most urgently need answering. Full article

In casting processes, mechanical properties such as hardness are highly sensitive to both chemical composition and process parameters, making parameter design a complex and uncertain task during the embodiment stage of engineering design. Conventional trial-and-error-based approaches are often costly, time-consuming, and impractical in industrial environments. To address these challenges, this study proposes an optimized fuzzy artificial neural network (FANN)-based decision-support approach for hardness-oriented parameter design in a casting process. The developed model uses chemical composition variables, including carbon, silicon, manganese, phosphorus, sulfur, chromium, copper, and tin, together with process parameters such as casting temperature and casting time as inputs, while Brinell hardness is considered as the output. A dataset consisting of 170 experimental casting samples was employed; 128 samples were used for model development and hyperparameter selection, and 42 samples were reserved as an independent final test set. The proposed model was implemented as a scaled direct FANN weighted ensemble, in which fuzzified input variables were used to predict standardized continuous hardness values. A total of 300 FANN configurations were evaluated using five-fold cross-validation, and the five best-performing configurations were combined through RMSE-based weighted ensemble averaging. The final model was compared with Random Forest, Linear Regression, Ridge Regression, and SVR-RBF models using MSE, RMSE, MAE, R², MAPE, normalized RMSE, and ±5% prediction success rate. The results showed that the optimized FANN ensemble achieved the lowest mean RMSE in the full-data five-fold cross-validation analysis, slightly outperforming the Random Forest benchmark. In the independent final test set, Random Forest produced the lowest prediction error, whereas the proposed FANN ensemble remained competitive and achieved the same ±5% prediction success rate as Random Forest, Linear Regression, and Ridge Regression. Furthermore, a target-hardness case study demonstrated that the proposed approach could identify candidate casting conditions very close to a desired hardness level, with the nearest prediction reaching 202.985 HB for a target value of 203 HB. These findings indicate that the proposed FANN-based framework can serve not only as a hardness prediction model but also as a practical fuzzy decision-support tool for target-hardness-oriented parameter design in casting processes. Full article

The global agricultural sector faces the dual challenge of increasing productivity while mitigating environmental impacts caused by synthetic agrochemicals and massive agro-industrial waste. This review examines the transition to “Biostimulants 4.0,” a circular economy paradigm driven by the valorization of biomass residues into high-value biological inputs through nanotechnology and Artificial Intelligence (AI). Our analysis highlights that green extraction methods, specifically enzymatic hydrolysis, preserve bioactive integrity and reduce carbon emissions by up to 23.2 times compared to synthetic nitrogen production. Furthermore, waste-derived formulations and nanoscale smart-delivery systems dramatically enhance crop performance; for instance, chitosan nanoparticles can achieve up to a 471% increase in specific growth metrics through sustained-release pathways. To move the industry beyond empirical trial-and-error, the integration of AI-driven predictive models now achieves up to 87% accuracy in forecasting biostimulant efficacy. Finally, we contrast global regulatory frameworks and evaluate the monetization of biostimulant-driven carbon sequestration, capable of generating high-integrity credits priced up to $35 per tonne, as a critical economic pathway to accelerate commercial adoption and incentivize a resilient, decarbonized agricultural system. Full article

Accurate multiphase flow measurement in horizontal wells is fundamentally challenged by the antagonistic electrical responses of water and gas: Electrical Resistance Tomography (ERT) loses sensitivity to thin liquid films, while Electrical Capacitance Tomography (ECT) suffers signal saturation in conductive water, preventing either modality from covering the full operating envelope alone. This study proposes a physics-guided hybrid modeling framework that integrates multi-modal ERT/ECT sensing to achieve high-precision flowrate inversion. The framework utilizes a corrected multi-modal fusion algorithm, achieving a liquid holdup MAPE of 2.5 ± 0.5% representing a nearly two-fold improvement over the best single-modality system (Direct ERT, 4.5%). For velocity estimation, an optimized cross-correlation method yields results with ± 3.0% error, incorporating multi-sensor and multi-sequence fusion. A key finding is that deep neural networks exhibit Architectural Phase Specialization: multi-branch architectures (MB-DNN) perform strongly on localized, heterogeneous liquid structures (2.0% liquid error), whereas fully-connected architectures (FC-DNN) excel at capturing the global patterns of the continuous gas core (1.2% gas error). By hybridizing a calibrated drift-flux physical model with these phase-specialized DNNs, the framework achieves overall averaged errors of 1.8% for gas and 1.5% for liquid across the full experimental envelope. The proposed framework was evaluated on 444,313 experimental samples and subsequently validated in a three-month industrial trial at the Puguang gas field under extreme conditions (26 MPa, 80 °C), where it maintained a prediction error of ± 2.3%. This work establishes a scalable, physically consistent paradigm for intelligent hydrocarbon production monitoring. Full article

Ceramic additive manufacturing offers strong potential for fabricating geometrically complex and application-specific components, yet achieving reliable dimensional fidelity remains challenging because dimensional deviation is governed by highly coupled material, process, thermal, and environmental factors. To address this problem, this study proposes an uncertainty-aware computational framework for dimensional error prediction in ceramic 3D printing under variable material and process conditions. The contribution is positioned as a system-level integration of established learning, uncertainty estimation, calibration, and reliability-interpretation components within a ceramic additive manufacturing dimensional-error prediction workflow, rather than as a fundamental methodological breakthrough. The validation is conducted using the publicly available Ceramic 3D Printing Process Control Dataset, a 1000-sample tabular dataset, and the resulting findings are therefore interpreted as dataset-specific computational evidence rather than direct proof of industrial deployment readiness. The methodology begins with a structured data-driven preprocessing pipeline that transforms the Ceramic 3D Printing Process Control Dataset into a multi-condition feature space through data cleaning, one-hot material encoding, min–max normalization, and engineered descriptors capturing extrusion–speed balance, thermal gradients, cooling intensity, deposition density, and material-conditioned interactions. A multi-branch deep computational architecture is then developed to encode material, process, thermal-environmental, and engineered-feature streams separately, followed by adaptive cross-condition fusion to learn nonlinear dependencies across ceramic printing regimes. To improve reliability beyond deterministic regression, the framework jointly models aleatoric and epistemic uncertainty and incorporates calibration refinement to align predictive confidence with observed error behavior, thereby enabling preliminary reliability-oriented interpretation of stable and high-risk operating conditions. Experimental results demonstrate that the full model achieves the best overall within-dataset performance, with a test MAE of 0.0118, RMSE of 0.0172, $R^2=0.999$, MAPE of 1.74%, calibration error of 0.003, PICP of 0.996, reliability score of 0.992, and a stable prediction rate of 98.7%. Although these values indicate strong predictive behavior under the current structured dataset, the exceptionally high $R^2$ should be interpreted cautiously because external experimental validation, larger measured datasets, and cross-machine ceramic printing trials are still required. These findings show that the proposed framework provides an effective system-level computational strategy for dataset-specific reliability-aware dimensional quality prediction in ceramic additive manufacturing and offers a preliminary data-driven foundation for uncertainty-aware intelligent process optimization. Full article

Background: Electroencephalographic (EEG) functional connectivity analysis requires multiple signal-processing, source-modelling, and statistical steps that can limit its adoption in clinician-led randomised controlled trials (RCTs). NeuroStat was developed as a prototype research tool to integrate this workflow; formal usability validation with clinician end-users has not yet been conducted. Methods: NeuroStat is an open-source Python/PyQt6 desktop application that integrates automated artefact removal (a Generalised Eigenvalue Decomposition for Artefact Identification [GEDAI] pathway and a traditional Artefact Subspace Reconstruction (ASR)/Independent Component Analysis (ICA)/ICLabel pathway), boundary element model (BEM) source localisation using the Desikan–Killiany atlas (68 cortical regions), Phase Lag Index (PLI) connectivity estimation across five canonical frequency bands, and RCT-oriented statistical analysis. Evaluation separated sensor-space and source-space claims: a sensor-level simulation (repeated across five independent random seeds) tested preprocessing robustness, a repeated source-space simulation tested recovery of a known cortical parcel-pair contrast after forward projection and inverse reconstruction, a PhysioNet benchmark tested posterior Desikan–Killiany alpha PLI in 20 healthy adults, and an illustrative application to 20 sessions from a published chiropractic RCT demonstrated real-world workflow applicability. Results: In the sensor-level simulation benchmark, the Traditional pathway achieved a mean absolute error of $0.168\pm 0.017$ PLI units and root mean squared error of $0.219\pm 0.045$ (mean ± SD across five independent random seeds) across all artefact conditions. In the source-space simulation, reconstructed alpha PLI for the known bilateral lateral-occipital parcel pair exceeded anterior control edges across 60 repeated condition runs (mean known-control difference = 0.105 PLI units, 95% CI 0.096–0.114; $t\left(59\right)=22.61$, $p<0.001$). In the PhysioNet source-space benchmark, posterior Desikan–Killiany alpha PLI was higher during eyes-closed than eyes-open rest (Cohen’s $d=0.85$, $p=0.001$; 16/20 subjects showing the expected direction) after ICLabel-enabled preprocessing. In the pilot RCT application, all 20 sessions completed processing without manual intervention, with default-mode network alpha PLI showing a pre-to-post change of +0.071 in the intervention group versus +0.015 in the active control group. Conclusions: NeuroStat integrates preprocessing, source-space construction, connectivity estimation, and statistical reporting within a parameter-logged desktop workflow for EEG functional connectivity studies. Current evidence supports initial technical feasibility, sensor-level preprocessing robustness for one pathway in controlled simulations, source-space recovery of a known parcel-level contrast, source-space sensitivity to an expected posterior alpha resting-state contrast, and error-free processing across 20 real RCT sessions in a pilot workflow demonstration. Formal usability testing, test–retest reliability analysis, participant-specific source-model validation, and clinical-population validation remain necessary before clinician-facing or trial-deployment claims can be made. Full article