Search Results (1,112)

In this study, parameter estimation-assisted sensorless control methods are proposed for compressor motors. As sensorless control strategies, rotating high-frequency injection (RHFI), pulsating high-frequency injection (RHFI), and an adaptive-gain sliding mode observer (AG-SMO) are employed. During startup, HFI-based methods are utilized, whereas AG-SMO is activated under steady-state operating conditions. To mitigate parameter variations and inverter nonlinearities, Adaline Neural Network (ANN), Recursive Least Squares (RLS), and Extended Kalman Filter (EKF) algorithms are integrated for the real-time estimation of stator resistance and dead-time voltage. The proposed framework is validated through both simulation and experimental studies on a 30 W, 20 V interior permanent magnet motor commonly used in compressor applications. The results demonstrate that sensorless control algorithms alone provide robust operation, while the incorporation of parameter estimation effectively eliminates stability issues and ensures reliable transitions from low to high speeds. Comparative analysis reveals that ANN has a simple structure, RLS achieves faster convergence, and EKF provides smoother estimates under noisy conditions. Overall, the integration of sensorless control algorithms with ANN/RLS/EKF-based parameter estimation and dead-time compensation offers a cost-effective and reliable solution for high-performance compressor applications. Full article

Support vector regression (SVR) is a well-established kernel-based method for nonlinear regression. However, standard SVR formulations minimize absolute-error losses, which are not consistent with the scale-free, relative-accuracy criteria prevalent in forecasting and industrial applications, where uncertainty is typically expressed as a percentage. This study proposes a unified SVR framework that incorporates percentage-error loss functions and symmetry constraints. Four specific variants are introduced: $\epsilon$-SVR with mean absolute percentage error (MAPE), its symmetric kernel extension, least-squares SVR (LS-SVR) with root mean square percentage error (RMSPE), and its symmetric counterpart. Each variant is formulated in primal, Lagrangian, and dual forms using Karush–Kuhn–Tucker analysis. The principal structural finding is that percentage scaling results in sample-dependent box constraints for $\epsilon$-SVR and a target-weighted diagonal regularization matrix for LS-SVR. In contrast, symmetry modifies only the kernel matrix, leaving the optimization structure unchanged. Convexity and the representer theorem are preserved in all cases. Experiments are conducted on three cross-sectional datasets (Boston Housing, Diabetes, and Energy Efficiency) and a time-series dataset on Victorian electricity demand. Evaluation utilizes three metrics (MAPE, MASE, and MAAPE), 95% bootstrap confidence intervals, and paired Wilcoxon tests, and compares performance against percentage-error-native baselines (weighted-MAE, quantile regression, and log-target SVR), classical $\epsilon$-SVR, Random Forest, and XGBoost. An additional reflection-based experiment assesses the symmetric-kernel variants. The results demonstrate that optimizing for percentage error consistently improves the targeted metric without adversely affecting absolute-error metrics. Full article

The leaf area index (LAI) is a key parameter reflecting vegetation canopy structure and growth status. This study systematically compares the performance of spectral and texture features derived from Sentinel-2A imagery for LAI retrieval in winter wheat and maize. Multiple vegetation indices and gray-level co-occurrence matrix (GLCM) texture features were extracted, and three types of texture indices—Normalized Difference Texture Index (NDTI), Ratio Texture Index (RTI), and Difference Texture Index (DTI)—were constructed. Modeling was performed using Partial Least Squares Regression (PLSR) and Gaussian Process Regression (GPR). Results show that red-edge vegetation indices and mean texture features (e.g., NDVI_M) are robust predictors for both crops, with correlation coefficients reaching 0.87 for winter wheat and 0.83 for maize. Texture indices further enhance the representation of canopy structural information; the optimal NDTI achieved |R| > 0.88 for both crops, though the specific feature pairs were crop-specific. Using the proposed two-stage feature optimization strategy combined with GPR, the LAI estimation accuracy for winter wheat reached R² = 0.87 with RMSE = 0.41 on an independent test set, while for maize the accuracy was R² = 0.75 with RMSE = 0.38. The strategy significantly improved accuracy for winter wheat (uniform canopy) but yielded limited gains for maize (heterogeneous canopy), largely due to differences in canopy architecture. This study demonstrates that integrating multi-dimensional features with nonlinear modeling enhances LAI estimation accuracy. By providing a side-by-side comparative evaluation across two contrasting crop canopies, this study underscores the necessity of crop-adaptive feature selection and modeling strategies. The findings offer practical guidance rather than a universal model for large-scale crop monitoring in agricultural remote sensing. Full article

Accurate modelling of nonlinear dynamical systems remains a fundamental challenge in control engineering, particularly in applications characterized by strong nonlinearities, uncertainty, and varying operating conditions such as anti-lock braking systems (ABSs). Although neural networks are widely used for nonlinear system identification, their performance is often limited by correlated input features, poor numerical conditioning, and reliance on computationally demanding nonlinear optimization. This paper proposes a novel neural network modelling framework that integrates improved almost-orthogonal functional input transformation with a linear-in-parameters structure. The proposed approach systematically constructs a nonlinear feature space in which correlations between basis functions are explicitly controlled through a perturbation-based near-orthogonality mechanism, resulting in improved conditioning of the regression matrix and enabling stable least-squares-based parameter estimation. The method is formulated for a general class of nonlinear discrete-time systems and experimentally validated on an Inteco ABS laboratory setup, where wheel slip dynamics are identified using measured wheel speeds and braking torque. The obtained results demonstrate improved modelling accuracy, increased robustness to measurement noise, non-Gaussian disturbances, and parameter drift, as well as lower computational complexity compared with conventional multilayer perceptron and polynomial-based models. These findings suggest that structured feature generation may improve the reliability of data-driven models and indicate potential applicability of the proposed framework for real-time and control-oriented applications in complex dynamical systems. Full article

Conventional Interferometric Synthetic Aperture Radar (InSAR)-based sub-canopy topography retrieval models often suffer from insufficient characterization of scattering mechanisms, strong nonlinearity, and poor parameter convergence. To address these issues, this study proposes an improved Interferometric Water Cloud Model (IWCM) that integrates Fractional Vegetation Cover (FVC) to retrieve sub-canopy topography. The proposed method accounts for both volume and ground scattering and introduces FVC as a constraint to improve the model’s physical realism. In addition, this study utilizes InSAR observations derived from TanDEM-X dual-baseline data, which enhance the information content of the measurements by providing multiple independent interferometric observations. A two-step nonlinear least squares optimization strategy is further employed to enhance the convergence of model parameter estimation. The proposed method was validated in the forested region of Genhe City, Inner Mongolia. Airborne LiDAR-derived surface elevation data were used for assessment. The results indicate that, compared with the original InSAR-derived Digital Elevation Model (DEM), the accuracy of the retrieved sub-canopy topography improves by 39.04%. Furthermore, compared with the previously proposed Normalized Difference Vegetation Index (NDVI)-based method, under their respective optimal initial extinction coefficient conditions (${\mu }_0$), an additional accuracy improvement of 11.69% is achieved. These results demonstrate that the proposed method effectively reduces the influence of the forest canopy on interferometric phase observations and improves the capability of sub-canopy topography reconstruction in complex forest environments. The method also provides a new approach for dual-baseline and multi-baseline InSAR-based sub-canopy topography retrieval. Full article

To address the main challenges in thickness estimation of SiC epitaxial layers from infrared reflectance spectra, including refractive index dispersion, multi-beam interference, and spectral uncertainty, this study develops a physics-constrained inversion framework for reflectance spectrum-based analysis. For the measured spectra, Savitzky–Golay filtering is first used to suppress spectral noise, and Gaussian fitting is then employed to improve the localization of interference extrema. The Sellmeier equation is introduced to characterize refractive index dispersion, and the layer thickness is obtained together with the dispersion parameters through nonlinear least squares fitting. To account for spectra affected by higher-order internal reflections, a multi-feature confidence-based identification strategy is further constructed, and an adaptive filtering procedure is introduced for multi-beam interference correction. A Monte Carlo perturbation analysis with ±0.1% peak perturbations and Gaussian noise is additionally performed to assess the robustness of the inversion results. Using SiC datasets measured at two incident angles, the proposed framework reduces the inter-angle deviation of the thickness estimates from 1.14% to 0.08% after multi-beam correction. The results support the effectiveness and robustness of the proposed workflow for the main SiC application scenario considered in this study. In addition, silicon wafer spectra are included as a supplementary transfer test to examine whether the multi-beam identification and correction strategy can be applied beyond the SiC example, rather than as a comprehensive cross-material validation of the framework. Full article

The work environment in automated laboratories and industrial sites exposes workers to the risks associated with chemical gas and vapor leaks caused by unforeseen incidents. Such leaks may result in severe health hazards as well as damage to equipment or infrastructure at the leak site. Therefore, the development of systems capable of early detection and highly accurate localization of chemical leaks is of high importance for occupational safety. In this work, a low-cost, portable sensor node based on the Internet of Things (IoT) is proposed for the detection and localization of gas and chemical leaks in indoor environments. The sensor node features a modular design that enables flexible integration and replacement of gas and environmental sensors depending on the target application. In addition, the system includes an ultra-wideband (UWB)-based positioning and tracking unit, allowing operation across multiple indoor zones. The main contribution of this work lies in the combined integration of (i) multi-sensor-based environmental event detection and prediction and (ii) high-precision location within a dynamic multi-zone tracking architecture. The system automatically selects the most relevant anchors in each zone and applies trilateration and least-squares estimation, enhanced by Kalman filtering techniques. In particular, an extended Kalman filter (EKF) and an unscented Kalman filter (UKF) are employed, with sensor fusion incorporating inertial measurement unit (IMU) data to mitigate the effects of on-line-of-sight (NLoS) conditions and signal degradation caused by obstacles. Experimental results demonstrate that both the EKF and UKF significantly reduce positioning errors and improve tracking stability compared to baseline methods under challenging indoor conditions. The UKF shows superior performance in highly nonlinear scenarios. A quantitative evaluation using manually surveyed reference points showed that the UKF achieved the best overall performance, with a mean error of 39.72 cm and an RMSE of 43.03 cm. These findings confirm the effectiveness of Kalman filter-based sensor fusion for reliable indoor positioning and highlight the suitability of the proposed system for real-time safety monitoring applications. Full article

Rapid and non-destructive nitrogen diagnosis in fruit orchards is critical for precision fertilization management and crop yield optimization. This study develops and evaluates a practical hyperspectral preprocessing pipeline for leaf nitrogen estimation in Korla fragrant pear (Pyrus sinkiangensis Yü), a commercially important cultivar in southern Xinjiang, China. Hyperspectral reflectance data and corresponding nitrogen measurements were collected from mature leaves of slender-spindle-trained trees. Four preprocessing strategies, comprising multiplicative scatter correction (MSC), wavelet threshold denoising, and their sequential combinations, were systematically compared to assess their effects on spectral information retention and model performance. The successive projections algorithm (SPA) was applied for characteristic wavelength selection, and four regression models, including linear regression (LR), partial least squares regression (PLSR), random forest (RF), and XGBoost, were constructed and evaluated. Results demonstrated that combined preprocessing strategies outperformed single-method approaches, and that preprocessing order significantly influenced predictive accuracy. Nonlinear models consistently outperformed linear models, confirming a pronounced nonlinear relationship between hyperspectral features and leaf nitrogen content. The MSC, followed by wavelet threshold denoising, combined with SPA and XGBoost, achieved the best predictive performance, with R² = 0.754, RMSE = 0.179 mg/g, and RPD = 2.017 on the test set. These findings provide a methodological reference for hyperspectral nitrogen monitoring and preprocessing workflow design under controlled conditions, with potential for further validation in field applications. Full article

Thermal infrared remote sensing offers a cost-effective means of regional geothermal reconnaissance, yet a fundamental challenge remains: isolating the weak geothermal surface signal (typically 1–3 °C) from dominant surface noise introduced by seasonal temperature cycles (annual amplitude > 20 °C), topographic variability, land cover heterogeneity, and irregular cloud-affected satellite sampling. Conventional single-scene or arithmetic-mean approaches are highly susceptible to these confounding factors and frequently produce pseudo-anomalies that obscure genuine geothermal targets. To overcome this limitation, we propose a physics-based time-series framework in which a nonlinear annual temperature variation model, T(t) = T0 + A·sin(2πt/τ + φ), is fitted to multi-temporal Landsat 8 thermal infrared data via the Levenberg–Marquardt algorithm. Applied to ~50 cloud-free scenes (2021–2022) processed on the Google Earth Engine over the Shanxi Graben System, northern China, the model simultaneously retrieves the background temperature parameter T0 and seasonal amplitude A—two physically interpretable quantities that encode distinct geothermal signatures more robustly than simple temporal statistics. Sub-regional corrections for the elevation (−4 °C/100 m above 800 m), aspect (R² > 0.95 in piecewise linear segments), and slope further suppress topographic pseudo-anomalies prior to anomaly extraction. Over known high-temperature geothermal fields (Tianzhen and Yanggao; >100 °C at 100 m depth), the method reveals clear T0 offsets of +1–2 °C (3–5% relative) and amplitude deficits of ~2 K (5–10% relative) relative to the background, with model-fitted T0 values averaging ~2 °C higher than arithmetic means due to the correction for seasonal sampling bias. Combined with 5 km fault-proximity buffers, extracted anomaly zones align well spatially with known geothermal sites and major structural corridors of the graben system. However, deeper low-temperature systems (45–50 °C at 300–500 m depth) produce ambiguous signals below the ~1.5 K detection threshold, indicating inherent limitations for deeply buried resources. The fully reproducible, training-data-free workflow is implementable via open satellite archives and cloud computing platforms, making it a transferable low-cost tool for structurally controlled geothermal reconnaissance across extensional basins worldwide. Full article

In networked sensing systems, nonlinear state monitoring and soft sensing are widely used to reconstruct key variables that cannot be directly measured in real time. For such nonlinear estimation tasks, the Extended Kalman Filter (EKF) is a commonly used recursive method. However, the conventional EKF neglects higher-order truncation terms during first-order Taylor linearization. As the nonlinearity increases, these neglected terms may accumulate and degrade filtering accuracy, and even lead to divergence in some cases. In addition, the statistical influence of the remainder terms and the correlation between prediction and measurement errors are usually ignored. To address these issues, this paper proposes an Extended Kalman Filter with remainder terms considering correlations (REKF). The proposed method replaces the higher-order terms in the Taylor expansion with remainder terms and identifies them incrementally by using least squares, thereby improving the EKF update process. A higher-order filtering framework is then constructed to jointly estimate the system state and the remainder-related random variables while accounting for the induced error correlation. Numerical simulations on typical nonlinear models demonstrate that the proposed REKF achieves better estimation performance than the conventional EKF. In this work, the proposed REKF is mainly developed for nonlinear estimation problems in which the dominant challenge arises from strong nonlinearity in the state evolution, while the measurement update is treated in a locally linearized EKF form. The results show that incorporating higher-order remainder information can effectively improve nonlinear state estimation for state monitoring and soft sensing tasks. Full article

We present an efficient incremental SLAM back-end that reduces computation while preserving accuracy close to that of a full incremental Gauss–Newton (GN) solver across benchmark pose-graph datasets. The method combines information-guided gating (IGG), which uses a log-determinant-based information surrogate to decide when broad updates are warranted, with selective partial optimization (SPO), which confines multi-iteration GN updates to variables that remain affected after each iteration. We provide a local perturbation analysis, showing that, under standard regularity conditions, the proposed approximation tracks full GN within a threshold-controlled neighborhood and recovers the same local minimizer and asymptotic convergence rate when the effective approximation error vanishes asymptotically. Experiments on benchmark pose-graph SLAM datasets show competitive final and increment-averaged accuracy together with substantial reductions in update and solve FLOPs. These results support IGG-SPO as a practically promising SLAM back-end for robots operating under limited onboard computational resources. Full article

The Soybean aphid (Aphis glycines) is a destructive pest that threatens soybeans. In order to develop green and effective control strategies, we propose an EQPAL epidemic model that integrates four developmental stages (1st–2nd stage nymphs, 3rd stage nymphs, 4th stage nymphs, and adults) and a ladybug (Harmonia axyridis) compartment. This model achieves green pest control by artificially releasing a natural enemy of soybean aphids to prey on adult soybean aphids. We analyzed the dynamic behavior of the model and derived the basic reproduction number ${\mathcal{R}}_0$. Using field monitoring data from Changchun City, Jilin Province, China in 2025, the segmented nonlinear least squares method was used for parameter estimation and fitting, resulting in an overall determination coefficient of $R^2=0.8204$. The numerical simulation results showed that the release of ladybugs significantly reduced the density and peak value of soybean aphid adults, and the predation rate $\beta$, predation conversion rate c, and ladybug migration rate $\omega$ were identified as key regulatory parameters. In addition, a cost–benefit analysis was conducted to determine the most cost-effective control measures. Full article

Accurate and trustworthy prediction of lithium-ion battery aging remains challenging due to multi-mechanistic degradation, cell-to-cell variability, and distribution shift between laboratory calibration and deployment. Fractional-order models have been proposed to capture long-memory effects in electrochemical systems; however, it remains unclear when such memory is empirically identifiable and beneficial within the common prognostics abstraction of state-of-health (SOH) versus cycle index. This work develops a fully reproducible computational pipeline for mechanistic battery aging based on a Caputo fractional differential equation (FDE) and evaluates its cross-cell generalization on open NASA cycling data. Parameters are identified using bounded robust nonlinear least squares and validated under a strict transfer protocol: calibration on cells B0005/B0006 and evaluation on held-out cells B0007/B0018 without refitting. The fractional model is benchmarked against a classical ODE surrogate, an ECM-inspired resistance-proxy baseline, and one-step-ahead machine-learning predictors. Uncertainty quantification is performed via parameter bootstrap and subsequently calibrated using conformal correction to target nominal coverage under transfer. Results show that the fractional order tends to collapse toward the integer-order limit (α → 1) in this dataset, indicating limited evidence of additional long-memory at the SOH-versus-cycle level under the considered protocol, while robust identification remains essential for stability. Calibrated prediction intervals achieve near-nominal coverage on held-out cells, highlighting the importance of UQ calibration under cell-to-cell shift. The proposed scripts and environment specifications enable direct replication and facilitate future extensions to stress-aware fractional models and hybrid physics–ML approaches. Full article

To address the limited accuracy of power demand prediction for hybrid electric vehicles under complex and dynamic driving conditions, this paper proposes a hybrid prediction approach based on the cascade correction of Long Short-Term Memory networks and Least Squares Support Vector Machines (LSTM-LSSVM-CC). The proposed method adopts a stage-wise modeling framework that exploits the least-squares optimality of LSSVM for low-frequency steady-state signals and the dynamic compensation capability of LSTM for high-frequency non-stationary residuals, thereby achieving complementary feature representation in the frequency domain. Specifically, an LSSVM is first used to construct a baseline regression model that captures stationary components, followed by an LSTM network that performs deep temporal modeling of the residual sequence to correct nonlinear prediction errors. Extensive experiments conducted on three standard driving cycles—CLTC-P, WLTP, and UDDS—demonstrate that the proposed model consistently outperforms conventional methods including LSSVM, RNN, ELMAN, and Random Forest in multi-step predictions, achieving an average RMSE reduction of 28–52% and maintaining correlation coefficients (R²) between 0.87 and 0.99. Particularly under highly dynamic and abrupt load conditions, the model exhibits superior real-time performance and stability while significantly mitigating cumulative prediction errors. These results demonstrate that the proposed LSTM-LSSVM-CC model achieves robust modeling performance of non-stationary time series while balancing prediction accuracy and computational efficiency, providing an effective technical foundation for hybrid vehicle energy management optimization and offering a transferable theoretical framework for time-series prediction in complex systems. Full article

To improve performance for automatic carrier landing under complex wind disturbances, an active anti-disturbance control method integrating predefined-time control, disturbance observation, and online disturbance prediction is proposed. A nonlinear model carrier-based unmanned aerial vehicle (UAV) under a composite wind environment, including airwake, steady wind, and gusts, is modeled. A predefined-time sliding mode controller is then developed to ensure that the system errors converge within a user-specified time. To enhance active anti-disturbance performance, a predefined-time disturbance observer is designed for disturbance estimation, and an online prediction method based on recursive least squares with forgetting factor is introduced to predict disturbances and mitigate the lag caused by observation and UAV dynamics. Moreover, a predefined-time reference model is incorporated to avoid the exponential explosion problem. Simulation results demonstrate that, compared with the baselines, the proposed method reduces the maximum following error by 16.9–82.0% and the touchdown error by 53.4–84.1%. These results indicate that the proposed method can effectively enhance anti-disturbance performance and landing accuracy under complex wind environments. Full article