Machine Model Research Articles

Analysis of magnetic saturation effects in the squirrel cage induction generators

This work concerns an investigation on the analysis of the magnetic saturation effects in the three-phase squirrel cage induction generator which is considered as a main device in wind energy conversion systems. The magnetic saturation is considered as an important factor causing destructive effects on power qualities such as harmonics and distortion. Several approaches have been presented in the literature for the modeling of the electric machines considering magnetic saturation. The widely used and precise approach is the finite elements method which is particularly characterized by its high computational time. The novelty in this paper is that a state model has been developed for the healthy conditions of the three-phase squirrel cage induction generators considering the experimental variation of the magnetizing inductance in terms of the magnetizing current. Simulation and experimental tests are provided to extract some important signatures on stator voltages and currents. It will be deduced that the spectrum analysis of stator currents contains useful information on magnetic saturation. Experimental and theoretical results illustrate the consistency of this approach for the modeling and analysis of the squirrel cage induction generators considering the magnetic saturation.

Steady state stability assessment of voltage source converter in a DC microgrid under weak grid conditions

Traditionally, steady-state assessment involves analyzing numerous variables using Eigen analysis. This paper presents a decision support application for diagnosing the steady-state assessment of droop-controlled voltage source inverters in islanded microgrid operations or weak grid operations with reduced input attributes. This paper proposes an approach using feature extraction from the state space variables of the droop-controlled voltage source inverter (VSI). Photovoltaic (PV) and wind energy sources are considered with their stipulated power-delivering capability considered. To improve the generalization of the predictive model, preprocessing techniques are employed to eliminate data distortions. Dimensionality reduction is achieved through principal component analysis (PCA) applied to the steady-state variables. The evaluation of the VSI's steady-state stability is conducted utilizing support vector classification algorithm. To ascertain the reliability of the steady-state stability classification, an assessment of the support vector machine (SVM) model's performance is carried out, which includes the examination of metrics like the area under the curve (AUC) and the receiver operating characteristics (ROC) curve. The findings from the assessment of VSI's steady-state stability indicate a commendable level of performance, achieving an accuracy rate of 93.5%.

Particle swarm optimization-extreme learning machine model combined with the ADA boost algorithm for short-term wind power prediction

In our proposed approach, we integrate ADA boosting with particle swarm optimization-extreme learning machine (PSO-ELM) to enhance the accuracy of wind power estimation, addressing the inherent unpredictability and variability in wind energy. Initially, we refine the thresholds and input weights of the extreme learning machine (ELM) and then construct the PSO-ELM prediction model. ADA Boost is utilized to generate multiple weak predictors, each comprising a distinct hidden layer node. The PSO technique is then employed to optimize the input weights and thresholds for each weak predictor. The final forecast is attained by amalgamating and weighting the outcomes from each weak predictor using a robust wind power forecast model. Experimental validation utilizing data from Turkish wind turbines underscores the efficacy of our approach. Comparative analysis against contemporary techniques such as ensemble learning models and optimal neural networks reveals that our ADA-PSO-ELM model demonstrates superior accuracy and generalizability in predicting wind power output under real-world conditions. The proposed approach offers a promising framework for addressing the challenges associated with wind power estimation, thereby facilitating more reliable and efficient utilization of wind energy resources.

High precision state of health estimation of lithium-ion batteries based on strong correlation aging feature extraction and improved hybrid kernel function least squares support vector regression machine model

The state of health (SOH) of lithium-ion batteries plays a crucial role in maintaining the stability of electric vehicle systems. To address the issue of low accuracy in existing prediction models, this article introduces an enhanced grey wolf algorithm for optimizing the hybrid kernel least squares support vector regression machine used in lithium-ion battery SOH prediction. This research extracted four key health features from the raw data of each battery in the Cycle dataset, which is publicly accessible. Data preprocessing of health features involved Pearson correlation analysis and Hampel filtering techniques. The framework of least squares support vector regression constructs a hybrid kernel function of polynomial kernel function and radial basis function. The integration of differential evolution and the law of survival of the fittest into the grey wolf algorithm enhances its optimization ability. The improved grey wolf algorithm optimizes the parameters of the hybrid kernel least squares support vector regression machine, improving the accuracy and robustness of the model. After data validation, it is known that the optimal average absolute error value predicted by the model can reach 0.32 %. This indicates that the proposed method is effective and feasible.

Comparative study of teachable machine for forest fire and smoke detection by drone

Forests play a vital role in maintaining ecological equilibrium and serving as vital habitats for wildlife. They regulate global climate, safeguard soil and water resources, and provide crucial ecosystem services such as air and water purification, essential for human well-being and sustainable development. Forest fires wreak havoc on ecosystems and wildlife, emitting harmful pollutants, disrupting communities, and increasing the risk of erosion and landslides. Detecting forest fires through satellite imaging, aerial reconnaissance, and ground-based sensors is pivotal for early detection and containment, safeguarding human lives, wildlife, and preserving natural resources for future generations. Utilizing drones and deep learning (DL) algorithms can significantly enhance early fire detection and minimize their devastating impact. In this paper, we examine teachable machine, a Google tool for creating DL models. We compare the top model generated by teachable machine for fire and smoke detection to models obtained through transfer learning from established DL models in image recognition and computer vision (CV), such as VGG16, VGG19, MobileNet, MobileNetv2, and MobileNetv3. The results underscore the significance of employing the teachable machine model in specific fire and smoke detection scenarios.

Making a Better Logistic Regression Model Using Ensemble Learning

Abstract: Machine learning is a hot research topic in today's society and an important direction in the field of image classification research. Image classification is a supervised learning method used to classify images. There are many image classification algorithms that perform differently in different conditions. Paper focuses on improving the performance of image classification algorithms by using ensemble learning. Paper analyses the performance of logistic regression model and support vector machine model and then uses ensemble learning to increase the performance of logistic regression model. In the research work, both theoretical and empirical approaches were followed. For the theoretical approach a review of both secondary data as well as data based on results obtained by application on the tools is studied. Secondary data was acquired from the research articles, text books, journals, technical reports, published thesis, websites, e-journals, software tool manuals, conference proceedings and any other research articles published in the related domain. The empirical study was carried out on the set of experiments, using software tools. The results obtained from the experiments were analyzed for the finding of the research. The paper compares the results of three algorithms when tested on same dataset, in same environment and on same system. The final results of the research prove that ensemble techniques give best results and this type of learning is effective.

Symbolic Regression as a Feature Engineering Method for Machine and Deep Learning Regression Tasks

Abstract In the realm of machine and deep learning regression tasks, the role of effective feature engineering (FE) is pivotal in enhancing model performance. Traditional approaches of FE often rely on domain expertise to manually design features for machine learning models. In the context of deep learning models, the FE is embedded in the neural network's architecture, making it hard for interpretation. In this study, we propose to integrate symbolic regression (SR) as an FE process before a machine learning model to improve its performance. We show, through extensive experimentation on synthetic and 21 real-world datasets, that the incorporation of SR-derived features significantly enhances the predictive capabilities of both machine and deep learning regression models with 34-86% root mean square error (RMSE) improvement in synthetic datasets and 4-11.5\% improvement in real-world datasets. In an additional realistic use case, we show the proposed method improves the machine learning performance in predicting superconducting critical temperatures based on Eliashberg theory by more than 20% in terms of RMSE. These results outline the potential of SR as an FE component in data-driven models, improving them in terms of performance and interpretability.

Optimization of Early Detection of Tuberculosis Through Machine Learning Using Clinical Data: Development and Evaluation of Multilayer Perceptron and Extreme Learning Machine for Tuberculosis Classification

This research takes an innovative step in the fight against Tuberculosis (TB), one of Indonesia's prominent public health challenges, by developing and evaluating Multilayer Perceptron (MLP) and Extreme Learning Machine (ELM) models in machine learning for early detection of TB using clinical data. The main result of this study was the discovery that the MLP model, when applied without the Synthetic Minority Over-sampling Technique (SMOTE), achieved an impressive accuracy of 95.00%, signaling significant progress in TB early detection efforts. This discovery not only highlights the great potential of applying machine learning technology in improving the accuracy of TB diagnosis but also paves the way for the possible application of advanced technology in the health sector to deal with infectious diseases. This research illustrates how machine learning technology can be integrated into clinical practice to effectively detect TB cases at an early stage, thus enabling faster and more precise treatment, which can ultimately reduce the spread of the disease. This is particularly important given TB's significant impact on public health, especially in developing countries. The results also open up opportunities for further research into the application of machine learning techniques to other infectious diseases, promising a paradigm shift in the way we detect and manage various health conditions.

Prediction of peptide hormones using an ensemble of machine learning and similarity-based methods.

Peptide hormones serve as genome-encoded signal transduction molecules that play essential roles in multicellular organisms, and their dysregulation can lead to various health problems. In this study, we propose a method for predicting hormonal peptides with high accuracy. The dataset used for training, testing, and evaluating our models consisted of 1174 hormonal and 1174 non-hormonal peptide sequences. Initially, we developed similarity-based methods utilizing BLAST and MERCI software. Although these similarity-based methods provided a high probability of correct prediction, they had limitations, such as no hits or prediction of limited sequences. To overcome these limitations, we further developed machine and deep learning-based models. Our logistic regression-based model achieved a maximum AUROC of 0.93 with an accuracy of 86% on an independent/validation dataset. To harness the power of similarity-based and machine learning-based models, we developed an ensemble method that achieved an AUROC of 0.96 with an accuracy of 89.79% and a Matthews correlation coefficient (MCC) of 0.8 on the validation set. To facilitate researchers in predicting and designing hormone peptides, we developed a web-based server called HOPPred. This server offers a unique feature that allows the identification of hormone-associated motifs within hormone peptides. The server can be accessed at: https://webs.iiitd.edu.in/raghava/hoppred/.

Partial Discharge Signal Pattern Recognition of Composite Insulation Defects in Cross-Linked Polyethylene Cables

To investigate the pattern recognition of complex defect types in XLPE (cross-linked polyethylene) cable partial discharges and analyze the effectiveness of identifying partial discharge signal patterns, this study employs the variational mode decomposition (VMD) algorithm alongside entropy theories such as power spectrum entropy, fuzzy entropy, and permutation entropy for feature extraction from partial discharge signals of composite insulation defects. The mean power spectrum entropy (PS), mean fuzzy entropy (FU), mean permutation entropy (PE), as well as the permutation entropy values of IMF2 and IMF13 (Pe) are selected as the characteristic quantities for four categories of partial discharge signals associated with composite defects. Six hundred samples are selected from the partial discharge signals of each type of compound defect, amounting to a total of 2400 samples for the four types of compound defects combined. Each sample comprises five feature values, which are compiled into a dataset. A Snake Optimization Algorithm-optimized Support Vector Machine (SO-SVM) model is designed and trained, using the extracted features from cable partial discharge datasets as case examples for recognizing cable partial discharge signals. The identification outcomes from the SO-SVM model are then compared with those from conventional learning models. The results demonstrate that for partial discharge signals of XLPE cable composite insulation defects, the SO-SVM model yields better identification results than traditional learning models. In terms of recognition accuracy, for scratch and water ingress defects, SO-SVM improves by 14.00% over BP (Back Propagation) neural networks, by 5.66% over GA-BP (Genetic Algorithm–Back Propagation), and by 12.50% over SVM (support vector machine). For defects involving metal impurities and scratches, SO-SVM improves by 13.39% over BP, 9.34% over GA-BP, and 12.56% over SVM. For defects with metal impurities and water ingress, SO-SVM shows enhancements of 13.80% over BP, 9.47% over GA-BP, and 13.97% over SVM. Lastly, for defects combining metal impurities, water ingress, and scratches, SO-SVM registers increases of 11.90% over BP, 9.59% over GA-BP, and 12.05% over SVM.

7 Tesla magnetic resonance spectroscopic imaging predicting IDH status and glioma grading.

With the application of high-resolution 3D 7 Tesla Magnetic Resonance Spectroscopy Imaging (MRSI) in high-grade gliomas, we previously identified intratumoral metabolic heterogeneities. In this study, we evaluated the potential of 3D 7T-MRSI for the preoperative noninvasive classification of glioma grade and isocitratedehydrogenase (IDH) status. We demonstrated that IDH mutation and glioma grade are detectable by ultra-high field (UHF) MRI. This technique might potentially optimize the perioperative management of glioma patients. We prospectively included 36 patients with WHO 2021 grade 2-4 gliomas (20 IDH mutated, 16 IDH wildtype). Our 7T 3D MRSI sequence provided high-resolution metabolic maps (e.g., choline, creatine, glutamine, and glycine) of these patients' brains. We employed multivariate random forest and support vector machine models to voxels within a tumor segmentation, for classification of glioma grade and IDH mutation status. Random forest analysis yielded an area under the curve (AUC) of 0.86 for multivariate IDH classification based on metabolic ratios. We distinguished high- and low-grade tumors by total choline (tCho) / total N-acetyl-aspartate (tNAA) ratio difference, yielding an AUC of 0.99. Tumor categorization based on other measured metabolic ratios provided comparable accuracy. We successfully classified IDH mutation status and high- versus low-grade gliomas preoperatively based on 7T MRSI and clinical tumor segmentation. With this approach, we demonstrated imaging based tumor marker predictions at least as accurate as comparable studies, highlighting the potential application of MRSI for pre-operative tumor classifications.

Robustness analysis and prediction of topological edge states in topological elastic waveguides

Abstract Topological elastic waveguides constructed using acoustic topological insulators have garnered significant attention due to their exceptional wave modulation properties. While the existence of these edge states is guaranteed by topology, their robustness to defects is unclear. In this paper, topological edge states based on the acoustic pseudo-spin Hall effect are constructed, and the robustness of the topological edge states is quantitatively studied by analyzing displacement fields of phononic crystal (PnC) plates with various defects. Our robustness assessment considers nearly all possible defect scenarios, focusing on the influence of defects on two primary indicators: maximum displacement and its specific location on the PnC plate. The results indicate that the topological edge states formed by this structure are highly robust to defects with varying rotation angles, but exhibit limited robustness to defects of different dimensions or positions. Furthermore, a Light Gradient Boosting Machine (LightGBM) model is employed to predict the displacement along the wave transmission path in the presence of diverse lattice defects. The model emerges as an accurate predictor of displacement distribution changes, and thus can provide potential optimization strategies for topologically elastic waveguide-based energy harvesting systems and self-powered sensors.

Machine learning-enhanced molecular network reveals global exposure to hundreds of unknown PFAS.

Unknown forever chemicals like per- and polyfluoroalkyl substances (PFASs) are difficult to identify. Current platforms designed for metabolites and natural products cannot capture the diverse structural characteristics of PFAS. Here, we report an automatic PFAS identification platform (APP-ID) that screens for PFAS in environmental samples using an enhanced molecular network and identifies unknown PFAS structures using machine learning. Our networking algorithm, which enhances characteristic fragment matches, has lower false-positive rate (0.7%) than current algorithms (2.4 to 46%). Our support vector machine model identified unknown PFAS in test set with 58.3% accuracy, surpassing current software. Further, APP-ID detected 733 PFASs in real fluorochemical wastewater, 39 of which are previously unreported in environmental media. Retrospective screening of 126 PFASs against public data repository from 20 countries show PFAS substitutes are prevalent worldwide.

Thermal finite element modeling and simulation of a squirrel-cage induction machine

Finite element models of electrical machines allow insights in electrothermal stresses which endanger the insulation system of the machine. This paper presents a thermal finite element model of a 3.7 kW squirrel-cage induction machine. The model resolves the conductors and the surrounding insulation materials in the stator slots. A set of transient thermal scenarios is defined and measured in the machine laboratory. These data are used to assess the finite element model.

Machine learning evaluation of inequities and disparities associated with nurse sensitive indicator safety events.

To use machine learning to examine health equity and clinical outcomes in patients who experienced a nurse sensitive indicator (NSI) event, defined as a fall, a hospital-acquired pressure injury (HAPI) or a hospital-acquired infection (HAI). This was a retrospective observational study from a single academic hospital over six calendar years (2016-2021). Machine learning was used to examine patients with an NSI compared to those without. Inclusion criteria: all adult inpatient admissions (2016-2021). Three approaches were used to analyze the NSI group compared to the No-NSI group. In the univariate analysis, descriptive statistics, and absolute standardized differences (ASDs) were employed to compare the demographics and clinical variables of patients who experienced a NSI and those who did not experience any NSIs. For the multivariate analysis, a light grading boosting machine (LightGBM) model was utilized to comprehensively examine the relationships associated with the development of an NSI. Lastly, a simulation study was conducted to quantify the strength of associations obtained from the machine learning model. From 163,507 admissions, 4643 (2.8%) were associated with at least one NSI. The mean, standard deviation (SD) age was 59.5 (18.2) years, males comprised 82,397 (50.4%). Non-Hispanic White 84,760 (51.8%), non-Hispanic Black 8703 (5.3%), non-Hispanic Asian 23,368 (14.3%), non-Hispanic Other 14,284 (8.7%), and Hispanic 30,271 (18.5%). Race and ethnicity alone were not associated with occurrence of an NSI. The NSI group had a statistically significant longer length of stay (LOS), longer intensive care unit (ICU) LOS, and was more likely to have an emergency admission compared to the group without an NSI. The simulation study results demonstrated that likelihood of NSI was higher in patients admitted under the major diagnostic categories (MDC) associated with circulatory, digestive, kidney/urinary tract, nervous, and infectious and parasitic disease diagnoses. In this study, race/ethnicity was not associated with the risk of an NSI event. The risk of an NSI event was associated with emergency admission, longer LOS, longer ICU-LOS and certain MDCs (circulatory, digestive, kidney/urinary, nervous, infectious, and parasitic diagnoses). Machine learning methodologies provide a new mechanism to investigate NSI events through the lens of health equity/disparity. Understanding which patients are at higher risk for adverse outcomes can help hospitals improve nursing care and prevent NSI injury and harm.

Research on thermal characteristics modeling of CNC machine tools based on submodel method

To improve the accuracy of thermal characteristics analysis of CNC machine tools, a modeling method for the thermal characteristics of CNC machine tools based on submodel method is proposed in this paper. In this method, the thermal-structural coupling calculation of the feed system and spindle system is initially completed in ABAQUS to obtain temperature and deformation results of the submodels. Subsequently, User Define Function (UDF) in Fluent is used to extract the temperature information from the surface of the submodels. The obtained surface temperature data is then imported into the overall machine model for fluid-structure coupling heat transfer calculation. The model developed in this study takes into account factors such as the dynamic heat generation of the heat source, the cooling fan system, and the secondary heat source effect of the cutting fluid. To validate the approach, a thermal characteristics experiment was conducted, and the research results demonstrate that the thermal analysis model established in this paper exhibits both high accuracy and efficiency. During the 180 min of machine operation, the thermal displacement between the tool tip and the workpiece increased. The maximum thermal deformation of the machine tool tip was 40.83 [Formula: see text], primarily observed in the X and Y directions.

Monitoring of Low Chl-a Concentration in Hulun Lake Based on Fusion of Remote Sensing Satellite and Ground Observation Data

China’s northern Hulun Lake is a significant body of water internationally. The issue of eutrophication has gained prominence in recent years. The achievement of precise chlorophyll-a (Chl-a) monitoring is crucial for safeguarding Hulun Lake’s ecosystem. The machine learning-based remote sensing inversion method has been shown to be effective in capturing the intricate relationship between independent and dependent variables; however, it lacks a priori knowledge and is limited by the quality of remote sensing data sources. The relationship between independent and dependent variables can be more accurately simulated with the use of suitable auxiliary variables. Therefore, three machine learning models—random forest (RF), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost)—were established in this study using meteorological observation parameters as auxiliary variables combined with Sentinel-2 satellite image remote sensing band combinations as independent variables and measured Chl-a data as dependent variables. The estimation effects before and after the fusion of meteorological ground observation data were compared, and the best model was used to estimate the spatial–temporal variation trend of Chl-a in the regional water body. The results show that (1) the addition of meteorological parameters as auxiliary variables improved the precision of the three machine models; the decision coefficient (R2) rose by 7.25%, 5.71%, and 7.20%, respectively, to 0.76, 0.66, and 0.73. (2) The concentration of Chl-a in the lake region was projected from June to October 2019 to October 2021 using the RF optimal estimating model of meteorological fusion. The northeast, southwest, and south of the lake were where the comparatively high concentration values of Chl-a were located, whereas the lake’s center had a generally low concentration of the substance. Chromatically, Chl-a typically peaked in August after initially increasing and then declining. (3) The three rivers that feed into the river have varying levels of water pollution, with chemical oxygen demand (COD) and total nitrogen (TN) pollution being the most severe. This is what primarily caused the higher levels of Chl-a in the northeast, southwest, and south. This study is crucial for the preservation and restoration of Hulun Lake’s natural ecosystem and offers some technical support for the monitoring of the lake’s concentration of Chl-a.

Selecting Pedal Load for Lower-Limb Rehabilitation Based on the Combination of Muscle Synergy and Fourier Series

This paper introduces a new lower-limb rehabilitation machine that meets the rehabilitation needs of hemiplegic patients. First, a left–right independent rotary pedal mechanism was selected to facilitate rehabilitation and adapt to the user’s physical condition. Then, a half model of the lower-limb rehabilitation machine is designed and manufactured with ergonomics in mind. As analytical tools, we combine non-negative matrix factorization and non-negative double singular value decomposition to calculate muscle synergy of the walking muscle surface electromyography (sEMG) signal, and use cosine similarity to evaluate the similarity between walking and pedaling activities. By comparing the results of the walking and pedaling experiments, the effectiveness of pedaling in gait rehabilitation is revealed. To further improve the similarity between walking and pedaling, double integration of the sEMG signal is introduced, and the relationship between load input and rotation angle is described for the first time using Fourier series. The results of the experiment confirmed that more than half of the 10 subjects performed pedaling exercises similar to walking using Fourier series loading compared to pedaling exercises with normal constant loading. This loading parameter may have the potential to improve rehabilitation efficiency for many subjects compared to the usual exercise.

An automated hybrid approach via deep learning and radiomics focused on the midbrain and substantia nigra to detect early-stage Parkinson’s disease

ObjectivesThe altered neuromelanin in substantia nigra pars compacta (SNpc) is a valuable biomarker in the detection of early-stage Parkinson’s disease (EPD). Diagnosis via visual inspection or single radiomics based method is challenging. Thus, we proposed a novel hybrid model that integrates radiomics and deep learning methodologies to automatically detect EPD based on neuromelanin-sensitive MRI, namely short-echo-time Magnitude (setMag) reconstructed from quantitative susceptibility mapping (QSM).MethodsIn our study, we collected QSM images including 73 EPD patients and 65 healthy controls, which were stratified into training-validation and independent test sets with an 8:2 ratio. Twenty-four participants from another center were included as the external validation set. Our framework began with the detection of the brainstem utilizing YOLO-v5. Subsequently, a modified LeNet was applied to obtain deep learning features. Meanwhile, 1781 radiomics features were extracted, and 10 features were retained after filtering. Finally, the classified models based on radiomics features, deep learning features, and the hybrid of both were established through machine learning algorithms, respectively. The performance was mainly evaluated using accuracy, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). The saliency map was used to visualize the model.ResultsThe hybrid feature-based support vector machine (SVM) model showed the best performance, achieving ACC of 96.3 and 95.8% in the independent test set and external validation set, respectively. The model established by hybrid features outperformed the one radiomics feature-based (NRI: 0.245, IDI: 0.112). Furthermore, the saliency map showed that the bilateral “swallow tail” sign region was significant for classification.ConclusionThe integration of deep learning and radiomic features presents a potent strategy for the computer-aided diagnosis of EPD. This study not only validates the accuracy of our proposed model but also underscores its interpretability, evidenced by differential significance across various anatomical sites.

A novel method of fuel consumption prediction for wing-diesel hybrid ships based on high-dimensional feature selection and improved blending ensemble learning method

Establishing an accurate fuel consumption prediction model is essential to optimize energy efficiency in wing-diesel hybrid ships. This study proposes an improved Blending ensemble learning method for predicting fuel consumption. Initially, the original data is cleaned using artificial experience and Interquartile Range (IQR) method. A high-dimensional feature selection method, variance analysis- Pearson correlation-mutual information-permutation importance (VA-PC-MI-PI), is then proposed to identify 16 key features from the initial 111 features. Furthermore, 9 algorithms are employed for prediction analysis under different temporal resolution data conditions. Based on the results, optimal time step and algorithm models are determined to construct the Blending ensemble model (BEM). Subsequently, the feature data of “sailing speed” and “bow draft”, which account for the highest permutation importance, are imported into the metadata set to alleviate insufficient BEM data utilization. Additionally, Extra Trees (ET) model is chosen as the meta-learner for adaptation and Bayesian method is employed for global optimization. The resulting improved Blending ensemble model (IBEM) exhibits optimal prediction accuracy and generalization ability with an RMSE of 66.04 kg/h, representing a reduction of 16.99% and 13.86% compared to the Support Vector Machine (SVM) model and BEM, respectively. Additionally, the IBEM exhibits significantly smaller residuals and absolute residuals, demonstrating superior predictive stability and consistency. This study provides an important reference and basis for energy efficiency prediction, control, and optimization of wing-diesel hybrid ships.