Combination Of Methods Research Articles

Diagnosis of gas path health states on a real flight data by convolutional neural network and dual-tree complex wavelet

As the core component of aircraft, the reliability and availability of aero-engines directly affect the entire cruise process of aircraft. Implementing health monitoring in the gas path of an aero-engine can ensure engine reliability and availability to a greater extent. It can also enable the move from traditional time-scheduled maintenance to condition-based maintenance and reduce life cycle costs. The existing models were mainly concentrated on simulation data and traditional machine learning methods. This paper provides a new pathway to classify the states of engine gas path performance by combining the convolutional neural network (CNN) with the dual-tree complex wavelet (DTCW) method. A real flight data accompanied by maintenance records collected from the airline was adopted to construct a data set. The data pre-processing and stable points extraction were carried out, and the combined CNN and DTCW method was developed to diagnose the healthy states of the gas path. The final accuracy can achieve higher than 94%. The diagnosis results indicate that the deep learning methods hold particular promise for aero-engine health monitoring.

Simulation and Experimental Design of Magnetic Fluid Seal Safety Valve for Pressure Vessel

This article focuses on the safety valve of pressure vessels, and a new ferrofluid sealing device for pressure vessel safety valves is developed based on a special magnetic circuit. A combined method of numerical calculation and experimental analysis is used to study the relationship between seal clearance, number of seals, pole slot width, pole tooth height, pole tooth width, and the sealing pressure of the ferrofluid sealing device. The research results show that seal clearance and pole tooth width have a significant impact on the sealing performance, and as the dimensions increase, the sealing pressure decreases. As the number of seals, pole tooth height, and slot width increase, the sealing performance initially improves and then decreases. This phenomenon is attributed to the increase in magnetic reluctance in the magnetic circuit. In experimental studies, when the excitation current of the electromagnet is 240 mA and the coil turns number 30, the sealing capacity is 61.22 kPa. When the excitation current is 200 mA and the coil turns number 80, the sealing capacity is 168.24 kPa. The experiments demonstrate the compensating ability of magnetic fluid seals in combination with safety valve seals, confirming that combined seals have higher reliability compared to conventional mechanical seals.

Lamb waves in sandwich structures: Anomalous dispersion and transverse (quasi) resonances

Guided waves propagating in three layered sandwich structures with extremely soft inner layer and thin stiff outer layers reveal peculiar phenomena related to the appearance of dual zero group velocities (ZGV) in the fundamental symmetric branch, transverse (quasi) resonances, and transverse energy fluxes, causing “ringing” of the plates and even material damage. The current research relates to sandwich plates, satisfying the so-called Wiechert condition. The analysis is based on the combined method comprising Cauchy sextic formalism and the exponential fundamental matrix method.

Spectroscopic techniques and chemometrics for ink analysis: Document analysis application

This study represents a methodology to determine the falsified documents via a combined method of spectroscopic techniques and chemometrics. The techniques of UV–Vis and FTIR-ATR spectroscopies and principal component analysis methods have been applied to black, blue, and red ballpoint pens available in the Türkiye market. The analysis results of the applied spectroscopic techniques were found to be consistent with each other for the examined eleven ink samples from three different brands, and it was observed that FTIR-ATR spectroscopy had higher discriminative power. A dried sample preparation technique developed for small amounts of samples for FTIR-ATR measurements and the increased the sensitivity of FTIR-ATR technique was associated with this sample preparation method. Statistical techniques showed that the UV–Vis technique proves useful outcomes in distinguishing inks according to their colors, whereas the FTIR-ATR technique is valuable for identifying ink brands. Additional analysis of the sub-brand of black inks and falsified old-dated check sample analysis validated that our methodology has the potential to classify and identify ballpoint inks in forensic applications. Due to the limited sample quantity available for analysis in real samples, only FTIR-ATR analysis was possible, and the results demonstrated that document forgery could be detected from small parts of samples in the document. When we look at the overall outcome of this study, a comprehensive methodology enriched with statistical calculations has been proposed that can be applied even in a laboratory with limited resources, having only UV–Vis and FTIR-ATR capabilities.

Dream housing: Exploring effective factors on housing livability in the neighborhood from the perspective of residents

The purpose of this study is to develop a new concept of livability as "livable housing" in order to identify the factors that determine the subjective satisfaction of residents with the internal and surrounding environment of the housing and to estimate its level among urban neighborhoods with subjective and objective data. In order to fill the knowledge gap in livability studies, especially housing livability, the present study has looked at the link between livability and housing indicators and has evaluated this link among the residents of urban neighborhoods with different socio-economic contexts. This study has been evaluated the indicators of livable housing in an empirical analysis among the neighborhoods of Karaj metropolitan area (as a leading city) with the cluster sampling method and choosing 8 neighborhoods (as the scope of the research) as well as 402 cases (as a sample statistics derived from Cochran's formula).In this evaluation, the questionnaire with (72 sub-indicators in 15 groups) is the main criterion for data collection, and the analyzes are using statistical and spatial combined methods. The statistical analysis of the questionnaire includes preparing the data for weighting and determining the important and influential factors with the exploratory factor analysis method in the SPSS environment. The stratification of neighborhoods is done with the multi-criteria decision-making model (TODIM) by combining the raw data and the weight of indicators extracted from the EFA method. Also, the accuracy of the results has been measured with the RMS method and the use of spatial methods in (GIS).The results showed environmental, social, economic and physical macro-factors respectively have the greatest effects on the livability of housing. The indicators of facilities and infrastructures, open and public space, cleanliness and pollution were the indicators of increasing livability and satisfaction, and the indicators of place connection and belonging, access and transportation, personal and social security were the indicators of decreasing livability. In general, the neighborhoods are in different conditions of housing livability and without continuity and principles of regularity. This difference in the different effects of indicators in neighborhoods is due to the inherent differences of neighborhoods and people's mental filters. The (89%) overlap obtained from the validation of the results indicates the existence of a very insignificant difference and acceptable agreement of the results of the two methods of spatial-spatial analysis. Considering the importance of the relationship between man and the urban environment and the quality of human life, it is recommended to pay special attention to community-orientedness and local assets and a bottom-up approach in livability surveys at any scale. Also, this study suggests important policy implications for achieving urban sustainability by improving housing livability.

Study of combined vibration-suppression method for vehicle vertical comprehensive performance

The constraint of invariant points leads to the trade-off between ride qualities and road-holding, limiting the improvement of vehicle comprehensive performance. This study presents a combined vibration-suppression method (CVSM) to address this issue. The CVSM includes a mechanical method (MM) and a control method (CM). The MM uses a tuned mass damper to eliminate the performance constraint. A multi-objective sliding mode controller functions as the CM to enhance comprehensive performance. In this paper, the nonlinear model of the MM is established, and a detailed dynamics analysis is conducted to provide insight into the constraint elimination theory. Then, the CM is designed to suit the novel suspension structure, improving both ride quality and road-holding. Analytical results show that the MM can share energy consumption with the suspension around the invariant point, which is the key to constraint elimination. Based on this, the CM increases the energy consumption efficiency of the MM. As a combination, the CVSM is more than just a simple sum of the two methods; they complement each other to improve overall performance.

Embeddedness in complex networks: Theoretical central debate, policy implications, and research agenda in ethnic entrepreneurship

Objective: This article explores ethnic entrepreneurship as an emerging organizational phenomenon, aiming to provide a comprehensive overview through a systematic literature review. Method: Triangulation employed bibliometric analysis, network analysis, citation and co-citation analysis, co-citation network, and a meta-analysis of bibliometrics over the period. It also includes content analysis demonstrating study characteristics, key findings, and suggestions for future research. Key Findings: The crucial role of ethnic networks in identity valorization and overcoming obstacles, exerting a moderating influence on entrepreneurial decisions, was identified. Furthermore, a broader theoretical framework for understanding the ethnic entrepreneurship phenomenon is synthesized. Theoretical/Methodological Contributions: A combined method of analyses is employed, offering an approach that can be adopted by similar research. The theoretical framework in which ethnic entrepreneurship studies are anchored is presented, emphasizing social immersion, co-ethnic network building, and Economic Sociology. Relevance/Originality: In a growing global migration movement, individuals have become entrepreneurs in the pursuit of ethnic valorization, equality, and survival. They face various barriers in host countries, influencing the decision to undertake entrepreneurship and their business. This study fills a gap by elucidating how research explains the interplay of these emerging phenomena. Social/Management Contributions: The article identifies future directions for ethnic entrepreneurship research, addressing crucial issues such as gender, network construction, financing, international refugee policies, public policies, ethnicity, ethnic markets, marginalization, and prejudice. Its conclusions offer valuable insights for managers, researchers, and policymakers.

Segment Anything Model Combined with Multi-Scale Segmentation for Extracting Complex Cultivated Land Parcels in High-Resolution Remote Sensing Images

Accurate cultivated land parcel data are an essential analytical unit for further agricultural monitoring, yield estimation, and precision agriculture management. However, the high degree of landscape fragmentation and the irregular shapes of cultivated land parcels, influenced by topography and human activities, limit the effectiveness of parcel extraction. The visual semantic segmentation model based on the Segment Anything Model (SAM) provides opportunities for extracting multi-form cultivated land parcels from high-resolution images; however, the performance of the SAM in extracting cultivated land parcels requires further exploration. To address the difficulty in obtaining parcel extraction that closely matches the true boundaries of complex large-area cultivated land parcels, this study used segmentation patches with cultivated land boundary information obtained from SAM unsupervised segmentation as constraints, which were then incorporated into the subsequent multi-scale segmentation. A combined method of SAM unsupervised segmentation and multi-scale segmentation was proposed, and it was evaluated in different cultivated land scenarios. In plain areas, the precision, recall, and IoU for cultivated land parcel extraction improved by 6.57%, 10.28%, and 9.82%, respectively, compared to basic SAM extraction, confirming the effectiveness of the proposed method. In comparison to basic SAM unsupervised segmentation and point-prompt SAM conditional segmentation, the SAM unsupervised segmentation combined with multi-scale segmentation achieved considerable improvements in extracting complex cultivated land parcels. This study confirms that, under zero-shot and unsupervised conditions, the SAM unsupervised segmentation combined with the multi-scale segmentation method demonstrates strong cross-region and cross-data source transferability and effectiveness for extracting complex cultivated land parcels across large areas.

Process Development and Techno-Economic Analysis for Combined and Separated CO2 Capture-Electrochemical Utilization

Combining CO2 capture and utilization into a single unit operation offers a feasible solution for converting a sustainable feedstock into marketable commodity chemicals, while reducing energy requirements from separated processes. In this research, we developed a process model and performed a techno-economic analysis (TEA) for point-source CO2 capture and electrochemical-based utilization in light olefins production under both separated and integrated scenarios. CO2 containing flue gas from a 500 MW power plant was utilized as a feed while CO2 utilization involved electrochemical reduction reactions to produce light olefins directly from CO2. A meticulous analysis was conducted, probing into the multifaceted impacts of various operating parameters, material properties, and downstream treatment units. Factors such as pressure, temperature, H2O/CO2 molar ratio, catalyst and adsorbent activities, deactivation rate, and heat integration were optimized to achieve 95 % CO2 recovery and > 90 % conversion, and > 85 % ethylene yield. Through a comprehensive TEA, our findings unveiled that the combined process utilizing bifunctional adsorbent/catalyst materials (BFMs) incurs costs of approximately $284/ton CO2, whereas the separated process reported expenses of ∼$516/ton CO2. This study, pivotal in its contributions, evaluated economic feasibility of combined capture-conversion method based on BFMs for CO2 removal and subsequent utilization via a promising advanced process model for sustainable feedstocks conversion to commodity chemicals.

Combined failure identification of intermediate bearing in aeroengine based on wavelet transform, second-order difference, and 1D-LBP

Intermediate bearing is one of key parts in double-rotor aeroengine, whose running state usually can only be monitored by casing signals. As the fault characteristic information detected from casing is weak and complex, it is generally difficult to be dug correctly. One-dimensional local binary pattern (1D-LBP) can depict failure information from the perspective of local feature extraction. Currently, the study on the application of 1D-LBP in fault identification is mostly based on original signals; due to the influence of component signals irrelevant to fault and noise, the fault information in original signals is weak and complex; besides, 1D-LBP is rather sensitive to noise, which is extremely possible to cause insufficient extraction of local textural features and the difficulty to identify a fault. To solve this problem and make it possible to precisely identify the fault of intermediate bearing of real aeroengine, the paper has proposed the combined method of wavelet transform (WT), second-order difference with 1D-LBP. WT is highly uncertain to determine the decomposition layer number. To solve the difficulty, correlation coefficient was introduced. Meanwhile, casing vibration signal was subjected to WT. Furthermore, because vibration signal often went with impact components in a bearing failure and second-order difference of signals was sensitive to impact feature, component signals obtained by WT were subjected to second-order difference operation. Additionally, taking advantage of 1D-LBP, second-order differences of signals were locally binarized with average value as criterion. Finally, 1D-LBP signals were re-transformed to decimal 1D local texture signals (1D-LTS). These 1D-LTS can embody local feature information of signals. According to the spectrum of 1D-LTS, combined failure type of intermediate bearing was identified. Through the comparison with WT and classical 1D-LBP method, and failure analysis after disassembly of aeroengine, the effectiveness and engineering applicability of proposed method have been verified.

Improved methods for genetic manipulation of the alkaliphile Halalkalibacterium halodurans.

An improved approach was developed for the genetic manipulation of the Gram-positive extremophile Halalkalibacterium halodurans (formerly called Bacillus halodurans). We describe an allelic replacement method originally developed for Staphylococcus aureus that allows the deletion, mutation, or insertion of genes without leaving markers or other genetic scars. In addition, a protocol for rapid in vitro plasmid methylation and transformation is presented. The combined methods allow the routine genetic manipulation of H. halodurans from initial transformation to the desired strain in 8 days. These methods improve H. halodurans as a model organism for the study of extremophiles.

An optimal demand side management for microgrid cost minimization considering renewables

AbstractIn an ordinary microgrid configuration, the required load changes from hour to hour. The power system firms determine the cost of energy at different times of day by considering the highest and lowest points of the consumption curve. This is referred to as time‐of‐use (TOU) pricing for power. The hourly basis load demand is divided into flexible and inflexible categories. Demand side management (DSM) lowers peak demand while rewarding customers for their participation based on load lowering. His rebuilds the whole load model on the pillars of demand cost movement. The research recommends a DSM methodology based on a combined intellect method to lower the total cost of employing loads in a microgrid (MG) structure while considering carbon tax as an unavoidable constraint to lower the emission of pollutants. This is because 40% of microgrid customers are willing to participate in the DSM scheme. The results obtained in each illustration demonstrate that the suggested DSM technique is suitable in terms of cost reduction. The generating cost was decreased from $15,488 to $15,354 when 0%–40% of clients engaged in the DSM programme. With just a 3% compromised increase in generation costs, a carbon price combined with economic emission dispatch reduced the pollutants emitted by up to 78%, from 70 to 15 tons.

Building an evaluation index system of musical collaborative capacity for China’s compulsory music education: Using a combined Delphi method and Analytic Hierarchy Process approach

The latest version of China’s National Compulsory Education Curriculum Programme and Standards 2022 (hereafter CECPS 2022) emphasises the cultivation of students’ collaborative capacities, mentioning ‘ carrying out the core literacy effectively’. From the perspective of music education, this study summarises the requirements for collaborative activities in compulsory courses of the music discipline within CECPS 2022 in the light of Social Interdependence Theory, and builds an Evaluation Index System of Collaborative Capacity (hereafter EISMCC) by employing the Delphi method and an Analytic Hierarchy Process approach. After 3 rounds of expert consultations and revisions, it was found that EISMCC in compulsory music education is comprised of 3 first-level indices, 7 second-level indices and 20 third-level indices. The index framework and the results of the weight distribution with reliable quality reflect the experts’ emphasis on the process, goal orientation and synergistic interaction of collaborative activities in music learning. The whole system considers people’s general understanding of collaborative capacity, the calls within CECPS 2022 for collaborative music activities, and the practical demands of music teaching in compulsory education. This study provides a theoretical basis, a design process paradigm, practical guidance and a valid tool for the evaluation of collaborative capacity in compulsory education.

Effects of Ball Combination Exercise Combined with cTBS Intervention on Sleep Problems in Children with Autism.

Sleep problems significantly affect the quality of life of autism spectrum disorder (ASD) children. This study aimed to evaluate the effects of a 12-week ball combination exercise, continuous theta burst stimulation (cTBS) stimulation, and combined intervention on sleep problems in children with ASD. Forty-five ASD children were divided into three intervention groups (ball combination exercise(n = 12), cTBS stimulation(n = 10), combined (n = 12) and a control group (n = 11). The intervention groups underwent intervention, while the control group maintained daily activities. The effects were assessed using the Children's Sleep Habits Questionnaire (CSHQ) scale. The results revealed that after 12 weeks of intervention, three programs reduced sleep problems in children with ASD. The post-test scores of the cTBS group (p = 0.002) and the combined group (p < 0.001) were significantly lower than the baseline scores on the CSHQ scale. The exercise group (p = 0.002) and the combined group (p < 0.001) showed significant improvement in sleep anxiety, while there was no statistically significant difference in the effectiveness of the three interventions for sleep-onset delay. The combined group outperformed the single intervention groups in the CSHQ score and sleep anxiety sub-dimensions. The combined intervention group showed slightly superior performance in sleep onset latency, however, there was no significant difference. Three interventions alleviated sleep issues in ASD children, with the combined method proving more effective. This study validates non-pharmacologic and combined approaches for ASD sleep problems. Future research should delve deeper into the mechanisms of these interventions in ASD children's sleep improvement.

Two-step deep-learning identification of heel keypoints from video-recorded gait.

Accurate and fast extraction of step parameters from video recordings of gait allows for richer information to be obtained from clinical tests such as Timed Up and Go. Current deep-learning methods are promising, but lack in accuracy for many clinical use cases. Extracting step parameters will often depend on extracted landmarks (keypoints) on the feet. We hypothesize that such keypoints can be determined with an accuracy relevant for clinical practice from video recordings by combining an existing general-purpose pose estimation method (OpenPose) with custom convolutional neural networks (convnets) specifically trained to identify keypoints on the heel. The combined method finds keypoints on the posterior and lateral aspects of the heel of the foot in side-view and frontal-view images from which step length and step width can be determined for calibrated cameras. Six different candidate convnets were evaluated, combining three different standard architectures as networks for feature extraction (backbone), and with two different networks for predicting keypoints on the heel (head networks). Using transfer learning, the backbone networks were pre-trained on the ImageNet dataset, and the combined networks (backbone + head) were fine-tuned on data from 184 trials of older, unimpaired adults. The data was recorded at three different locations and consisted of 193 k side-view images and 110 k frontal-view images. We evaluated the six different models using the absolute distance on the floor between predicted keypoints and manually labelled keypoints. For the best-performing convnet, the median error was 0.55 cm and the 75% quartile was below 1.26 cm using data from the side-view camera. The predictions are overall accurate, but show some outliers. The results indicate potential for future clinical use by automating a key step in marker-less gait parameter extraction.

Activating colloidal synthesized Au catalyst by the electrochemical strategy: Gas atmosphere, electrolyte and electrochemical technique

Organic ligands are necessarily used to stabilize nanoparticles (NPs) in colloid synthesis, and the presence of these ligands in most cases can have adverse effects on heterogeneous nanocatalysis. Therefore, it is crucial to develop efficient methods to remove ligands and study the removal mechanism. In this article, we developed a combined electrochemical method (chronoamperometry (CA) + cyclic voltammetry (CV)), which can completely and efficiently remove thiol ligand from Au NPs to produce cleaned Au/C catalyst. Using the oxygen reduction reaction (ORR) activity as the evaluation criterion for ligand removal, we found that gas atmosphere (O2) plays an important role in the removal process, while the acidity and alkalinity of electrolyte have no effect on the removal efficiency. A proposed thiol ligand removal mechanism along with Au degradation is presented. The results of CA activation at an oxidation constant potential (1.7 V) indicate that oxidation of thiol alone cannot remove thiol ligand. Only if a reduction constant potential of 0.2 V is further applied, the ORR activity of Au/C catalyst will increase, indicating that both the oxidation and reduction processes of Au NPs are crucial for ligand removal. Although the CA method (with an upper potential of 1.7 V and a lower potential of 0.2 V) can efficiently remove the majority of thiol ligand, complete removal of thiol ligand requires further CV activation. Based on the relevant results, a combined electrochemical method (CA + CV) is established. Developing standardized methods for removing ligands on the surface of catalysts is important for obtaining efficient catalysts and is also important for the reproducibility of catalytic results.

Versatile and durable polyvinyl alcohol/alginate/gelatin/quaternary ammonium chitosan/Fe3O4 particles hybrid hydrogel beads: adsorption capabilities for cleaning pollutants

A novel hybrid hydrogel bead (HHBFe) composed of polyvinyl alcohol/sodium alginate/gelatin/quaternary ammonium chitosan (PVA/GA/SA/QCS) and Fe3O4 magnetic nanoparticles was developed through green cross-linking of Ca2+ and tannic acid (TA) combined freeze-thaw method. HHBFe exhibited a good spherical shape, porosity, magnetic properties, and excellent mechanical properties and durability. The adsorption capacity of HHB and HHBFe towards methyl orange (MO), tetracycline (Tc), and Cr (VI) was systematically studied and compared. Results revealed similar adsorption capacities for MO and Cr (VI) between HHB and HHBFe, while the presence of Fe3O4 significantly enhanced Tc adsorption, indicating the versatile adsorption functions of HHBFe. Adsorption kinetic followed the pseudo-second-order model, with external diffusion and intra-particle diffusion controlling process. The adsorption data were consistent with the Langmuir isothermal adsorption model, indicating predominantly monolayer adsorption of pollutants by beads. Notably, the beads exhibited easily regenerated, maintaining 60 % of initial adsorption capacity after 5 cycles, particularly for Tc and Cr (VI). The good adsorption performance of HHBFe can be attributed to the strong interaction between their multi-functional groups including phenolic hydroxyl groups, carboxyl groups, amino groups, etc., and pollutant molecules. The multifunctional HHBFe beads prepared in this study and the results obtained with three completely different types of pollutants provide reliability support for their use in different wastewater treatment fields and even in the field of drug carriers.

Rice Husk as Raw Material in Synthesis of NaA (LTA) Zeolite.

The present work deals with the hydrothermal synthesis of a Na-A (LTA) zeolite using rice husk as a starting material. The focus was on defining the most favorable conditions for the synthesis of zeolite Na-A from rice husk in order to economize on both energy (i.e., synthesis temperatures) and reaction time and to enlarge the field of the pure and isolated synthesized phase. Four sets of experiments were carried out at environmental pressure temperatures varying from 40 °C to 85 °C with a SiO2/Al2O3 ratio from 1.75 to 3.5. Optimal conditions for crystallization of the Na-A zeolite from rice husk were reached at 60 °C with a SiO2/Al2O3 ratio of 1.75. Sixty degrees Celsius represents the minimum known temperature used for the synthesis of NaA zeolite from rice husk. The products of synthesis were characterized by X-ray diffraction, scanning electron microscopy, infrared and Raman spectroscopy. The purity of the synthesized zeolite is verified here for the first time through quantitative phase analysis using the combined Rietveld and reference intensity ratio methods.

TPAFNet: Transformer-Driven Pyramid Attention Fusion Network for 3D Medical Image Segmentation.

The field of 3D medical image segmentation is witnessing a growing trend in the utilization of combined networks that integrate convolutional neural networks and transformers. Nevertheless, prevailing hybrid networks are confronted with limitations in their straightforward serial or parallel combination methods and lack an effective mechanism to fuse channel and spatial feature attention. To address these limitations, we present a robust multi-scale 3D medical image segmentation network, the Transformer-Driven Pyramid Attention Fusion Network, which is denoted as TPAFNet, leveraging a hybrid structure of CNN and transformer. Within this framework, we exploit the characteristics of atrous convolution to extract multi-scale information effectively, thereby enhancing the encoding results of the transformer. Furthermore, we introduce the TPAF block in the encoder to seamlessly fuse channel and spatial feature attention from multi-scale feature inputs. In contrast to conventional skip connections that simply concatenate or add features, our decoder is enriched with a TPAF connection, elevating the integration of feature attention between low-level and high-level features. Additionally, we propose a low-level encoding shortcut from the original input to the decoder output, preserving more original image features and contributing to enhanced results. Finally, the deep supervision is implemented using a novel CNN-based voxel-wise classifier to facilitate better network convergence. Experimental results demonstrate that TPAFNet significantly outperforms other state-of-the-art networks on two public datasets, indicating that our research can effectively improve the accuracy of medical image segmentation, thereby assisting doctors in making more precise diagnoses.

Hyperspectral prediction model of soil Cu content based on WOA-SPA algorithm

ABSTRACT The content of heavy metal Cu in soil is an important indicator for assessing soil quality. However, soil hyperspectral data contain a large amount of redundant data, which can affect the effectiveness of spectral modelling. To address this problem, a combined method based on Whale Optimization Algorithm and Successive Projection Algorithm (WOA-SPA) is proposed to select the characteristic bands. And a prediction model of soil heavy metal Cu content was constructed using the partial least squares method. The experimental results show that: (1) The prediction accuracy of soil Cu content using the WOA-PLSR model was higher than that of the SPA-PLSR model, with RPD increased by 0.229, the R2 increased by 0.07, and RMSE decreased by 0.354. (2) Running the WOA and WOA-SPA combination algorithms 30 times respectively to prove the stability of the algorithms, the prediction accuracy of the model constructed based on the WOA-SPA combination algorithm is better than that of the model constructed based on the WOA algorithm as a whole. (3) Compared with the WOA or SPA algorithm alone, the prediction model constructed based on the WOA-SPA algorithm has a better prediction performance, with RPD of 2.259, R2 of 0.804, and RMSE of 2.396 for the prediction set. (4) Comparing the spatial distribution maps of the measured and predicted values, it can be observed that the spatial distribution between the predicted Cu content values based on the combined WOA-SPA algorithm and the measured Cu content values are basically consistent. This study indicates that the WOA-SPA-PLSR model has good stability and prediction accuracy for the prediction of Cu content in soil, which is of great practical significance for the rapid and accurate estimation of heavy metal Cu content in soil.