Convergence Speed Research Articles

Estimation of PEMFC optimal parameters based on an improved butterfly optimization algorithm.

This paper introduces a novel butterfly optimization algorithm, called the spiral search and dynamic crossover based butterfly optimization algorithm (SCBO), for parameter estimation in proton exchange membrane fuel cell (PEMFC) models. To enhance the global performance of the butterfly algorithm, a spin-search strategy is incorporated to expand its exploration range, while an adaptive factor is introduced to strike a balance between exploration and exploitation. Additionally, a dynamic crossover operation is integrated to enhance solution diversity, addressing the algorithm's tendency to converge to local optima. Extensive experimentation on benchmark functions in comparison with common optimization algorithms demonstrates that SCBO outperforms others in terms of convergence accuracy and speed. Finally, we employ SCBO for parameter identification in a PEMFC model, showcasing its superior results and its ability to capture the model's dynamics when compared to other algorithms.

An Improved Pied Kingfisher Optimizer for Maritime UAV Path Planning

Maritime activities have become increasingly frequent with the deepening of economic globalization, highlighting the burgeoning significance of maritime rescue. However, in practical applications, UAVs for maritime rescue face numerous challenges, such as limited endurance and inadequate autonomous planning capabilities. To optimize flight routes and circumvent adverse sea conditions, an improved Pied Kingfisher Optimizer (IPKO) that incorporates refraction reverse learning, variable spiral search, and Cauchy mutation strategies was proposed. Comparative experiments conducted on CEC2005 and CEC2022 datasets with seven traditional algorithms demonstrate that the proposed algorithm exhibits superior precision and convergence speed. Subsequently, a path planning objective function was constructed based on trajectory cost and threat cost to simulate a 3D space for UAV maritime rescue missions, and the IPKO algorithm was applied to address the UAV path planning problem. The results showed that the total cost incurred by the IPKO algorithm decreased by 5.77% compared to the PKO algorithm and by 51.19% compared to the SCA algorithm. Finally, through UAV flight tests validating its practical applicability, it is ascertained that IPKO can enhance rescue efficiency in complex maritime rescue environments.

Low-Voltage Biological Electric Shock Fault Diagnosis Based on the Attention Mechanism Fusion Parallel Convolutional Neural Network/Bidirectional Long Short-Term Memory Model

Electric shock protection is critical for ensuring power safety in low-voltage grids, and robust fault diagnosis methods provide an essential foundation for the accurate operation of such protection devices. However, current low-voltage electric shock protection devices often suffer from limitations in operational precision and in their ability to effectively recognize electric shock types. To address these challenges, this paper proposes a fault diagnosis method for low-voltage electric shocks based on an attention-enhanced parallel CNN-BiLSTM model. The method first utilizes CNN to extract local spatial features of the electric shock signal and BiLSTM to capture temporal features. An attention mechanism is then introduced to fuse the local spatial and temporal features with weighted emphasis. Finally, a fully connected layer maps the fused features to the output layer, generating diagnostic results. Visualization through T-SNE analysis validates the improvement in model performance due to the attention mechanism. Comparative experiments show that the proposed model outperforms single models and other combined models in terms of accuracy, precision, recall, F1 score, and convergence speed. The results demonstrate that the proposed model achieves a fault diagnosis accuracy of 99.55%.

Unifying optimization forces: Harnessing the fine-structure constant in an electromagnetic-gravity optimization framework

Abstract The electromagnetic-gravity optimization (EMGO) framework is a novel optimization technique that integrates the fine-structure constant and leverages electromagnetism and gravity principles to achieve efficient and robust optimization solutions. Through comprehensive performance evaluation and comparative analyses against state-of-the-art optimization techniques, EMGO demonstrates superior convergence speed and solution quality. Its unique balance between exploration and exploitation, enabled by the interplay of electromagnetic and gravity forces, makes it a powerful tool for finding optimal or near-optimal solutions in complex problem landscapes. The research contributes by introducing EMGO as a promising optimization approach with diverse applications in engineering, decision support systems, machine learning, data mining, and financial optimization. EMGO’s potential to revolutionize optimization methodologies, handle real-world problems effectively, and balance global exploration and local exploitation establishes its significance. Future research opportunities include exploring adaptive mechanisms, hybrid approaches, handling high-dimensional problems, and integrating machine learning techniques to enhance its capabilities further. EMGO gives a novel approach to optimization, and its efficacy, advantages, and potential for extensive adoption open new paths for advancing optimization in many scientific, engineering, and real-world domains.

Optimization method of task uninstallation in mobile edge computing environment combining improved deep Q-learning and transmission learning

Traditional task uninstallation methods are difficult to cope with the continuous changes in network environment and device status, therefore a more intelligent solution is urgently needed. This article studied the optimization method of task uninstallation in mobile edge computing (MEC) environment, and studied the optimization method of task uninstallation in combination with improved deep Q-learning and transmission learning (TL). Firstly, it provided an overview of the basic concepts and optimization problems of task uninstallation in MEC environments, and then delved into the application of improved deep Q-learning in task uninstallation optimization, namely the application of deep Q-network (DQN) in task uninstallation optimization. Next, this article designed the TL-DQN method by combining DQN and TL. This method utilizes the DQN algorithm to construct a model that can handle complex states and action spaces. Meanwhile, by introducing TL, the model can quickly transfer knowledge and achieve adaptive optimization of tasks in new environments, thereby improving the generalization ability and efficiency of the decision-making process. Experiments have shown that TL-DQN performs better in convergence speed compared to other algorithms. For delay sensitive users, the delay growth of TL-DQN algorithm is relatively slow. When the task volume reached 10, the delay of TL-DQN was 7.97 s, which was 1.99 s lower than reinforcement learning. When the number of unloading tasks increased to 500, the energy consumption of TL-DQN was 554 J, which was 282 J lower than the energy consumption required by the task uninstallation method constructed by reinforcement learning algorithms. The task uninstallation method studied in this article has achieved significant results in reducing latency, improving energy efficiency, and adapting to network dynamic changes, bringing users a more stable and reliable service experience.

Research and development project portfolio benefit prediction: an improved backpropagation neural network-based approach

PurposeEffectively predicting research and development project portfolio benefit (R&D PPB) could assist organizations in monitoring the execution of research and development project portfolio (R&D PP). However, due to the uncertainty and complexity of R&D PPB, current research remains lacking a valid R&D PPB prediction tool. Therefore, an R&D PPB prediction model is proposed via a backpropagation neural network (BPNN).Design/methodology/approachThe R&D PPB prediction model is constructed via a refined immune genetic algorithm coupling backpropagation neural network (RIGA-BPNN). Firstly, considering the characteristics of R&D PP, benefit evaluation criteria are identified. Secondly, the benefit criteria values are derived as input variables to the model via trapezoidal fuzzy numbers, and then the R&D PPB value is determined as the output variable through the CRITIC method. Thirdly, a refined immune genetic algorithm (RIGA) is designed to optimize BPNN by enhancing polyfitness, crossover and mutation probabilities. Lastly, the R&D PPB prediction model is constructed via the RIGA-BPNN, followed by training and testing.FindingsThe accuracy of the R&D PPB prediction model stands at 99.26%. In addition, the comparative experiment results indicate that the proposed model surpasses BPNN and the immune genetic algorithm coupling backpropagation neural network (IGA-BPNN) in both convergence speed and accuracy, showcasing superior performance in R&D PPB prediction. This study enriches the R&D PPB predicting methodology by providing managers with an effective benefits management tool.Research limitations/implicationsThe research implications of this study encompass three aspects. First, this study provides a profound insight into R&D PPB prediction and enriches the research in PP fields. Secondly, during the construction of the R&D PPB prediction model, the utilization of the composite system synergy model for quantifying synergy contributes to a comprehensive understanding of intricate interactions among benefits. Lastly, in this research, a RIGA is proposed for optimizing the BPNN to efficiently predict R&D PPB.Practical implicationsThis study carries threefold implications for the practice of R&D PPM. To begin with, the approach proposed serves as an effective tool for managers to predict R&D PPB. Then, the model excels in efficiency and flexibility. Furthermore, the proposed model could be used to tackle additional challenges in R&D PPM, such as gauging the potential risk level of R&D PP.Social implicationsEffective predicting of R&D PPB enables organizations to allocate their limited resources more strategically, ensuring optimal use of capital, manpower and time. By accurately predicting benefit, an organization can prioritize high-potential initiatives, thereby improving innovation efficiency and reducing the risk of failed investments. This approach not only strengthens market competitiveness but also positions organizations to adapt more effectively to changing market conditions, fostering long-term growth and sustainability in a competitive business environment.Originality/valueIncorporating the characteristics of R&D PP and quantifying the synergy between benefits, this study facilitates a more insightful R&D PPB prediction. Additionally, improvements to the polyfitness, crossover and mutation probabilities of IGA are made, and the aforementioned RIGA is applied to optimize the BPNN. It significantly enhances the prediction accuracy and convergence speed of the neural network, improving the effectiveness of the R&D PPB prediction model.

Performance iterative learning control on nonlinear systems for tracking varying-scale and morphologically similar targets

This paper proposes a novel three-dimensional (3D) performance iterative learning control (PILC) scheme on nonlinear systems for tracking varying-scale and morphologically similar targets. The condition and performance weighted K-nearest neighbour (KNN) and the historical database update algorithms are developed to match the historical control inputs closest to the current operating conditions, and further realise the learning process along the performance domain. The control inputs of the PILC scheme can be updated by utilising the control information obtained from the time, iteration and performance dimensions. Also, the convergence property of the proposed framework is proved via the contraction mapping principle. Finally, compared with the existing ILC works, the illustrative simulation and experimental results are presented to illustrate that the PILC scheme has better tracking performance and robustness, smaller initial error, and faster convergence speed.

Autonomous Decision-Making for Air Gaming Based on Position Weight-Based Particle Swarm Optimization Algorithm

As the complexity of air gaming scenarios continues to escalate, the demands for heightened decision-making efficiency and precision are becoming increasingly stringent. To further improve decision-making efficiency, a particle swarm optimization algorithm based on positional weights (PW-PSO) is proposed. First, important parameters, such as the aircraft in the scenario, are modeled and abstracted into a multi-objective optimization problem. Next, the problem is adapted into a single-objective optimization problem using hierarchical analysis and linear weighting. Finally, considering a problem where the convergence of the particle swarm optimization (PSO) is not enough to meet the demands of a particular scenario, the PW-PSO algorithm is proposed, introducing position weight information and optimizing the speed update strategy. To verify the effectiveness of the optimization, a 6v6 aircraft gaming simulation example is provided for comparison, and the experimental results show that the convergence speed of the optimized PW-PSO algorithm is 56.34% higher than that of the traditional PSO; therefore, the algorithm can improve the speed of decision-making while meeting the performance requirements.

Research on Unmanned Aerial Vehicle Emergency Support System and Optimization Method Based on Gaussian Global Seagull Algorithm

In emergency rescue scenarios, drones can be equipped with different payloads as needed to aid in tasks such as disaster reconnaissance, situational awareness, communication support, and material assistance. However, rescue missions typically face challenges such as limited reconnaissance boundaries, heterogeneous communication networks, complex data fusion, high task latency, and limited equipment endurance. To address these issues, an unmanned emergency support system tailored for emergency rescue scenarios is designed. This system leverages 5G edge computing technology to provide high-speed and flexible network access along with elastic computing power support, reducing the complexity of data fusion across heterogeneous networks. It supports the control and data transmission of drones through the separation of the control plane and the data plane. Furthermore, by applying the Tammer decomposition method to break down the system optimization problem, the Global Learning Seagull Algorithm for Gaussian Mapping (GLSOAG) is proposed to jointly optimize the system’s energy consumption and latency. Through simulation experiments, the GLSOAG demonstrates significant advantages over the Seagull Optimization Algorithm (SOA), Particle Swarm Optimization (PSO), and Beetle Antennae Search Algorithm (BAS) in terms of convergence speed, optimization accuracy, and stability. The system optimization approach effectively reduces the system’s energy consumption and latency costs. Overall, our work alleviates the pain points faced in rescue scenarios to some extent.

A Multi-Strategy Improved Honey Badger Algorithm for Engineering Design Problems

A multi-strategy improved honey badger algorithm (MIHBA) is proposed to address the problem that the honey badger algorithm may fall into local optimum and premature convergence when dealing with complex optimization problems. By introducing Halton sequences to initialize the population, the diversity of the population is enhanced, and premature convergence is effectively avoided. The dynamic density factor of water waves is added to improve the search efficiency of the algorithm in the solution space. Lens opposition learning based on the principle of lens imaging is also introduced to enhance the ability of the algorithm to get rid of local optimums. MIHBA achieves the best ranking in 23 test functions and 4 engineering design problems. The improvement of this paper improves the convergence speed and accuracy of the algorithm, enhances the adaptability and solving ability of the algorithm to complex functions, and provides new ideas for solving complex engineering design problems.

Kolmogorov-Arnold Network Made Learning Physics Laws Simple.

In recent years, contrastive learning has gained widespread adoption in machine learning applications to physical systems primarily due to its distinctive cross-modal capabilities and scalability. Building on the foundation of Kolmogorov-Arnold Networks (KANs) [Liu, Z. et al. Kan: Kolmogorov-arnold networks. arXiv 2024, 2404.19756], we introduce a novel contrastive learning framework, Kolmogorov-Arnold Contrastive Crystal Property Pretraining (KCCP), which integrates the principles of CLIP and KAN to establish robust correlations between crystal structures and their physical properties. During the training process, we conducted a comparative analysis between Multilayer Perceptron (MLP) and KAN, revealing that KAN significantly outperforms MLP in both accuracy and convergence speed for this task. By extending the capabilities of contrastive learning to the realm of physical systems, KCCP offers a promising approach for constructing cross-data structural and cross-modal physical models, representing an area of considerable potential.

Vehicle Mass Estimation via Practical Supervisory Artificial Neural Networks Using Perturbed Engine Torque and Acceleration Inputs

Various model-based mass estimation approaches have been discussed for a long time. However, estimation performance often deteriorates in some driving situations and, in particular, slow convergence and excessive overshoot of estimates are a major issue for model-based approaches. Meanwhile, mass estimation approaches using ANN models have recently emerged to propose better solutions, but their usefulness has not been fully investigated. Therefore, this paper presents a vehicle mass estimation strategy using practical supervisory artificial neural networks to achieve more accurate results with better convergence. Here, the perturbed engine torque and vehicle longitudinal acceleration are selected as the inputs of the ANN (instead of the original engine torque and vehicle acceleration), which allows for the faster convergence of estimates with high accuracy; these inputs are existing sensor values already available in the vehicle system. The effectiveness of the proposed ANN approach was verified using simulation and software-in-the-loop simulation (SILS) with field test data, and it was found that the convergence speed of the proposed ANN is almost twice as fast as that of the model-based approach, the accuracy is much better, and the estimation quality is constantly stable without any excessive transient responses. This study will provide further insights into mass estimation using the ANN approach.

An Enhanced Crowned Porcupine Optimization Algorithm Based on Multiple Improvement Strategies

The Crowned Porcupine Optimization (CPO) algorithm exhibits certain deficiencies in initialization efficiency, convergence speed, and adaptability. To address these issues, this paper proposes an enhanced Crowned Porcupine Optimization algorithm (ICPO) based on multiple improvement strategies. ICPO optimizes the initialization process by introducing Logistic chaotic mapping, thereby expanding the search space. It accelerates convergence through an elite retention strategy and enhances global search capability by integrating stochastic operations, mutation-like operations, and crossover-like operations to increase population diversity. Additionally, adaptive step tuning based on fitness values is employed to comprehensively improve the algorithm’s performance. To verify the effectiveness of ICPO, 23 standard functions were used for a comprehensive evaluation, and its practicality was further validated through optimization of actual engineering design problems. The experimental results demonstrate significant improvements in convergence speed, solution quality, and adaptability with ICPO.

Balance Strategy Prediction Model Based on Power Load Data Mining

To meet the purpose of a multi-objective solution, a scheme is introduced into the optimal strategy-intensive training process. It supports a multi-task-driven computing model and has good reasoning accuracy, which makes the hydropower management system have efficient collaborative strategy prediction ability. Aiming at the trade-off problem between the cost-benefit and energy load of the hydropower control system, based on the neural network model to improve the stacked sparse denoising auto encoder second-order cone programming (SSDAE-SOCP) algorithm, a low-level backtracking depth uncertainty optimization scheduling model is proposed to obtain the optimal scheduling strategy. It intends to improve the poor accuracy of the global optimal results caused by the lack of priority sampling in the traditional strategy. The feature space without boundary conditions is set to solve the optimal solution for global/local organizations. Further, the flexibility is transferred according to the single-core function of task decomposition for improving the calculation accuracy of the whole solution data and the dynamic double-mutation balance. Simulation results have shown that the proposed algorithm enhances the training quality and performance by 9.5% and 15.2% compared with the traditional MOPSO and MOIMPA algorithms. Gradient descent and convergence speed, as well as the stability and security of intensive training, are better than the comparison methods. The training features verify the stability of the balanced prediction model, showing its importance in enhancing the anti-noise ability of the matrix. The research results can further enhance the multiple dispatching and command capabilities of the hydropower projects, providing technical support for the sustainable development of maximizing the benefits for the systems.

Prediction of Air Quality Index Based on Support Vector Machine and Improved Butterfly Optimization Algorithm

Air pollution is an increasingly serious problem. Air pollution has been become a main cause of environmental degradation and health effects. Accurate prediction of air quality can help improve environmental quality and human living conditions. The traditional methods for predicting the air quality index have the problem of low accuracy and efficiency. To solve this problem, this paper proposes a novel support vector machine prediction model based on improved butterfly optimization algorithm, which is called IBOA-SVM model. In the improved butterfly optimization algorithm, the sigmoid function is used to optimize the update of the parameter c, which increases the search diversity and improves the convergence speed. The performance of the improved butterfly optimization algorithm is verified using eight benchmark functions. Compared with performances of the traditional butterfly optimization algorithm and the particle swarm optimization algorithm, the improved butterfly optimization algorithm has strong competitiveness in accuracy and stability. We establish the IBOA-SVM prediction model for forecasting air quality based on the improved butterfly optimization algorithm. The performance of our proposed model is compared with other predicting models. The experimental results show that our proposed model has higher accuracy and efficiency in predicting the air quality index of four cities in southern China.

Kernel Adaptive Filtering Algorithm Based on Hyperbolic Tangent Mixed Error Function

This paper proposes an adaptive filtering algorithm based on the symmetry Kernel Hyperbolic Tangent Mixed Error Criterion (KHTMC), aimed at addressing the identification of nonlinear systems under non-Gaussian noise environments. The algorithm optimizes signal processing by constructing a mixed cost function that combines the symmetry logarithmic square error and the hyperbolic tangent function and integrates it with the kernel adaptive filtering method. Simulation results show that, compared to existing kernel adaptive filtering algorithms, the KHTMC algorithm exhibits significant advantages in terms of convergence speed and steady-state mean square error. It demonstrates strong robustness and tracking performance, especially when dealing with mixed non-Gaussian noise. Therefore, this algorithm shows great potential in signal processing applications under complex noise conditions, offering a more reliable and efficient solution.

A Method for Detecting Edge Continuity in Art and Design Images Based on Visual Attention Mechanism

To address the issues of low accuracy and significant noise impact in edge continuity detection of art and design images, this paper proposes a visual attention-based edge continuity detection method for art and design images. Determine the edge position points of art and design images using the Laplace operator, and obtain the horizontal and vertical gradients of the image edges by calculating the first-order difference method to determine the amplitude of the image edge gradient; By using the maximum and minimum operations in binary morphology instead of intersection and union operations, the image grayscale is determined, and the HSI color space features are determined to complete the edge feature extraction of art and design images. Using the SUSAN operator to clarify the kernel similarity zone of the edges of art and design images, removing similar edge image pixels, using spatial domain denoising and frequency domain denoising to reduce the edge noise of art and design images, and achieving edge preprocessing of art and design images. Introducing visual attention mechanism to transform the pixel space of edge features in art and design images, performing threshold segmentation on the edges of art and design images, and continuously annotating the segmented edge pixels. Introducing loss function to improve the convergence speed of detection, constructing an art and design image edge continuity detection model based on visual attention mechanism, outputting detection results, and implementing research. The experimental results show that the proposed method has better continuity due to the successful avoidance of noise interference by introducing visual attention mechanisms and other operations. As the number of detected pixels increases, the detection deviation rate of the proposed method remains between 0.02% and 0.03%. The proposed method has a lower detection bias rate and can effectively improve the performance of edge continuity detection in art and design images.

Combining Galileo HAS and Beidou PPP-B2b with Helmert coordinate transformation method

The European Galileo High Accuracy Service (HAS) started to provide freely and openly accessible real-time precise satellite orbit, clock and code bias products to global users on January 24, 2023. Combined with the already running BeiDou PPP-B2b service, the launch of a variety of satellite-based PPP services provided more choices to users. However, different satellite-based PPP services provide services for different GNSS systems, which hamper users to make full use of multi-GNSS systems. Therefore, the combination of different satellite-based products can further improve the availability of corrections, usage of multi-GNSS observation data and positioning performance. This paper proposes to combine HAS and PPP-B2b products by the Helmert coordinate transformation method. To validate the algorithm, HAS and PPP-B2b products of day of year (DOY) 308–317 in 2023 were collected in Zhengzhou, China. First, they are evaluated in terms of correction availability, orbit and clock quality. Then the HAS and PPP-B2b products are combined by the Helmert coordinate transformation method. Two combination strategies are proposed. The first strategy is integrating BDS satellites of PPP-B2b products into HAS products (denoted as C_H), while the second strategy is integrating Galileo satellites of HAS products into PPP-B2b products (denoted as C_B). Finally, the combined strategies are evaluated with static and kinematic data. Based on the static data of 18 Multi-GNSS Experiment (MGEX) stations in China and its surrounding areas, the results show that, when separately using HAS and PPP-B2b products for PPP, the average accuracy in horizontal and vertical directions are (2.4, 2.7 cm) and (2.4, 2.0 cm), respectively. The average accuracy of C_H strategy is 2.1 and 1.7 cm, which was improved by 31.3% compared with separately using the products. Similarly, the average accuracy of C_B strategy is 2.1 and 1.9 cm, corresponding to improvements of 29.6%. When comparing the two combined strategies, it is noted that the C_B strategy converges faster. Based on the data from vehicle platform, the results show that the horizontal and vertical accuracy of the C_B strategy is 8.6 and 15.7 cm respectively. The accuracy improvement of C_B is better than that of C_H strategy, and the average accuracy is 68.4% better than that of separately using the products. The above results show that the two combined strategies can improve positioning accuracy. In addition, the improvements in accuracy and convergence speed of C_B strategy are more significant. Users are advised to use C_B strategy for the combination of HAS and PPP-B2b products, which will greatly expand the application of HAS and PPP-B2b services.

Cross-social-network user alignment research based on multi-dimensional user features

Accurately aligning the same users on different flat social networks to merge user information and create more nuanced user profiles is critical. However, the current research in this area faces challenges related to low efficiency and inadequate alignment accuracy. To address these challenges, we introduce a cross-social network user alignment model based on multi-dimensional user features (MDUF). First, inspired by the principles of entity recognition and Hartley's association method, we employed a block matrix association algorithm to project the original dataset into different high-dimensional spaces. Second, we proposed a new inertia weight calculation method to improve the convergence speed from linear to nonlinear transformations. This method improves the performance of traditional particle swarm optimization algorithms. Finally, we utilize improved particle swarm optimization and residual connection techniques to optimize bidirectional long short-term memory networks. The experimental results show that our proposed model significantly outperforms traditional alignment models in terms of alignment efficiency and accuracy, which is highly practical and has the potential to inspire further research on social network user alignment.

Separation and Dynamic Binding Mechanism of 3D Model Animation by Integrating Improved Genetic Algorithm and WebAR

With the development of the economy, the demand for 3D model animation in fields such as games, film and television, and education is constantly increasing. At present, many 3D model animations are built based on genetic algorithm. However, due to the slow convergence speed and poor local search ability of genetic algorithm, this model still has many shortcomings. Therefore, a cellular automaton is used to optimize the genetic algorithm, and a cellular genetic algorithm is proposed. It is integrated with WebAR technology, which has the characteristics of lightweight and low cost, aiming to improve the separation and dynamic binding mechanism of 3D model animation. Experimental analysis showed that when the number of chromosome genes was 90, the vertex gene value of the research algorithm was the highest, ranging from 281 to 501, and the convergence was the highest. The file size of the model dataset based on the research method was reduced by 50% compared with before. The FPDT based on the animation separation and dynamic binding mechanism was decreased by 15.2 s on average. To sum up, it can be seen that the designed 3D model animation is more detailed and the animation dynamic is also the best. This research method can significantly improve the separation and dynamic binding mechanism of 3D model animation. This research will improve the integration of genetic algorithm and WebAR technology, which can not only effectively deal with complex 3D models and animations, but also has broad application prospects.