检索结果-内蒙古大学图书馆

Studying the geometrical models of tubular braided composite using micro computed tomography and particle swarm optimization

引用

COMPOSITES PART B-ENGINEERING 2023年 260卷

作者： Gholami, Ali Melenka, Garrett W. York Univ Dept Mech Engn Toronto ON Canada

This paper compares the geometrical model of a 2DTBC with its actual model generated by the Micro-Computed Tomography (& mu;CT) method. First, the geometrical models' equations are edited to simulate the manufacturing process more accurately, and the equations are incorporated into the TBC-Gen program. Then, a & mu;CT scan is done on a cured carbon fiber TBC, and 2D and 3D models are created. Next, two yarns of the scanned models are extracted and modelled. The segmented yarns are analyzed, and their geometrical data, including cross-section area, major and minor yarn diameters, orientation, mandrel diameter, portion angle and centre points, are extracted. Next, a yarn path simulating the scanned yarn is generated using the TBC-Gen and the extracted parameters. Then, the generated geometrical model is compared with the & mu;CT model. To do that, a parameter named portion angle is introduced to help the geometrical model better fit the & mu;CT model. Finally, particle swarm optimization (PSO) is used to optimize the portion angle. The result of the fitting algorithm shows the accuracy of the geometrical model (less than 1% error) to simulate actual TBC. Understanding the amount of error between a geometrical model and the actual model will help to evaluate the application of geometrical models more thoroughly. Also, the more accurate geometrical model will contribute less error to the FEM simulation. The quantitative comparison between these two models can give a clear understanding of the amount of error existing in the geometrical model compared to an accurate model generated by & mu;CT.

关键词： Braided composite material Mico-CT Geometrical model Inverse problem particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of compressive strength of multiple types of fiber-reinforced concrete based on optimized machine learning models

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 152卷

作者： Zhao, Ning Zhang, Haonan Xie, Peilun Chen, Xiaowei Wang, Xuewei Sichuan Agr Univ Sch Civil Engn Chengdu 611830 Peoples R China Southeast Univ Sch Civil Engn Nanjing 211189 Peoples R China

The accurate prediction of compressive strength of fiber-reinforced concrete (FRC) is essential for its design optimization and performance assessment, as it can significantly reduce testing costs. However, the high variability of FRC's compressive strength poses considerable prediction challenges. Current research has predominantly focused on developing prediction models for single-type FRC, while the prediction of compressive strength across multiple types of FRC remains a critical and unresolved issue in the field. To address this gap, this study proposes a novel hybrid approach integrating Deep Neural Networks (DNN), Generalized Regression Neural Networks (GRNN), and Extreme Gradient Boosting (XGBoost) with optimization techniques-particle swarm optimization (PSO), Bayesian optimization (BO), and Bald Eagle Search (BES). A comprehensive dataset of 386 peer-reviewed compressive strength measurements was utilized, with K-means++ algorithm ensuring balanced training and testing set distributions. Hyperparameter optimization for DNN, GRNN, and XGBoost was conducted by combining PSO, BO, and BES with five-fold cross-validation. Results demonstrate strong model performance, with the BES-XGBoost model achieving the highest accuracy, exhibiting deviations of approximately 15 % between actual and predicted values. Additionally, Shapley Additive Explanations (SHAP) and partial dependence plots were employed to analyze the feature importance on compressive strength and the coupling effects of fiber characteristics. The proposed approach not only provides enhanced prediction accuracy for multiple types of FRC but also delivers valuable insights for FRC proportioning design, advancing the field of FRC performance evaluation.

关键词： Fiber-reinforced concrete Neural network Compressive strength prediction particle swarm optimization algorithm Bayesian optimization algorithm Bald eagle search optimizer

来源：评论

学校读者我要写书评

暂无评论

Regional Load Frequency Control of BP-PI Wind Power Generation Based on particle swarm optimization

引用

ENERGIES 2023年第4期16卷 2015-2015页

作者： Sun, Jikai Chen, Mingrui Kong, Linghe Hu, Zhijian Veerasamy, Veerapandiyan Qingdao Univ Coll Elect Engn Qingdao 266071 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

The large-scale integration of wind turbines (WTs) in renewable power generation induces power oscillations, leading to frequency aberration due to power unbalance. Hence, in this paper, a secondary frequency control strategy called load frequency control (LFC) for power systems with wind turbine participation is proposed. Specifically, a backpropagation (BP)-trained neural network-based PI control approach is adopted to optimize the conventional PI controller to achieve better adaptiveness. The proposed controller was developed to realize the timely adjustment of PI parameters during unforeseen changes in system operation, to ensure the mutual coordination among wind turbine control circuits. In the meantime, the improved particle swarm optimization (IPSO) algorithm is utilized to adjust the initial neuron weights of the neural network, which can effectively improve the convergence of optimization. The simulation results demonstrate that the proposed IPSO-BP-PI controller performed evidently better than the conventional PI controller in the case of random load disturbance, with a significant reduction to near 10 s in regulation time and a final stable error of less than 10(-3) for load frequency. Additionally, compared with the conventional PI controller counterpart, the frequency adjustment rate of the IPSO-BP-PI controller is significantly improved. Furthermore, it achieves higher control accuracy and robustness, demonstrating better integration of wind energy into traditional power systems.

关键词： wind power generation sudden load disturbance load frequency control BP neural network particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fractional order total variational infrared image denoising with fused flower pollination particle swarm optimization

引用

OPTICAL ENGINEERING 2023年第3期62卷 033105-033105页

作者： Liu, Tingting Zhang, Yanzhu Yang, Fan Shenyang Ligong Univ Sch Automat & Elect Engn Shenyang Peoples R China Sci & Technol Electroopt Informat Secur Control L Tianjin Peoples R China

The traditional fractional order total variational model has better results in denoising and maintaining texture details in infrared images. However, it is difficult to determine the order of fractional order differentiation in image processing so that the model has the best denoising effect. To solve this problem, a fractional order total variational infrared image denoising model incorporating a flower pollination particle swarm optimization (PSO) algorithm is proposed in this paper. The model combines the search advantages of the flower pollination optimization algorithm and the PSO algorithm. The maximization multiobjective equation is designed as the fitness function of the optimization algorithm. The optimal order of the fractional order total variational model is found adaptively according to different features in different regions of the infrared image. The experimental results show that the improved model not only achieves the adaptivity of the adaption of the fractional order of total variational model order but also effectively removes the noise and retains the texture structure of infrared images to the maximum extent. (c) 2023 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： fractional order total variational model infrared image denoising flower pollination optimization algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on pulse laser detection anti-interference method in smoke environment

引用

INFRARED PHYSICS & TECHNOLOGY 2025年 145卷

作者： Qu, Qinyang Su, Zerun Xu, Xiaobin Li, Moyuan Chen, Shanshan Ran, Yingying Tan, Zhiying Hohai Univ Coll Mech & Elect Engn Chang Zhou 213200 Peoples R China Hohai Univ Coll Informat Sci & Engn Chang Zhou 213200 Peoples R China

To address the problem of smoke medium interference on pulse laser detection signals, this study employs Monte Carlo method to precisely establish the backscattered signals model of pulsed lasers in smoke conditions, and proposes an anti-interference strategy combining particle swarm optimization (PSO) and convolutional neural network (CNN) by echo signals collected experimentally. Specifically, this study uses the Monte Carlo method and scattering phase function to simulate particle collisions and constructs a sampling model of reflected photons based on the target surface's reflective properties. Semi-analytical reception technology is used to extract the received backscattered photon signals. Finally, a CNN is built taking all the backscattered data points as the input. The parameter of the network is optimized using PSO algorithm. To verify the accuracy of the simulated backscattered echo signals and the effectiveness of the anti-interference algorithm, a laser detection experiment in a smoke environment was conducted. The experimental results show that the simulated detection back- scattered signals and the experimental backscattered signals have a high degree of consistency, with a maximum root mean square error of only 0.043. The recognition accuracy of the CNN optimized by the PSO algorithm is 96.154 %, with a computational parameter size of 193.008 KB. This study provides solid theoretical support and technical assurance for the pulse laser detection technology in the anti-interference field.

关键词： Pulse laser Smoky environment Echo model Monte Carlo method particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Exploring interpretable and non-interpretable machine learning models for estimating winter wheat evapotranspiration using particle swarm optimization with limited climatic data

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2023年第1期212卷

作者： Zhao, Xin Zhang, Lei Zhu, Ge Cheng, Chenguang He, Jun Traore, Seydou Singh, Vijay P. North China Univ Water Resources & Elect Power Sch Water Conservat Zhengzhou 450045 Henan Peoples R China North China Univ Water Resources & Elect Power Sch Informat Engn Zhengzhou 450045 Henan Peoples R China Henan Water Conservancy Survey Design & Res Co Ltd Zhengzhou 450046 Peoples R China China Three Gorges Univ Coll Hydraul & Environm Engn Yichang 443002 Hubei Peoples R China Texas A&M Univ Dept Biol & Agr Engn Zachry Dept Civil & Environm Engn College Stn TX 77843 USA Metropolitan Solar Inc Washington DC 20032 USA UAE Univ Natl Water & Energy Ctr Al Ain 15551 U Arab Emirates

Accurate estimation of crop evapotranspiration (ETc) is crucial for improving the water use efficiency and designing and operating irrigation systems. To accurately calculate winter wheat ETc with limited meteorological data, the present study proposed two interpretable machine learning (ML) models (random forest (RF) and extreme gradient boosting (XGBoost)) as well as non-interpretable ML models (support vector machine (SVM) and deep neural network (DNN)) based on the particle swarm optimization (PSO) algorithm using observed winter wheat ETc data during the period from 2007 to 2013 at Luan Cheng Agro-ecosystem Experimental Station. Mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), coefficient of determination (R-2), and global performance indicator (GPI) were used to assess the performance of models. This demonstrated that the ML models based on the crop coefficient (Kc) and solar radiation (Rn) were accurate and offered a workaround for calculating winter wheat ETc in the absence of meteorological data. In four ML models, the ninth input combination, consisting of Kc, Rn, daily air maximum temperature (Tmax), daily air minimum temperature (Tmin), sunshine hours (n), and wind speed with a height of 2 m (U2), produced the best estimate of ETc. Among them, the PSO-based SVM (PSO-SVM) model obtained the best results for estimating ETc with MAE, RMSE, NSE, R2, and GPI values of 0.389 mm center dot d(-1), 0.562 mm center dot d(-1) 0.910, 0.911, and 0.975, respectively, showing the advantages of the non-interpretable ML model in ETc forecasting. Accurate descriptions of actual hydrological and climatic processes were given by local interpretable model-agnostic explanations (LIME). The inflection points of daily climatic parameters (Tmin, Tmax, Rn, n) related to ETc were determined to be 3.80 degrees C, 5.50 degrees C, 1.62 MJ center dot m(-2)center dot d(-1), 1.37 h, respectively. This work has potential to overcome the difficult

关键词： Winter wheat Crop evapotranspiration particle swarm optimization algorithm Machine learning Interpretability

来源：评论

学校读者我要写书评

暂无评论

Research on the precision forming cathode design method of electrochemical machining all-metal screw drill stator

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第7-8期133卷 3663-3671页

作者： Tang, Lin Wang, Yi Zhang, Jingjing Zhang, Jun Cao, Tong Deng, Wen Xian Technol Univ Sch Mechatron Engn Xian 710021 Peoples R China Xian Technol Univ Sch Def Sci &Technol Xian 710021 Peoples R China China Natl Heavy Machinery Res Inst Co Ltd Xian 710021 Peoples R China

In order to shorten the cathode design cycle, reduce design cost and improve forming accuracy for all-metal screw drill stator electrochemical machining (ECM), this paper proposed a precision forming cathode design method based on particle swarm optimization BP neural network (PSO-BP). The cathode design algorithm model of all-metal screw drill stator electrochemical machining was established, completed the camber feed cathode design. By using self-developed large scale horizontal CNC electrochemical machining equipment, under the condition of voltage 19 V, electrolyte 15%NaCl, electrolyte temperature 35 +/- 1degree celsius, electrolyte inlet pressure 1.6 MPa, and feed speed 10 mm/min, the stable and reliable electrochemical machining processing of the 4-m length of 38CrMoAlA all-metal screw drill stator was completed. The contour forming accuracy is +/- 0.03 mm, and the surface roughness is Ra0.848 mu m. Research showed that it is an efficient and feasible method to design the electrochemical machining camber feed cathode of all-metal screw drill stator using PSO-BP neural network.

关键词： All-metal screw drill stator Electrochemical machining (ECM) particle swarm optimization algorithm BP neural network Cathode design

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Agricultural Information Collection Robot Integrating Ant Colony algorithm and particle swarm algorithm

引用

IEEE ACCESS 2024年 12卷 50821-50833页

作者： Wu, Qiong Chen, Hua Liu, Baolong Xian Technol Univ Sch Comp Sci & Engn Xian 710021 Peoples R China Xian Technol Univ Sch Mechatron Engn Xian 710021 Peoples R China

Faced with complex and ever-changing environmental conditions in the agricultural field, efficient agricultural information gathering is crucial for optimising agricultural output. Therefore, a new path planning algorithm combining ant colony algorithm and particle swarm optimization is proposed in this study. The aim is to achieve fast and accurate path planning for agricultural information gathering robots in diverse agricultural environments. The global search ability of particle swarm optimization algorithm in finding optimal paths and the local search advantage of ant colony algorithm in obstacle avoidance are used to optimise the movement strategy of robots in agricultural environments. The research results showed that the global path planning distance of this method was 19.328m. The execution time was 0.97s. In local path planning, the proposed algorithm had a fitness function value of 30.123 when the number of iterations reached 53. In mixed path planning, the proposed algorithm reduced the movement time by 3.2s. The conclusion shows that the algorithm proposed in this study has high applicability and efficiency in practical applications, providing an effective strategy for path planning of agricultural information gathering robots. It has important practical significance for promoting the development of intelligent agriculture.

关键词： Ant colony algorithm particle swarm optimization algorithm agriculture robot path pheromone

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Analysis of Slope Stability Considering Geomaterial Dilatancy

引用

INTERNATIONAL JOURNAL OF GEOMECHANICS 2024年第4期24卷

作者： Hu, Shihong Zhao, Lianheng Li, Liang Zuo, Shi Xie, Zhouzhou Qiao, Nan Cent South Univ Sch Civil Engn Changsha 410075 Hunan Province Peoples R China Cent South Univ Sch of Civil Engn Key Lab Heavy Haul Railway Engn Struct Hunan Prov Key Lab Disaster Prevent & Mitigat Rail Changsha 410075 Hunan Province Peoples R China Changsha Univ Coll Civil Engn Changsha 410022 Hunan Province Peoples R China

Shear dilation occurs during the failure of geomaterials subjected to shear stress. To account for the dilatancy and nonlinearity of geomaterials, a nonlinear upper-bound analysis method was proposed for evaluating the stability of homogeneous slopes based on the coaxial nonassociated flow rule. The rotational failure mechanism of a homogeneous slope was established within the kinematic approach of limit analysis, using the Davis approach to convert the nonassociated flow rule into an associated one. By applying the variation principle, ordinary differential equations of the potential sliding surface and its corresponding stress were derived, which were then solved using a fourth-order Runge-Kutta method in conjunction with appropriate boundary conditions. Furthermore, the balance equation was derived from the virtual power principle, and the critical height of the slope was calculated using a particle swarm optimization algorithm. The strength reduction technique was then introduced to determine the factor of safety of the slope. The accuracy and effectiveness of the proposed nonlinear upper-bound variation method for evaluating the stability of homogeneous slopes under nonassociated flow rule and nonlinear failure criteria were verified when compared with existing studies and techniques, such as the finite-element limit analysis and the finite difference method. This study accurately reflects the nonlinearity and dilatancy of geomaterials and avoids assumptions regarding the sliding surface and its corresponding stress, making it a valuable reference for future research.

关键词： Slope stability Nonassociated flow rule Nonlinear Mohr-Coulomb failure criterion Kinematic approach of limit analysis Strength reduction Variation principle particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative study on constitutive models of a near β titanium alloy TC18 during thermoplastic deformation based on machine learning

引用

MATERIALS TODAY COMMUNICATIONS 2025年 42卷

作者： Ding, Shaoling Gao, Shuai Jiang, Xiang Shi, Shuangxi Liang, Yaobiao Guilin Univ Technol Sch Math & Stat Guilin 541006 Peoples R China Guangxi Coll & Univ Key Lab Appl Stat Guilin 541006 Peoples R China Guilin Univ Aerosp Technol Guangxi Key Lab Special Engn Equipment & Control Guilin 541004 Peoples R China

The hot deformation behavior of TC18 alloy has been systematically studied at the temperature of 993-1113 K and strain rate of 0.001-1 s-1. Based on the stress-strain data obtained under the above process parameters, machine learning models describing the thermoplastic constitutive relationship of the alloy were established by using random forest (RF), support vector regression (SVR), back propagation artificial neural network (BPANN) and Gaussian process regression (GPR). The hyper-parameters of these models were optimized by adaptive inertial weighted particle swarm optimization (APSO) algorithm, and the models were further evaluated by statistical analysis and cross-validation. The results show that the prediction ability of the developed four machine learning models was ranked as GPR>BPANN>RF>SVR. Then APSO was applied to four models to further enhance their prediction accuracy, and the prediction accuracy of these APSO models was ranked as APSOGPR>APSO-BPANN>APSO-RF>APSO-SVR. The developed APSO-GPR model has the highest R2 (>0.999), as well as the lowest RMSE (<1.77) and MAPE (<0.63 %) on both the training set and the testing set, demonstrating its strong predictive performance. Sixteen cross-validation tests also confirm the APSO-GPR model has high prediction accuracy.

关键词： TC18 alloy Hot deformation Flow stress Machine learning particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：