检索结果-内蒙古大学图书馆

Inverse calculation of vessel emission source intensity based on optimized Gaussian puff model and particle swarm optimization algorithm

引用

MARINE POLLUTION BULLETIN 2024年第Pt A期209卷 117117页

作者： Wu, Hao Li, Xueyao Wang, Chao Ye, Zhirui Jinling Inst Technol Sch Network &Commun Engn Nanjing Peoples R China Wuhan Univ Technol Hubei Key Lab Inland Shipping Technol Wuhan Hubei Peoples R China Southeast Univ Sch Transportat Nanjing Peoples R China Southeast Univ Sch Econ & Management Nanjing Peoples R China

Maritime transportation has significantly contributed to global economic development but is also a major source of air pollution. This study aims to provide an inverse calculation framework of vessel emission source intensity for emission monitoring. This research enhanced the traditional Gaussian diffusion model by specific characteristics of ship emissions and various influencing factors identified through simulation experiments. An inverse model is developed using pattern search and particle swarm optimization (PSO) algorithms to estimate marine exhaust source strengths. Results indicate that the PSO algorithm is the most accurate and efficient, especially with an iteration step size of 0.1 s. Practical application using data from 86 monitored ships revealed that 76 had fuel sulfur content exceeding the 0.1 % threshold, achieving an accuracy rate of 88.37 %. These findings are crucial for improving the understanding of marine exhaust dispersion and advancing remote monitoring technologies, contributing to better environmental management of maritime transport emissions.

关键词： Gaussian model Inverse calculation particle swarm optimization algorithm Vessel emission

来源：评论

学校读者我要写书评

暂无评论

State of health estimation for lithium-ion battery based on particle swarm optimization algorithm and extreme learning machine

引用

Green Energy and Intelligent Transportation 2024年第1期3卷 46-54页

作者： Kui Chen Jiali Li Kai Liu Changshan Bai Jiamin Zhu Guoqiang Gao Guangning Wu Salah Laghrouche School of Electrical Engineering Southwest Jiaotong UniversityChengdu611756China FEMTO-ST UMR CNRS 6174and FCLABFR CNRS 3539UniversitéBourgogne Franche-ComtéBelfortUTBM90000France

Lithium-ion battery State of Health(SOH)estimation is an essential issue in battery management *** order to better estimate battery SOH,Extreme Learning Machine(ELM)is used to establish a model to estimate lithium-ion battery *** swarm optimization algorithm(PSO)is used to automatically adjust and optimize the parameters of ELM to improve estimation ***,collect cyclic aging data of the battery and extract five characteristic quantities related to battery capacity from the battery charging curve and increment capacity *** Grey Relation Analysis(GRA)method to analyze the correlation between battery capacity and five characteristic ***,an ELM is used to build the capacity estimation model of the lithium-ion battery based on five characteristics,and a PSO is introduced to optimize the parameters of the capacity estimation *** proposed method is validated by the degradation experiment of the lithium-ion battery under different *** results show that the battery capacity estimation model based on ELM and PSO has better accuracy and stability in capacity estimation,and the average absolute percentage error is less than 1%.

关键词： Lithium-ion battery State of health estimation Grey relation analysis method particle swarm optimization algorithm Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Software cost estimation predication using a convolutional neural network and particle swarm optimization algorithm

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-21页

作者： Draz, Moatasem. M. Emam, Osama Azzam, Safaa. M. Kafrelsheikh Univ Fac Comp & Informat Software Engn Dept Kafrelsheikh Egypt Helwan Univ Fac Comp & Artificial Intelligence Informat Syst Dept Helwan Egypt

Over the past decades, the software industry has expanded to include all industries. Since stakeholders tend to use it to get their work done, software houses seek to estimate the cost of the software, which includes calculating the effort, time, and resources required. Although many researchers have worked to estimate it, the prediction accuracy results are still inaccurate and unstable. Estimating it requires a lot of effort. Therefore, there is an urgent need for modern techniques that contribute to cost estimation. This paper seeks to present a model based on deep learning and machine learning techniques by combining convolutional neural networks (CNN) and the particle swarm algorithm (PSO) in the context of time series forecasting, which enables feature extraction and automatic tuning of hyperparameters, which reduces the manual effort of selecting parameters and contributes to fine-tuning. The use of PSO also enhances the robustness and generalization ability of the CNN model and its iterative nature allows for efficient discovery of hyperparameter similarity. The model was trained and tested on 13 different benchmark datasets and evaluated through six metrics: mean absolute error (MAE), mean square error (MSE), mean magnitude relative error (MMRE), root mean square error (RMSE), median magnitude relative error (MdMRE), and prediction accuracy (PRED). Comparative results reveal that the performance of the proposed model is better than other methods for all datasets and evaluation criteria. The results were very promising for predicting software cost estimation.

关键词： Software cost estimation Software effort estimation Promise database SCE Convolutional neural network particle swarm optimization algorithm PSO CNN

来源：评论

学校读者我要写书评

暂无评论

Improved particle swarm optimization algorithm with Logistic Function and Trigonometric Function for Three-dimensional Path Planning Problems

引用

ENGINEERING LETTERS 2025年第2期33卷 442-459页

作者： Wang, Yu-Bo Wang, Jie-Sheng Sui, Xiao-Fei Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan 114051 Peoples R China

particle swarm optimization algorithm is a widely used swarm intelligence algorithm. Aiming at the path length, algorithm stability, running time and other problems obtained by the PSO algorithm for solving the three-dimensional path planning problem, an improved particle swarm optimization algorithm based on Logistic function and trigonometric function is proposed to solve the three-dimensional path planning problem. Two types and six modification strategies for the inertia weights and learning factors of PSO algorithm are proposed, the two types are PSO algorithm based on the change of inertia weights omega of different functions, and LWDPSO algorithm and TCPSO algorithm based on the change of C-1 and C-2 of different learning functions, and these two algorithms are combined into an Improved particle swarm optimization algorithm (IPSO). Finally, the feasibility and effectiveness of the proposed method is verified by simulating the UAV flying over the mountain peaks, and the effect of the change of inertia weight and learning factor on the PSO algorithm is discussed by classifying the IPSO algorithm with the LWDPSO algorithm and the TCPSO algorithm, and finally comparing the IPSO algorithm with the PSO algorithm, the genetic algorithm, and the artificial swarm algorithm, and the simulation results show that the proposed IPSO algorithm is more advantageous compared with the other algorithms. The simulation results show that the proposed IPSO algorithm is more advantageous than other algorithms and can better accomplish the path planning task.

关键词： 3D path planning particle swarm optimization algorithm Inertia weights Learning factors

来源：评论

学校读者我要写书评

暂无评论

Research on a hybrid model for flood probability prediction based on time convolutional network and particle swarm optimization algorithm

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-13页

作者： Yu, Qiying Liu, Chengshuai Li, Runxi Lu, Zhenlin Bai, Yungang Li, Wenzhong Tian, Lu Shi, Chen Xu, Yingying Cao, Biao Zhang, Jianghui Hu, Caihong Zhengzhou Univ Sch Water Conservancy & Transportat Zhengzhou 450001 Peoples R China Xinjiang Inst Water Resources & Hydropower Res Urumqi 830049 Xinjiang Peoples R China

Accurate flood forecasting in advance is crucial for planning and implementing watershed flood prevention measures. This study developed the PSO-TCN-Bootstrap flood forecasting model for the Tailan River Basin in Xinjiang by integrating the particle swarm optimisation (PSO) algorithm, temporal convolutional network (TCN), and Bootstrap probability sampling method. Evaluated on 50 historical flood events from 1960 to 2014 using observed rainfall-runoff data, the model showed, under the same lead time conditions, a higher Nash efficiency coefficient, along with lower root mean square and relative peak errors in flood forecasting. These results highlight the PSO-TCN-Bootstrap model's superior applicability and robustness for the Tailan River Basin. However, when the lead time exceeds 5 h, the model's relative peak error remains above 20%. Future work will focus on integrating flood generation mechanisms and enhancing machine learning models' generalisability in flood forecasting. These findings provide a scientific foundation for flood management strategies in the Tailan River Basin.

关键词： Flood forecasting Machine learning Temporal convolutional neural network particle swarm optimization algorithm Bootstrap probability sampling algorithm PSO-TCN model Tailan River Basin

来源：评论

学校读者我要写书评

暂无评论

Application of the particle swarm optimization algorithm-back propagation neural network algorithm introducing new parameter terms in the application field of industrial design

引用

RESULTS IN ENGINEERING 2024年 21卷

作者： Tian, Yuan Chang, Yu North China Inst Aerosp Engn Sch Art & Design Langfang 065000 Peoples R China Tianjin Univ Commerce Sch Arts Tianjin 300134 Peoples R China

With the development of the modern industry, to continuously use large precision instruments, the circuits protecting method through circuit design has gradually been promoted. And this method can prevent the excessive accumulation of electric heat from causing fires. The voltage at the starting point of power transmission is constant. However, during the transportation process, some lines have low resistance values, which can generate large instantaneous currents. To address this issue, this study conducted simulation experiments on selfcollected Circuit dataset based on particle swarm optimization and backpropagation neural networks. This study first introduced new parameter term learning factors into backpropagation neural networks. Then they were imported into the support vector machine, and the nonlinear variables were mapped to high plane, and the optimal hyperplane was established. Then the traditional circuit design method was improved, 40 Resistor were connected in parallel and connected to the experimental circuit in series with the rheostat. Finally, the algorithm was introduced into Circuit dataset collected in this experiment, and its protective effect on the circuit was compared with the other three algorithms. Under the protection of this design, the working times of four algorithms were 0.28, 0.42, 0.38, and 0.43 s, respectively. Their phase displacements were 0.19, 0.26, 0.36, and 0.41, respectively. The circuit design method proposed in this study can effectively address circuit faults. And the fusion algorithm can disconnect the circuit at the fastest speed and significantly reduce excitation current intensity, and it is suitable for circuit design in the field of industrial design.

关键词： Adaptive learning Support vector machine particle swarm optimization algorithm Voltage sag Circuit protection design

来源：评论

学校读者我要写书评

暂无评论

optimization Management of Storage Location in Stereoscopic Warehouse by Integrating Genetic algorithm and particle swarm optimization algorithm

引用

JOURNAL OF APPLIED MATHEMATICS 2024年第none期2024卷 1-13页

作者： Zhang, Shuhong Zheng, Xianghui Xu, Fan Wang, Suzhen Zhang, Qixia Cao, Yuan Anhui Sanlian Univ Fac Engn Hefei 230601 Peoples R China Hefei Coll Finance & Econ Dept Artificial Intelligence Hefei 230601 Peoples R China Anhui Honglu Steel Struct Grp Co Ltd Operat Dept Hefei 230601 Peoples R China Hefei Coll Finance & Econ Dept Bldg & Mapping Hefei 230601 Peoples R China

The management of a three-dimensional warehouse is a key part of the upper computer monitoring and management system for three-dimensional warehouses. Currently, there are problems such as unreasonable planning and inability to respond to real-time demands. Therefore, further improvement is needed to optimize the management of storage locations. The main purpose of the research is to achieve better storage stability and improve storage and retrieval efficiency. First, the study constructed a multiobjective mathematical model based on the weight, frequency of use, and category of the goods. Three objective functions were constructed. Therefore, the operational efficiency of the stacker crane and the turnover rate of items were improved. Meanwhile, the overall stability of the shelves was ensured, and the management efficiency of the warehouse was improved. At the same time, the study introduced the GA-PSO algorithm to solve the mathematical model and optimize the goods location planning. These results confirmed that the proposed algorithm had significantly lower iteration times than traditional particle swarm optimization in different warehouse sizes and types of goods. The iteration required to reach the optimal value in Situation 1 was only 80, which was 90 fewer than PSO. Meanwhile, in Situation 2, the optimization results of the proposed algorithm in four objective functions were as high as 42.94%, 26.03%, 30.72%, and 46.15%, respectively, which increased by 1.20%, 8.04%, 5.61%, and 7.38% compared to PSO. The proposed algorithm can achieve more efficient and intelligent warehouse management, improving the efficiency and accuracy of logistics operations. It is significant for logistics industry development and enterprise competitiveness enhancement.

关键词： automated stereoscopic warehouse GA-PSO genetic algorithm monitoring and management system particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Active Distribution Network Fault Location Based on Petri Nets and Improved particle swarm optimization algorithm

ELECTRICA

引用

ELECTRICA 2024年第3期24卷 789-798页

作者： Xia, Yunfeng Yang, Jie Chen, Junan Lai, Yeming Ye, Sheng Hainan Power Grid Co Ltd Transmiss Maintenance Branch Haikou Hainan Peoples R China

To address issues such as inadequate fault tolerance, long computation time, and limited universality in fault location for active distribution networks, this paper proposes a fault location method that combines Petri nets with an improved particle swarm optimization (PSO) algorithm. This method enhances the efficiency of fault location in distribution networks with distributed power sources, demonstrating good applicability and convergence, especially in complex network scenarios. The results from two test functions and simulation analyses of two types of node distribution networks show that (1) in the single-point fault simulation, the improved algorithm successfully located the fault in the ninth iteration, outperforming the 14th iteration result of the standard PSO algorithm. (2) In networks with randomly interconnected distributed power sources, the algorithm accurately located both single and multiple faults. (3) Experimental verification further supports the simulation results, proving the effectiveness of this method in practical applications.

关键词： Active distribution network fault location Petri nets particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Structure optimization of electromagnetic clinching die based on response surface methodology and particle swarm optimization algorithm

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2023年第3-4期126卷 1611-1628页

作者： Ji, Yanan Huang, Changqing Sun, Xiaoming Wang, Shu Yang, Huan Cui, Xiaohui Cent South Univ Light Alloy Res Inst Changsha 410083 Peoples R China Cent South Univ State Key Lab High Performance Complex Mfg Changsha 410083 Peoples R China Cent South Univ Coll Mech & Elect Engn Changsha 410083 Peoples R China

Electromagnetic clinching (EMC) is a high-speed connection technology that combines electromagnetic forming and mechanical clinching. The die structure significantly affects the mechanical properties of the joint. In this paper, an optimal method based on response surface methodology (RSM) and particle swarm optimization algorithm (PSO) is proposed to improve the mechanical properties of joints clinched by EMC. The mathematical models of die geometrical parameters and cross-sectional parameters of the joint are obtained by RSM and numerical simulation. Then, the die structure is optimized through PSO. Finally, the experiments are carried out using the optimized and standardized die. The results show small errors between the simulation and the experiment. The joint strength using a standardized die is 878 N, and energy absorption is 0.758 J. The joint strength using the optimized die is 1322 N, and energy absorption is 1.335 J. Compared with the standardized die, the joint strength and energy absorption of parts obtained by the optimized die are increased by 50.5% and 76.1%, respectively.

关键词： Electromagnetic clinching Die structure optimization Response surface methodology particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Load balancing in virtual machines of cloud environments using two-level particle swarm optimization algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2023年第6期45卷 9433-9444页

作者： Zhou, Chunrong Jiang, Zhenghong ChongqingVocat Coll Transportat Sch Big Data Chongqing 402247 Peoples R China

Load balancing in cloud computing refers to dividing computing characteristics and workloads. Distributing resources among servers, networks, or computers enables enterprises to manage workload demands. This paper proposes a novel load-balancing method based on the Two-Level particle swarm optimization (TLPSO). The proposed TLPSO-based load-balancing method can effectively solve the problem of dynamic load-balancing in cloud computing, as it can quickly and accurately adjust the computing resource distribution in order to optimize the system performance. The upper level aims to improve the population's diversity and escape from the local optimum. The lower level enhances the rate of population convergence to the global optimum while obtaining feasible solutions. Moreover, the lower level optimizes the solution search process by increasing the convergence speed and improving the quality of solutions. According to the simulation results, TLPSO beats other methods regarding resource utilization, makespan, and average waiting time.

关键词： Load balancing cloud computing virtualization 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

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

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：