检索结果-内蒙古大学图书馆

Parameter calibration method of clustered-particle logic concrete DEM model using BP neural network-particle swarm optimisation algorithm (BP-PSO) inversion method

引用

ENGINEERING FRACTURE MECHANICS 2023年 292卷

作者： Pan, Xupeng Niu, Yanwei Zhao, Yu Huang, Pingming Wu, Yizhen Chang An Univ Sch Highway Xian 710064 Shaanxi Peoples R China Chang An Univ Coll Future Transportat Xian 710064 Shaanxi Peoples R China

A high precision back propagation neural network-particle swarm optimization (BP-PSO) algorithm inversion method is proposed to calibrate the microparameters of the clustered-particle logic concrete discrete element method model. The calibration targets include initial damage, failure mode, and mechanical properties of the material. The research utilise 243 training datasets generated through orthogonal experimental design and conducted simulations to train the BP neural network. In addition, a parameter sensitivity analysis is employed on the trained BP neural network to quantify the impact level of each microparameter and guide future macroparameter fine-tuning. The results indicate that the mean absolute percentage error of the BP-PSO inversion method is only 3.79%. This research also study on the concrete failure mechanism by using a mesoscale model based on clustered-particle logic, which considered concrete as a three-phase composite composed of mortar matrix, aggregates, and interfacial transition zone. The crack initiation, propagation and coalescence of DEM model show a good agreement with the experimental results.

关键词： Discrete element method Initiation damage BP neural network particle swarm optimisation algorithm Parameter sensitivity analysis Concrete failure mechanism

来源：评论

学校读者我要写书评

暂无评论

Global Source optimisation Based on Adaptive Nonlinear particle swarm optimisation algorithm for Inverse Lithography

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2021年第4期13卷 1页

作者： Sun, Haifeng Du, Jing Jin, Chuan Feng, Jinhua Wang, Jian Hu, Song Liu, Junbo Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Sichuan Peoples R China Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Sichuan Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Source optimisation (SO) is an approved approach to improve the imaging quality in inverse lithography techniques. It is critical to apply an optimisation approach with high convergence efficiency and minimum errors in pixel-based SO. To improve the convergence efficiency of the pixel-based SO, a route of particle swarm optimiser (PSO) combined with the adaptive nonlinear control strategy (ANCS) is proposed in this study. As a global optimisation algorithm, ANCS-PSO has the attributes of breaking away from the local optimum by adjusting the particle learning factor adaptively. In addition, the nonlinear control approach can broaden the search range and speed up the convergence of the iteration operation. The proposed approach also is compared with the linear decreasing inertia weight strategy and the simulated annealing strategy. The performance verification simulation displays the validity of PSO-ANCS and its potentials in SO with high convergence efficiency and optimisation capacity, by comparing the linear decreasing inertia weight strategy and the simulated annealing strategy.

关键词： Source optimisation particle swarm optimisation algorithm adaptive nonlinear control strategy inverse lithography techniques

来源：评论

学校读者我要写书评

暂无评论

Hybrid firefly particle swarm optimisation algorithm for feature selection problems

引用

EXPERT SYSTEMS 2024年第7期41卷 e13363-e13363页

作者： Ragab, Mahmoud King Abdulaziz Univ Fac Comp & Informat Technol Informat Technol Dept Jeddah Saudi Arabia King Abdulaziz Univ Ctr Excellence Smart Environm Res Jeddah Saudi Arabia King Abdulaziz Univ Univ Oxford Ctr Artificial Intelligence Precis Med Jeddah Saudi Arabia King Abdulaziz Univ Fac Comp & Informat Technol Informat Technol Dept Jeddah Saudi Arabia

Feature selection techniques play a vital role in the processes that deal with enormous amounts of data. These techniques have become extremely crucial and necessary for data mining and machine learning problems. Researchers have always been in a race to develop and provide libraries and frameworks to standardise this procedure. In this work, we propose a hybrid meta-heuristic algorithm to facilitate the problem of feature selection for classification problems in machine learning. It is a python based, lucid and efficient algorithm geared towards optimising and striking a balance between the number of features selected and accuracy. The proposed work is a binary hybrid of existing meta-heuristic algorithms, the particle swarm optimisation (PSO) algorithm, and the firefly algorithm (FA) such that it blends the best of each algorithm to provide an optimised and efficient way of solving the said problem. The suggested approach is assessed against six datasets from different domains that are publicly available at the UCI repository to demonstrate its validity. The datasets are Breast cancer, Iris, WBC, Mushroom, Glass ID, and Abalone. This approach has also been evaluated against similar, such evolutionary-based approaches to prove its superiority. Various metrics such as accuracy, precision, recall, f1 score, number of selected features, and run time have been analysed, measured, and compared. The hybrid firefly particle swarm optimisation algorithm is found to be suitable for feature selection problems.

关键词： classification evolutionary algorithm feature selection firefly algorithm hybrid algorithm nature-inspired particle swarm optimisation algorithm

来源：评论

学校读者我要写书评

暂无评论

A NEW HYBRID WHALE particle swarm optimisation algorithm FOR ROBOT TRAJECTORY PLANNING AND TRACKING CONTROL

引用

MECHATRONIC SYSTEMS AND CONTROL 2024年第1期52卷 48-57页

作者： Zhang, Huakai Yancheng Teachers Univ Logist Support Grp Yancheng 224000 Peoples R China

In recent years, the use of robotic arms in the automation industry has become increasingly prevalent due to advances in science and technology. This paper aims to enhance the control accuracy of manipulators by designing a hybrid optimisation algorithm. The whale algorithm has been optimised and combined with the particle swarm optimisation (PSO) algorithm to achieve this goal. The trajectory of the manipulator is planned through the utilisation of the hybrid algorithm. The membership function of the fuzzy controller is optimised via the hybrid whale PSO algorithm, and combined with the sliding-mode controller, resulting in the design of a fuzzy sliding-mode controller. The results show that in the convergence curve, the iterations for the hybrid algorithm to reach the global optimal solution is 52, 75, and 183. The rate of convergence is faster. In the joint angle change curve, the total time of optimised B-spline interpolation is 19.95 s. The working efficiency of the manipulator is improved. In the calculation of tracking error, the optimised controller has a tracking error between-0.25 and 0.25, resulting in higher trajectory tracking accuracy. Therefore, the hybrid algorithm has good convergence, and the optimised controller has high accuracy, providing good technical support for trajectory planning and tracking control of robotic arms.

关键词： Robotic arm whale algorithm particle swarm optimisation algorithm fuzzy sliding-mode controller trajectory planning tracking control

来源：评论

学校读者我要写书评

暂无评论

Bacterial foraging optimisation algorithm, particle swarm optimisation and genetic algorithm: a comparative study

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION 2017年第4期10卷 275-282页

作者： Sadeghiram, Soheila Univ Mohaghegh Fac Engn Dept Informat Technol Ardabili Iran

Nature inspired meta-heuristic algorithms have been widely used in order to find efficient solutions for optimisation problems, and granted results have been achieved. particle swarm optimisation (PSO) algorithm is one of the most utilised algorithms in recent years, which has indicated acceptable efficiency. On the other hand, bacterial foraging optimisation algorithm (BFOA) is relatively new compared to other meta-heuristic algorithms, and like PSO has shown a good ability to solve different optimisation problems. Genetic algorithms (GAs) are a well-known group of meta-heuristic algorithms which have been in use earlier than the other in various research fields. In this paper, we compare the efficiency of BFOA and PSO algorithms in an identical condition by minimising different test functions (from two to 20 dimensional). In this experiment, GA is used as a basic method in comparing the two algorithms. The methodology and results are presented. Although results verify the accurate convergency of both algorithms, the efficiency of BFOA on high-dimensional functions is dramatically better than that of PSO.

关键词： particle swarm optimisation algorithm bacterial foraging optimisation algorithm BFOA genetic algorithms high-dimensional functions

来源：评论

学校读者我要写书评

暂无评论

Ore blending scheme optimization of copper smelting based on improved PSO algorithm

引用

CANADIAN METALLURGICAL QUARTERLY 2025年

作者： Li, Shilei Zhu, Daofei Yang, Yingbao Fu, Yanxiong Yan, Tao Kunming Univ Sci & Technol Fac Met & Energy Engn Kunming 650093 Peoples R China Yimen Copper Co Ltd Yuxi Peoples R China

In copper smelting, the ore blending scheme is crucial for product quality and cost. Traditional methods, relying on manual experience, have limitations and can't reach the optimal. This study thus presents an intelligent ore blending method. It starts by constructing a mathematical model. The objective function covers three aspects: minimising the cost of raw materials entering the furnace, minimising deviation of elemental content of raw materials entering the furnace from set values, and minimising deviation of the total weight of the ore blend from the set value. Constraint conditions consider production processes to ensure model feasibility. An improved PSO algorithm, with a linearly decreasing inertia weight and constriction factor method, is designed to solve the model. Tests using two sets of data from a large copper smelting enterprise show that for the same Cu and S contents, the cost of raw materials entering the furnace decreased by 40.044 yuan and 35.186 yuan per ton, respectively. Also, the intelligent method converges quickly, getting an optimised scheme in about 20s. This reduces ore blending workload, improves efficiency, cuts costs, and brings economic benefits to the enterprise. Dans le proc & eacute;d & eacute;de fusion du cuivre, le sch & eacute;ma de m & eacute;lange du minerai joue un r & ocirc;le d & eacute;cisif dans la qualit & eacute;et le co & ucirc;t du produit. Cependant, les m & eacute;thodes traditionnelles de m & eacute;lange du minerai se fondent principalement sur l'exp & eacute;rience manuelle et pr & eacute;sentent des limites importantes, ce qui rend difficile l'obtention d'un sch & eacute;ma de m & eacute;lange du minerai proche de l'optimal. Par cons & eacute;quent, cette & eacute;tude propose une m & eacute;thode intelligente de m & eacute;lange du minerai. En premier, cette m & eacute;thode construit un mod & egrave;le math & eacute;matique dont la fonction objective comprend trois aspects: premi & egrave;rement, le co & uci

关键词： Multi-objective nonlinear programming model particle swarm optimisation algorithm ore blending plan linearly decreasing inertia weight constriction factor method

来源：评论

学校读者我要写书评

暂无评论

Production planning and scheduling by means of artificial immune systems and particle swarm optimisation algorithms

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION 2012年第4期4卷 237-248页

作者： Budinska, Ivana Kasanicky, Tomas Zelenka, Jan Slovak Acad Sci Inst Informat Bratislava 84507 Slovakia

The main task of the scheduling optimisation process in production systems is to minimise production cost, overall production time and to ensure optimal utilisation of the resources. Application of stochastic search techniques to find a feasible schedule that minimise cost and satisfy all constraints jointed with all products can bring a particular solution of the complexity problem. On the other hand, the cost and the time of an optimisation process have to reciprocate with the found schedule;otherwise the optimisation loses its meaning. The article presents two stochastic methods, based on biologically inspired techniques, applied on a scheduling optimisation process. The first one is based on the mechanism inspired by biological evolution and the one method applies the swarm intelligence. The application of methods is illustrated on a real world example of a production line.

关键词： artificial immune systems AISs particle swarm optimisation algorithm production planning and scheduling bio-inspired computation

来源：评论

学校读者我要写书评

暂无评论

Prediction of permeability characteristics of mine slurries and sediments using finite-strain framework by optimisation algorithms

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 261卷

作者： Vasudev, Akhila Bharat, Tadikonda Venkata Indian Inst Technol Guwahati Dept Civil Engn Gauhati 781039 Assam India

Determining the permeability characteristics of mine tailing slurries through laboratory finite-strain consolidation tests is costly due to the extensive testing required. An alternative approach involves back-predicting hydraulic conductivities from settling column test data. This study employed settlement and excess pore pressure data as inputs in optimising the permeability parameters using the finite-strain consolidation (FSC) framework. The proposed approach used the finite difference method to solve the governing equation for FSC in the forward analysis. Two novel variants of the Artificial Bee Colony (ABC) algorithm, namely the Modified Artificial Bee Colony (MABC) and the Hybrid Artificial Bee Colony (HABC) algorithms, were used to back-predict the hydraulic conductivity function parameters from the FSC test data. These models predicted the permeability characteristics using the temporal variation of the settlements for six slurries and excess pore pressure dissipation data for four slurries. The performance of the proposed algorithms along with Hybrid particle swarm optimisation (HPSO) was compared with the conventional optimisation algorithms, viz., PSO, ABC, and Quantum PSO (QPSO). The HABC and HPSO exhibited remarkable stability, consistently converging to identical solution sets across multiple iterations, thereby outperforming other algorithms in this study. Despite its higher time complexity by HABC relative to the other evaluated methods, this complexity is warranted for enhanced robustness. The current study is helpful in brining practical and reliable methodologies for estimating the hydraulic conductivity function from field-scale conductivity (FSC) data, providing critical insights for the safe and efficient management of slurry wastes.

关键词： Finite strain consolidation Hydraulic conductivity function particle swarm optimisation algorithm Artificial bee colony algorithm Inverse analysis

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF PSO-ACO algorithm IN PATH PLANNING OF INTELLIGENT ROBOTS

引用

MECHATRONIC SYSTEMS AND CONTROL 2025年第1期53卷 42-53页

作者： Wang, Xiaohan Miao, Yanzi Jiuzhou Polytech Sch Electromech & Automot Engn Xuzhou 221116 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China

As robot technology continues to develop and innovate, it is widely applied in various fields of production and life. Path planning (PP) is the cornerstone of autonomous navigation of intelligent robots (IRs). However, the current particle swarm optimisation (PSO) and ant colony optimisation (ACO) algorithms still have problems, such as slow convergence rate (CR), complexity, and large amount of computation. Therefore, research will improve the hybrid ACO algorithm and PSO algorithm to obtain feasible robot PP. Then, ACO algorithm is used to obtain the optimal solution (OS), and the particle swarm ant colony fusion algorithm is obtained. Compared with PSO and ACO algorithms, the shortest path of the fusion algorithm is 43.78 m, which is closer to the optimal path. In an environment with an obstacle ratio of 0.4, the optimal performance index of the fusion algorithm is 8.84%, and the number of iterations during convergence is 24. Compared with genetic algorithm (GA) and sampling based PP algorithm, CR of this fusion algorithm is faster and the average value of the optimal path is smaller when the obstacle ratio is 0.7. In summary, the fusion algorithm proposed in this research is effective in IR path planning (IRPP). This can improve the path optimisation ability of IRs and provide a basis for exploring more effective global dynamic PP methods in the future.

关键词： Path planning particle swarm optimisation algorithm ant colony optimisation intelligent robot fusion algorithm

来源：评论

学校读者我要写书评

暂无评论

Identification and depth determination of potholes based on vibration acceleration of vehicles

引用

ROAD MATERIALS AND PAVEMENT DESIGN 2025年

作者： Zhang, Hongliang Pu, Haodong Zhuge, Xuchen Lv, Wenjiang Tang, Zujie Changan Univ Key Lab Special Area Highway Engn Minist Educ Xian Peoples R China Shandong Hispeed Grp Co Ltd Jinan Shandong Peoples R China Shaanxi Transportat Holding Grp CO LTD Xian Peoples R China Fujian Commun Construct Qual & Safety Ctr Fuzhou Fujian Peoples R China

The vibration acceleration of vehicles passing through potholes have been only used to identify the location of potholes with high accuracy, while this paper proposed a method for both identifying potholes and determining their depths based on vibration accelerations. The study first preprocessed the collected acceleration data. Then, a Newmark method was established to solve the vibration equations and get the acceleration of the vehicles passing potholes, in which vehicle vibration parameters were identified through drop test. Finally, the particle swarm optimisation algorithm was used to back estimate the pothole depths according to the vibration acceleration, followed by a verification test. Result show that the proposed pothole identification algorithm, based on the vibration acceleration threshold, can accurately identify potholes and mark their positions on the time-domain map. For pothole depth determination, the average error rate based on vibration accelerations is 8.94%, with a minimum error rate of just 0.50%, proving the method's high accuracy.

关键词： Potholes identification depth determination acceleration Newmark method particle swarm optimisation 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：