检索结果-内蒙古大学图书馆

Offshore wind power prediction based on chaotic optimisation PSO-SCN-LSTM model

INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS 2025年第1期21卷 48-63页

作者： Li, Xu Kou, Lei Zhang, Benfa Wang, Zhen Wen, Jingya Zhang, Fangfang Du, Jinyan Zhou, Yan Ke, Wende Qilu Univ Technol Inst Oceanog Instrumentat Shandong Acad Sci Qingdao 266075 Peoples R China State Grid Songyuan Power Supply Co Songyuan 138099 Peoples R China Southern Univ Sci & Technol Dept Mech & Energy Engn Shenzhen 518055 Peoples R China

Offshore wind power, as a clean energy source, is receiving increasing attention worldwide. To enhance the economic and safety performance of offshore wind power, short-term forecasting of wind power is essential. This paper proposes a model based on chaos optimisation integrated with particle swarm optimisation (PSO), stochastic configuration network (SCN), and long short-term memory (LSTM) algorithm. Firstly, leveraging the randomness and ergodicity of the complex logistic chaos system, the collected power data from wind turbines is utilised as the input data source for the PSO, enhancing the randomness of the data. Subsequently, the SCN is employed to optimise the PSO, increasing the variation in the hidden layer during iterations and mitigating the PSO's tendency to fall into local optima, thereby obtaining initial prediction values. Finally, the mechanism model of the LSTM is utilised for secondary prediction, further improving prediction accuracy. Compared with traditional algorithms, the optimised algorithm significantly reduces errors and enhances prediction precision.

关键词： chaos theory particle swarm optimisation algorithm random configuration network LSTM prediction model

来源：评论

学校读者我要写书评

暂无评论

Urban heat island distribution observation by integrating remote sensing technology and deep learning

引用

INTERNATIONAL JOURNAL OF IMAGE AND DATA FUSION 2025年第1期16卷

作者： Lin, Huanuan Yantai Inst Sci & Technol Supervis Dept Yantai 265600 Peoples R China

Using particle swarm optimisation algorithm to optimise support vector machines enhances urban heat island observation methods, while remote sensing technology aids in selecting temperature estimation parameters. Then the two are combined to construct a model for estimating urban near-surface temperature. A contribution study is conducted on the selected parameters. The selected parameters have contributions in the near-surface temperature estimation. The determination coefficient of the constructed urban near-surface temperature estimation model was 0.892. The root mean square error was 0.42 degrees C, the F1 value is 0.82, and the running time is 0.41 seconds, which was superior to other comparison models. Additionally, this model was applied to observe the urban heat island in Xi'an. The overall spatial distribution was low in the south and high in the north, with the central area being higher than the surrounding area, the highest temperature is 23.51 degrees C, and the lowest temperature is 19.05 degrees C. Moreover, the intensity level in the high-temperature area accounted for 16.9%. Based on the above results, the near-surface temperature estimation model constructed in the study has shown high accuracy and efficiency in urban heat island observation. It can be applied in practice, providing theoretical reference for urban planning and ecological environment protection.

关键词： Remote sensing technology deep learning particle swarm optimisation algorithm support vector machine urban heat island

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid particle swarm optimisation method applied to economic dispatch

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION 2010年第1期2卷 9-17页

作者： Zhang, Tao Cai, Jin-ding Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350002 Fujian Peoples R China

Economic load dispatch is complex and non-linear problem, it is difficult to solve the problem using traditional optimisation method. PSO has been successfully applied to a wide range of applications, in solving continuous non-linear optimisation problems. This paper presents a novel hybrid PSO algorithm with dynamic inertial weight and chaotic search to solve the problem. The improved hybrid PSO enhanced the global search ability of the algorithm and improved its convergence speed. The hybrid PSO algorithm was successfully validated for two test systems. Numerical simulation results show that the modified hybrid PSO algorithm outperformed standard PSO algorithm and genetic algorithm on the same problem and can save considerable cost of economic load dispatch.

关键词： economic dispatch particle swarm optimisation algorithm genetic algorithm GA chaotic search valve-point effect globe optimisation dynamic inertial weight non-linear optimisation

来源：评论

学校读者我要写书评

暂无评论

Adaptive prescribed-time disturbance observer using nonsingular terminal sliding mode control: Extended Kalman filter and particle swarm optimization

引用

IET CONTROL THEORY AND APPLICATIONS 2020年第19期14卷 3301-3311页

作者： Vahidi-Moghaddam, Amin Rajaei, Arman Ayati, Moosa Vatankhah, Ramin Hairi-Yazdi, Mohammad Reza Michigan State Univ Dept Mech Engn E Lansing MI 48824 USA Shiraz Univ Sch Mech Engn Shiraz Iran Univ Tehran Sch Mech Engn Coll Engn Tehran Iran

In this study, adaptive prescribed finite-time stabilisation of uncertain single-input and single-output non-linear systems is considered in the presence of unknown states, unknown parameters, external load disturbance, and non-symmetric input saturation. A prescribed finite time disturbance observer is designed to approximate the unmeasured external disturbance. Also, a non-singular prescribed finite time terminal sliding mode control is proposed for the closed-loop control of the system with the non-symmetric input saturation. Extended Kalman filter algorithm is employed for the real-time estimations of the states and unknown parameters of the system. Moreover, a particle swarm optimisation algorithm is used to obtain the design parameters of the proposed disturbance observer and controller. To show the performance of designed control scheme, the proposed approach is employed to guarantee prescribed finite time stabilisation of non-linear vibration of a non-local strain gradient nanobeam. The Galerkin projection method is used to reduce the non-dimensional form of the governing non-linear partial differential equation of Euler-Bernoulli nanobeam to the ordinary differential equation. Finally, numerical simulations are performed to illustrate the effectiveness and performance of the developed adaptive control scheme for the vibration control of nanobeam in comparison with the conventional sliding mode control.

关键词： observers uncertain systems Kalman filters Galerkin method control system synthesis differential equations adaptive control stability closed loop systems partial differential equations vibration control linear systems vibrations particle swarm optimisation variable structure systems nonlinear control systems uncertain nonlinear systems nonsingular terminal finite-time stabilisation uncertain single-input single-output unknown states unknown parameters external load disturbance nonsymmetric input saturation prescribed finite time disturbance observer approximate the unmeasured external disturbance nonsingular prescribed finite time terminal closed-loop control Extended Kalman filter algorithm real-time estimations particle swarm optimisation algorithm design parameters controller designed control scheme prescribed finite time stabilisation nonlinear vibration nonlocal strain gradient nanobeam nondimensional form governing nonlinear partial differential equation developed adaptive control scheme

来源：评论

学校读者我要写书评

暂无评论

Cascaded controller for a standalone microgrid-connected inverter based on triple-action controller and particle swarm optimisation

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第17期14卷 3389-3399页

作者： Salim, Omar M. Aboraya, Amgad Arafa, Shawky I. Benha Univ Dept Elect Engn Banha Egypt October 6 Univ Dept Elect Engn Giza 12585 Egypt

In this study, power quality (PQ) improvement has been addressed, in the form of total harmonic distortion (THD) minimisation, as well as, voltage regulation using two cascaded schemes. The first scheme is the optimised triple action controller (TAC)-based pulse width modulated voltage source inverter. TAC consists of a proportional resonant controller, selective harmonic compensator, and a new added current-assisted feed forward controller. The second scheme is the optimised cascaded dual-level control of a standalone microgrid. Cascaded level control consists of droop, secondary, and synchronisation control loops. The two approaches have been optimised for best parameter selection out of the possible solution space using a particle swarm optimisation algorithm to satisfy the study objectives. The optimisation objectives/constraints were to minimise THD and minimise overshoot/undershoot, rise time, and steady-state error for voltage compensation under two disturbance scenarios, sudden load change, and voltage flicker injection as a power frequency disturbance. These research results have been compared to other existing simulation and experimental work. The results proved to be better in output voltage, frequency, response time, and THD. Furthermore, the proposed schemes ensure power factor improvement, high efficiency, overall system PQ, and reliability at various load conditions.

关键词： particle swarm optimisation harmonic distortion invertors power generation control power grids feedforward distributed power generation voltage control electric current control cascade control power factor power supply quality cascaded controller standalone microgrid-connected inverter triple-action controller power quality improvement total harmonic distortion voltage regulation cascaded schemes optimised triple action controller-based pulse TAC modulated voltage source inverter proportional resonant controller selective harmonic compensator added current-assisted feed forward controller optimised cascaded dual-level control cascaded level control synchronisation control loops particle swarm optimisation algorithm study objectives THD voltage compensation voltage flicker injection power frequency disturbance output voltage power factor improvement

来源：评论

学校读者我要写书评

暂无评论

particle swarm algorithm for Smart Contract Vulnerability Detection Based on Semantic Web

引用

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS 2024年第1期20卷 1页

作者： Feng, Tao Cui, Yuyang Lanzhou Univ Technol Sch Comp & Commun Lanzhou Peoples R China

In recent years, smart contracts have risen rapidly in the blockchain field, but security issues have also become increasingly prominent. Due to the lack of unified evaluation standards, the security analysis of smart contracts mainly relies on complex and not easily scalable expert rules. To address these issues, we employ slicing techniques to reduce the interference of extraneous code on the detection process, apply normalisation techniques to eliminate the differences between different compiler versions and use particle swarm optimisation algorithms to determine the similarity between contracts, thus improving the accuracy and efficiency of detection. In addition, we combine a variety of features such as static analysis, dynamic analysis and symbolic execution to gain a more comprehensive understanding of contract characteristics and behaviours for more accurate vulnerability identification. Experimental results show that the scheme significantly improves the detection capability and provides a new solution for the security detection of smart contracts.

关键词： Graph Embedding algorithm Multimodal Feature Fusion particle swarm optimisation algorithm Smart Contracts Vulnerability Detection

来源：评论

学校读者我要写书评

暂无评论

Electric vehicle modelling and energy-efficient routing using particle swarm optimisation

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2016年第2期10卷 65-72页

作者： Abousleiman, Rami Rawashdeh, Osamah Oakland Univ Dept Elect & Comp Engn Rochester MI 48309 USA

Vehicle routing is traditionally based on Dijkstra or Dijkstra-like algorithms. These algorithms worked well for fossil fuel vehicles. The increase in pollution levels, government regulations, and pressure from environmental groups have caused an increase in electric vehicles (EVs) production and use. EVs are capable of regenerating energy which creates negative weights in search graphs that traditional algorithms are incapable of handling without some modifications. This study presents a model that characterises the energy consumption of an electric vehicle. Most passive and active factors are presented and applied in the formulation. The presented model is verified against 306 kilometres of driven data and proved to have 1.3% absolute error difference between the real vehicle's consumed energy versus the predicted energy consumption as generated by the model. The model is then used with a particle swarm optimisation algorithm to solve the single constraint optimisation problem of finding the most energy efficient route between 2 points on a map. Simulation and real-world test results demonstrate savings in the energy consumption of the electric vehicle. Results showed more than 9.2% reductions in the energy consumption of the electric vehicle when driven on the developed algorithms' suggested routes rather than the ones generated by Google Maps and MapQuest.

关键词： particle swarm optimisation electric vehicles vehicle routing energy conservation energy consumption search problems graph theory electric vehicle modelling energy-efficient routing vehicle routing Dijkstra-like algorithms fossil fuel vehicles pollution levels government regulations EVs production energy regeneration search graphs energy consumption active factors passive factors particle swarm optimisation algorithm single constraint optimisation problem

来源：评论

学校读者我要写书评

暂无评论

particle swarm approach to the optimisation of trenched cantilever-based MEMS piezoelectric energy harvesters

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2019年第4期13卷 582-588页

作者： Kordrostami, Zoheir Roohizadegan, Sajjad Shiraz Univ Technol Dept Elect Engn Shiraz Iran

A micro-electro-mechanical system (MEMS) trenched piezoelectric energy harvester based on a cantilever structure has been proposed. The trenched piezoelectric layer has increased the output voltage and the generated power. It also provides three additional design parameters such as the trench position, depth and length. A particle swarm approach has been used for optimisation of the piezoelectric energy harvester geometry with the aim of finding the optimum design which transfers the maximum harvested power to a definite load. The optimisations and comparisons have been made for unimorph, bimorph, trenched and non-trenched cantilever beams. The results are quite revealing that the generated power for a trenched bimorph energy harvester is much larger than other structures. The optimum design found by particle swarm optimisation algorithm has asymmetric trenches in the top and bottom piezoelectric layers and can generate much more power than the unoptimised structure.

关键词： micromechanical devices piezoelectric transducers cantilevers particle swarm optimisation energy harvesting optimisation particle swarm approach piezoelectric energy harvester geometry trenched bimorph energy harvester particle swarm optimisation algorithm piezoelectric layers trenched cantilever-based MEMS piezoelectric energy harvesters microelectro-mechanical system cantilever structure piezoelectric layer

来源：评论

学校读者我要写书评

暂无评论

A new localization method based on improved particle swarm optimization for wireless sensor networks

引用

IET SOFTWARE 2022年第3期16卷 251-258页

作者： Yang, Qiaohe Shanghai Univ Sch Commun & Informat Engn Key Lab Special Fiber Opt & Opt Access Networks Shanghai Peoples R China

Wireless sensor network (WSN) node localisation technology based on received signal strength indication (RSSI) is widely used as it does not need additional hardware devices. The ranging accuracy of RSSI is poor, and the particle swarm optimisation (PSO) algorithm can effectively improve the positioning accuracy of RSSI. However, the particle swarm diversity of the PSO algorithm is easy to lose quickly and fall into local optimal solution in the iterative process. Based on the convergence conditions and initial search space characteristics of the PSO algorithm in WSN localisation, an improved PSO algorithm (improved self-adaptive inertia weight particle swarm optimisation [ISAPSO]) is proposed. Compared with the other two PSO location estimation algorithms, the ISAPSO location estimation algorithm has good performance in positioning accuracy, power consumption and real-time performance under different beacon node proportions, node densities and ranging errors.

关键词： improved PSO algorithm WSN localisation node densities improved particle swarm optimization particle swarm diversity ranging accuracy wireless sensor networks sensor placement ranging errors mobile radio particle swarm optimisation additional hardware devices initial search space characteristics ISAPSO location estimation algorithm different beacon node proportions localization method received signal strength indication self-adaptive inertia weight particle swarm optimisation PSO location estimation algorithms positioning accuracy particle swarm optimisation algorithm search problems RSSI wireless sensor network node localisation technology local optimal solution

来源：评论

学校读者我要写书评

暂无评论

Hybrid precoding for millimetre wave MIMO systems based on particle swarm optimisation

引用

IET COMMUNICATIONS 2019年第11期13卷 1643-1650页

作者： Cui, Mingyang Zou, Weixia Wang, Ye Zhang, Ran Beijing Univ Posts & Telecommun MOE Key Lab Univ Wireless Commun Beijing 100876 Peoples R China Southeast Univ State Key Lab Millimeter Waves Nanjing 210096 Jiangsu Peoples R China

Millimetre wave (mmWave) multiple-input multiple-output (MIMO) systems have been proposed to enable Gbps communication for next-generation cellular systems and local area networks. To compensate for the severe propagation loss of the mmWave channel, a cost-effective hybrid precoding architecture, combining a digital precoder and an analogue precoder, is widely used in mmWave MIMO systems. In this study, two hybrid precoding algorithms based on particle swarm optimisation (PSO) algorithm will be proposed for two different hybrid precoding structures, i.e. the fully connected and partially connected structures. First, the authors use the phase of the analogue precoding variable to replace the corresponding variable with the constraints of the unit norm to solve the non-convex constraints skillfully. Then they design analogue precoding by using PSO algorithm and compute the digital precoding based on the least squares solution. Finally, the proposed algorithms are compared with the existing advanced algorithms. Simulation results demonstrate that the proposed algorithms can approach the optimal performance under the corresponding structure.

关键词： particle swarm optimisation precoding MIMO communication channel coding concave programming millimetre wave communication cellular radio local area networks wireless channels digital precoder analogue precoder mmWave MIMO systems hybrid precoding algorithms particle swarm optimisation algorithm fully connected structures partially connected structures analogue precoding PSO algorithm digital precoding millimetre wave MIMO systems millimetre wave multiple-input multiple-output systems next-generation cellular systems local area networks severe propagation loss mmWave channel cost-effective hybrid precoding architecture hybrid precoding structures least squares solution nonconvex constraints

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：