检索结果-内蒙古大学图书馆

International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology

作者： Saheli Ray Subhadeep Bhattacharjee Anirudhha Bhattacharya Department of Electrical Engineering National Institute of Technology

ISBN: (纸本)9781479929948

This paper proposes differential search algorithm (DS) to solve optimization problem of radial distribution system reliability with distributed generation being present in the system as standby unit. DS algorithm simulates the seasonal migration behavior of many organisms which migrate from one habitat to a more efficient one in terms of availability of food. Here, optimum failure rate and repair time of feeder segments have been calculated in order to enhance reliability of radial distribution system. The proposed method has been applied to a test case and compared with differential evolution (DE) technique. Simulation results reveal that the proposed approach performs better in terms of quality of solution obtained and computational efficiency as applied to optimize failure rate and repair time of radial distribution network with distributed generation.

关键词： differential search algorithm Distributed Generation Failure rate Optimization Radial distribution system Repair time

来源：评论

学校读者我要写书评

暂无评论

differential search Optimized Random Forest Regression algorithm for State of Charge Estimation in Electric Vehicle Batteries

Differential Search Optimized Random Forest Regression Algor...

引用

Annual Meeting of the IEEE-Industry-Applications-Society (IAS)

作者： Lip, M. S. Hossain Hannan, M. A. Hussain, Aini Ansari, Shaheer Ayob, Afida Saad, Mohamad H. M. Muttaqi, K. M. Univ Kebangsaan Malaysia Dept Elect Elect & Syst Engn Bangi 43600 Malaysia Univ Tenaga Nas Coll Engn Dept Elect Power Engn Kajang 43000 Malaysia Univ Wollongong Fac Engn & Informat Sci Northfields Ave Wollongong NSW 2522 Australia

ISBN: (纸本)9781728164014

This paper presents an improved machine learning approach for the accurate and robust state of charge (SOC) in electric vehicle (EV) batteries using differential search optimized random forest regression (RFR) algorithm. The precise SOC estimation confirms the safety and reliability of EV. Nevertheless, SOC is influenced by numerous factors which cannot be measured directly. RFR is suitable for SOC estimation due to its robustness to noise, overfitting issues and capacity to work with huge datasets. However, proper selection of RFR architecture and hyperparameters combination remains a key issue to be explored. Hence, a differential search algorithm (DSA) is employed to search for the optimal values of trees and leaves in RFR algorithm. DSA optimized RFR eliminates the utilization of the filter in data pre-processing steps and does not require a detailed understanding and knowledge about battery chemistry, rather only needs sensors to monitor battery voltage and current. The developed approach is validated at room temperature using two types of lithium-ion batteries under a pulse discharge test. In addition, the proposed model is verified under varying temperature settings under EV drive cycles. The experimental results demonstrate that the DSA optimized RFR algorithm is superior to other optimized machine learning approaches in achieving a lower error rate which illustrates the suitability of the proposed model in the online battery management system.

关键词： State of charge electric vehicle lithium-ion battery random forest regression differential search algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimating model parameters from SP anomaly of sheet-shaped sources using differential search and particle swarm optimization algorithms

引用

JOURNAL OF GEOPHYSICS AND ENGINEERING 2023年第4期20卷 661-679页

作者： Ozyalin, Senol Sindirgi, Petek Dokuz Eylul Univ Engn Fac Dept Geophys Engn Tinaztepe Campus TR-35390 Izmir Turkiye

In this study, the efficiency of estimating the model parameters of sheet-shaped single and multiple sources of the self-potential (SP) anomaly using the differential search algorithm (DSA) is investigated. First, noise-free and noisy synthetic anomalies are calculated for a single sheet-shaped source, and its model parameters estimated by DSA. The DSA inversion is also done for a model consisting of three inclined sheets. To test the effectiveness of the method, the same processes are repeated with a more conventional algorithm, particle swarm optimization (PSO), and the solutions of both methods are compared. The results of synthetic anomaly analyses show that DSA can predict the parameters as accurately as PSO. Then, both algorithms are also applied to two field SP anomalies (Surda and Beldih) that have been evaluated by different algorithms in the literature. The source of the Surda anomaly is modelled as one sheet, whereas the source model of the Beldih anomaly is assumed to consist of three sheets. The five model parameters for each model are estimated using both algorithms and it is determined that they are in good agreement with the findings of the previous studies. The contribution of the regional background anomaly to the synthetic and field anomalies are also included and regional coefficients are estimated. Finally, we conclude that DSA can solve the source parameters without the need for the initial values required in conventional iterative inversion methods and is an efficient and promising algorithm for determining the parameters of SP sources.

关键词： self-potential differential search algorithm particle swarm optimization sheet model inversion

来源：评论

学校读者我要写书评

暂无评论

Optimal allocation of remote control switches in radial distribution network for reliability improvement

引用

AIN SHAMS ENGINEERING JOURNAL 2018年第3期9卷 403-414页

作者： Ray, Saheli Bhattacharjee, Subhadeep Bhattacharya, Aniruddha Natl Inst Technol Agartala Dept Elect Engn Agartala 799046 Tripura India

This paper presents differential search algorithm in order to solve reliability optimization problem of radial distribution network. Remote control switches have been optimally allocated to improve reliability at a compromised cost. A multi-objective problem has been formulated and solved using differential search algorithm. The test systems considered in this paper are an 8 bus radial distribution network and a 33 bus radial distribution network. Simulation results obtained using differential search algorithm when applied to the test cases, have been compared with those obtained by particle swarm optimization. differential search algorithm has been found to provide superior results as compared to particle swarm optimization. (C) 2016 Production and hosting by Elsevier B.V. on behalf of Ain Shams University.

关键词： differential search algorithm Multi-objective function Radial distribution system Remote control switches Repair time Restoration time

来源：评论

学校读者我要写书评

暂无评论

Frequency Phase Space Empirical Wavelet Transform for Rolling Bearings Fault Diagnosis

引用

IEEE ACCESS 2019年 7卷 86306-86318页

作者： Huang, Xin Wen, Guangrui Liang, Lin Zhang, Zhifen Tan, Yuan Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Shaanxi Peoples R China Xinjiang Univ Sch Mech Engn Urumqi 830047 Peoples R China

As one of the most important components in rotating machinery, rolling bearings are fragile due to their harsh working environment. The empirical wavelet transform (EWT) method has been used to identify bearing faults by constructing an adaptive filter bank and decomposing the vibration signal into different modes. However, the EWT method separates different parts based on the local extremum of the Fourier spectrum. This segmentation strategy is highly susceptible to other components such as gears, and sometimes the fault characteristics of bearings cannot be detected. To overcome the above drawbacks, frequency phase space empirical wavelet transform (FPSEWT) method is proposed in this paper, which divides the spectrum into several parts and uses the Teager energy distribution as a reference for dividing the Fourier spectrum. Then, the differential search (DS) algorithm is applied to automatically identify the optimal right and left boundaries of the sensitive frequency band. The effectiveness of the proposed approach is verified by both simulated signals and experimental data. The fault feature ratio (FFR) values of sensitive components increased from 8.08% to 18.67%, which indicate that the proposed method can successfully extract fault symptoms of rolling element bearings in the presence of environmental disturbance.

关键词： differential search algorithm empirical wavelet transform phase space rolling bearing fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Comparative study between different optimisation techniques for finding precise switching angle for SHE-PWM of three-phase seven-level cascaded H-bridge inverter

引用

IET POWER ELECTRONICS 2018年第3期11卷 600-609页

作者： Kundu, Sourabh Burman, Arka Deb Giri, Santu K. Mukherjee, Sarbani Banerjee, Subrata Natl Inst Technol NIT Durgapur Dept Elect Engn Durgapur 713209 India CSIR Cent Mech Engn Res Inst SET Grp Durgapur 713209 India

Selective harmonic elimination pulse-width modulation (SHE-PWM) works at low-frequency switching, which reduces switching losses, device stress, and increases energy conversion efficiency. So, it can be an effective control strategy for multilevel inverter working on medium-voltage, high-power industrial energy conversion application. It provides desired output voltage by retaining the requested fundamental component as well as eliminating some low-order harmonics. The application of SHE-PWM in industries is having an influence on precise solvability of complex and non-linear equations. This study presents two recently reported optimisation techniques, namely backtracking search algorithm and differential search algorithm (DSA) for obtaining a more accurate solution of the harmonics elimination problem. The superiority of the proposed optimisation algorithms over the well known ancient algorithm such as genetic algorithm, BEE algorithm and particle swarm optimisation have been established by a comparative study with respect to the possibility of attaining global minima, the rank of convergence rate, and inverter performance analysis. Simulation and experimental results validate the efficacy of the DSA optimisation technique for calculating more precise switching angles that totally eliminate 5th- and 7th-order harmonics with fulfilling the requested fundamental component.

关键词： PWM invertors switching convertors harmonics suppression search problems genetic algorithms particle swarm optimisation SHE-PWM three-phase seven-level cascaded H-bridge inverter selective harmonic elimination pulse-width modulation multilevel inverter medium-voltage high-power industrial energy conversion application energy conversion efficiency low-order harmonic elimination complex equation nonlinear equation backtracking search algorithm DSA differential search algorithm genetic algorithm BEE algorithm particle swarm optimisation 5th-order harmonic elimination 7th-order harmonic elimination

来源：评论

学校读者我要写书评

暂无评论

Real-Time State of Charge Estimation of Lithium-Ion Batteries Using Optimized Random Forest Regression algorithm

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第1期8卷 639-648页

作者： Lipu, M. S. Hossain Hannan, M. A. Hussain, Aini Ansari, Shaheer Rahman, S. A. Saad, Mohamad H. M. Muttaqi, K. M. Green Univ Bangladesh Dept Elect & Elect Engn Dhaka 1207 Bangladesh Univ Tenaga Nas Coll Engn Dept Elect Power Engn Kajang 43000 Malaysia Univ Kebangsaan Malaysia Dept Elect Elect & Syst Engn Bangi 43600 Malaysia Univ Wollongong Fac Engn & Informat Sci Wollongong NSW 2522 Australia

This paper presents an improved machine learning approach for the accurate and robust state of charge (SOC) in electric vehicle (EV) batteries using differential search optimized random forest regression (RFR) algorithm. The precise SOC estimation confirms the safety and reliability of EV. Nevertheless, SOC is influenced by numerous factors which cannot be measured directly. RFR is suitable for real-time SOC estimation due to its robustness to noise, overfitting issues and capacity to work with huge datasets. However, proper selection of RFR architecture and hyper-parameters combination remains a key issue to be explored. Hence, a differential search algorithm (DSA) is employed to search for the optimal values of trees and leaves in the RFR algorithm. DSA optimized RFR eliminates the utilization of the filter in data pre-processing steps and does not require a detailed understanding and knowledge about battery chemistry, rather only needs sensors to monitor battery voltage and current. The developed approach is validated at room temperature using two types of lithium-ion batteries under a pulse discharge test. In addition, the proposed model is verified under varying temperature settings under EV drive cycles. The experimental results demonstrate that the DSA optimized RFR algorithm achieves RMSE of 0.382% in the HPPC test using LiNMC battery. Besides, the proposed method obtains satisfactory outcomes in EV drive cycles, estimating MAE of 0.193% and 0.346% in DST and FUDS cycles, respectively, at 25 degrees C.

关键词： State of charge Batteries Estimation Prediction algorithms Random forests Mathematical models Training differential search algorithm electric vehicle lithium-ion battery random forest regression state of charge

来源：评论

学校读者我要写书评

暂无评论

Improvement of power utilisation capability for a three-phase seven-level CHB inverter using an improved selective harmonic elimination-PWM scheme by sharing a desired proportion of power among the H-bridge cells

引用

IET POWER ELECTRONICS 2019年第12期12卷 3242-3253页

作者： Kundu, Sourabh Bhowmick, Supratik Banerjee, Subrata Natl Inst Technol NIT Durgapur Dept Elect Engn Durgapur 713209 India

An improved selective harmonic elimination-pulse width modulation (SHE-PWM) scheme has been proposed for a three-phase seven-level cascaded H-bridge (CHB) inverter that enhances the power utilisation capability of the inverter by sharing the desired amount of power among the H-bridge cells and also eliminates both 5th- and 7th-order harmonic components from the inverter output voltage maintaining the desired fundamental voltage component for a wide range of modulation index. Compared to conventional SHE-PWM, this scheme introduces two additional switching in the first cell, while the second and the third cells are switched at advanced switching angles. The differential search algorithm (DSA) technique has been applied to solve the proposed SHE-PWM scheme, and it exhibited comparatively better performance than the algorithm based on genetic algorithm, BEE algorithm and particle swarm optimisation. The effectiveness of the proposed scheme has been verified by both simulation and experimental study on a seven-level CHB inverter. Finally, the proposed scheme has been applied to the closed-loop constant V/f control of the induction motor drive application. It has been established that the proposed scheme is independent of the load power factor angle, and it improved the power conversion efficiency of the conventional SHE-PWM scheme.

关键词： PWM invertors genetic algorithms particle swarm optimisation switching convertors harmonics suppression closed loop systems power factor search problems power utilisation capability H-bridge cells 7th-order harmonic components inverter output voltage modulation index advanced switching angles optimal switching angles genetic algorithm BEE algorithm seven-level CHB inverter load power factor angle transient condition smooth speed variation induction motor drive application closed-loop constant V-f control convergence rate global optimum solution particle swarm optimisation DSA technique differential search algorithm fundamental voltage component 5th-order harmonic components three-phase seven-level cascaded H-bridge inverter SHE-PWM scheme improved selective harmonic elimination-pulse width modulation scheme three-phase seven-level CHB inverter power conversion efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimal Control Vector Parameterization Approach with a Hybrid Intelligent algorithm for Nonlinear Chemical Dynamic Optimization Problems

引用

CHEMICAL ENGINEERING & TECHNOLOGY 2015年第11期38卷 2067-2078页

作者： Zhang, Panpan Liu, Xinggao Ma, Liang Zhejiang Univ Inst Ind Proc Control Control Dept Hangzhou 310027 Zhejiang Peoples R China

A control vector parameterization (CVP)-based hybrid algorithm, HAPSODSA-CVP, is proposed to solve the nonlinear chemical dynamic optimization problems, where adaptive particle swarm optimization (APSO) is applied to enhance the global search ability, while differential search algorithm (DSA) is used to improve the local exploitation ability. Three well-known classic nonlinear chemical dynamic optimization problems are tested as illustration, and detailed comparisons are carried out among PSO-CVP, APSO-CVP, and HAPSODSA-CVP approaches. The research results not only demonstrate the efficiency of the HAPSODSA-CVP approach for this kind of dynamic optimization problems, but also its superiority to both APSO-CVP and PSO-CVP approaches in terms of accuracy as well as convergence rate.

关键词： Control vector parameterization differential search algorithm Dynamic optimization Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Heuristic Modelling of traffic accident characteristics

引用

TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION REsearch 2021年第7期13卷 522-530页

作者： Tercan, Emre Besdok, Erkan Tapkin, Serkan Gen Directorate Highways Dept Survey Project & Environm Reg 13 Antalya Turkey Erciyes Univ Dept Geomat Engn Kayseri Turkey Antalya Bilim Univ Dept Civil Engn Antalya Turkey

Due to the complex structure of observation based traffic accident data and the absence of an analytic model to define their characteristics, different models are required. Accident characteristics have been modeled for different road segments with two different methods: evolutionary data clustering method and resilient neural networks. In the first method, observation data was clustered using an evolutionary search-based clustering algorithm. The first method is based on determining whether observation based test data have the conditions of a possible death or injury accident based on the distance to the cluster centers obtained. The second one is a regression method that predicts whether an accident will cause death or injury according to observation based traffic data in test road segments by using resilient neural networks. Experiment results show that data analysis methods are very effective in determining the existence of the conditions that may cause accidents resulting in death or injury.

关键词： Traffic accident traffic safety data clustering resilient neural networks evolutionary computation optimization differential search algorithm Calinski-Harabasz index

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：