检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence and Computational Intelligence

作者： Xu, Jie Gao, Mingyu He, Zhiwei Yao, Jianbin Xu, Hongfeng Hangzhou Dianzi Univ Automobile Elect Lab Elect Circuit & Syst Dept Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9780769538167

State of charge (SOC) estimation is an increasingly important issue in battery management system (BMS) and has become a core factor to promote the development of electric vehicle (EV). In addition to offering the real time display of battery parameters to user, the accurate SOC information would exert some controls over the charging and discharging process that in turn reduces the risk of cell over voltage. Considering the shortcoming of traditional estimation methods and the harsh requirements in EV environment, a new method named combination algorithm is proposed in this paper in accordance with the characteristics of lithium-ion power battery. Some capacity effect factors, such as current rate and cell temperature, are also taken into consideration in the algorithm. The dynamic discharge test shows that the maximal SOC estimation error is less than 5%, which validates the feasibility and availability of the combination algorithm in the SOC estimation of electric vehicle.

关键词： combination algorithm state of charge (SOC) open circuit voltage (OCV) extended Kalman filtering (EKF) ampere hour (Ah) battery management system (BMS) electric vehicle (EV)

来源：评论

学校读者我要写书评

暂无评论

A Method of Automatic Test Case Generation Based on CT-LSSVM algorithm in FAO Systems 5

A Method of Automatic Test Case Generation Based on CT-LSSVM...

引用

IEEE 5th International Conference on Intelligent Transportation Engineering (ICITE)

作者： Wang, Sha Shang, Qingyuan Ling, Zhujun Liu, Dandan Chen, Xiangxian UniTTEC Co Ltd Hangzhou Peoples R China Zhejiang Univ Dept Instrumentat Sci & Engn Hangzhou Peoples R China

ISBN: (纸本)9781728194097

The FAO system is a new-generation railway signaling system, the comprehensive and accurate testing is the main means to verify the safety and stability of the system, and the design and generation of test cases is an important link of the system testing. Traditionally, test cases are manually generated, which is inefficient, time-consuming and inaccurate. To solve this problem, we proposed an automatic test case generation method for the FAO system specified scenario using the CT-LSSVM algorithm. The CT algorithm was used to realize multi-factor combination to generate test cases, and the LSSVM method was used to predict and analyze the expected results of the test cases. The results showed that when the LSSVM method was used to model and analyze the test cases generated by the CT five-factor combination, the recognition rate of the calibration set was 96.58% and the recognition rate of the test set was 97.73%;At the same time, some test cases of the twelve-factor combination were predicted and analyzed, and the recognition rate reached 98.57% This proves that the CT-LSSVM method can be applied to the test case generation of the FAO system.

关键词： FAO system test cases combination algorithm least square support vector machine

来源：评论

学校读者我要写书评

暂无评论

Harmonic and Inter-harmonic Detection Based on FFT and Nonlinear Optimization

Harmonic and Inter-harmonic Detection Based on FFT and Nonli...

引用

2nd International Conference on Advanced Design and Manufacturing Engineering (ADME 2012)

作者： Zhang Huaiqing Liu Ran Xiong Hao State Key Lab Transmiss Equipment & Syst Safety & Chongqing Peoples R China

ISBN: (纸本)9783037855034

In order to analyze harmonic and inter-harmonic parameters more accurately, a new detecting method that combined the nonlinear least squares and fast Fourier transform(FFT) was proposed. The FFT was used to produce a rough estimated value of harmonic parameters and then the signal model was set. Finally, the parameters can be estimated more accurately by the use of optimization algorithm which based on damped nonlinear-least squares method. The combined method solves the problem of inaccurate estimate by FFT and solves the problem of how to set the signal model and to choose initial value. The simulation results show that the combined method is effective and far more accuracy than interpolated Hanning window method.

关键词： harmonic detection inter-harmonic nonlinear optimization FFT combination algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Genetic algorithm Evidence Model and Its Application for Discriminating Enemy Radar Operation Intention

Adaptive Genetic Algorithm Evidence Model and Its Applicatio...

引用

24th Chinese Control and Decision Conference (CCDC)

作者： Pan Wei Li Wenjun Yang Jinsong Shenyang Artillery Acad Elect Detect Dept Shenyang 110867 Peoples R China Shenyang Artillery Acad Self Propelled Artillery & Command Shenyang 110867 Peoples R China

ISBN: (纸本)9781457720727

Considering the signatures captured from information about the hostile radar operation intention, this paper puts forward concepts of the simplest evidence support format, duality evidence support format, and same-type evidence and so on. Based on these concepts, it discusses the problem of the orthogonal sum with the duality evidence support format expressed as the simplest evidence support format, and then, drawing its conclusion to show the relation between the enemy intention and the characteristic information. Thereby, it establishes a system for radar operation intention discrimination to complete the final determinant. This new model brings expression and combination of evidences simplified and computation reduced. By practical application, this algorithm has been proved feasibility and effectiveness.

关键词： radar intention recognition evidence model performance analysis combination algorithm adaptive genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Wind Speed Forecasting Based on Fuzzy-neural Network combination Method

Wind Speed Forecasting Based on Fuzzy-neural Network Combina...

引用

第27届中国控制与决策会议

作者： Shanzhi LI Haoping WANG Yang TIAN Yanyan SHEN Abdel AITOUCHE Sino-French Int.J.Laboratory of Automatic Control and Signal Processing(LaFCAS) Automation SchoolNanjing University of Science & Technology LaFCAS and LAGIS Laboratories HEIUniversity Lille Nord de France

ISBN: (纸本)9781479970186

Wind speed forecasting is significant for power system *** and rapidity are essential *** paper is proposed a combination method based on a fuzzy neural *** combination weight of the proposed hybrid model which combines an Autoregressive Integrated Moving Average(ARIMA) model and a Radial Basis Function Neural Network(RBFNN) model is adjusted online according to the previous *** validate the proposed method effectiveness and performance,two cases of wind data have been *** first one is a simulation wind case and created by TurbSim code,which is developed by National Renewable Energy *** other one is a real-time wind speed case and its wind farm is located in northern Gulf of *** with the single models of ARIMA,RBFNN,hybrid mean strategy and variance strategy,the result of fuzzy-neural network combination method reduce both mean square and mean absolute errors.

关键词： Wind speed forecasting ARIMA RBF Fuzzy-neural network combination algorithm

来源：评论

学校读者我要写书评

暂无评论

A segment-based approach for digital terrain model derivation in airborne laser scanning data

A segment-based approach for digital terrain model derivatio...

引用

作者： Yuxiang He University of Twente

学位级别：硕士

A method for automatic extraction of Digital Terrain Model (DTM) from huge laser scanning data is presented. With the characteristics of LiDAR system, raw point clouds represent both terrain and non-terrain surface. In order to generate DTM, several methods were developed to remove non-terrain points. algorithms for removing non-terrain points are named as filtering. The filtering method can be categorized as point-based and segment-based algorithms. Point-based filtering can not deal with landscape with discontinuities. Segment-based filtering, on the other hand, generates segments by clustering points based on surface fitting and uses topological and geometric properties for classification. Segment-based algorithms, by global looking of surroundings, can give more reliable results. Traditionally, filtering algorithms are performed and tested in small site. For the huge amount of point clouds, applying segmentation or segment-based filtering can not accomplish in one go in physical computer memory. To extract DTM from huge amount of LiDAR data, three major steps are involved. First, the whole datasets is split into several small overlapping tiles. For each tile, by removing wall and vegetation points, accurate segments are found. The segments from all tiles are assigned unique segment number. In the following step, topological descriptions for the segment distribution pattern and height jump between adjacent segments are identified in each tile. Based on the topology and geometry, segment-based filtering algorithm is performed for classification in each tile. Then, based on the spatial location of the segment in one tile, two confidence levels are assigned to the classified segments. The segments with low confidence level are because of losing geometric or topological information in one tile. Thus, a combination algorithm is generated to detect corresponding parts of incomplete segment from multiple tiles. Then another classification algorithm is performed for thes

关键词： Huge ALS datasets Splitting Overlap Segmentation combination algorithm Classification

来源：评论

学校读者我要写书评

暂无评论

Combining the outputs of various k-nearest neighbor anomaly detectors to form a robust ensemble model for high-dimensional geochemical anomaly detection

引用

JOURNAL OF GEOCHEMICAL EXPLORATION 2021年 231卷 106875-106875页

作者： Chen, Yongliang Zhao, Qingying Lu, Laijun Jilin Univ Coll Earth Sci Changchun 130061 Jilin Peoples R China

Machine learning techniques provide useful methods for high-dimensional geochemical anomaly detection for mineral exploration targeting. However, the instability of the machine learning models often leads to the uncertainty of high-dimensional geochemical anomaly detection result. Combining various individual models to form an adaptive ensemble anomaly detector is a feasible way to enhance the robustness of machine learning anomaly detectors. In this study, the average method, maximization method, average of maximum (AOM) method, and maximum of average (MOA) method were adopted to combine the outputs of various k-nearest neighbor (KNN) anomaly detectors to improve the robustness of the KNN models in the high-dimensional geochemical anomaly detection in the Baishan district (Jilin Province, China). The effectiveness of the four combination algorithms for high-dimensional geochemical anomaly detection was evaluated by comparing the ensemble models obtained by using the four combination algorithms with the single KNN model, Gaussian mixture model (GMM), one-class support vector machine (OCSVM), and isolation forest (IForest) in the case study. It is found that the four ensemble models (a) perform similarly well in high-dimensional geochemical anomaly detection, and (b) perform better than the single KNN model, GMM, OCSVM, and IForest in highdimensional geochemical anomaly detection. Therefore, the average method, maximization method, AOM method, and MOA method are potentially useful algorithms for combining the outputs of various KNN models to form robust ensemble models for high-dimensional geochemical anomaly detection.

关键词： K-nearest neighbor Gaussian mixture model One-class support vector machine Isolation forest combination algorithm Geochemical anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent decision-making for a "Three-Variable"frequency-hopping pattern based on OC-CDRL

引用

PHYSICAL COMMUNICATION 2024年 66卷

作者： Meng, Ziyu Dai, Shaogang Zhao, Zhijin Ye, Xueyi Zheng, Shilian Lou, Caiyi Yang, Xiaoniu Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310000 Peoples R China Natl Key Lab Electromagnet Space Secur Jiaxing 314000 Peoples R China

The frequency hopping pattern of the existing frequency hopping communication system is not designed according to the electromagnetic interference environment, resulting in blind anti-jamming. Therefore, to address this problem, a "three-variable"frequency-hopping pattern is proposed, where the frequency, hopping rate, and instantaneous bandwidth of the frequency-hopping signal vary randomly based on the background electromagnetic interference. The decision-making problem of the "three-variable"frequency-hopping pattern is modeled as a Markov decision process (MDP) by constructing the state-action-reward tuple. The designed frequency varies continuously within a small frequency band selected from a pseudo-random sequence to alleviate the problem of dimension explosion in decision-making. At the same time, discrete values for the hopping rate and instantaneous bandwidth are designed. To solve this MDP problem efficiently, a combined deep reinforcement learning algorithm (OC-CDRL) based on optimistic exploration and conservative estimation is proposed, which combines the features of TD3 and D3QN algorithms and designs the corresponding states, actions, and rewards to deal with continuous and discrete action spaces, respectively. To address the problem that the D3QN algorithm tends to fall into local optimal solutions, an optimistic exploration strategy (OES) for action selection is proposed to improve the degree of exploration. Moreover, the loss function is improved by conservatively estimating state-action pairs outside the experience replay buffer, reducing the overestimation of the optimistic action-value function and increasing the stability and convergence of the algorithm. Comparative simulation results of the algorithms in different electromagnetic interference environments show that the OC-CDRL algorithm effectively avoids most regions with higher interference and has better adaptability and anti-jamming capability.

关键词： Anti-jamming communication "Three-variable"frequency-hopping pattern combination algorithm Optimistic exploration

来源：评论

学校读者我要写书评

暂无评论

Short-term Wind Speed Combined Prediction Model Based on ARIMA-GARCH and Elman

Short-term Wind Speed Combined Prediction Model Based on ARI...

引用

Image Processing, Electronics and Computers (IPEC), Asia-Pacific Conference on

作者： Hanjie Xiao Honglei Tang Jianhua Zhou Business School Huzhou University Huzhou China

ISBN: (数字)9781728160672

ISBN: (纸本)9781728160689

In order to effectively improve the prediction accuracy, short-term wind speed combination prediction model based on ARIMA-GARCH and Elman is proposed. It adopts ARIMA model to linearly predict short-term wind speed and GARCH to improve the non-stationary series heteroscedasticity problems. What's more, Elman neural network is used to nonlinearly predict short-term wind speed. Finally, the minimum weighting method of absolute error is used to determine the optimal linear weight of single model so as to realize short-term wind speed prediction. Case analysis shows that, compared with other prediction models, the combination model not only has significantly improved short-term wind speed prediction accuracy, but provides a certain reference to short-term wind speed prediction in relevant fields.

关键词： ARIMA-GARCH Elman combination algorithm short-term wind speed composite algorithm wind speed short duration Prediction models absolute error

来源：评论

学校读者我要写书评

暂无评论

A New Evidence Model and Its Application for Discriminating Enemy Operation Intention

A New Evidence Model and Its Application for Discriminating ...

引用

2009中国控制与决策会议

作者： LI Ying,Liu Wei-dong The Second Artillery Engineering College,Xi'an,710025,China

Considering the signatures captured from information about the hostile operation intention,this paper puts forward concepts of the simplest evidence support format,duality evidence support format,and same-type evidence and so *** on these concepts,it discusses the problem of the orthogonal sum with the duality evidence support format expressed as the simplest evidence support format,and then,drawing its conclusion to show the relation between the enemy intention and the characteristic ***,it establishes a system for operation intention discrimination to complete the final *** new model brings expression and combination of evidences simplified and computation *** practical application,this algorithm has been proved feasibility and effectiveness.

关键词： Intention recognition Evidence model Performance analysis combination 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：