期刊:
Information Technology Journal,2013年12(21):5987-5992 ISSN:1812-5638
通讯作者:
Wang, X.-H.
作者机构:
[Wang, Xu-Hong; Fan, Shao-Sheng] College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, Hunan, 410004, China;[Liu, Qiu-Ping] Hunan Electric Power Corporation Maintenance, Changsha, Hunan, 410000, China
通讯机构:
[Wang, X.-H.] C;College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha, Hunan, 410004, China
作者机构:
[谭冠政] School of Information Science and Engineering, Central South University, Changsha 410083, China;[樊绍胜] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China;[范必双] School of Information Science and Engineering, Central South University, Changsha 410083, China<&wdkj&>School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China
通讯机构:
[Tan, G.-Z.] S;School of Information Science and Engineering, Central South University, China
作者机构:
[范必双; 邓泽林; 谭冠政] School of Information Science and Engineering, Central South University, Changsha 410083, Hunan Province, China;[樊绍胜] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410076, Hunan Province, China
通讯机构:
School of Information Science and Engineering, Central South University, China
关键词:
三电平逆变器;虚拟矢量;混合空间矢量调制;电容电压平衡;时间分配因子
摘要:
针对二极管中点钳位型(neutral point clamped,NPC)三电平逆变器容易造成直流侧电容电压不平衡问题,提出一种新的中点电位平衡控制方法。在该方法中,采用分扇区精细控制,对不同的小矢量设置不同的时间分配因子,以增加相应正或负小矢量对中点电流的控制能力。对于正负小矢量不能成对出现的扇区,根据相电流的变化情况,使调制在传统算法和基于虚拟矢量的算法之间切换,从而削弱中矢量对中点电流不可控的影响。仿真和实验证实了该方法的正确性和有效性。
作者机构:
School of Electrical & Information Engineering, Changsha University of Science and Technology, Chang;School of Information Science and Engineering, Central South University, Changsha 410083, China
会议名称:
第二届全国语言动力系统研讨会
会议时间:
2011-11-02
会议地点:
长沙
会议论文集名称:
第二届全国语言动力系统研讨会论文集
关键词:
自我监督学习;计算模型;学习框架
摘要:
Computational models of learning are typically divided into supervised learning, unsupervised learning,Computational models of learning are typically divided into supervised learning, unsupervised learning,for expanding incomplete knowledge, via self-directed learning that incorporates knowledge not previously experienced. This article defines a new self-supervised learning framework to address these pregnant learning contexts, and implements this framework using adaptive resonance theory. The learning framework learns about novel features from unlabeled patterns without destroying knowledge previously acquired from labeled patterns.
作者机构:
[谢文彪; 樊绍胜] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China;[谢文彪; 樊晓平] School of Information Science and Engineering, Central South University, Changsha 410083, China
通讯机构:
School of Electrical and Information Engineering, Changsha University of Science and Technology, China
作者机构:
[樊绍胜] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China;[费洪晓; 樊晓平] School of Information Science and Engineering, Central South University, Changsha 410083, China;[谢文彪] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China<&wdkj&>School of Information Science and Engineering, Central South University, Changsha 410083, China
通讯机构:
[Xie, W.-B.] S;School of Electrical and Information Engineering, Changsha University of Science and Technology, China
关键词:
two link robotic manipulator;sliding mode control;radial basis function neural network (RBFNN);adaptive fuzzy gain control
摘要:
A adaptive Radial basis function neural network (RBFNN) based fuzzy sliding mode control scheme for two link robot manipulator is proposed in this paper. In the scheme, RBFNN is used to approximate system dynamic, the weights of the RBFNN are changed according to adaptive algorithm to ensure the system state hitting the sliding surface and sliding along it. In order to guarantee the stability and the convergence of the system, the sliding mode control gain is adjusted by the adaptive fuzzy systems to compensate the network approximation error and the external disturbances. The simulation results demonstrate that the control scheme is effective.
摘要:
Communication using power line as a medium of signal transmission offers a convenient and inexpensive solution for multimedia signal transmission and control applications. This paper aims to present a de-noising scheme which is a combination between chaotic spread spectrum sequence system and the wavelet transform in power line communications (PLC). The proposed communication scheme is based on two key ideas. The first concept consists of the use of the spread-spectrum based on chaotic sequence in order to minimize interference caused by the power line and to secure the transmission information. The second idea consists of the use of discrete wavelet transform to reduce the noise from a chaotic sequence. Signal-to-noise (SNR) and root mean squared error (RMSE) are made. Analyses of bit error rate (BER) illustrate the superior communication performance of the proposed PLC de-noising scheme based on chaotic spread spectrum and wavelet.
会议名称:
International Conference on Intelligent Computation Technology and Automation(2008 智能计算技术与自动化国际会议 ICICTA 2008)
会议时间:
2008-10-20
会议地点:
长沙
会议论文集名称:
International Conference on Intelligent Computation Technology and Automation(2008 智能计算技术与自动化国际会议 ICICTA 2008)论文集
摘要:
Accurate identification of soil resistivity of dynamic grounding system is extremely important to define the operational safety and proper functioning of electric power system. Conventional methods can't achieve good result due to non-linearity of grounding system. To cope with the problem, a novel approach based on fuzzy modeling is proposed. In this approach, T-S fuzzy model is employed to appropriate the non-linear process, fuzzy model is derived from input-output data by means of product-space fuzzy clustering, similarity driven rule base simplification is applied to detect and merges compatible fuzzy sets in the model and real coded genetic algorithm is adopted to optimize model parameters. All these techniques make the fuzzy model transparent and accurate. Based on this approach, a simulation experiment is made. The result shows the approach yields accurate result with error less than 1.5%, other parameters such as grounding resistance, over voltage can also be identified in the same way.