According to statistic data,machinery faults contribute to largest proportion of High-voltage circuit breaker failures,and traditional maintenance methods exist some disadvantages for that issue.Therefore,based on the...According to statistic data,machinery faults contribute to largest proportion of High-voltage circuit breaker failures,and traditional maintenance methods exist some disadvantages for that issue.Therefore,based on the wavelet packet decomposition approach and support vector machines,a new diagnosis model is proposed for such fault diagnoses in this study.The vibration eigenvalue extraction is analyzed through wavelet packet decomposition,and a four-layer support vector machine is constituted as a fault classifier.The Gaussian radial basis function is employed as the kernel function for the classifier.The penalty parameter c and kernel parameterδof the support vector machine are vital for the diagnostic accuracy,and these parameters must be carefully predetermined.Thus,a particle swarm optimizationsupport vector machine model is developed in which the optimal parameters c andδfor the support vector machine in each layer are determined by the particle swarm algorithm.The validity of this fault diagnosis model is determined with a real dataset from the operation experiment.Moreover,comparative investigations of fault diagnosis experiments with a normal support vector machine and a particle swarm optimization back-propagation neural network are also implemented.The results indicate that the proposed fault diagnosis model yields better accuracy and e-ciency than these other models.展开更多
Multi-terminal direct current(MTDC)grids provide the possibility of meshed interconnections between regional power systems and various renewable energy resources to boost supply reliability and economy.The modular mul...Multi-terminal direct current(MTDC)grids provide the possibility of meshed interconnections between regional power systems and various renewable energy resources to boost supply reliability and economy.The modular multilevel converter(MMC)has become the basic building block for MTDC and DC grids due to its salient features,i.e.,modularity and scalability.Therefore,the MMC-based MTDC systems should be pervasively embedded into the present power system to improve system performance.However,several technical challenges hamper their practical applications and deployment,including modeling,control,and protection of the MMC-MTDC grids.This paper presents a comprehensive investigation and reference in modeling,control,and protection of the MMC-MTDC grids.A general overview of state-of-the-art modeling techniques of the MMC along with their performance in simulation analysis for MTDC applications is provided.A review of control strategies of the MMC-MTDC grids which provide AC system support is presented.State-of-the art protection techniques of the MMCMTDC systems are also investigated.Finally,the associated research challenges and trends are highlighted.展开更多
基金Supported by National Natural Science Foundation of China(Grant No.51705372)National Science and Technology Project of the Power Grid of China(Grant No.5211DS16002L).
文摘According to statistic data,machinery faults contribute to largest proportion of High-voltage circuit breaker failures,and traditional maintenance methods exist some disadvantages for that issue.Therefore,based on the wavelet packet decomposition approach and support vector machines,a new diagnosis model is proposed for such fault diagnoses in this study.The vibration eigenvalue extraction is analyzed through wavelet packet decomposition,and a four-layer support vector machine is constituted as a fault classifier.The Gaussian radial basis function is employed as the kernel function for the classifier.The penalty parameter c and kernel parameterδof the support vector machine are vital for the diagnostic accuracy,and these parameters must be carefully predetermined.Thus,a particle swarm optimizationsupport vector machine model is developed in which the optimal parameters c andδfor the support vector machine in each layer are determined by the particle swarm algorithm.The validity of this fault diagnosis model is determined with a real dataset from the operation experiment.Moreover,comparative investigations of fault diagnosis experiments with a normal support vector machine and a particle swarm optimization back-propagation neural network are also implemented.The results indicate that the proposed fault diagnosis model yields better accuracy and e-ciency than these other models.
基金funded by SGCC Science and Technology Program under project Research on Electromagnetic Transient Simulation Technology for Large-scale MMC-HVDC Systems.
文摘Multi-terminal direct current(MTDC)grids provide the possibility of meshed interconnections between regional power systems and various renewable energy resources to boost supply reliability and economy.The modular multilevel converter(MMC)has become the basic building block for MTDC and DC grids due to its salient features,i.e.,modularity and scalability.Therefore,the MMC-based MTDC systems should be pervasively embedded into the present power system to improve system performance.However,several technical challenges hamper their practical applications and deployment,including modeling,control,and protection of the MMC-MTDC grids.This paper presents a comprehensive investigation and reference in modeling,control,and protection of the MMC-MTDC grids.A general overview of state-of-the-art modeling techniques of the MMC along with their performance in simulation analysis for MTDC applications is provided.A review of control strategies of the MMC-MTDC grids which provide AC system support is presented.State-of-the art protection techniques of the MMCMTDC systems are also investigated.Finally,the associated research challenges and trends are highlighted.
