检索结果-南通市图书馆

Fault Identification in power Network Based on Deep Reinforcement Learning

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2022年第3期8卷 721-731页

作者： Mengshi Li Huanming Zhang Tianyao ji q.H.Wu School of Electric power Engineering South China University of TechnologyGuangzhou510641China

With the integration of alternative energy and renewables,the issue of stability and resilience of the power network has received considerable *** basic necessity for fault diagnosis and isolation is fault identification and *** conventional intelligent fault identification method needs supervision,manual labelling of characteristics,and requires large amounts of labelled *** enhance the ability of intelligent methods and get rid of the dependence on a large amount of labelled data,a novel fault identification method based on deep reinforcement learning(DRL),which has not received enough attention in the field of fault identification,is investigated in this *** proposed method uses different faults as parameters of the model to expand the scope of fault *** addition,the DRL algorithm can intelligently modify the fault parameters according to the observations obtained from the power network environment,rather than requiring manual and mechanical tuning of *** methodology was tested on the IEEE 14 bus for several scenarios and the performance of the proposed method was compared with that of population-based optimization methods and supervised learning *** obtained results have confirmed the feasibility and effectiveness of the proposed method.

关键词： Artificial intelligence deep q network deep reinforcement learning fault diagnosis fault identification parameter identification power network

A Hybrid Signal processing Method Combining Mathematical Morphology and Walsh Theory for power quality Disturbance Detection and Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2024年第2期10卷 584-592页

作者： Zhi Ding Tianyao ji Mengshi Li q.H.Wu School of Electric power Engineering South China University of Technology(SCUT)Guangzhou 510641China

In this paper, a novel signal processing method combining mathematical morphology (MM) and Walsh theory is proposed, which uses Walsh functions to control the structuring element (SE) and MM operators. Based on the Walsh-MM method, a scheme for power quality disturbances detection and classification is developed, which involves three steps: denoising, feature extraction and morphological clustering. First, various evolution rules of Walsh function are used to generate groups of SEs for the multiscale Walsh-ordered morphological operation, so the original signal can be denoised. Next, the fundamental wave of the denoised signal is suppressed by Hadamard matrix;thus, disturbances can be extracted. Finally, the Walsh power spectrum of the waveform extracted in the previous step is calculated, and the parameters of which are taken by morphological clustering to classify the disturbances. Simulation results reveal the proposed scheme can effectively detect and classify disturbances, and the Walsh-MM method is less affected by noise and only involves simple calculation, which has a potential to be implemented in hardware and more suitable for real-time application.

关键词： Hadamard matrix mathematical morphology morphological clustering power quality disturbance Walsh theory

Fault Location in Distribution System Using Convolutional Neural Network Based on Domain Transformation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2021年第3期7卷 472-484页

作者： Yang Yu Mengshi Li Tianyao ji q.H.Wu School of Electric power Engineering South China University of TechnologyGuangzhou 510640China

Distribution lines are integral parts of the modern power system,which can affect the security and stability of power supply *** effective power system protection scheme should be able to detect all occurring faults as soon as *** are two tasks in fault *** is the fault classification,where high accuracy rates have already ***,this paper focuses on the other task,*** *** by Fourier transform,this paper proposes an online data-driven method,which transforms signals from time domain to image domain through signal-to-image(SIG)algorithm and then process the transformed images with framework based on convolutional neural network(CNN).On the one hand,we can extract more crucial characteristic and information from image *** the other hand,the CNN-based structure is much smaller than *** needs less memory space and would be easier to be transplanted to hardware ***,the proposed algorithm does not require synchronous *** numerical comparison shows that the proposed SIG-CNN fault location model achieves robust and accurate results compared with other data-driven algorithms.

关键词： Convolutional neural network distribution lines domain transformation fault location

Stochastic Economic Dispatch Considering the Dependence of Multiple Wind Farms Using Multivariate Gaussian Kernel Copula

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2022年第5期8卷 1352-1362页

作者： Yantai Lin Tianyao ji Yuzi jiang q.H.Wu School of Electric power Engineering South China University of TechnologyGuangzhou 510641China

Wind farms usually cluster in areas with abundant wind ***,spatial dependence of wind speeds among nearby wind farms should be taken into account when modeling a power system with large-scale wind power *** paper proposes a novel non-parametric copula method,multivariate Gaussian kernel copula(MGKC),to describe the dependence structure of wind speeds among multiple wind *** speed scenarios considering the dependence among different wind farms are sampled from the MGKC by the quasi-Monte Carlo(qMC)method,so as to solve the stochastic economic dispatch(SED)problem,for which an improved meanvariance(MV)model is established,which targets at minimizing the expectation and risk of fuel cost *** this model,confidence interval is applied in the wind speed to obtain more practical dispatch solutions by excluding extreme scenarios,for which the quantile-copula is proposed to construct the confidence interval *** studies are carried out on a modified IEEE 30-bus power system with wind farms integrated in two areas,and the results prove the superiority of the MGKC in formulating the dependence among different wind farms and the superiority of the improved MV model based on quantilecopula in determining a better dispatch solution.

关键词： Multivariate Gaussian kernel copula quasi-Monte Carlo quantile-copula stochastic economic dispatch

A novel friction stir diffusion bonding process using convex-vortex pin tools

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2020年第13期47卷 23-30页

作者： S.D.ji q.Wen Z.W.Li College of Aerospace Engineering Shenyang Aerospace UniversityShenyang 110136China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150001China

In this work,a novel friction stir diffusion bonding(FSDB)method was proposed to eliminate hook when joining thin *** tools,with several convex-vortex pins were innovatively designed to improve the diffusion bonding effect of the lap *** showed that sound joints,excellently bonded at the lap interface and without hook,were *** lap interfaces on the joints welded using the T-tool and F-tool almost remained intact,thereby indicating that they were formed by diffusion *** material flow behavior was also simulated by FLUENT software and the results showed that the material flow along thickness was significantly enhanced by increasing the pin *** joint welded by the T-tool showed shear fracture *** bonding was formed at the lap interface when using the F-tool and thus the joint showed tensile fracture.

关键词： Friction stir diffusion bonding Convex-vortex pin Hook Material flow Failure

Ultra-short Term Wind Speed prediction Using Mathematical Morphology Decomposition and Long Short-term Memory

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2020年第4期6卷 890-900页

作者： Mengshi Li Zhiyuan Zhang Tianyao ji q.H.Wu School of Electric power Engineering South China University of TechnologyGuangzhou 510641China

This paper proposes a new model,which consists of a mathematical morphology(MM)decomposer and two long short term memory(LSTM)networks,to perform ultra-short term wind speed *** MM decomposer is developed in order to improve the forecast accuracy,which separates the wind speed into two parts:a stationary long-term baseline and a nonstationary short-term ***,two LSTM networks are implemented to forecast the baseline and residue,***,this paper makes an integrated forecast that takes into account multiple climate factors,such as temperature and air *** baseline,temperature and air pressure are used as the inputs of baseline network for training and prediction,and the baseline,residue,temperature and air pressure are used as the inputs of residue network for training and *** performance of the proposed model has been validated using data collected from the Australian Meteorological Station,which is compared with least squares-support vector machine(LS-SVM),back-propagation artificial neural network(BpNN),LSTM,MM-LS-SVM,and *** results demonstrate that the proposed model is more suitable to solve non-stationary time-series forecast,and achieves higher accuracy than the other models under various conditions.

关键词： Deep learning long short-term memory network mathematical morphology wind speed forecast

Experimental and numerical study of the effect of pulsatile flow on wall displacement oscillation in a flexible lateral aneurysm model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mechanica Sinica 2019年第5期35卷 1120-1129页

作者： L.Z.Mu X.Y.Li q.Z.Chi S.q.Yang p.D.Zhang C.J.ji Y.He G.Gao School of Energy and power Engineering Dalian University of TechnologyDalian 116024China School of Biomedical Engineering Capital Medical UniversityBeijing 100069China The First Affiliated Hospital of University of Science and Technology of China Hefei 230036China

This study experimentally and numerically investigated the effect of pulsatile flow of different frequencies and outflow resistance on wall deformation in a lateral aneurysm.A method for constructing a flexible aneurysm model was developed,and a self-designed piston pump was used to provide the pulsatile flow conditions.A fluid-structure interaction simulation was applied for comparison with and analysis of experimental *** maximum wall displacement oscillation increased as the pulsation frequency and outflow resistance increased,especially at the aneurysm *** is an obvious circular motion of the vortex center accompanying the periodic inflow fluctuation,and the pressure at the aneurysm dome at peak flow increased as the pulsatile flow frequency and terminal flow resistance *** results could explain why abnormal blood flow with high frequency and high outflow resistance is one of the risk factors for aneurysm rupture.

关键词： Lateral aneurysm In vitro experiment pulsatile flow Wall displacement oscillation Fluid-structure interaction simulation

Multi-mapping Fault Diagnosis of High Voltage Circuit Breaker Based on Mathematical Morphology and Wavelet Entropy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2019年第1期5卷 130-138页

作者： Tianyao ji Lin Yi Wenhu Tang Mengjie Shi q.H.Wu School of Electric power Engineering South China University of TechnologyGuangzhou 510641China

Mechanical faults of high voltage circuit breakers(CBs)seriously affect the reliability of their operation,which may cause severe damage to power *** order to monitor operational conditions and detect mechanical faults of CBs,a multi-parameter monitoring system is designed and a fault diagnosis method based on multi-mapping is *** paper focuses on the trip/close circuits,the spring-charging mechanism and the transmission mechanism,and obtains four current signals and a vibration signal that can reflect CB *** the current signals,a morphological filter is used to remove noise and then characteristics of the waveforms’shape information are *** vibration signals,the wavelet packet transform is used to decompose the signal into various frequency bands,and the sample entropy of the low frequency bands and the wavelet energy of the high frequency bands are calculated,*** on these feature parameters,a multi-mapping strategy is proposed for CB fault *** experiments have been conducted to obtain on-site signals under various conditions,and experiment results have verified that monitoring the aforementioned signals and using the corresponding feature extraction and fault diagnosis methods,the mechanical faults of high voltage CBs can be effectively diagnosed.

关键词： Fault diagnosis high voltage circuit breaker multi-mapping sample entropy wavelet energy

pLASMA SpRAYED Ti AND HA COATINGS: A COMpARATIVE STUDY BETWEEN ApS AND VpS

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2005年第3期18卷 339-344页

作者： X.B.Zheng H.ji J.q.Huang C.X.Ding ShanghaiInstituteofCeramics TheChineseAcademyofSciencesShanghai200050China

Titanium (Ti) and hydroxyapatite (HA) coatings have been prepared via air (ApS) and vacuum plasma spraying (VpS), and then their composition, structure, bonding strength and bioactivity were examined. The results obtained reveal that in ApS process many of Ti were oxidized, but in VpS the oxidization was avoided. VpS T i coating possesses better bonding condition than ApS Ti coating. As for HA coat ing, higher crystallinity has been obtained while the coating was deposited by V pS as compared with ApS. The simulated body fluid (SBF) tests show that both of ApS and VpS HA coatings possess good bioactivity. As compared with ApS, VpS is r ecommended as a better method to deposit Ti and HA coatings that can be applied as hard tissue replacement implants.

关键词： vacuum plasma spray Ti HA biocoating