检索结果-南通市图书馆

Hybrid Model of Power Transformer Fault Classification Using C-set and MFCM – MCSVM

在线全文

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 672-685页

作者： Ali Abdo Hongshun Liu Yousif Mahmoud Hongru Zhang Ying Sun Qingquan Li Jian Guo shandong provincial key laboratory of UHV Transmission Technology and Equipment School of Electrical EngineeringShandong UniversityJinan 250061China

This paper aims to increase the diagnosis accuracy of the fault classification of power transformers by introducing a new off-line hybrid model based on a combination subset of the et method(C-set)&modified fuzzy C-mean algorithm(MFCM)and the optimizable multiclass-SVM(MCSVM).The innovation in this paper is shown in terms of solving the predicaments of outliers,boundary proportion,and unequal data existing in both traditional and intelligence models.Taking into consideration the closeness of dissolved gas analysis(DGA)data,the C-set method is implemented to subset the DGA data samples based on their type of faults within unrepeated subsets.Then,the MFCM is used for removing outliers from DGA samples by combining highly similar data for every subset within the same cluster to obtain the optimized training data(OTD)set.It is also used to minimize dimensionality of DGA samples and the uncertainty of transformer condition monitoring.After that,the optimized MCSVM is trained by using the(OTD).The proposed model diagnosis accuracy is 93.3%.The obtained results indicate that our model significantly improves the fault identification accuracy in power transformers when compared with other conventional and intelligence models.

关键词： Combination subset of set(C-set)method modified fuzzy C-means(MFCM) optimizable multiclass-SVM(MCSVM) optimized training data(OTD)

Improved information entropy weighted vague support vector machine method for transformer fault diagnosis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2022年第3期7卷 510-522页

作者： Hongru Zhang Jiaxiang Sun Kaining Hou Qingquan Li Hongshun Liu shandong provincial key laboratory of UHV Transmission Technology and Equipment School of Electrical EngineeringShandong UniversityJinanChina

A combined model based on improved information entropy and vague support vector machine(IVSVM)is introduced into transformer fault diagnosis using dissolved gas analysis in oil(DGA).The improved information entropy method is used to obtain the weights of each gas and to weight the raw data,and the processed training data and the corresponding fault types are inputted into the vague support vector machine(VSVM)model to obtain classifiers.Firstly,the training data are weighted by the improved information entropy method to discretise the original data from the mixed state for subsequent classifier training.Then,the vague set divides the events into true,false and unknown factors,which can optimise the sub-interface of SVM and improve the accuracy of the boundary point clas-sification.Finally,fault data from the literature and actual collections are selected for training and testing.By comparing with the widely used ratio method and artificial intelligence method,it can be concluded that the method described herein can effectively improve the accuracy of fault diagnosis.The result shows that this method has better applicability when facing actual fault type classification with higher data similarity.

关键词： fault entropy artificial

Experimental Study of Irregular Wave Reflection by a Perforated Caisson Breakwater Under Wave Overtopping Conditions

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 Ocean University of China 2022年第4期21卷 926-934页

作者： LIU Xiao LIU Yong shandong provincial key laboratory of Ocean engineering Ocean University of ChinaQingdao 266100China

The characteristics of irregular wave reflection by a perforated caisson breakwater under wave overtopping conditions were investigated using physical model tests.The effects of various parameters,especially the mean overtopping discharge that was mainly determined by the relative crest freeboard,on the reflection coefficient of perforated caisson breakwater were analyzed using experimental data.The results showed that the wave overtopping occurrence had no appreciable effect on the reflection coefficient when the mean overtopping discharge was less than 0.2 m^(3)(m s)^(−1).Under the wave overtopping condition,the reflection coefficient of the perforated caisson breakwater in this study was reduced by 20%-50% compared with that of the non-perforated caisson breakwater.A predictive formula of the reflection coefficient for perforated caisson breakwaters in terms of relative water depth,relative chamber width,and porosity of the caisson front wall,was developed for practical engineering design.

关键词： perforated caisson model test reflection coefficient wave overtopping predictive formula

Detection of maize leaf diseases using improved MobileNet V3-small

在线全文

学校读者我要写书评

暂无评论

International Journal of Agricultural and Biological engineering 2023年第3期16卷 225-232页

作者： Ang Gao Aijun Geng Yuepeng Song Longlong Ren Yue Zhang Xiang Han College of Mechanical and Electrical engineering Shandong Agricultural UniversityTai’an 271018ShandongChina shandong provincial engineering laboratory of Agricultural Equipment Intelligence Tai’an 271018ShandongChina shandong provincial key laboratory of Horticultural Machineries and Equipment Tai’an 271018ShandongChina

In order to realize the intelligent identification of maize leaf diseases for accurate prevention and control,this study proposed a maize disease detection method based on improved MobileNet V3-small,using a UAV to collect maize disease images and establish a maize disease dataset in a complex context,and explored the effects of data expansion and migration learning on model recognition accuracy,recall rate,and F1-score instructive evaluative indexes,and the results show that the two approaches of data expansion and migration learning effectively improved the accuracy of the model.The structured compression of MobileNet V3-small bneck layer retains only 6 layers,the expansion multiplier of each layer was redesigned,32-fold fast downsampling was used in the first layer,and the location of the SE module was optimized.The improved model had an average accuracy of 79.52%in the test set,a recall of 77.91%,an F1-score of 78.62%,a model size of 2.36 MB,and a single image detection speed of 9.02 ms.The detection accuracy and speed of the model can meet the requirements of mobile or embedded devices.This study provides technical support for realizing the intelligent detection of maize leaf diseases.

关键词： maize leaf disease image recognition model compression MobileNetV3-small

Instance Segmentation and Berry Counting of Table Grape before Thinning Based on AS-SwinT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plant Phenomics 2023年第4期5卷 703-713页

作者： Wensheng Du Ping Liu shandong Agricultural Equipment Intelligent engineering laboratory Shandong Provincial Key Laboratory of HorticulturalMachinery and EquipmentCollege of Mechanical and Electronic EngineeringShandong Agricultural UniversityTai'an 271000China School of Construction Machinery Shandong Jiaotong UniversityJinan 250357China

Berry thinning is one of the most important tasks in the management of high-quality table grapes.Farmers often thin the berries per cluster to a standard number by counting.With an aging population,it is hard to find adequate skilled farmers to work during thinning season.It is urgent to design an intelligent berry-thinning machine to avoid exhaustive repetitive labor.A machine vision system that can determine the number of berries removed and locate the berries removed is a challenge for the thinning machine.A method for instance segmentation of berries and berry counting in a single bunch is proposed based on AS-SwinT.In AS-Swin T,Swin Transformer is performed as the backbone to extract the rich characteristics of grape berries.An adaptive feature fusion is introduced to the neck network to sufficiently preserve the underlying features and enhance the detection of small berries.The size of berries in the dataset is statistically analyzed to optimize the anchor scale,and Soft-NMS is used to filter the candidate frames to reduce the missed detection of densely shaded berries.Finally,the proposed method could achieve 65.7 AP^(box),95.0 AP^(box)_(0.5),57 AP^(box)_(s),62.8 AP^(mask)94.3 AP^(mask)_(0.5),48 AP^(mask)_(s),which is markedly superior to Mask R-CNN,Mask Scoring R-CNN,and Cascade Mask R-CNN.Linear regressions between predicted numbers and actual numbers are also developed to verify the precision of the proposed model.RMSE and R^(2)values are 7.13 and 0.95,respectively,which are substantially higher than other models,showing the advantage of the AS-SwinT model in berry counting estimation.

关键词： Berry network removed

The failure propagation of weakly stable sediment:A reason for the formation of high-velocity turbidity currents in submarine canyons

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 Oceanology and Limnology 2023年第1期41卷 100-117页

作者： Yupeng REN Yi ZHANG Guohui XU Xingbei XU Houjie WANG Zhiyuan CHEN shandong provincial key laboratory of Marine Environment and Geological engineering Qingdao 266100China shandong provincial key laboratory of Marine Environment and Geological engineering Ocean University of ChinaQingdao 266100China key laboratory of Marine Environment and Ecology Ocean University of ChinaMinistry of EducationQingdao 266100China

The long-distance movement of turbidity currents in submarine canyons can transport large amounts of sediment to deep-sea plains.Previous studies show obvious differences in the turbidity current velocities derived from the multiple cables damage events ranging from 5.9 to 28.0 m/s and those of field observations between 0.15 and 7.2 m/s.Therefore,questions remain regarding whether a turbid fluid in an undersea environment can flow through a submarine canyon for a long distance at a high speed.A new model based on weakly stable sediment is proposed(proposed failure propagation model for weakly stable sediments,WS S-PFP model for short)to explain the high-speed and long-range motion of turbidity currents in submarine canyons through the combination of laboratory tests and numerical analogs.The model is based on two mechanisms:1)the original turbidity current triggers the destabilization of the weakly stable sediment bed and promotes the destabilization and transport of the soft sediment in the downstream direction and 2)the excitation wave that forms when the original turbidity current moves into the canyon leads to the destabilization and transport of the weakly stable sediment in the downstream direction.The proposed model will provide dynamic process interpretation for the study of deep-sea deposition,pollutant transport,and optical cable damage.

关键词： turbidity current excitation wave dense basal layer velocity WSS-PFP model

Bracelet salt glands of the recretohalophyte Limonium bicolor:Distribution,morphology,and induction

在线全文

学校读者我要写书评

暂无评论

Journal of Integrative Plant Biology 2023年第4期65卷 950-966页

作者： Boqing Zhao Yingli Zhou Xiangmei Jiao Xi Wang Baoshan Wang Fang Yuan shandong provincial key laboratory of Plant Stress College of Life SciencesShandong Normal UniversityJi'nan 250014China

Halophytes complete their life cycles in saline environments.The recretohalophyte Limonium bicolor has evolved a specialized salt secretory structure,the salt gland,which excretes Na+to avoid salt damage.Typical L.bicolor salt glands consist of 16 cells with four fluorescent foci and four secretory pores.Here,we describe a special type of salt gland at the base of the L.bicolor leaf petiole named bracelet salt glands due to their beaded-bracelet-like shape of blue auto-fluorescence.Bracelet salt glands contain more than 16 cells and more than four secretory pores.Leaf disc secretion measurements and non-invasive micro-test techniques indicated that bracelet salt glands secrete more salt than normal salt glands,which helps maintain low Na+levels at the leaf blade to protect the leaf.Cytokinin treatment induced bracelet salt gland differentiation,and the developed ones showed no further differentiation when traced with a living fluorescence microscopy imager,even though new salt gland development and leaf expansion were observed.Transcriptome revealed a NAC transcription factor gene that participates in bracelet salt gland development,as confirmed by its genome editing and overexpression in L.bicolor.These findings shed light on bracelet salt gland development and may facilitate the engineering of salt-tolerant crops.

关键词： bracelet salt gland 6‐BA differentiation NAC transformation

Performance of bimetallic nanoscale zero-valent iron particles for removal of oxytetracycline

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2018年第7期30卷 173-182页

作者： Yuwei Wu Qinyan Yue Yuan Gao Zhongfei Ren Baoyu Gao shandong provincial key laboratory of Water Pollution Control and Resource Reuse School of Environmental Science and EngineeringShandong University

In this study, bimetallic nanoscale zero-valent iron particles（nZVI）, including copper/nanoscale zero-valent iron particles（Cu/nZVI） and nickel/nanoscale zero-valent iron particles（Ni/nZVI）, were synthesized by one-step liquid-phase reduction and applied for oxytetracycline（OTC） removal. The effects of contact time and initial p H on the removal efficiency were studied. The as-prepared nanoscale particles were characterized by scanning electron microscopy（SEM）, energy dispersive spectroscopy（EDS） and X-ray diffraction（XRD）. Finally, the degradation mechanisms of OTC utilizing the as-prepared nanoparticles were investigated by using X-ray photoelectron spectroscopy（XPS） and mass spectrometry（MS）. Cu/n ZVI presented remarkable ability for OTC degradation and removed71.44% of OTC（100 mg/L） in 4 hr, while only 62.34% and 31.05% of OTC was degraded by Ni/nZVI and nZVI respectively. XPS and MS analysis suggested that OTC was broken down to form small molecules by ·OH radicals generated from the corrosion of Fe0. Cu/nZVI and Ni/n ZVI have been proved to have potential as materials for application in OTC removal because of their significant degradation ability toward OTC.

关键词： Bimetallic nanoscale zero-valent iron particles Oxytetracycline Degradation mechanism Hydroxyl radicals

Trace Elements of Multi-stage Minerals and Titanite U-Pb Dating for the Gneisses from Liansan Island,Sulu UHPM Belt

在线全文

学校读者我要写书评

暂无评论

Acta Geologica Sinica(English Edition) 2023年第6期97卷 1640-1656页

作者： SONG Lihao CAO Yuting XIE Tianhe CHEN Yuyao GAO Yuan WANG Songjie LI Xuping shandong provincial key laboratory of Depositional Mineralization&Sedimentary Minerals College of Earth Science and EngineeringShandong University of Science and TechnologyQingdaoShandong 266590China

Gneisses with anatectic characteristics from the Liansan island in the Sulu UHPM(ultra-high pressure metamorphic)belt were studied for petrography,titanite U-Pb dating and mineral geochemistry.Three origins of garnets are distinguished:metamorphic garnet,peritectic garnet and anatectic garnet,which are formed in the stages of peak metamorphism,retrograde anatexis and melt crystallization,respectively.The euhedral titanite has a high content of REE and high Th/U ratios,which is interpreted as indicating that it was newly-formed from an anatectic melt.The LA-ICP-MS titanite U-Pb dating yields 214-217 Ma ages for the titanite(melt)crystallization.The distribution of trace elements varies in response to the different host minerals at different stages.At the peak metamorphic stage,Y and HREE are mainly hosted by garnet,Ba and Rb by phengite,Sr,Nb,Ta,Pb,Th,U and LREE by allanite and Y,U and HREE by zircon.During partial melting,Y,Pb,Th,U and REE are released into the melt,which causes a dramatic decline of these element contents in the retrograde minerals.Finally,titanite absorbs most of the Nb,U,LREE and HREE from the melt.Therefore,the different stages of metamorphism have different mineral assemblages,which host different trace elements.

关键词： partial melting multi-stage minerals trace element migration titanite U-Pb dating Sulu UHPM belt