检索结果-南通市图书馆

Rotating machinery fault detection and diagnosis based on deep domain adaptation:A survey

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2023年第1期36卷 45-74页

作者： Siyu ZHANG Lei SU jiefei GU Ke li Lang ZHOU Michael PECHT Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology School of Mechanical EngineeringJiangnan UniversityWuxi 214122China HUST-Wuxi Research Institute Wuxi 214071China Center for Advanced life Cycle Engineering University of MarylandCollege ParkMD 20742USA

In practical mechanical fault detection and diagnosis,it is difficult and expensive to collect enough large-scale supervised data to train deep networks.Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task,which performs well on small data and reduces the demand for high computation power.However,the detection performance is significantly reduced by the direct transfer due to the domain difference.Domain adaptation(DA)can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data.In this survey,we review various current DA strategies combined with deep learning(DL)and analyze the principles,advantages,and disadvantages of each method.We also summarize the application of DA combined with DL in the field of fault diagnosis.This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.

关键词： Deep learning Domain adaptation Fault detection and diagnosis Transfer learning

Application of multishot diffusion tensor imaging in spinal cord tumors

在线全文

学校读者我要写书评

暂无评论

Brain Science Advances 2019年第1期5卷 59-64页

作者： Jiefei Li Le He Yuqi Zhang Department of Neurosurgery Yuquan HospitalTsinghua UniversityBeijing 100040China Department of Center for Biomedical Imaging Research Tsinghua UniversityBeijing 100084China

Objective:To explore the usefulness of multishot diffusion tensor imaging(DTI)for evaluating the neurological function of patients with spinal cord tumors Methods:Routine magnetic resonance imaging and multishot DTI were performed in five patients with spinal cord tumors.The values of fractional anisotropy(FA)and radial diffusivity(RD)were analyzed.Results:Multishot DTI of spinal cord tumors allowed for defining the margins of tumors and determining the relationship of tumors with the adjacent white matter structures of the spinal cord.Multishot DTI demonstrated significantly increased RD and decreased FA of spinal cord tumors compared with those of the normal spinal cord.Conclusions:Multishot DTI is a potentially useful modality for differentiating resectable tumors from nonresectable ones based on preoperative imaging alone as well as for differentiating intramedullary tumors from extramedullary ones.Further prospective studies are warranted to confirm these results.

关键词： diffusion tensor imaging(DTI) spinal cord tumor magnetic resonance imaging multishot DTI

Three-in-one fire-retardant poly(phosphate)-based fast ion-conductor for all-solid-state lithium batteries

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2023年第5期80卷 324-334,I0008页

作者： Jiaying Xie Sibo Qiao Yuyang Wang jiefei Sui lixia Bao He Zhou Tianshi li Jiliang Wang School of Chemical Science and Technology National Demonstration Center for Experimental Chemistry and Chemical Engineering EducationYunnan UniversityKunming 650091YunnanChina

The development of flame retardant or nonflammable electrolytes is the key to improve the safety of lithium batteries,owing to inflammable organic solvents and polymer matrix in common liquid and polymer electrolytes regarded as the main cause of battery fire.Herein,a series of solid-state polyphosphate oligomers(SPPO)as a three-in-one electrolyte that integrated the roles of lithium salt,dissociation matrix,and flame retardant were synthesized.The well-designed SPPO electrolytes showed an optimal ionic conductivity of 5.5×10^(-4)S cm-1at 30℃,an acceptable electrochemical window up to 4.0 V vs.li/li+,and lithium ion transference number of 0.547.Stable li-ion stripping/plating behavior for 500 h of charge-discharge cycles without internal short-circuit in a li|SPPO|li cell was confirmed,together with outstanding interface compatibility between the SPPO electrolyte and lithium foil.The optimal li|SPPO|liFePO4cell presented good reversible discharge capacity of 149.4 mA h g-1at 0.1 C and Coulombic efficiency of 96.4%after 120 cycles.More importantly,the prepared SPPO cannot be ignited by the lighter fire and show a limited-oxygen-index value as high as 35.5%,indicating splendid nonflammable nature.The SPPO could be a promising candidate as a three-in-one solid-state electrolyte for the improved safety of rechargeable lithium batteries.

关键词： Three-in-one Poly(phosphate) Organic fast ion-conductor Solid-state polymer electrolyte Flame-retardant Secondary lithium batteries

Roles of hydroxyl and oxygen vacancy of CeO;·xH;O in Pd-catalyzed ethanol electro-oxidation

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2022年

作者： Zhenyu li Jiefei Li Zexuan Zheng Kunhong Jiang Tianrun Zheng Dongmin Wang Hang Wei Zhiming Shi Xiaotian li Haibin Chu College of Chemistry and Chemical Engineering Inner Mongolia Engineering and Technology Research Center for Catalytic Conversion and Utilization of Carbon Resource Molecules Inner Mongolia University College of Materials Science and Engineering Jilin University College of Chemistry Jilin University State Key Laboratory of Luminescence and Applications Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences

In the field of noble metal-catalyzed alcohol electro-oxidation reaction（AOR）, huge attention is paid on the composition, size,facet, and structure of the metals, while the support engineering should also be emphasized. CeO;has been widely used as an unique support in AOR, primarily due to its abundant oxygen vacancies（Ov）. Herein, we report CeO;·xH;O nanoparticles with both massive hydroxyl groups（OH） and Ovremarkably enhance the catalytic activity and stability of Pd toward ethanol oxidation reaction（EOR）. The CO striping experiments and density functional theory（DFT） calculations suggest that OH and Ov on CeO;·xH;O surface bring about a large downshift of Pd d-band center and a significant weakening of CO absorption on Pd.Moreover, OH and Ovalso play synergic roles in the removal of toxic intermediates. Consequently, the important roles of OH and Ovof CeO;·xH;O are confirmed in Pd-catalyzed EOR. The facile CeO;·xH;O-enhanced strategy can contribute to the catalyst design for other energy conversion reactions.

关键词：

A novel approach for flip chip inspection based on improved SDELM and vibration signals

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第5期65卷 1087-1097页

作者： SU Lei ZHANG SiYu JI Yong WANG Gang MING XueFei GU jiefei li Ke PECHT Michael Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology School of Mechanical EngineeringJiangnan UniversityWuxi214122China The 58th Research Institute of China Electronics Technology Group Corporation Wuxi214000China Center for Advanced life Cycle Engineering University of MarylandCollege ParkMD20742USA

This paper proposes a novel nondestructive diagnostic method for flip chips based on an improved semi-supervised deep extreme learning machine(ISDELM)and vibration signals.First,an ultrasonic transducer is used to generate and focus ultrasounds on the surface of the flip chip to excite it,and a laser scanning vibrometer is applied to acquire the chip’s vibration signals.Then,an extreme learning machine-autoencoder(ELM-AE)structure is adopted to extract features from the original vibration signals layer by layer.Finally,the study proposes integrating the ELM with sparsity neighboring reconstruction to diagnose defects based on unlabeled and labeled data.The ISDELM algorithm is applied to experimental vibration data of flip chips and compared with several other algorithms,such as semi-supervised ELM(SS-ELM),deep ELM,stacked autoencoder,convolutional neural network,and ordinary SDELM.The results show that the proposed method is superior to the several currently available algorithms in terms of accuracy and stability.

关键词： flip chip nondestructive diagnosis improved semi-supervised deep extreme learning machine vibration signal

Cerebral glioblastoma mimicking a cavernous malformation: A case report and literature review

在线全文

学校读者我要写书评

暂无评论

Translational Neuroscience and Clinics 2017年第1期3卷 35-39页

作者： Jiefei Li Yuqi Zhang Huancong Zuo Department of Neurosurgery Tsinghua University Yuquan Hospital

Glioblastomas are highly malignant and invasive brain tumors. Cerebral cavernous malformations(CCMs) are vascular diseases of congenital and occult vascular dysplasia, which may arise sporadically or may be inherited due to autosomal dominant condition. To the best of our knowledge, cases of glioblastoma in the cerebral hemisphere mimicking cavernous malformation have not been reported in the literature. We reported a case of glioblastoma mimicking CCM. The patient was admitted at our hospital in July 2015 due to a 9-day history of intermittent dizziness. The present study reports a case of a glioblastoma on the right temporal lobe mimicking CCM, which was confirmed by postoperative pathology. The diagnosis of glioblastoma was not determined even during surgery, and the lesion was totally resected with no complications. During the surgical procedure, the lesion was very similar to a CCM. In conclusion, it is difficult to distinguish between glioblastoma and CCM. Therefore, when a lesion is present with hemorrhage and the imaging features are very similar to a vascular disease, a tumor must be considered in the differential diagnosis.

关键词： glioblastoma cerebral cavernous malformation intracranial hemorrhage neurosurgery

Application of multimodal image fusion technology in brain tumor surgical procedure

在线全文

学校读者我要写书评

暂无评论

Translational Neuroscience and Clinics 2016年第4期2卷 215-226页

作者： Jiefei Li Yuqi Zhang Le He Huancong Zuo Department of Neurosurgery Medical Center Tsinghua UniversityYuquan Hospital Center for Biomedical Imaging Research Tsinghua University

Objective: To construct brain tumors and their surrounding anatomical structures through the method of registration, fusion and, three-dimensional(3D) reconstruction based on multimodal image data and to provide the visual information of tumor, skull,brain, and vessels for preoperative evaluation, surgical planning, and function protection.Methods: The image data of computed tomography(CT) and magnetic resonance imaging(MRI) were collected from fifteen patients with confirmed brain tumors.We reconstructed brain tumors and their surrounding anatomical structures using Neuro Tech software. Results: The whole 3D structures including tumor, brain surface, skull, and vessels were successfully reconstructed based on the CT and MRI images. Reconstruction image clearly shows the tumor size, location, shape, and the anatomical relationship of tumor and surrounding structures. We can hide any reconstructed images such as skull,brain tissue, blood vessles, or tumors. We also can adjust the color of reconstructed images and rotate images to observe the structures from any direction. Reconstruction of brain and skull can be semi transparent to display the deep structure; reconstruction of the structures can be axial, coronal, and sagittal cutting to show relationship among tumor and surrounding structures. The reconstructed 3D structures clearly depicted the tumor features, such as size, location, and shape, and provided visual information of the spatial relationship among its surrounding structures. Conclusions: The method of registration, fusion, and 3D reconstruction based on multimodal images to provide the visual information is feasible and practical. The reconstructed 3D structures are useful for preoperative assessment, incision design,the choice of surgical approach, tumor resection, and functional protection.

关键词： neurosurgical procedures imaging three-dimensional multimodal imaging magnetic resonance imaging

The impact of neuroimaging advancement on neurocognitive evaluation in pediatric brain tumor survivors: A review

在线全文

学校读者我要写书评

暂无评论

Brain Science Advances 2019年第2期5卷 117-127页

作者： Juan Fan Ronald Milosevic Jiefei Li Jianjun Bai Yuqi Zhang Yuquan Hosipital Tsinghua UniversityBeijing 100040China Clinical Centre of Nis Nis 18000The Republic of Serbia School of Medicine Tsinghua UniversityBeijing 100084China

Pediatric brain tumors are a type of tumors that are commonly present in children and young adults.With the improvement of treatment,the quality of life,especially the cognitive functioning,is gaining increasingly more attention.Apart from cognitive evaluations,neuroimaging studies begin to play an important part in neurocognitive functioning investigation.In this way,the brain tissue changes caused by tumor variables(including tumor location and tumor size)and treatment variables(including surgery,chemotherapy and radiotherapy)can be detected by neuroimaging.Recent advancement of neuroimaging techniques,such as functionalMRI(f MRI)and diffusion tensor imaging(DTI),made great contributions to understanding cognitive dysfunction and quantifying the effects of tumor variables and treatment variables.In recent years,laminar-f MRI provided a potentially valuable tool for examining the exact origins of neural activity and cognitive function.On the other hand,molecular f MRI might guide diagnosis and treatment of brain disease in the future by using new biomarkers,and DTI can detect white matter changes and obtain some anatomically specific information.

关键词： pediatric brain tumors cognitive function neuroimaging f MRI DTI

Co-assembly of FeTPP@Fe_(3)O_(4) nanoparticles with photo-enhanced catalytic activity for synergistic tumor therapy

在线全文

学校读者我要写书评

暂无评论

Nano Research 2022年第10期15卷 9114-9124页

作者： Tian Tian Jianshuai Bao Jinghan Wang jiefei Wang Yan Ge Zengyin li Shanqing Gao Zhongqi You Xiaoyan Yang Yong Zhong Feng Bai Key Laboratory for Special Functional Materials of Ministry of Education National&Local Joint Engineering Research Center for High-efficiency Display and Lighting TechnologySchool of Materials Science and EngineeringCollaborative Innovation Center of Nano Functional Materials and ApplicationsHenan UniversityKaifeng 475004China Henan-Macquarie University Joint Centre for Biomedical Innovation School of Life SciencesHenan UniversityKaifeng 475004China

Chemodynamic therapy(CDT)offers a promising alternative to conventional cancer treatment.However,the limited acidity and H_(2)O_(2) concentration in tumor microenvironment(TME)severely impair the anticancer effects of CDT.In this study,we report a microemulsion-assisted coassembly method to prepare iron(III)tetraphenylporphyrin(FeTPP)and magnetic(Fe_(3)O_(4))nanocomposite material(FeTPP@Fe_(3)O_(4)),using photoactive FeTPP and Fe_(3)O_(4) nanocrystals as building blocks.The selfassembling nature of FeTPP results in disordered aggregation and fluorescence quenching,leading to a high light-to-heat conversion efficiency.Continuously,the photo-thermal effect enhances the catalytic decomposition of hydrogen peroxide(H_(2)O_(2))in the Fenton reaction on Fe_(3)O_(4) nanocrystals to generate highly toxic hydroxyl radicals(·OH)to destroy cancer cells.This cascade reaction produces a synergistic therapeutic effect between CDT and photothermal therapy(PTT),which significantly amplifies the therapeutic effect and enhances the treatment outcome of cancer patients.The highly efficient tumor catalytic therapy in vivo results confirmed that this nanomedicine treatment is an excellent biocompatible catalytic nanomedicine therapy achieved through a photo-enhanced Fenton reaction activity approach.

关键词： porphyrin photo-enhanced nanocatalyst synergistic therapy