State-of-charge Estimation for Lithium-ion Batteries Using a Multi-state Closed-loop Observer

Zhao, Yulan,Yun, Haitao,Liu, Shude,Jiao, Huirong,Wang, Chengzhen The Korean Institute of Power Electronics 2014 JOURNAL OF POWER ELECTRONICS Vol.14 No.5

Lithium-ion batteries are widely used in hybrid and pure electric vehicles. State-of-charge (SOC) estimation is a fundamental issue in vehicle power train control and battery management systems. This study proposes a novel model-based SOC estimation method that applies closed-loop state observer theory and a comprehensive battery model. The state-space model of lithium-ion battery is developed based on a three-order resistor-capacitor equivalent circuit model. The least square algorithm is used to identify model parameters. A multi-state closed-loop state observer is designed to predict the open-circuit voltage (OCV) of a battery based on the battery state-space model. Battery SOC can then be estimated based on the corresponding relationship between battery OCV and SOC. Finally, practical driving tests that use two types of typical driving cycle are performed to verify the proposed SOC estimation method. Test results prove that the proposed estimation method is reasonably accurate and exhibits accuracy in estimating SOC within 2% under different driving cycles.

State-of-charge Estimation for Lithium-ion Batteries Using a Multi-state Closed-loop Observer

Yulan Zhao,Haitao Yun,Shude Liu,Huirong Jiao,Chengzhen Wang 전력전자학회 2014 JOURNAL OF POWER ELECTRONICS Vol.14 No.5

Lithium-ion batteries are widely used in hybrid and pure electric vehicles. State-of-charge (SOC) estimation is a fundamental issue in vehicle power train control and battery management systems. This study proposes a novel model-based SOC estimation method that applies closed-loop state observer theory and a comprehensive battery model. The state-space model of lithium-ion battery is developed based on a three-order resistor?capacitor equivalent circuit model. The least square algorithm is used to identify model parameters. A multi-state closed-loop state observer is designed to predict the open-circuit voltage (OCV) of a battery based on the battery state-space model. Battery SOC can then be estimated based on the corresponding relationship between battery OCV and SOC. Finally, practical driving tests that use two types of typical driving cycle are performed to verify the proposed SOC estimation method. Test results prove that the proposed estimation method is reasonably accurate and exhibits accuracy in estimating SOC within 2% under different driving cycles.

동작 인식을 위한 교사-학생 구조 기반 CNN

Yulan Zhao,이효종 한국정보처리학회 2022 정보처리학회논문지. 컴퓨터 및 통신시스템 Vol.11 No.3

Convolutional neural network (CNN) generally uses two-stream architecture RGB and optical flow stream for its action recognitionfunction. RGB frames stream display appearance and optical flow stream interprets its action. However, the standard method of usingoptical flow is costly in its computational time and latency associated with increased action recognition. The purpose of the study wasto evaluate a novel way to create a two sub-networks in neural networks. The optical flow sub-network was assigned as a teacher andthe RGB frames as a student. In the training stage, the optical flow sub-network extracts features through the teacher sub-network andtransmits the information to student sub-network for baseline training. In the test stage, only student sub-network was operational withdecreased in latency without computing optical flow. Experimental results shows that our network fed only by RGB stream gets a competitiveaccuracy of 54.5% on HMDB51, which is 1.5 times better than that on R3D-18. 대부분 첨단 동작 인식 컨볼루션 네트워크는 RGB 스트림과 광학 흐름 스트림, 양 스트림 아키텍처를 기반으로 하고 있다. RGB 프레임 스트림은모양 특성을 나타내고 광학 흐름 스트림은 동작 특성을 해석한다. 그러나 광학 흐름은 계산 비용이 매우 높기 때문에 동작 인식 시간에 지연을초래한다. 이에 양 스트림 네트워크와 교사-학생 아키텍처에서 영감을 받아 행동 인식을 위한 새로운 네트워크 디자인을 개발하였다. 제안 신경망은두 개의 하위 네트워크로 구성되어있다. 즉, 교사 역할을 하는 광학 흐름 하위 네트워크와 학생 역할을 하는 RGB 프레임 하위 네트워크를 연결하였다. 훈련 단계에서 광학 흐름의 특징을 추출하고 교사 서브 네트워크를 훈련시킨 다음 그 특징을 학생 서브 네트워크를 훈련시키기 위한 기준선으로지정하여 학생 서브 네트워크에 전송한다. 테스트 단계에서는 광학 흐름을 계산하지 않고 대기 시간이 줄어들도록 학생 네트워크만 사용한다. 제안 네트워크는 실험을 통하여 정확도 면에서 일반 이중 스트림 아키텍처에 비해 높은 정확도를 보여주는 것을 확인하였다.

The Development of Deep Learning in China

조옥란 ( Zhao Yulan ),이효종 ( Hyo Jong Lee ) 한국정보처리학회 2019 한국정보처리학회 학술대회논문집 Vol.26 No.1

This paper is to summarize the academic status of deep learning in Chinese scientific institutions and universities based on the literatures from CNKI. We analyzed the various development of deep learning in China based on the application of computer vision, voice recognition and natural language processing.

FTSnet: 동작 인식을 위한 간단한 합성곱 신경망

조옥란 ( Yulan Zhao ),이효종 ( Hyo Jong Lee ) 한국정보처리학회 2021 한국정보처리학회 학술대회논문집 Vol.28 No.2

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.

Proteomic Analysis on Exosomes Derived from Patients’ Sera Infected with Echinococcus granulosus

Wen Wang,Xiaojing Zhou,Fang Cui,Chunli Shi,Yulan Wang,Yanfei Men,Wei Zhao,Jiaqing Zhao 대한기생충학ㆍ열대의학회 2019 The Korean Journal of Parasitology Vol.57 No.5

Cystic echinococcosis (CE), a zoonotic disease caused by Echinococcus granulosus at the larval stage, predominantly develops in the liver and lungs of intermediate hosts and eventually results in organ malfunction or even death. The interaction between E. granulosus and human body is incompletely understood. Exosomes are nanosized particles ubiquitously present in human body fluids. Exosomes carry biomolecules that facilitate communication between cells. To the best of our knowledge, the role of exosomes in patients with CE is not reported. Here, we isolated exosomes from the sera of patients with CE (CE-exo) and healthy donors and subjected them to liquid chromatography-tandem mass spectrometry analysis. Proteomic analysis identified 49 proteins specifically expressed in CE-exo, including 4 proteins of parasitic origin. The most valuable parasitic proteins included tubulin alpha-1C chain and histone H4. And 8 proteins were differentially regulated in CE-exo (fold change>1.5), as analyzed with bioinformatic methods such as annotation and functional enrichment analyses. These findings may improve our understanding about the interaction between E. granulosus and human body, and may contribute to the diagnosis and prevention of CE.

Glutamate attenuates lipopolysaccharide induced intestinal barrier injury by regulating corticotropin-releasing factor pathway in weaned pigs

Guo Junjie,Liang Tianzeng,Chen Huifu,Li Xiangen,Ren Xiaorui,Wang Xiuying,Xiao Kan,Zhao Jiangchao,Zhu Huiling,Liu Yulan 아세아·태평양축산학회 2022 Animal Bioscience Vol.35 No.8

Objective: The purpose of this study was to evaluate the protection of glutamate (GLU) against the impairment in intestinal barrier function induced by lipopolysaccharide (LPS) stress in weaned pigs. Methods: Twenty-four weaned pigs were divided into four treatments containing: i) nonchallenged control, ii) LPS-challenged control, iii) LPS+1.0% GLU, and iv) LPS+2.0% GLU. On day 28, pigs were treated with LPS or saline. Blood samples were collected at 0, 2, and 4 h post-injection. After blood samples collection at 4 h, all pigs were slaughtered, and spleen, mesenteric lymph nodes, liver and intestinal samples were obtained. Results: Dietary GLU supplementation inhibited the LPS-induced oxidative stress in pigs, as demonstrated by reduced malondialdehyde level and increased glutathione level in jejunum. Diets supplemented with GLU enhanced villus height, villus height/crypt depth and claudin-1 expression, attenuated intestinal histology and ultrastructure impairment induced by LPS. Moreover, GLU supplementation reversed intestinal intraepithelial lymphocyte number decrease and mast cell number increase induced by LPS stress. GLU reduced serum cortisol concentration at 4 h after LPS stress and downregulated the mRNA expression of intestinal corticotropin-releasing factor signal (corticotrophin-releasing factor [CRF], CRF receptor 1 [CRFR1], glucocorticoid receptor, tryptase, nerve growth factor, tyrosine kinase receptor A), and prevented mast cell activation. GLU upregulated the mRNA expression of intestinal transforming growth factor β. Conclusion: These findings indicate that GLU attenuates LPS-induced intestinal mucosal barrier injury, which is associated with modulating CRF signaling pathway. Objective: The purpose of this study was to evaluate the protection of glutamate (GLU) against the impairment in intestinal barrier function induced by lipopolysaccharide (LPS) stress in weaned pigs.Methods: Twenty-four weaned pigs were divided into four treatments containing: i) non-challenged control, ii) LPS-challenged control, iii) LPS+1.0% GLU, and iv) LPS+2.0% GLU. On day 28, pigs were treated with LPS or saline. Blood samples were collected at 0, 2, and 4 h post-injection. After blood samples collection at 4 h, all pigs were slaughtered, and spleen, mesenteric lymph nodes, liver and intestinal samples were obtained.Results: Dietary GLU supplementation inhibited the LPS-induced oxidative stress in pigs, as demonstrated by reduced malondialdehyde level and increased glutathione level in jejunum. Diets supplemented with GLU enhanced villus height, villus height/crypt depth and claudin-1 expression, attenuated intestinal histology and ultrastructure impairment induced by LPS. Moreover, GLU supplementation reversed intestinal intraepithelial lymphocyte number decrease and mast cell number increase induced by LPS stress. GLU reduced serum cortisol concentration at 4 h after LPS stress and downregulated the mRNA expression of intestinal corticotropin-releasing factor signal (corticotrophin-releasing factor [<i>CRF</i>], CRF receptor 1 [<i>CRFR1</i>], glucocorticoid receptor, tryptase, nerve growth factor, tyrosine kinase receptor A), and prevented mast cell activation. GLU upregulated the mRNA expression of intestinal transforming growth factor β.Conclusion: These findings indicate that GLU attenuates LPS-induced intestinal mucosal barrier injury, which is associated with modulating CRF signaling pathway.