Search

Your search keyword '"Liu, Wenxia"' showing total 767 results
Start Over Author "Liu, Wenxia"
767 results on '"Liu, Wenxia"'

1. Input Convex Neural Network-Assisted Optimal Power Flow in Distribution Networks: Modeling, Algorithm Design, and Applications

Author

Cheng, Rui, Yang, Yuze, Liu, Wenxia, Liu, Nian, and Wang, Zhaoyu

Subjects
Electrical Engineering and Systems Science - Systems and Control
Abstract

This paper proposes an input convex neural network (ICNN)-Assisted optimal power flow (OPF) in distribution networks. Instead of relying purely on optimization or machine learning, the ICNN-Assisted OPF is a combination of optimization and machine learning. It utilizes ICNN to learn the nonlinear but convex mapping from control variables to system state variables, followed by embedding into constrained optimization problems as convex constraints. Utilizing a designed ICNN structure, a fast primal-dual gradient method is developed to solve the ICNN-Assisted OPF, with the chain rule of deep learning applied to accelerate the algorithmic implementation. Convergence and optimally properties of the algorithm design are further established. Finally, different distribution network applications are discussed and proposed by means of the ICNN-Assisted OPF.

Published
2024

24. Disentangled Non-Local Network for Hyperspectral and LiDAR Data Classification

Author

Liu, Wenxia, Gao, Feng, and Dong, Junyu

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

As the ground objects become increasingly complex, the classification results obtained by single source remote sensing data can hardly meet the application requirements. In order to tackle this limitation, we propose a simple yet effective attention fusion model based on Disentangled Non-local (DNL) network for hyperspectral and LiDAR data joint classification task. In this model, according to the spectral and spatial characteristics of HSI and LiDAR, a multiscale module and a convolutional neural network (CNN) are used to capture the spectral and spatial characteristics respectively. In addition, the extracted HSI and LiDAR features are fused through some operations to obtain the feature information more in line with the real situation. Finally, the above three data are fed into different branches of the DNL module, respectively. Extensive experiments on Houston dataset show that the proposed network is superior and more effective compared to several of the most advanced baselines in HSI and LiDAR joint classification missions., Comment: Accepted for publication in the International Geoscience and Remote Sensing Symposium (IGARSS 2021)

Published
2021

42. Deep desulfurization of alkylated oil by alumina adsorbents: characteristics and mechanism study

Author

Li, Hui, Wang, Bingjie, Yang, Hang, Lu, Zhaojin, Liu, Wenxia, and Bai, Zhishan

Subjects
Petroleum -- Desulfurization, Sulfur compounds -- Usage, Chemical reaction, Rate of -- Analysis, Aluminum oxide -- Usage, Chemistry
Abstract

Deep desulfurization of alkylated oil is the primary problem that has long plagued the petroleum refining industry. In this study, alkaline alumina adsorbent microspheres were synthesized by carbonization-hot oil column pelletization method. The adsorption desulfurization performance of as-synthesized adsorbent and three commercial alumina-based adsorbents were systematically evaluated and compared. The results showed that alkaline alumina adsorbent had the optimal adsorption performance with a saturated adsorption capacity of 8.604 mg/g. Meanwhile, FTIR and sulfur speciation analysis indicated that the alkaline alumina adsorbent could deeply remove various sulfides (methyl mercaptan, dimethyl disulfide, hexacarbon sulfide, dibenzothiophene, etc.) from alkylated oil. Furthermore, the adsorption kinetics study manifested that the adsorption of sulfide was dominated by chemical adsorption, supplemented by physical adsorption, and accompanied by competitive adsorption among different sulfides. In addition, the regeneration experiment showed that nitrogen (90 [degrees]C) could realize the stable regeneration of the alkaline alumina adsorbent. To ensure stable regeneration performance in the industry, it is recommended that the alkaline alumina adsorbent be regenerated once with nitrogen at 90 [degrees]C. This study will provide theoretical support for the process optimization of deep desulfurization of alkylated oil and contribute to the high-quality production of clean fuels worldwide. Key words: alkylated oil, adsorption, desulphurization, alumina, kinetic study La desulfuration profonde d'hydrocarbures ramifies est depuis longtemps la plus importante nuisance pour l'industrie du rafnage petrolier. Dans le cadre de la presente etude, nous avons synthetise des microspheres d'adsorbant a base d'alumine alcaline par la methode de carbonisation et bouletage dans une colonne d'huile chaude. Nous avons evalue et compare les performances de desulfuration par adsorption de l'adsorbant tel que synthetise et de trois adsorbants commercialises a base d'alumine. Les resultats ont montre que l'adsorbant a base d'alumine alcaline offrait une performance optimale d'adsorption a une capacite d'adsorption a saturation de 8,604 mg/g. Par ailleurs, la spectroscopie infrarouge a transformee de Fourier (FTIR) et l'analyse de speciation du soufre ont indique que l'adsorbant a base d'alumine alcaline permettait d'eliminer en profondeur divers composes sulfures (methylmercaptan, disulfure de dimethyle, sulfure d'hexacarbone, dibenzothiophene, etc.) des hydrocarbures ramifies. En outre, l'etude cinetique a montre que la cinetique d'adsorption des sulfures etait regie majoritairement par l'adsorption chimique et minoritairement par l'adsorption physique, et que les differents sulfures s'adsorbaient de maniere competitive. De plus, l'experience de regeneration a montre qu'il etait possible d'effectuer une regeneration stable de l'adsorbant a base d'alumine alcaline par l'azote (90 [degrees]C). Afin d'assurer une regeneration stable en milieu industriel, on recommande de regenerer l'adsorbant a base d'alumine alcaline une fois avec de l'azote a 90 [degrees]C. Cette etude offre des bases theoriques sur lesquelles appuyer l'optimisation du processus de desulfuration profonde des hydrocarbures ramifies et qui permettront de contribuer a la production de carburants propres de haute qualite dans le monde entier. [Traduit par la Redaction.] Mots-cles : hydrocarbures ramifies, adsorption, desulfuration, alumine, etude cinetique, 1. Introduction Alkylated oil is the reaction product of the upstream products (isobutane, propylene/butene and others) of petroleum refining under acidic catalyst environment. It mainly consists of isooctane and is [...]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results