Search

Your search keyword '"Li, Zhengjian"' showing total 161 results
Start Over Author "Li, Zhengjian"
Sorry, I don't understand your search. ×
161 results on '"Li, Zhengjian"'

6. A bottom air temperature prediction model based on PSO-Elman neural network

Author

CHENG Lei, LI Zhengjian, SHI Haorong, and WANG Xin

Subjects
underground heat hazard prevention and control, bottom air temperature prediction, particle swarm optimization algorithm, elman neural network, pso-elman, Mining engineering. Metallurgy, TN1-997
Abstract

Currently, most underground wind temperature predictions use BP neural networks. But their prediction precision is affected by the number of learning samples and they are prone to falling into local optima. Elman neural networks have local memory capability, which improves the stability and dynamic adaptability of the network. However, there are still problems such as slow convergence speed and easy falling into local optima. In order to solve the above problems, the particle swarm optimization (PSO) algorithm is used to optimize the weights and thresholds of the Elman neural network. A bottom air temperature prediction model based on the PSO Elman neural network is established. The analysis shows that the relative humidity of the inlet and outlet wind, the surface inlet wind temperature, the surface atmospheric pressure, and the depth of the shaft are the main influencing factors of the bottom air temperature. Therefore, they are used as input data for the model, and the output data of the model is the bottom air temperature. The experimental results on the same sample dataset show that the Elman model converges at 90 iterations and the PSO Elman model converges at 41 iterations. It indicates that the PSO-Elman model converges faster. Compared with the BP neural network model, support vector regression (SVR) model, and Elman model, the prediction error of the PSO-Elman model is significantly reduced. The mean absolute error, mean square error (MSE), and mean absolute percentage error are 0.376 0 ℃, 0.278 3, and 1.95%, respectively. The determination coefficient R2 is 0.992 4, which is very close to 1, indicating that the prediction model has good predictive performance. The verification results of the example show that the relative error range of the PSO-Elman model is −4.69%-1.27%, the absolute error range is −1.06-0.29 ℃, and the MSE is 0.26. The overall prediction precision can meet the actual needs of the underground.

Published
2024
Full Text
View/download PDF

14. An Information-Assisted Deep Reinforcement Learning Path Planning Scheme for Dynamic and Unknown Underwater Environment

Author

Xi, Meng, Yang, Jiachen, Wen, Jiabao, Li, Zhengjian, Lu, Wen, and Gao, Xinbo

Abstract

An autonomous underwater vehicle (AUV) has shown impressive potential and promising exploitation prospects in numerous marine missions. Among its various applications, the most essential prerequisite is path planning. Although considerable endeavors have been made, there are several limitations. A complete and realistic ocean simulation environment is critically needed. As most of the existing methods are based on mathematical models, they suffer from a large gap with reality. At the same time, the dynamic and unknown environment places high demands on robustness and generalization. In order to overcome these limitations, we propose an information-assisted reinforcement learning path planning scheme. First, it performs numerical modeling based on real ocean current observations to establish a complete simulation environment with the grid method, including 3-D terrain, dynamic currents, local information, and so on. Next, we propose an information compression (IC) scheme to trim the mutual information (MI) between reinforcement learning neural network layers to improve generalization. A proof based on information theory provides solid support for this. Moreover, for the dynamic characteristics of the marine environment, we elaborately design a confidence evaluator (CE), which evaluates the correlation between two adjacent frames of ocean currents to provide confidence for the action. The performance of our method has been evaluated and proven by numerical results, which demonstrate a fair sensitivity to ocean currents and high robustness and generalization to cope with the dynamic and unknown underwater environment.

Published
2025
Full Text
View/download PDF

17. Enhanced electrocatalytic biomass oxidation at low voltage by Ni2+-O-Pd interfaces.

Author

Pei, An, Wang, Peng, Zhang, Shiyi, Zhang, Qinghua, Jiang, Xiaoyi, Chen, Zhaoxi, Zhou, Weiwei, Qin, Qizhen, Liu, Renfeng, Du, Ruian, Li, Zhengjian, Qiu, Yongcai, Yan, Keyou, Gu, Lin, Ye, Jinyu, Waterhouse, Geoffrey I. N., Huang, Wei-Hsiang, Chen, Chi-Liang, Zhao, Yun, and Chen, Guangxu

Subjects
LOW voltage systems, CATALYTIC oxidation, ACTIVATION energy, STANDARD hydrogen electrode, ALCOHOL oxidation, BIOMASS
Abstract

Challenges in direct catalytic oxidation of biomass-derived aldehyde and alcohol into acid with high activity and selectivity hinder the widespread biomass application. Herein, we demonstrate that a Pd/Ni(OH)2 catalyst with abundant Ni2+-O-Pd interfaces allows electrooxidation of 5-hydroxymethylfurfural to 2, 5-furandicarboxylic acid with a selectivity near 100 % and 2, 5-furandicarboxylic acid yield of 97.3% at 0.6 volts (versus a reversible hydrogen electrode) in 1 M KOH electrolyte under ambient conditions. The rate-determining step of the intermediate oxidation of 5-hydroxymethyl-2-furancarboxylic acid is promoted by the increased OH species and low C–H activation energy barrier at Ni2+-O-Pd interfaces. Further, the Ni2+-O-Pd interfaces prevent the agglomeration of Pd nanoparticles during the reaction, greatly improving the stability of the catalyst. In this work, Pd/Ni(OH)2 catalyst can achieve 100% 5-hydroxymethylfurfural conversion and >90% 2, 5-furandicarboxylic acid selectivity in a flow-cell and work stably over 200 h under a fixed cell voltage of 0.85 V. Catalytic oxidation of biomass-derived aldehydes and alcohols into acids is challenging due to low activity and selectivity. Here the authors report a Pd/Ni(OH)2 electrocatalyst with abundant Ni2+-O-Pd interfaces that enables efficient electrooxidation of 5-hydroxymethylfurfural to 2,5-furandicarboxylic acid with high selectivity and product yield. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

39. CeO2/Cu2O/Cu Tandem Interfaces for Efficient Water–Gas Shift Reaction Catalysis

Author

Li, Zhengjian, Wang, Mingzhi, Jia, Yanyan, Du, Ruian, Li, Tan, Zheng, Yanping, Chen, Mingshu, Qiu, Yongcai, Yan, Keyou, Zhao, Wei-Wei, Wang, Pei, Waterhouse, Geoffrey I. N., Dai, Sheng, Zhao, Yun, and Chen, Guangxu

Abstract

Metal–oxide interfaces on Cu-based catalysts play very important roles in the low-temperature water–gas shift reaction (LT-WGSR). However, developing catalysts with abundant, active, and robust Cu-metal oxide interfaces under LT-WGSR conditions remains challenging. Herein, we report the successful development of an inverse copper–ceria catalyst (Cu@CeO2), which exhibited very high efficiency for the LT-WGSR. At a reaction temperature of 250 °C, the LT-WGSR activity of the Cu@CeO2catalyst was about three times higher than that of a pristine Cu catalyst without CeO2. Comprehensive quasi-in situ structural characterizations indicated that the Cu@CeO2catalyst was rich in CeO2/Cu2O/Cu tandem interfaces. Reaction kinetics studies and density functional theory (DFT) calculations revealed that the Cu+/Cu0interfaces were the active sites for the LT-WGSR, while adjacent CeO2nanoparticles play a key role in activating H2O and stabilizing the Cu+/Cu0interfaces. Our study highlights the role of the CeO2/Cu2O/Cu tandem interface in regulating catalyst activity and stability, thus contributing to the development of improved Cu-based catalysts for the LT-WGSR.

Published
2023
Full Text
View/download PDF

40. Atomic-Interface Effect of Single-Atom Ru/CoOxfor Selective Electrooxidation of 5-Hydroxymethylfurfural

Author

Gu, Wenlei, Pei, An, Zhang, Shiyi, Jiang, Feifei, Jia, Yanyan, Qin, Qizhen, Du, Ruian, Li, Zhengjian, Liu, Renfeng, Qiu, Yongcai, Yan, Keyou, Zhao, Yun, Liang, Cheng, and Chen, Guangxu

Abstract

The development of single-atom catalysts with effective interfaces for biomass conversion is a promising but challenging research area. In this study, a Ru1/CoOxcatalyst was successfully fabricated with the impregnation method, which featured Ru single atoms on a cobalt oxide substrate. The Ru1/CoOxcatalyst showed superior performance in the selective electrooxidation of 5-hydroxymethylfurfural (HMF) to produce 2,5-furandicarboxylic acid (FDCA), a high value-added product. The introduction of Ru single atoms with an ultralow loading of ∼0.5 wt % was revealed to accelerate the electroredox of Co2+/Co3+/Co4+and improve the intrinsic activity of the CoOxsubstrate with an FDCA selectivity of 76.5%, which is better than that of the pristine CoOxelectrocatalysts (62.7%). The interfacial synergistic effect of the Ru1/CoOxinterface clarified that Ru single atoms can enhance the adsorption of HMF at the Ru1/CoOxinterface, which promoted the rate-determining step of the selective C–H bond activation for FDCA production. This finding provides valuable insights into the rational design of single-atom catalysts with functional interfaces for biomass upgrading.

Published
2023
Full Text
View/download PDF

43. Online monitoring and control of upstream cell culture process using 1D and 2D‐LC with SegFlow interface

Author

Chemmalil, Letha, primary, Wasalathanthri, Dhanuka P., additional, Zhang, Xin, additional, Kuang, June, additional, Shao, Chun, additional, Barbour, Robin, additional, Bhavsar, Sohil, additional, Prabhakar, Tanushree, additional, Knihtila, Ryan, additional, West, Jay, additional, Puri, Neha, additional, McHugh, Kyle, additional, Rehmann, Matthew S., additional, He, Qin, additional, Xu, Jianlin, additional, Borys, Michael C., additional, Ding, Julia, additional, and Li, Zhengjian, additional

Published
2021
Full Text
View/download PDF

45. Untargeted proteomics reveals upregulation of stress response pathways during CHO-based monoclonal antibody manufacturing process leading to disulfide bond reduction

Author

Park, Seo-Young, primary, Egan, Susan, additional, Cura, Anthony J., additional, Aron, Kathryn L., additional, Xu, Xuankuo, additional, Zheng, Mengyuan, additional, Borys, Michael, additional, Ghose, Sanchayita, additional, Li, Zhengjian, additional, and Lee, Kyongbum, additional

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results