检索结果-南通市图书馆

A multiscale adaptive framework based on convolutional neural network:Application to fluid catalytic cracking product yield prediction

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第4期21卷 2849-2869页

作者： Nan Liu Chun-Meng Zhu Meng-Xuan Zhang Xing-Ying Lan College of Artificial Intelligence China University of Petroleum(Beijing)Beijing102249China State Key Laboratory of Heavy Oil Processing China University of Petroleum(Beijing)Beijing102249China

Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production *** the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical *** light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale ***,the industrial data from the fluid catalytic cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature ***,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale ***,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final *** Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as *** conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series ***,its robustness and transferability underscore its promising potential for broader applications.

关键词： fluid catalytic cracking Product yield Data-driven modeling Multiscale prediction Data decomposition Convolution neural network

Effect of baffles on performance of fluid catalytic cracking riser

在线全文

学校读者我要写书评

暂无评论

Particuology 2018年第3期16卷 18-30页

作者： Milinkumar T. Shah Vishnu K. Pareek Geoffrey M. Evans Ranjeet P. Utikar Department of Chemical Engineering Curtin University Western Australia Australia Department of Chemical Engineering University of Newcastle New South Wales Australia

Increasing demand of automobile fuel and a need to process heavier crude oil makes it imperative to find improvements to the design of existing fluid catalytic cracking （FCC） units. Several modifications to the design of the riser section of FCC units have been suggested in previous studies including： improved feed nozzle designs, multiple nozzle configurations, internal baffles, and novel two-stage-riser systems. In this study, we investigate the effects of baffles on the performance of FCC risers using computational fluid dynamics simulations. In this study, predictions from a basis model （without baffles） are compared with those from four different configurations including：（i） 5-cm baffles at 5-m spacing, （ii） 7.5-cm baffles at 5- m spacing, （iii） 10-cm baffles with 5-m spacing, （iv） lO-cm baffles at 2.5-m spacing, and （v） lO-cm baffles at 1-m spacing. The baffles force the catalyst away from wails toward the center of the riser, enhancing the radial dispersion of the catalyst and the heat transfer inside the riser. The use of longer baffles and smaller spacings further increases the dispersion, yielding more homogeneous radial profiles. The changes in the radial dispersion result in variations in the conversion, yields, and pressure drops. The baffles increase conversion of vacuum gas oil （VGO） and the yield of gasoline. However, the simulations showed that longer baffles and a larger number of baffles did not always give a higher yield or higher conversion. Among the simulated configurations, the 5-cm baffles at 5-m spacing gave the highest conversion of VGO, whereas the 10-cm baffles at 1 -m spacing resulted in the highest yield of the gasoline. Thus, rational optimization of baffle configurations is required to achieve optimal performance.

关键词： fluid catalytic cracking Riser Baffles Computational fluid dynamics

Industrial Application and Fundamental Research Progress on fluid catalytic cracking Technology of Downer Reactors

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Petroleum Processing & Petrochemical Technology 2022年第3期24卷 139-150页

作者： Liu Wenming Yuan Qimin Zhu Genquan Yang Chao SINOPEC Research Institute of Petroleum Processing Co. Ltd.Beijing 100083

fluid catalytic cracking(FCC)technologies of downer reactors,which have reached the demonstration or commercial scale,are systematically discussed,i.e.,millisecond catalytic cracking,fluidization lab of Tsinghua University,and high-severity ***,aiming to promote industrial application,the fundamental studies are comprehensively described,particularly focusing on high-density downer reactors,clusters,and ***,from the perspective of industrial application,some research directions toward further developments are suggested.

关键词： fluid catalytic cracking downer reactor light olefins clean gasoline

Application of New Heavy Metals Resistant Porous Binder Material Used in fluid catalytic cracking Reaction

在线全文

学校读者我要写书评

暂无评论

China Petroleum Processing & Petrochemical Technology 2014年第1期16卷 35-39页

作者： Zhang Zhongdong Liu Zhaoyong Yan Zifeng Gao Xionghou Zhang Haitao Wang Zhifeng State Key Laboratory of Heavy Oil Processing China University of Petroleum Lanzhou Petrochemical Research Center Petrochemical Research Institute PetroChina

A novel porous binder was obtained from acid-treated kaolin. This new binder possessed abundant meso/macropores, good hydrothermal stability and heavy metal resistance. The prepared catalyst using new binder featured low attrition index and large pore volume. The catalysts were contaminated with Ni, V, and tested in a fixed-fluidized bed reactor unit. In comparison with the reference sample, the oil conversion achieved by the above-mentioned catalyst increased by 3.50 percentage points, and heavy oil yield decreased by 2.86 percentage points, while the total liquid yield and light oil yield increased by 2.82 percentage points and 0.79 percentage points, respectively. The perfect pore structure, good hydrothermal stability and heavy metal resistant performance of new binder were the possible causes leading to its outstanding performance.

关键词： fluid catalytic cracking binder conversion porous material hydrothermal stability heavy metal resistant

Modeling and Optimization of a Fractionation,Absorption,and Stabilization System in an Industrial fluid catalytic cracking Process

在线全文

学校读者我要写书评

暂无评论

China Petroleum Processing & Petrochemical Technology 2022年第3期24卷 117-127页

作者： Long Jian Jiang Siyi Wang Wei Zhang Feng Han Jifei Fan Chen Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China SINOPEC Jiujiang Company Jiujiang 332013China SINOPEC Research Institute of Petroleum Processing Beijing 100083China

fluid catalytic cracking(FCC)is a vitally important refinery *** fractionation,absorption,and stabilization system in the FCC process is a significant way to obtain key products,and its parameters will directly affect the quality of the *** this work,using industrial data from an actual FCC process,a model of the FCC fractionation,absorption,and stabilization system was developed using process simulation *** sequence quadratic program algorithm was then used to identify the parameters of each tower,increasing the accuracy of the simulation ***,using this improved model,a sensitivity analysis was performed to examine the effects of different operating *** pattern-search method was then used to optimize the operating parameters of the *** results showed that the optimized model has good prediction accuracy,and using the model,it was found that changing the operation parameters could result in a 1.84%improvement in economic *** such,the developed model was demonstrated to be usefully applicable to the optimization of the process operation of an FCC fractionation,absorption,and stabilization system.

关键词： fluid catalytic cracking sequence quadratic program process modeling parameters identification patternsearch method

Study of Carbon Nanotube Supported Co-Mo Selective Hydrodesulphurization Catalysts for fluid catalytic cracking Gasoline

在线全文

学校读者我要写书评

暂无评论

Journal of Natural Gas Chemistry 2005年第3期14卷 163-167页

作者： Wenkui Yin Mei Li Hongyan Shang Chenguang Liu Fei Wei State Key Laboratory of Heavy Oil Processing Key Laboratory of Catalysis CNPC China University of Petroleum Dongying 257061 China Department of Chemical Engineering Tsinghua University Bejing 100083 China

In this paper, carbon nanotube supported Co-Mo catalysts for selective hydrodesulphurization （HDS） of fluid catalytic cracking （FCC） gasoline were studied, using di-isobutylene, cyclohexene, 1-octene and thiophene as model compounds to simulate FCC gasoline. The results show that the Co-Mo/CNT has very high HDS activity and HDS/hydrogenation selectivity comparing with the Co-Mo/γ-Al2O3 and Co-Mo/AC catalyst systems. The saturation ratio of cyclohexene was lower than 50%, and the saturation ratio of 1,3-di-isobutylene lower than 60% for the Co-Mo/CNT catalysts. Co/Mo atomic ratio was found to be one of the most important key factors in influencing the hydrogenation selectivity and HDS activity, and the most suitable Co/Mo atomic ratio was 0.4. Co/CNT and Mo/CNT mono-metallic catalysts showed lower HDS activity and selectivity than the Co-Mo/CNT bi-metallic catalysts.

关键词： XRD hydrodesulphurization carbon nanotube cobalt molybdenum selectivity fluid catalytic cracking gasoline

Numerical Predication of cracking Reaction of Particle Clusters in fluid catalytic cracking Riser Reactors

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2008年第5期16卷 670-678页

作者：王淑彦陆慧林高金森徐春明孙丹 School of Energy Science and Engineering Harbin Institute of Technology Harbin 150001 China State Key Laboratory of Heavy Oil Processing China University of Petroleum Beijing 102249 China

Behavior of catalytic cracking reactions of particle cluster in fluid catalytic cracking （FCC） riser reactors was numerically analyzed using a four-lump mathematical model. Effects of the cluster porosity, inlet gas velocity and temperature, and coke deposition on cracking reactions of the cluster were investigated. Distributions of temperature, gases, and gasoline from both catalyst particle cluster and an isolated catalyst particle are presented. The reaction rates from vacuum gas oil （VGO） to gasoline, gas and coke of individual particle in the cluster are higher than those of the isolated particle, but it reverses for the reaction rates from gasoline to gas and coke. Less gasoline is produced by particle clustering. Simulated results show that the produced mass fluxes of gas and gasoline increase with the operating temperature and molar concentration of VGO, and decrease due to the formation of coke.

关键词： cluster fluid catalytic cracking numerical simulation riser

Supervised Imitation Training for Deep Reinforcement Learning Control of a fluid catalytic cracking System

在线全文

学校读者我要写书评

暂无评论

Supervised Imitation Training for Deep Reinforcement Learnin...

Effects of Temperature and Catalyst to Oil Weight Ratio on the catalytic Conversion of Heavy Oil to Propylene Using ZSM-5 and USY Catalysts

第43届中国控制会议

作者： Wei Wang Lingjian Ye Zeyu Yang Jingsheng Qin Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University

Reinforcement Learning(RL) based intelligent automation techniques have been widely applied in various industrial sectors, ranging from unmanned aerial vehicles to autonomous driving vehicles. However, training a sophisticated RL controller for the industry-level application is usually time-consuming and expensive. To tackle this challenge, a supervised imitation training approach is proposed in this work. This approach utilizes state-of-art industrial controllers, particularly the PID controllers, to facilitate training RL controllers. The actor network within the RL controller is pre-trained by fitting the data which are collected from traditional controllers. As a result, the agent at first behaves similarly to the conventional controller, but its performance could be improved during the online stage for training the RL agent. Experiments were conducted for a simulated fluid catalytic cracking, where the effectiveness of the supervised imitation approach is verified.

关键词： Reinforcement learning fluid catalytic cracking PID controller supervised imitation training

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Natural Gas Chemistry 2007年第1期16卷 92-99页

作者： Xiaohong Li Chunyi Li Jianfang Zhang Chaohe Yang Honghong Shan State Key Laboratory of Heavy Oil Processing China University of Petroleum （Huadong） Dongying 257061 Shandong China

It is useful for practical operation to study the rules of production of propylene by the catalytic conversion of heavy oil in FCC （fluid catalytic cracking）. The effects of temperature and C/O ratio （catalyst to oil weight ratio） on the distribution of the product and the yield of propylene were investigated on a micro reactor unit with two model catalysts, namely ZSM-5/Al2O3 and USY/Al2O3, and Fushun vacuum gas oil （VGO） was used as the feedstock. The conversion of heavy oil over ZSM-5 catalyst can be comparable to that of USY catalyst at high temperature and high C/O ratio. The rate of conversion of heavy oil using the ZSM-5 equilibrium catalyst is lower compared with the USY equilibrium catalyst under the general FCC conditions and this can be attributed to the poor steam ability of the ZSM-5 equilibrium catalyst. The difference in pore topologies of USY and ZSM-5 is the reason why the principal products for the above two catalysts is different, namely gasoline and liquid petroleum gas （LPG）, repspectively. So the LPG selectivity, especially the propylene selectivity, may decline if USY is added into the FCC catalyst for maximizing the production of propylene. Increasing the C/O ratio is the most economical method for the increase of LPG yield than the increase of the temperature of the two model catalysts, because the loss of light oil is less in the former case. There is an inverse correlation between HTC （hydrogen transfer coefficient） and the yield of propylene, and restricting the hydrogen transfer reaction is the more important measure in increasing the yield of propylene of the ZSM-5 catalyst. The ethylene yield of ZSM-5/A1203 is higher, but the gaseous side products with low value are not enhanced when ZSM-5 catalyst is used. Moreover, for LPG and the end products, dry gas and coke, their ranges of reaction conditions to which their yields are dependent are different, and that of end products is more severe than that of LPG. So it is clear that maximizin

关键词： fluid catalytic cracking heavy oil propylene temperature catalyst to oil weight ratio ZSM-5 USY