资源类型

期刊论文 2

年份

2023 1

2018 1

关键词

检索范围:

排序: 展示方式:

Research and development of hydrocracking catalysts and technologies in China

Chong Peng, Yanze Du, Xiang Feng, Yongkang Hu, Xiangchen Fang

《化学科学与工程前沿(英文)》 2018年 第12卷 第4期   页码 867-877 doi: 10.1007/s11705-018-1768-x

摘要:

Hydrocracking of petroleum feedstock represents a compelling route for the production of industrial clean fuels, which has triggered the continuous research and development of core technology related areas such as catalysts, reaction engineering and engineering design. This review particularly focuses on the research and development of catalysts and catalytic processes for hydrocracking of petroleum feedstock in China. Hydroprocessing technologies of China keep pace with the up-to-date progress of the world, and some of the technologies have achieved leading role in the world. It is noted that China Petroleum and Chemical Corporation has a full range of hydroprocessing technologies and provides corresponding “tailor-made” catalysts. Through the efforts of several generations, 20 categories of the catalysts including more than 60 brands have been developed, among which more than 40 brands have been successfully applied for more than 130 times. Importantly, the pivotal technical improvements including the deep drawing vacuum gas-oil (VGO) and de-asphalting oil hydrocracking technology to improve material adaptability, the high value-added hydrogenation technology to convert high aromatic diesel conversion to naphtha, the hydrocracking technology using VGO-catalytic diesel blends, the Fushun Research Institute of Petroleum and Petrochemicals’ diesel to gasoline and diesel hydrocracking technologies, and the Sheer hydrocracking technology to reduce energy are reviewed.

关键词: hydrocracking     process     catalyst     China    

Multiple input self-organizing-map ResNet model for optimization of petroleum refinery conversion units

《化学科学与工程前沿(英文)》 2023年 第17卷 第6期   页码 759-771 doi: 10.1007/s11705-022-2269-5

摘要: This work introduces a deep-learning network, i.e., multi-input self-organizing-map ResNet (MISR), for modeling refining units comprised of two reactors and a separation train. The model is comprised of self-organizing-map and the neural network parts. The self-organizing-map part maps the input data into multiple two-dimensional planes and sends them to the neural network part. In the neural network part, residual blocks enhance the convergence and accuracy, ensuring that the structure will not be overfitted easily. Development of the MISR model of hydrocracking unit also benefits from the utilization of prior knowledge of the importance of the input variables for predicting properties of the products. The results show that the proposed MISR structure predicts more accurately the product yields and properties than the previously introduced self-organizing-map convolutional neural network model, thus leading to more accurate optimization of the hydrocracker operation. Moreover, the MISR model has smoother error convergence than the previous model. Optimal operating conditions have been determined via multi-round-particle-swarm and differential evolution algorithms. Numerical experiments show that the MISR model is suitable for modeling nonlinear conversion units which are often encountered in refining and petrochemical plants.

关键词: hydrocracking     convolutional neural networks     self-organizing map     deep learning     data-driven optimization    

标题 作者 时间 类型 操作

Research and development of hydrocracking catalysts and technologies in China

Chong Peng, Yanze Du, Xiang Feng, Yongkang Hu, Xiangchen Fang

期刊论文

Multiple input self-organizing-map ResNet model for optimization of petroleum refinery conversion units

期刊论文