检索结果-内蒙古大学图书馆

Novel Ensemble Modeling Method for Enhancing Subset Diversity Using Clustering Indicator Vector Based on Stacked Autoencoder

引用

Computer Modeling in Engineering & Sciences 2019年第10期121卷 123-144页

作者： Yanzhen Wang Xuefeng Yan Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and TechnologyShanghai200237China

A single model cannot satisfy the high-precision prediction requirements given the high nonlinearity between *** contrast,ensemble models can effectively solve this *** key factors for improving the accuracy of ensemble models are namely the high accuracy of a submodel,the diversity between subsample sets and the optimal ensemble *** study presents an improved ensemble modeling method to improve the prediction precision and generalization capability of the *** proposed method first uses a bagging algorithm to generate multiple subsample ***,an indicator vector is defined to describe these subsample ***,subsample sets are selected on the basis of the results of agglomerative nesting clustering on indicator vectors to maximize the diversity between ***,these subsample sets are placed in a stacked autoencoder for ***,XGBoost algorithm,rather than the traditional simple average ensemble method,is imported to ensemble the model during *** machine learning public datasets and atmospheric column dry point dataset from a practical industrial process show that our proposed method demonstrates high precision and improved prediction ability.

关键词： Ensemble model deep learning bagging stacked autoencoder XGBoost

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Strategy for Few Shot Industrial Process Based on Data Augmentation and Depth Information Extraction

SSRN

引用

SSRN 2022年

作者： Tian, Ying Xiang, Xin Peng, Xin Zhong, Yin Zhang, Wei Department of control science and Engineering School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China

Data based intelligent fault diagnosis method is an important tool for ensuring the stability of industrial process. However, in the actual industrial process, due to the difficulty of feature extraction and the lack of labeled fault data, it is hard to form a fault diagnosis model with good performance. To address this problem, the Self-Attention embedded Generative Adversarial Networks combined with the Residual Network(SAGAN-ResNet) is proposed in this study. Firstly, to handle the lack of the fault data, the data enhancement method which consists of Self-Attention embedded generator and discriminator is adopted. Then, to extract the feature for better diagnosis performance, based on the augmented training dataset, Residual Network (ResNet) is introduced. Finally, the proposed method is compared with others, the results show that proposed method has advantages in the case of complex process fault diagnosis with few shot industrial data. © 2022, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Trajectory planning in 3D dynamic environment with non-cooperative agents via fast marching and Bézier curve

引用

Cyber-Physical Systems 2019年第2期5卷 119-143页

作者： Zong, Xuepeng Sun, Qiyu Yao, Dachen Du, Wei Tang, Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai China

In this paper, we propose a framework for trajectory planning in a 3D dynamic environment where other non-cooperative agents may obstruct the active quadrotor. A trajectory predictor is designed for the non-cooperative agent via least squares. In addition, based on Euclidean signed distance field (ESDF), a velocity map configuration is developed for both dynamic and static obstacles, and then utilized in fast marching method to find a feasible discrete path. The smooth and dynamic feasible trajectory generation problem is formulated as a quadratic programming (QP) problem, where a safe flight corridor generator is developed for safe constraints in a dynamic environment. Piecewise Bézier curves are used to represent the generated trajectory. With the help of flight corridor, along with the convex hull property of Bézier curve, the quadratic programming problem turns into a convex optimization problem. Simulation results show that the proposed approach is validated for collision avoidance in a dynamic environment. © 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Techno-Economic Assessment of Modified Fischer-Tropsch Synthesis Process for Direct Co2 Conversion into Jet Fuel

SSRN

引用

SSRN 2023年

作者： Han, Yide Kamkeng, Ariane D.N. Otitoju, Olajide Ding, Yuxing Wang, Meihong Department of Chemical and Biological Engineering The University of Sheffield SheffieldS1 3JD United Kingdom Key Laboratory of Advanced Control and Optimisation for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China

Direct use of CO2 through modified Fischer-Tropsch synthesis (FTS) process presents a viable approach for the production of carbon-neutral jet fuel. However, achieving high performance for the CO2-FTS process remains a significant challenge. Current technology can only achieve low CO2 conversion and low jet fuel yield using tailored catalysts, which hinders the commercial deployment of direct CO2-FTS process. This paper presents a techno-economic assessment (TEA) of jet fuel production via CO2-FTS process at commercial-scale. Two ex-situ water removal configurations: (a) multi-stage CO2-FTS process and (b) CO2-FTS with tail gas recycle process were conducted to assess their potential for performance improvement. Process performance was evaluated using a model developed in Aspen Plus® linking with Aspen Custom Modeller®, while economic evaluation was carried out in Aspen Process Economic Analyzer®. The CO2-FTS model was based on first principles and modified Anderson-Schulz-Flory (ASF) distribution. Results indicated that both ex-situ water removal configurations can significantly improve the process performance. CO2-FTS process with 90% tail gas recycle has the best performance for both technical and economic analysis. The process achieved 85.8% CO2 conversion and 35.6% jet fuel yield with the lowest energy demand of 5.30 MWh per tonne of produced jet fuel. Moreover, it boasts the lowest minimum selling price (MSP) of jet fuel at $2.6/kg despite incurring the second-highest capital expenditure cost of M$ 451.3. A comparison of the two ex-situ water removal configurations at 61.9% and 76.5% CO2 conversion, suggests that both processes exhibit comparable technical performances, yet the recycling of tail gas holds the potential to reduce economic costs. Consequently, this study will inspire researchers on process improvement and cost reduction of the commercial-scale CO2-FST jet fuel production. © 2023, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Monitoring and path optimization of catalytic reformer in a refinery:principal component analysis and big data application

Monitoring and path optimization of catalytic reformer in a ...

引用

第32届中国过程控制会议(CPCC2021)

作者： Zhi Li Yuhui Ying Minglei Yang Liang Zhao Ling Zhao Wenli Du Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology School of Chemical Engineering East China University of Science and Technology

Catalytic naphtha reformer is an essential unit in *** converts naphtha from crude oil distillation,hydrocracking,and light hydrocarbon recovery units and other purchased reformates into reforming gasoline,aromatic feedstock,and high-purity hydrogen through catalytic *** hydrocarbons are important raw materials for chemical and polyester industries,and highpurity hydrogen is an extremely valuable product used in other hydrogenation *** gasoline has a high-octane number and low *** is unleaded and nearly does not contain olefin and is thus an ideal raw material for gasoline blending.A PCA model was developed on the basis of the industrial process' historical database,and the first two PCs were selected for the construction of a ***,every sample point was projected onto this plane by using the scores of first principle component(PC-1) and second principle component(PC-2).Then,a 95% confidence ellipse was *** profit of each operating condition was calculated by using the prices of input,output,and other necessary ***,highand low-efficiency intervals were easily divided on the ellipse,and the operating conditions were optimized by using the position of the projection point on the plane.A path optimization method(A* algorithm) was introduced for the optimization of the new sample,and the trajectory of the sample moving from the current projection position to the better area was *** trend of the original operating variable in the path was *** effectiveness of the proposed framework is verified by applying it to a Sinopec *** innovations of this study were summarized as follows:(1) PCA projection and remapping methods were provided for the monitoring of the naphtha catalytic reforming process.(2) A* algorithm was used for the path optimization of the operating conditions of naphtha catalytic reformer on the derived projection plane.(3) A case study of the refinery wa

关键词： Catalytic reformer Industrial big data PCA projection and remapping Process monitoring Path optimization

来源：评论

学校读者我要写书评

暂无评论

Factored Trace Lasso Based Linear Regression Methods: optimizations and Applications 5th

Factored Trace Lasso Based Linear Regression Methods: Optimi...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhang, Hengmin Du, Wenli Liu, Xiaoqian Zhang, Bob Qian, Feng School of Information Science and Engineering Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing210031 China Department of Computer and Information Science University of Macau 999078 China

ISBN: (纸本)9789811623356

Consider that matrix trace lasso regularized convex p -norm with p= 1, 2 regression methods usually have the higher computational complexity due to the singular value decomposition (SVD) of larger size matrix in big data and information processing. By factoring the matrix trace lasso into the squared sum of two Frobenius-norm, this work studies the solutions of both adaptive sparse representation (ASR) and correlation adaptive subspace segmentation (CASS), respectively. Meanwhile, the derived models involve multi-variable nonconvex functions with at least two equality constraints. To solve them efficiently, we devise the nonconvex alternating direction multiplier methods (NADMM) with convergence analysis satisfying the Karush-Kuhn-Tucher (KKT) conditions. Finally, numerical experiments to the subspace clustering can show the less timing consumptions than CASS and the nearby performance of our proposed method when compared with the existing segmentation methods like SSC, LRR, LSR and CASS. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Investigating impacts of cost functions to atmospheric dispersion modeling and source term estimation in turbulent condition

引用

Huagong Xuebao/CIESC Journal 2020年第3期71卷 1163-1173页

作者： Dong, Jikai Du, Wenli Wang, Bing Xu, Qiaoyi Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China

Hazardous gas release will threaten social security and cause damage to property and environment. Establish an effective emergency response system with monitoring devices can help reduce the potential risk and provide evaluation for release accident emergencies. The gas concentration is detected by the gas concentration sensor arranged in the risk area, and the leakage assessment is carried out according to the meteorological conditions and the forward diffusion model. Because the data of leakage scenarios is not easy to obtain, the large eddy simulation method based on Fires Dynamics Simulator (FDS) is used in this paper to generate date through simulating release scenarios with turbulent condition. On this basis, the impacts of the cost function to the modeling process and source term estimation are studied. The results of source term estimation shows the function of the square sum of concentration deviation is better than other functions. However, the function cannot avoid the condition that the estimation index of some scenes is far from the average value because of turbulent flow. In addition, a combination of the estimation results of different cost functions can improve the situation to a certain extent. © All Right Reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Data-Driven controller Synthesis for Parameters Unknown Linear-delay Systems with Input Constraint

Data-Driven Controller Synthesis for Parameters Unknown Line...

引用

第33届中国控制与决策会议

作者： Jinggao Sun Guanghao Su Xianfeng Chen Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and Technology

In practical control engineering,delay and actuator saturation are main challenges which may lead to system performance degradation,or even controlled variables *** of Smith predictor and model recovery anti windup method is an effective solution to linear delay system anti-windup synthesis,however model dependent property of the above two methods brings obstacles for the application and *** overcome such a difficulty,a data-driven approach is proposed in this paper,operating data is collected and utilized to simultaneously tune feedback controller parameters and estimate internal model applied in Smith ***,anti-windup compensator is constructed with the estimated model and a compensator gain optimization structure is proposed based on Lyapunov ***,simulations have been implemented to three typical processes in chemical engineering,and detailed performance comparison is provided to illustrate the effectiveness of the proposed method.

关键词： anti-windup data-driven control smith predictor unknown linear delay system

来源：评论

学校读者我要写书评

暂无评论

Fuzzy H∞Sliding Mode control of Persistent Dwell-Time Switched Nonlinear Systems

引用

IEEE Transactions on Fuzzy Systems 2022年第12期30卷 5143-5151页

作者： Wang, Jing Wang, Haitao Yan, Huaicheng Wang, Yueying Shen, Hao Anhui University of Technology AnHui Province Key Laboratory of Special Heavy Load Robot The School of Electrical and Information Engineering Ma'anshan243032 China East China University of Science and Technology School of Information Science and Engineering Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education Shanghai200237 China Shanghai University School of Mechatronic Engineering and Automation Shanghai201620 China

In this article, the fuzzy H∞ sliding mode control problem for continuous-time switched nonlinear systems is investigated. The switching signal conforms to the persistent dwell-time switching mechanism. The first objective of this article is to construct a switched integral sliding surface that not only accommodates the switched nonlinear model, but ensures that the sliding mode dynamics are globally uniformly exponentially stable and have an H∞ performance by the equivalent controller derived from the sliding surface. Another aim is to integrate the switched sliding mode control law to force the system trajectories to the sliding surface in a finite amount of time. Then, on the basis of the Lyapunov function technique, the specific form of the sliding mode control law gains is given first, and later the finite-time reachability of the sliding surface is ensured. Finally, the validity of the proposed switched sliding mode control method is validated by a numerical example. © 1993-2012 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Switchable PID controller Tuning Based on Golden Section Reduction Rule

引用

IFAC-PapersOnLine 2020年第2期53卷 11068-11073页

作者： Jingao Sun Guanghao Su Xianfeng Chen Wen Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes of the Ministry of Education East China University of Science and Technology Shanghai 200237 China

Resulting from the complexity and sensitivity instinct, high-order control system design is always a challenge faced by engineers from process industry. To solve this challenging task, a switchable control scheme consisted of two sub-controllers tuned based on two complementary simplified models respectively is proposed in this paper, and golden section is introduced into process model reduction to simplify parameter tuning. Inspired by adaptive control strategy, the controller switch mechanism depends on the time domain response similarity between the original high-order model and the simplified model. Besides, PID controller structure and corresponding parameter tuning method, such as Ziegler-Nichols method and SIMC method, are remained to guarantee the facility and efficiency of sub-controller design. The proposed method has been tested on several examples (balanced, lag-dominant, and a delay-dominant process) and the comparison with other tuning method based on step-response data resulting in favorable control performance.

关键词： high-order system model reduction multiple models switching PID control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：