检索结果-南通市图书馆

Deep learning technique for process fault detection and diagnosis in the presence of incomplete data

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2020年第9期28卷 2358-2367页

作者： Cen Guo Wenkai Hu Fan Yang dexian huang Department of Automation Tsinghua UniversityBeijing 10084China Cornell University NY 14850United States of America University of Alberta EdmontonAB T6G 1H9Canada

In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder,a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.

关键词： Alarm configuration Deep learning Fault detection and diagnosis Incomplete data Stacked autoencoder

A decision tree based decomposition method for oil refinery scheduling

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2018年第8期26卷 1605-1612页

作者： Xiaoyong Gao dexian huang Yongheng Jiang Tao Chen Institute for Ocean Engineering China University of Petroleum Department of Automation Tsinghua University Department of Chemical and Process Engineering University of Surrey

Refinery scheduling attracts increasing concerns in both academic and industrial communities in recent ***, due to the complexity of refinery processes, little has been reported for success use in real world refineries. In academic studies, refinery scheduling is usually treated as an integrated, large-scale optimization problem,though such complex optimization problems are extremely difficult to solve. In this paper, we proposed a way to exploit the prior knowledge existing in refineries, and developed a decision making system to guide the scheduling process. For a real world fuel oil oriented refinery, ten adjusting process scales are predetermined. A C4.5 decision tree works based on the finished oil demand plan to classify the corresponding category(i.e. adjusting scale). Then,a specific sub-scheduling problem with respect to the determined adjusting scale is solved. The proposed strategy is demonstrated with a scheduling case originated from a real world refinery.

关键词： Refinery scheduling Decision tree C4.5 Decomposition method

A continuous-time formulation for refinery production scheduling problems involving operational transitions in mode switching

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2016年第8期24卷 1020-1031页

作者： Lei Shi Yongheng Jiang Ling Wang dexian huang Institute of Process Control Engineering Department of Automation Tsinghua University Tsinghua National Laboratory for Information Science and Technology Tsinghua University

In the refinery scheduling, operational transitions in mode switching are of great significance to formulate dynamic nature of production and obtain efficient schedules. The discrete-time formulation meets two main challenges in modeling: discrete approximation of time and large size of mixed-integer linear problem(MILP).In this article, a continuous-time refinery scheduling model, which involves transitions of mode switching, is presented due to these challenges. To reduce the difficulty in solving large scale MILPs resulting from the sequencing constraints, the global event-based formulation is chosen. Both transition constraints and production transitions are introduced and the numbers of key variables and constraints in both of the discrete-time and continuous-time formulations are analyzed and compared. Three cases with different lengths of time horizons and different numbers of orders are studied to show the efficiency of the proposed model.

关键词： Refinery scheduling Operational transitions Continuous-time representation

A review of control loop monitoring and diagnosis:Prospects of controller maintenance in big data era

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2016年第8期24卷 952-962页

作者： Xinqing Gao Fan Yang Chao Shang dexian huang Department of Automation Tsinghua University Tsinghua National Laboratory for Information Science and Technology

Owing to wide applications of automatic control systems in the process industries, the impacts of controller performance on industrial processes are becoming increasingly significant. Consequently, controller maintenance is critical to guarantee routine operations of industrial processes. The workflow of controller maintenance generally involves the following steps: monitor operating controller performance and detect performance degradation, diagnose probable root causes of control system malfunctions, and take specific actions to resolve associated problems. In this article, a comprehensive overview of the mainstream of control loop monitoring and diagnosis is provided, and some existing problems are also analyzed and discussed. From the viewpoint of synthesizing abundant information in the context of big data, some prospective ideas and promising methods are outlined to potentially solve problems in industrial applications.

关键词： Control loop performance assessment Industrial alarm system Process knowledge Root cause diagnosis Big data

Trajectory Planning for Automated Driving Based on Ordinal Optimization

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2017年第1期22卷 62-72页

作者： Xiaoxin Fu Yongheng Jiang dexian huang Kaisheng huang Jingchun Wang Department of Automation Tsinghua UniversityBeijing 100084 China Department of Automobile Engineering Tsinghua UniversityBeijing 100084 China

This paper proposes an approach based on Ordinal Optimization（OO） to solve trajectory planning for automated driving. As most planning approaches based on candidate curves optimize the trajectory curve and the velocity profile separately, this paper formulates the problem as an unified Non-Linear Programming（NLP） model,optimizing the trajectory curve and the acceleration profile（acceleration is the derivative of velocity） *** a hybrid optimization algorithm named OODE, developed by combining the idea of OO and Differential Evolution（DE）, is proposed to solve the NLP model. With the acceleration profile optimized ＂roughly＂, OODE computes and compares ＂rough＂（biased but computationally-easier） curve evaluations to select the best curve from candidates, so that a good enough curve can be obtained very efficiently. Then the acceleration profile is optimized again ＂accurately＂ with the selected curve. Simulation results show that good enough solutions are ensured with a high probability and our method is capable of working in real time.

关键词： ordinal optimization trajectory planning automated driving autonomous vehicle rough evaluation

Intelligent Garbage Recycling: Design and Implementation Exploration of Automatic Classification System

在线全文

学校读者我要写书评

暂无评论

Meteorological and Environmental Research 2024年第2期15卷 37-39,43页

作者： dexian huang Binjun GAN Environmental Sanitation Station in Wuming District of Nanning City Nanning 530100China Smart Agriculture College Yulin Normal UniversityYulin 535000China

This paper introduces an intelligent waste recycling automatic classification system,which integrates sensors,image recognition,and robotic arms to achieve automatic identification and classification of *** system monitors the composition and properties of waste in real time through sensors,and uses image recognition technology for precise classification,and the robotic arm is responsible for grabbing and *** design and implementation of the system have important practical significance and application value,and help promote the popularization and standardization of waste *** paper details the system s architecture,module division,sensors and recognition technology,robotic arm and grabbing technology,data processing and control system,and testing and optimization *** results show that the system has efficient waste recycling efficiency and accuracy in practical applications,bringing new development opportunities to the waste recycling industry.

关键词： Waste classification and recycling Sensors Image recognition Robotic arms Convolutional neural networks

Design and Implementation of an Intelligent Monitoring and Early Warning System for Kitchen Garbage Treatment

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

Meteorological and Environmental Research 2024年第3期15卷 68-71页

作者： dexian huang Binjun GAN Environmental Health Workstation in Wuming District Nanning 530100China Smart Agriculture College of Yulin Normal University Yulin 535000China

With a population of 1.4 billion in China and a huge daily output of kitchen waste,intelligent treatment of kitchen waste is *** article elaborates on the design and implementation of an intelligent monitoring and early warning system from five aspects:system architecture design,hardware equipment selection and configuration,data collection and processing flow,early warning algorithm and model development,and system integration and testing *** also points out the advantages of the intelligent monitoring and early warning system in kitchen waste treatment.

关键词： Environmental sanitation Ecological environment Garbage disposal Intelligent systems

Recognition of amino acids and anions by a Zn(Ⅱ)-methylazacalix[4]pyridine complex

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

Science China Chemistry 2009年第10期52卷 1639-1645页

作者： GONG HanYuan, WANG dexian, huang ZhiTang & WANG MeiXiang Beijing National Laboratory for Molecular Sciences, CAS Laboratory of Molecular Recognition and Function, Institute of Chemistry, Chinese Academy of Sciences, Beijing 100190, China Beijing National Laboratory for Molecular Sciences CAS Laboratory of Molecular Recognition and Function Institute of Chemistry Chinese Academy of Sciences Beijing 100190 China

As a powerful macrocyclic host molecule with unique conformation and cavity structure that are fine-tuned by the bridging nitrogen atoms, methylazacalix[4]pyridine (MACP-4) has been shown to selectively recognize Zn2+ and form stable Zn(Ⅱ)-MACP-4 complexes both in solid state and solution with an association constant up to 5.97 (logKs). The molecular recognition of Zn(Ⅱ)-MACP-4 complexes towards various amino acids and anions with different geometry was investigated by using the spectral titration methods and X-ray analysis. The Zn(Ⅱ)-MACP-4 complex was found to recognize the 17 amino acids tested with the association constant up to 3.97 (logKs). On the other hand, the Zn(Ⅱ)-MACP-4 complex selectively interacted with anions and the maximum association constant of 3.9 (logKs) was obtained.

关键词： Zn(Ⅱ)-MACP-4 complex amino acids anions recognition

基于差分进化算法和HYSYS机理模型的催化重整过程优化

在线全文

学校读者我要写书评

暂无评论

化工学报 2008年第7期59卷 1755-1760页

作者：王钧炎黄德先清华大学自动化系北京100084

选取催化重整18集总31反应集总动力学模型,以流程模拟软件HYSYS为工具,建立了催化重整机理模型。以最大化芳烃产率为优化目标,以4个反应器入口温度为决策变量,建立了过程优化模型。利用差分进化算法求解该优化问题,并利用可行性规则处... 详细信息

选取催化重整18集总31反应集总动力学模型,以流程模拟软件HYSYS为工具,建立了催化重整机理模型。以最大化芳烃产率为优化目标,以4个反应器入口温度为决策变量,建立了过程优化模型。利用差分进化算法求解该优化问题,并利用可行性规则处理约束。仿真结果表明,芳烃产率有较大提高,证实了差分进化算法的有效性。

关键词：催化重整动力学模型约束优化差分进化算法可行性规则