检索结果-内蒙古大学图书馆

Graph-guided masked autoencoder for process anomaly detection

process Safety and Environmental Protection 2024年 186卷 1345-1357页

作者： Jia, Mingwei Xu, Danya Yang, Tao Yao, Yuan Liu, Yi Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Chemical Engineering National Tsing Hua University Hsinchu300044 Taiwan

Developing an accurate and reliable anomaly detection model is of great significance for safe operation in the process industry. To minimize false positives, it is crucial to accurately model the intricate topological and nonlinear connections among variables. In this study, a process anomaly detection method based on graph-guided masked autoencoder (GGMAE) is proposed by introducing the concept of the graph to the process industry. GGMAE first constructs a topology graph according to the process flowchart. Then, the patch and mask mechanism forces GGMAE to learn the process intrinsic information to reconstruct the input according to the variable topological relationship and temporal characteristics. Additionally, Kullback-Leibler divergence is used as the loss to ensure that the distribution of input and output is consistent. Experiments on two publicly available anomaly detection benchmarks demonstrate the superiority of GGMAE over existing methods. Visualization of the results demonstrates the physically compliant reconstruction logic. © 2024 The Institution of Chemical Engineers

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

State Estimation Moving Window Gradient Iterative Algorithm for Bilinear Systems Using the Continuous Mixed p-norm Technique

引用

Computer Modeling in engineering & Sciences 2023年第2期134卷 873-892页

作者： Wentao Liu Junxia Ma Weili Xiong Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) School of Internet of Things EngineeringJiangnan UniversityWuxi214122China

This paper studies the parameter estimation problems of the nonlinear systems described by the bilinear state space models in the presence of disturbances.A bilinear state observer is designed for deriving identification algorithms to estimate the state variables using the input-output *** on the bilinear state observer,a novel gradient iterative algorithm is derived for estimating the parameters of the bilinear systems by means of the continuous mixed p-norm cost *** gain at each iterative step adapts to the data quality so that the algorithm has good robustness to the noise ***,to improve the performance of the proposed algorithm,a dynamicmoving window is designed which can update the dynamical data by removing the oldest data and adding the newestmeasurement data.A numerical example of identification of bilinear systems is presented to validate the theoretical analysis.

关键词： Bilinear state space model parameter estimation moving window continuous mixed p-norm

来源：评论

学校读者我要写书评

暂无评论

Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2233-2247页

作者： Hongyu Ding Yuanze Tang Qing Wu Bo Wang Chunlin Chen Zhi Wang the Department of Control Science and Intelligence Engineering School of Management and EngineeringNanjing UniversityNanjing 210093China the Department of Power Engineering and Process Machinery School of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237China IEEE

Goal-conditioned reinforcement learning(RL)is an interesting extension of the traditional RL framework,where the dynamic environment and reward sparsity can cause conventional learning algorithms to *** shaping is a practical approach to improving sample efficiency by embedding human domain knowledge into the learning *** reward shaping methods for goal-conditioned RL are typically built on distance metrics with a linear and isotropic distribution,which may fail to provide sufficient information about the ever-changing environment with high *** paper proposes a novel magnetic field-based reward shaping(MFRS)method for goal-conditioned RL tasks with dynamic target and *** by the physical properties of magnets,we consider the target and obstacles as permanent magnets and establish the reward function according to the intensity values of the magnetic field generated by these *** nonlinear and anisotropic distribution of the magnetic field intensity can provide more accessible and conducive information about the optimization landscape,thus introducing a more sophisticated magnetic reward compared to the distance-based ***,we transform our magnetic reward to the form of potential-based reward shaping by learning a secondary potential function concurrently to ensure the optimal policy invariance of our *** results in both simulated and real-world robotic manipulation tasks demonstrate that MFRS outperforms relevant existing methods and effectively improves the sample efficiency of RL algorithms in goal-conditioned tasks with various dynamics of the target and obstacles.

关键词： Dynamic environments goal-conditioned reinforcement learning magnetic field reward shaping

来源：评论

学校读者我要写书评

暂无评论

Toward a rapid and convenient nanoplastic quantification method in laboratory-scale study based on fluorescence intensity

引用

Frontiers of Environmental Science & engineering 2024年第5期18卷 117-126页

作者： Ruiqi Yan Sen Lin Qian Ding Lei Zhang Xia Yu Wentao Zhao Qian Sui State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process School of Resources and Environmental EngineeringEast China University of Science and TechnologyShanghai200237China State Key Laboratory of Pollution Control and Resource Reuse College of Environmental Science and EngineeringTongji UniversityShanghai200092China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092China

The thorough investigation of nanoplastics(NPs)in aqueous environments requires efficient and expeditious quantitative analytical methods that are sensitive to environmentally relevant NP concentrations and convenient to *** analysis-based quantitative methods have been acknowledged as effective and rapid approaches for quantifying NP concentrations in laboratory-scale ***,we compared three commonly used optical response indicators,namely fluorescence intensity(FI),ultraviolet absorbance,and turbidity,to assess their performance in quantifying ***,orthogonal experiments were conducted to evaluate the influence of various water quality parameters on the preferred indicator-based quantification *** results revealed that FI exhibits the highest correlation coefficient(>0.99)with NP ***,the limit of quantification(LOQ)for various types of NPs is exceptionally low,ranging from 0.0089 to 0.0584 mg/L in ultrapure water,well below environmentally relevant *** variations in water quality parameters such as pH,salinity,suspended solids(SS),and humic acid,a robust relationship between detectable FI and NP concentration was ***,an increased matrix,especially SS in water samples,results in an enhanced LOQ for ***,the quantitative method remains applicable in real water bodies,especially in drinking water,with NP LOQ as low as 0.0157–0.0711 mg/*** exceeds the previously reported detectable concentration for 100 nm NPs at 40µg/mL using surface-enhanced Raman *** study confirms the potential of FI as a reliable indicator for the rapid quantification of NPs in aqueous environments,offering substantial advantages in terms of both convenience and cost-effectiveness.

关键词： Nanoplastic quantification Fluorescence intensity Drinking water Limit of quantification(LOQ) Matrix effects

来源：评论

学校读者我要写书评

暂无评论

Fused attention mechanisms-based facial expression recognition

Fused attention mechanisms-based facial expression recogniti...

引用

2024 International Conference on Electronics, Electrical and Information engineering, ICEEIE 2024

作者： Xia, Wenxuan Process Equipment and Control Engineering East China University of Science and Technology Shanghai200000 China

ISBN: (数字)9781510686809

ISBN: (纸本)9781510686793

In recent years, the utilization of Facial Expression Recognition (FER) has gained significant traction across diverse domains including healthcare, marketing, and human-computer interface. This trend has prompted a gradual shift towards the adoption of deep learning methodologies for facial expression recognition. The paper highlights the importance of FER systems in comprehending human communication, detailing traditional methods and recent advancements in the field. It proposes a new framework integrating attention mechanisms into the VGGNet model for FER, utilizing the FER-2013 dataset for evaluation. Data augmentation techniques are employed to enhance model robustness, and attention mechanisms are integrated into the VGGNet-SE model. Through Comparative experiments, it is shown that the model of VGGNet-SE-last which adds attention mechanisms after the last convolutional layer of VGG16 achieves the most significant improvement in accuracy and reduction in Top 5 error, particularly with a ratio of 16 in SENet. Experimental results indicate that after incorporating attention mechanisms, the model can more accurately focus on important regions related to emotions in the images, leading to improved performance in recognizing facial expressions. In the future, further research on FER will be implemented by suggesting further optimizations in model architecture and exploration of more complex datasets for future research in FER. © 2024 SPIE.

关键词： Facial recognition systems Data modeling Performance modeling Education and training Feature extraction Machine learning Emotion Deep learning Image classification Network architectures

来源：评论

学校读者我要写书评

暂无评论

UAV longitudinal autopilot design using SLC and TECS controllers

引用

CEAS Aeronautical Journal 2024年第2期15卷 351-362页

作者： Ghelem, Nourddine Boudana, Djamel Bouchhida, Ouahid Laboratory of Process Control LCP Department of Engineering Control Systems and Applied Mathematics National Polytechnic School ENP of Algiers 10 St Hacen Badi El Harrach Algiers Algeria Department of Electrical Engineering LREA Laboratory University of Medea Medea Algeria

UAVs are becoming increasingly prevalent in a wide range of fields, including surveillance, photography, agriculture, transportation, and communications. Hence, research institutions have developed a range of linear and non-linear controllers that can enhance the stability and efficiency of these UAVs while performing their assigned tasks. In this paper, we present a longitudinal autopilot design for the Sky Sailor solar UAV using two different control techniques. The first technique is a classic controller known as SLC (Successive Loop Closure), which is based on consecutive closed loops using a PID controller. The second technique is the TECS (Total Energy control System) controller, which uses the specified total energy rate and energy distribution rate to regulate the airspeed and altitude of the UAV. After detailing the working principle of each controller and calculating the tuning parameters for each one, we applied the two techniques to the non-linear model that describes the behavior of the Sky Sailor UAV using MATLAB Simulink. The simulation results showed that the TECS controller is superior to the SLC controller in terms of stability and energy efficiency. As such, this technique is an excellent choice for solar drones, as it can increase their endurance. © Deutsches Zentrum für Luft- und Raumfahrt e.V. 2024.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning for optimal tracking of large-scale systems with multitime scales

引用

Science China(Information Sciences) 2023年第7期66卷 5-29页

作者： Jinna LI Hao NIE Tianyou CHAI Frank L.LEWIS School of Information and Control Engineering Liaoning Petrochemical University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University UTA Research Institute University of Texas at Arlington

This paper aims to solve an optimal tracking control(OTC) problem of large-scale systems with multitime scales and coupled subsystems using singular perturbation(SP) theory and reinforcement learning(RL) techniques. A considerable contribution of this paper is the development of a data-driven SP-based RL method for the OTC of unknown large-scale systems with multitime scales. To achieve this, a multitime scale tracking problem was decomposed into a linear quadratic tracker problem for slow subsystems and a dynamical game problem for fast subsystems using the SP theory. Then, the distributed composite feedback controllers were found using a distributed off-policy integral RL algorithm that uses only measured data from the system in real time. Thus, the operational index can follow its prescribed target value via an approximately optimal approach. Theoretical analysis and proof are presented to demonstrate that the sum of the performances of reduced-order subsystems is approximately equal to the performance of the original large-scale system. Finally, numerical and practical examples are provided to validate the effectiveness of the proposed method.

关键词： reinforcement learning singular perturbation multitime scales data-driven control

来源：评论

学校读者我要写书评

暂无评论

Operation Strategies for modular large-scale alkaline electrolysis systems 22

Operation Strategies for modular large-scale alkaline electr...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Lange, Hannes Schirmer, Christioph Mock, Michael Viedt, Isabell Klose, Anselm Urbas, Leon Process Systems Engineering Group TUD Dresden University of Technology Dresden Germany Process Control Systems TUD Dresden University of Technology Dresden Germany

ISBN: (纸本)9798331527471

In this paper we compare different operation strategies for alkaline electrolyzis (AEL) systems using numeric simulation. We derived general models for mass and energy balances from literature and composed them into a model for an AEL system. Here we considered a numbered-up plant topology, containing multiple AEL stacks with single electrolyte distribution and gas separation systems. The gas impurities and achievable minimal load distribution were compared for the different operating strategies. The results were discussed and further conclusions for the operation of a homogeneous numbered-up AEL system were derived. © 2024 IEEE.

关键词： Electrolysis

来源：评论

学校读者我要写书评

暂无评论

A Prototype for Navigation in Signed Directed Graphs of Chemical processes 28

A Prototype for Navigation in Signed Directed Graphs of Chem...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Hamedi, Nazanin Richter, Julia Schrank, Bernhard Lischinski, Eric Chen, Jiaxin Sun, Xiaoyu Klose, Anselm Urbas, Leon TU Dresden DFG RTG Conducive Design of Cyber Physical Systems Dresden Germany TU Dresden Process Control Systems Dresden Germany TU Dresden Process Control Systems Process-to-Order Lab Dresden Germany TU Dresden Process Control Systems & Process Systems Engineering Dresden Germany

ISBN: (纸本)9798350339918

Signed Directed Graphs (SDGs) are among the very beneficial, and well-known tools for fault diagnosis in chemical process plants. Based on the size of the process plant, their corresponding SDGs can be very large in size;and therefore, significantly difficult to navigate. Besides that, the recent advancement in semantic description of process structures and intelligent process and Instrumentation Diagrams (P&IDs), has led to the development of several computer tools for navigating in a process plant structure and examining the connectivity of different process equipment to each other. In this study a prototype for an intelligent P&ID, in which the SDG is considered to help the user understand the influence of process parameters on each other is developed. Requirements were derived and implemented as a click prototype, using Axure RP. The evaluation results indicate that despite the high understandability of the prototype, the cognitive efforts for linking the information derived from the SDG with the plant's P&ID scheme are still too high for achieving a good overall usability. © 2023 IEEE.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

High concentration of Ti^(3+)in C-TiO_(x)nanosheets boosting efficient photodegradation

引用

Science China(Technological Sciences) 2025年第3期68卷 156-166页

作者： Chongbei WU Xuan LI Haibin WANG Jiaxin TANG Shuai WEI Yuanyuan WU Aobing WANG Jizhou JIANG Hebei Key Laboratory of Man-machine Environmental Thermal Control Technology and Equipment Hebei Vocational University of Technology and EngineeringXingtai054000China School of Materials Science and Engineering Key Laboratory of Green Chemical Engineering Process of Ministry of EducationEngineering Research Center of Phosphorus Resources Development and Utilization of Ministry of EducationWuhan Institute of TechnologyWuhan430205China

Semiconductor photocatalysis holds significant promise for addressing dye-pollution in ***,the efficiency of photocatalytic water purification is constrained by the weak light absorption capacity and low active site distribution of *** a bottom-up approach,carbon-doped TiO_(x)(C-TiO_(x))nanosheets with high concentrations of Ti^(3+)active sites were fabricated by etching the Al element in Ti_(3)Ai C_(2)with H_(2)O_(2).Experimental evidence demonstrates that the optimal C-TiO_(x)nanosheets exhibit high activity for the photocatalytic degradation of methylene blue,achieving a degradation rate of 100%within 50 *** introduction of carbon into the C-TiO_(x)nanosheets induces a red shift in the absorption edge,boosting the migration of photo-generated charge ***,there is a significant correlation between the concentration of Ti^(3+)active sites and the density of oxygen vacancies in the C-TiO_(x)nanosheets,which synergistically influence the photocatalytic degradation performance of MB dye wastewater.

关键词： bottom-up strategies C-TiO_(x)nanosheets high-concentrations Ti^(3+) photocatalytic degradation

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：