检索结果-内蒙古大学图书馆

Performance Comparison of Lightweight CNN Models for Drone Collision Avoidance Dataset 20

Performance Comparison of Lightweight CNN Models for Drone C...

20th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Zufar, Rifqi Nabila Banjerdpongchai, David Chulalongkorn University Center of Excellence in Intelligent Control Automation of Process Systems Department of Electrical Engineering Faculty of Engineering 254 Phayathai Road Bangkok Pathumwan10330 Thailand

ISBN: (纸本)9798350310467

Collision Avoidance System (CAS) is important for drone safety. CAS consists of three steps e.g., obstacle sensing, collision prediction, and collision avoidance. Collision prediction enables drones to gain information, process information, and estimate whether the object has a risk of collision. Convolution Neural Network (CNN) is one of the methods that can be employed for collision prediction. However, CNN is a method that needs a large data in the training. Dario Pedro et al. provided a dataset called the CoLANet dataset that consists of VDOs of collision drones. Subsequently, they proposed a new algorithm called Neural Network Pipeline which has a Convolution Neural Network (CNN) part to extract the feature from a couple of images. CNN extracts images by using MobileNetV2 as a pre-trained model. They chose MobileNetV2 due to training performance from another dataset. This paper aims to assess the performance of lightweight CNN models using the CoLANet dataset. The models will be trained on the Keras library with parameters of fewer than ten million. The models will be validated by Confusion Matrix and Receiver Operating Characteristics. In conclusion, we examine which pre-trained CNN model has the best performance and suggest ongoing work. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Impulsive controller Design for Positive Interval Type-2 Polynomial Fuzzy Systems with Input Saturation 13

Stability Analysis and Impulsive Controller Design for Posit...

引用

13th IEEE International Conference on CYBER Technology in automation, control, and Intelligent Systems, CYBER 2023

作者： Han, Meng Huang, Yongjie Guo, Ge Wang, Zhengsong School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

ISBN: (纸本)9798350315196

This paper designs an impulsive controller for nonlinear positive systems with uncertain parameters and input saturation constraints. To address the issue of modeling errors caused by parameter uncertainties, system modeling is done using an interval type-2 (IT2) polynomial fuzzy model. Also, a premise mismatched controller design strategy is employed to improve controller design flexibility. In addition, to attenuate the conservatism of the analytical results, a novel impulse-time-dependent discretized polynomial copositive Lyapunov function (IDDPCLF) is employed, and the obtained non-convex resultant conditions are handled by the proposed convexification method. Finally, the usefulness of the impulsive controller design approach and the convexification method are verified through an example. © 2023 IEEE.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Optimal Dispatch of Cogeneration with Thermal and Battery Energy Storage for BEMS Subject to Load Demand Uncertainty 19

Optimal Dispatch of Cogeneration with Thermal and Battery En...

引用

19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Trairat, Parichada Banjerdpongchai, David Chulalonkorn University Intelligent Control Automation of Process Systems Research Unit Dept of Electrical Engineering Bangkok10330 Thailand

ISBN: (纸本)9781665485845

This paper presents optimal dispatch of cogeneration with thermal energy storage (TES) and battery energy storage (BES) for Building Energy Management System (BEMS) subject to load demand uncertainty. The energy supply of BEMS consists of combined heat and power (CHP), an auxiliary boiler, an absorption chiller, battery energy storage (BES), spinning reserve (SR) and power grids. Previous research related to CHP for BEMS provides optimal operation to minimize total operating cost (TOC), but their operation has only CHP and TES for supply the electrical energy. In this paper, we propose to add BES and SR which aims to supply the electrical energy in the building subject to load demand uncertainty. The load demand uncertainty arises from the difference between the forecasted load demand and the actual load demand. We apply artificial neural network (ANN) to analyze the load demand uncertainty. BES and SR are utilized to tackle the load uncertainty. Then, we design economic optimal operationwith TOC as the objective function. We apply the proposed BEMS with a large shopping mall to demonstrate improvements in energy efficiency. The numerical results manifest that the proposed dispatch can reduce 12.52% of TOC compared to the previous BEMS without BES and SR. © 2022 IEEE.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Towards High-Integrity Redundancy Role Leasing

Towards High-Integrity Redundancy Role Leasing

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Bjarne Johansson Olof Holmgren Håkan Forsberg Thomas Nolte Alessandro V. Papadopoulos ABB Process Automation Process Control Platform Västerås Sweden Mälardalen University Västerås Sweden

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

control systems are often an integral part of automation solutions where high reliability is crucial due to the high cost of downtime. The risk of unplanned downtime is typically reduced with redundant solutions. Additionally, safety-critical automation functions require high-integrity controllers. Today, the prevalent redundancy solution is a standby scheme, where one active primary controller drives the process while a standby backup controller is ready to take over in case of primary failure. This redundant controller pair can consist of high - integrity controllers. The automation industry is trending towards Ethernet as the sole communication medium. Our work presents an initial study of a high-integrity realization of a redundancy failure detection mechanism that guarantees only one primary controller, even in the case of network partitioning between the redundant controller pair. The failure detection is a lease-based function that leases the primary role from a central lease broker. This work discusses a high-integrity realization of the primary redundancy role leasing. We deduce and present the high-integrity-related requirements and a high-level design as an initial step towards a high-integrity realization of the redundancy role leasing.

关键词： Industries Costs Redundancy process control Ethernet control systems Reliability Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Redundancy Link Security Analysis: An automation Industry Perspective

Redundancy Link Security Analysis: An Automation Industry Pe...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Björn Leander Bjarne Johansson Saad Mubeen Mohammad Ashjaei Tomas Lindström ABB Process Automation Process Control Platform Västerås Sweden Mälardalen University Västerås Sweden

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Industrial automation and control systems are responsible for running our most important infrastructures, providing electricity and clean water, producing medicine and food, along with many other services and products we take for granted. The safe and secure operation of these systems is therefore of great importance. Reliability is a fundamental requirement, with spatial controller redundancy being one important fault-tolerance mechanism. In current control system solutions, controller redundancy is implemented using state and heartbeat transfer communicated over dedicated physical links, based on an assumption of implicit trust. However, with the emerging network-centric control strategies there is a desire to transition into dynamic redundancy scenarios, where such dedicated links are unfeasible. In this paper, an approach for a threat-model based security analysis is presented from the perspective of the automation industry. The approach is applied to the communication links used for supporting control system redundancy within a network-centric architecture.

关键词： Industries Threat modeling Protocols Prevention and mitigation Redundancy Switches control systems Security Time factors Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Command Filtered Finite/Fixed-time Heading Tracking control of Surface Vehicles

引用

IEEE/CAA Journal of Automatica Sinica 2021年第10期8卷 1667-1676页

作者： Zhenyu Gao Ge Guo School of Control Engineering Northeastern University QinhuangdaoQinhuangdao 066004China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819

This paper investigates the heading tracking problem of surface vehicles with unknown model *** on finite/fixed-time control theories and in the context of command filtered control,two novel adaptive control laws are developed by which the vehicle can track the desired heading within settling time with all signals of the closed-loop system are uniformly *** effectiveness and performance of the schemes are demonstrated by simulations and comparison studies.

关键词： Command filter finite-time control fixed-time control heading tracking control surface vehicles

来源：评论

学校读者我要写书评

暂无评论

Causal-Transformer: Spatial-temporal causal attention-based transformer for time series prediction

引用

IFAC-PapersOnLine 2024年第14期58卷 79-84页

作者： Yaqi Zhu Fan Yang Andrei Torgashov Department of Automation Beijing National Research Center for Information Science and Technology Tsinghua University Beijing 100084 China Process Control Laboratory Institute of Automation and Control Processes Far-Eastern Branch Russian Academy of Sciences Vladivostok 690041 Russia

Real-time monitoring and accurate prediction of key variables are indispensable to ensure industrial production activities proceed as expected. With the increase in measurement data volume and the improvement of hardware computing power, the Transformer and its variants, due to their excellent capability in extracting global dependencies, are playing an increasingly important role among deep learning-based multidimensional time series prediction models. In addition, from the perspective of causality, cause variables contain parts of information in effect variables and can reduce the uncertainty of effect variables, which is beneficial for prediction. However, there has been relatively limited research on combining the Transformer and causal feature analysis. To fully use both advantages, this paper introduces the Causal-Transformer (CT) model, which utilizes semi-orthogonal projection to extract causal features from multiple input variables. A multi-head spatial-temporal causal attention mechanism is designed in the encoder block based on the classical Transformer model to simultaneously reduce feature dimensions and extract implicit causal features in both the temporal and spatial dimensions. The CT also utilizes the Granger causality analysis to select the causal teaching indicators of target variables to provide stable assistance by injecting explicit causality into the inputs of the decoder block. By leveraging more condensed and independent causal features, the CT possesses inherent advantages in predicting time series variables. Case study results show that the CT model outperforms the other models on the diesel refinery dataset, especially with a reduction of 46.0% and 30.4% in MSE towards the classic Transformer and informer in five-step prediction.

关键词： Machine learning Time series modelling Transformer Causal analysis Attention machenism

来源：评论

学校读者我要写书评

暂无评论

State Estimator for Linear High-Dimensional Systems With State Partition and Block-Dependent Compensation

State Estimator for Linear High-Dimensional Systems With Sta...

引用

第35届中国过程控制会议

作者： Ke Li Shunyi Zhao Fei Liu Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Institute of Automation Jiangnan University

This paper proposes a Bayesian estimation scheme with block-dependent compensation for linear high-dimensional systems. The state vector is divided into blocks by considering the relationship of state variables in time series and physical interpretation to reduce the underlying computational cost. However, blocking states damages the original system and introduces systematic errors. Consequently, the divided state blocks are compensated by introducing distinct compensation coefficients to improve state estimation accuracy. Considering the difference and uniqueness of state blocks, the distinct compensation coefficients are adaptively adjusted and updated over time to ensure higher accuracy of state estimation. Simulation results of numerical example are used to evaluate the performance of the proposed algorithm. It shows that the proposed algorithm possesses moderate computational cost and higher estimation accuracy compared with the existing methods.

关键词： State estimation Bayesian inference Block-dependent compensation Linear high-dimensional systems

来源：评论

学校读者我要写书评

暂无评论

Phase Fraction Estimation Using Measured Dilation, a Lattice Parameter Model, and a Curve-Fitting Method

引用

IFAC-PapersOnLine 2024年第22期58卷 48-53页

作者： Solveig Sannes Lukas Jadachowski Martin Niederer Andreas Kugi Andreas Steinboeck Christian Doppler Laboratory for Intelligent Process Control for High-Quality Steel Products Automation and Control Institute TU Wien Austria AIT Austrian Institute of Technology GmbH Vienna Austria

Dilatometry is a measurement frequently used to analyze phase transformations in steels during austenite decomposition. Such analyses are essential for the design of heat treatments and for determining the final phase fractions. This paper presents a simple and systematic method to estimate the evolution of the non-measurable phase fraction of ferrite, pearlite, bainite, and martensite during Continuous Cooling Transformation (CCT) experiments. The optimization-based method uses the measured dilation curve, a lattice parameter model, and a semi-empirical curve-fitting method. The latter assumes specific shapes of the transformation rates. The proposed approach can reconstruct the dilation curve and estimate the phase fractions with high accuracy.

关键词： Dilatometry austenite decomposition lattice parameter phase trajectory estimation curve-fitting method optimization-based parametrization

来源：评论

学校读者我要写书评

暂无评论

Electrical Scheme Digitization Using Deep Learning Methods

Electrical Scheme Digitization Using Deep Learning Methods

引用

Proceedings of the International Convention MIPRO

作者： Marko Putak Vatroslav Zuppa Bakša Andrea Bednjanec Zagreb University of Applied Sciences/Automation and Process Control Engineering Zagreb Croatia

The use of software tools and applications progressively became a standard in both education and industry. A solution for hand-drawn electrical scheme digitization has been proposed to match the fast-paced dynamic of the modern world in the field of electrical engineering. The aim is to notably reduce time-consuming and error-prone electrical scheme tracing from hand-drawn to simulating software. The means have been achieved through the usage of state-of-the-art deep learning model YOLOv5 for electrical elements detection along with Python and OpenCV library for data processing. The user’s input is an image of a hand-drawn circuit, and the end result is an LTspice digitized electrical scheme ready for simulation.

关键词：

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：