检索结果-内蒙古大学图书馆

56th International Symposium on Robotics, ISR Europe 2023

作者： Pham, Huy Xuan Heiß, Micha Tran, Dung Nguyen, Minh Anh Nguyen, Anh Quang Kayacan, Erdal Department of Electrical and Computer Engineering Aarhus University Aarhus C8000 Denmark Hanoi Viet Nam Automatic Control Group Department of Electrical Engineering and Information Technology Paderborn University Paderborn Germany

ISBN: (纸本)9783800761418

Deep learning-based methods have enhanced the performance of many robot applications thanks to their superior ability to robustly extract rich high-dimensional features. However, it comes with a high computational cost that often increases the latency of the overall system. On the other hand, traditional feature extraction methods, such as oriented FAST and rotated BRIEF (ORB), can be computed efficiently and remains the backbone of some critical robot algorithms, e.g. ORB-SLAM for robot state estimation. In this work, the usefulness of the aforementioned features for a robot navigation task is investigated. The features are experimentally incorporated with a deep-learning method, called ORB-Net1, which allows an agile aerial robot to learn a motion policy to complete a racing track in an autonomous drone racing context. The experimental studies demonstrate that it can be beneficial to reuse these computed features for end-to-end motion planning for the agile quadrotor, as the proposed method using combined input of ORB feature position and RGB images outperforms the baseline methods which use only RGB images. © VDE VERLAG GMBH Berlin Offenbach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer Fault Detection Using DGA Based on Three Ratio Technique and Random Forest Algorithm 16

Transformer Fault Detection Using DGA Based on Three Ratio T...

引用

16th International Conference on Applied and Theoretical Electricity, ICATE 2024

作者： Nitu, Maria-Cristina Aciu, Ancuta-Mihaela Nicola, Marcel Nicola, Claudiu-Ionel National Institute for Research Development and Testing in Electrical Engineering-ICMET Craiova Research and Development Department Craiova Romania National Institute for Research Development and Testing in Electrical Engineering-ICMET Craiova Department of Automatic Control and Electronics University of Craiova Craiova Romania

ISBN: (纸本)9798350388107

Power transformers are essential elements in the production and distribution of electricity, and keeping them in optimum operating condition is a constant concern for specialists in the field. The condition of power transformers is mainly determined by the condition of the mixed insulation system, i.e. solid cellulose paper insulation and liquid insulating oil insulation. This is why the Three Ratio Technique (TRT) is used with good results for the early detection of power transformer faults. In this paper, the ratios defined by the TRT method are used to train a machine learning classifier based on ensemble and random forest algorithms. The validation of the power transformer fault identification software application for the proposed method is carried out in the experimental section. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for Time Series Forecasting Using NARMAX-LSTM 27

Multi-Task Learning for Time Series Forecasting Using NARMAX...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Nikentari, Nerfita Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Traditional time series forecasting models based on neural networks are usually designed for a single task, which ignores the source of knowledge or information from other related tasks. On the other hand, multitask learning (MTL) offers a new perspective where one model is not only for one forecasting case or task but several tasks at the same time. The MTL model proposed in this study is based on the Nonlinear AutoRegressive Moving Average with eXogenous input (NARMAX) model and Long-Short Term Memory (LSTM) Neural Networks. The NARMAX-LSTM model is tested and validated using three different time horizons and different cases/tasks. The model forecasting performance is compared with that of three other linear and nonlinear models. The comparison results show that the multi-task NARMAX-LSTM model does not only have better prediction performance but also avoid suffering from negative transfer and overfitting. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Higher-order properties and extensions for indirect MRAC and APPC of linear systems

引用

Science China(Information Sciences) 2024年第4期67卷 218-238页

作者： Yanjun ZHANG Zhipeng ZHANG Jian SUN Lei WANG Kangkang ZHANG National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology School of Automation Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center College of Control Science and Engineering Zhejiang University Department of Electrical and Electronic Engineering Imperial College London KIOS Research and Innovation Center of Excellence University of Cyprus

Recently, a reference derived some new higher-order output tracking properties for direct model reference adaptive control（MRAC） of linear time-invariant（LTI） systems: limt→∞ e（i）（t） = 0, i = 1,..., n*-1, where n*and e（i）（t） denote the relative degree of the system and the i-th derivative of the output tracking error, respectively. However, a naturally arising question involves whether indirect adaptive control（including indirect MRAC and indirect adaptive pole placement control） of LTI systems still has higher-order tracking properties. Such properties have not been reported in the literature. Therefore, this paper provides an affirmative answer to this question. Such higher-order tracking properties are new discoveries since they hold without any additional design conditions and, in particular, without the persistent excitation condition. Given the higher-order properties, a new adaptive control system is developed with stronger tracking features.（1） It can track a reference signal with any order derivatives being unknown.（2） It has higher-order exponential or practical output tracking properties.（3） Finally, it is different from the usual MRAC system, whose reference signal's derivatives up to the n*order are assumed to be known. Finally, two simulation examples are provided to verify the theoretical results obtained in this paper.

关键词： higher-order tracking indirect adaptive control model reference adaptive control adaptive pole placement control

来源：评论

学校读者我要写书评

暂无评论

Computing the explicit MPC solution in the constrained zonotope case 63

Computing the explicit MPC solution in the constrained zonot...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Stoican, Florin Mihai, Stefan S. Monnigmann, Martin Ciubotaru, Bogdan D. University 'Politehnica' of Bucharest Department of Automatic Control and Systems Engineering 313 Splaiul Independenţei Sector 6 Bucharest060042 Romania Ruhr University Bochum Martin Mönnigmann Is with Automatic Control and System Theory Bochum44801 Germany

ISBN: (纸本)9798350316339

Solving the explicit model predictive control (MPC) problem entails enumerating a list of critical regions and their ancillary feedback laws. Unfortunately, their number and the time required to compute them increase exponentially with the problem size (state-space model dimension and length of the prediction horizon). We show that when, as it is often the case, the problem's constraints take the form of boxes or zonotopes, the resulting feasible domain can be compactly described as a constrained zonotope. Subsequently, we investigate whether, and under which circumstances, the combinatorial structure of the constrained zonotope interpretation accelerates the computation of the explicit solution. © 2024 IEEE.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Optimal Tuning of FOPID-Like Fuzzy controller for High-Performance Fractional-Order systems

引用

Computers, Materials & Continua 2022年第1期70卷 171-180页

作者： Ahmed M.Nassef Hegazy Rezk College of Engineering at Wadi Addawaser Prince Sattam Bin Abdulaziz UniversityAl-Kharj11911Saudi Arabia Department of Computers and Automatic Control Engineering Faculty of EngineeringTanta UniversityTanta31733Egypt Department of Electrical Engineering Faculty of EngineeringMinia UniversityMinia61517Egypt

This paper addresses improvements in fractional order(FO)system *** the classical proportional-integral-derivative(PID)-like fuzzy controller can provide adequate results for both transient and steady-state responses in both linear and nonlinear systems,the FOPID fuzzy controller has been proven to provide better *** high performance was obtained thanks to the combinative benefits of FO and fuzzy-logic *** paper describes how the optimal gains and FO parameters of the FOPID controller were obtained by the use of a modern optimizer,social spider optimization,in order to improve the response of fractional dynamical *** group of systems had usually produced multimodal error surfaces/functions that occasionally had many variant local *** integral time of absolute error(ITAE)used in this study was the error *** results showed that the strategy adopted produced superior performance regarding the lowest ITAE *** reached a value of 88.22 while the best value obtained in previous work was 98.87.A further comparison between the current work and previous studies concerning transient-analysis factors of the model’s response showed that the strategy proposed was the only one that was able to produce fast rise time,low-percentage overshoot,and very small steady-state ***,the other strategies were good for one factor,but not for the others.

关键词： Fuzzy-logic control fractional-order systems parameter estimation optimization

来源：评论

学校读者我要写书评

暂无评论

Output Tracking for Uncertain Time-Delay systems via Robust Reinforcement Learning control

Output Tracking for Uncertain Time-Delay Systems via Robust ...

引用

第43届中国控制会议

作者： Zezhi Tang J Anthony Rossiter Xin Jin Benyuan Zhang George Panoutsos Department of Automatic Control and Systems Engineering University of Sheffield

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The composite optimal output tracking control problem of time-delay uncertain systems is investigated in this paper. To improve the robustness of the uncertain systems, a disturbance observer-based(DOB) compensation scheme is proposed to reduce the influence of the *** further enhance the control efficiency, we incorporate a Smith predictor into the control framework to precisely predict future states of the delayed system. Subsequently, a composite actor-critic reinforcement learning(RL) scheme is built for approximating both the ideal value function associated with the compensated system and the optimal control policy in real-time, by augmenting the system states with the output tracking error. To counteract the impact of the probing signal, concurrent learning is employed in this paper with the data collected from the known system *** results based on an experimental platform of slot die coating machines demonstrate the effectiveness of the proposed scheme.

关键词： Smith Output Tracking for Uncertain Time-Delay systems via Robust Reinforcement Learning control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Vertical Transport Safety Through an IoT-Based System 5

Enhancing Vertical Transport Safety Through an IoT-Based Sys...

引用

5th International Conference on Emerging systems and Intelligent Computing, ESIC 2025

作者： Kumar, Swetha R. Aditi, S. Poovisha, S. Vellore Institute of Technology School of Electrical Engineering Tamil Nadu Chennai India Psg College of Technology Department of Instrumentation and Control Systems Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798331522100

Vertical transportation systems, such as elevators and escalators, are essential components of modern infrastructure, necessitating robust safety mechanisms to ensure user well-being. This paper proposes an Internet of Things (IoT)-based system to enhance the safety, monitoring, and efficiency of vertical transport. The system addresses critical issues, such as sudden elevator cable failures leading to entrapment or uncontrolled descent, power losses during operation, and fire hazards caused by material friction. By leveraging IoT technology, the system enables real-time monitoring and immediate notification of potential problems via messaging. The implementation requires components such as ultrasonic sensors, smoke sensors, vibration sensors, microcontrollers, DC motors, batteries, relays, and the UBIDOT application. The resulting system is low-cost, user-friendly, and economically viable, making it accessible to individuals with minimal technical expertise. Furthermore, it is designed for ease of construction and troubleshooting, offering a practical and scalable solution to improve elevator safety and reliability. © 2025 IEEE.

关键词： Fire hazards

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Calibration Approaches for Single-Beam and Multiple-Beam Distance Sensors

引用

IEEE Sensors Journal 2024年第1期24卷 975-983页

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Biernacki, Piotr Ziebinski, Adam National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice44-100 Poland Silesian University of Technology Department of Distributed Systems and Informatic Devices Gliwice44-100 Poland

Sensors are the foundation to facilitate smart cities, smart grids, and smart transportation, and distance sensors are especially important for sensing the environment and gathering information. Researchers have developed various methods to calibrate distance sensors;however, they mainly focus on using external information for calibration, which is inefficient and computationally expensive. To alleviate the above problems, we propose machine learning (ML)-based calibration approaches for distance sensors. We develop two calibration mechanisms, where the naive mechanism directly predicts the true distance, while the residual mechanism predicts the residual for calibration. The conventional ML regression algorithms are then adopted to predict the true distance or calibration residual. Experimental results show that the designed residual calibration mechanism outperforms the naive mechanism by reducing the root mean square error (RMSE) by 92.2% and mean absolute error (MAE) by 93.3% in the fitting task. In prediction, the proposed 2-D-residual mechanism achieves an improvement of 78.6% and 65.7% compared to the state-of-the-art method. The experimental results show the effectiveness and generalization of the proposed ML-based calibration method, especially for the 2-D mechanism, which achieves the highest robustness in all fitting and prediction tasks. © 2001-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Tide Level Prediction Using NARX-based Recurrent Neural Networks 27

Tide Level Prediction Using NARX-based Recurrent Neural Netw...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Nikentari, Nerfita Wei, Hua-Liang University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Tide level forecasting is one of major components in oceanography and marine research. The future prediction of tides is an important issue for human and environment. This study proposes new tide level prediction methods with multiple input multiple output (MIMO) approach based on nonlinear autoregressive with exogenous inputs (NARX) model and three types of recurrent neural networks (RNNs), namely, long short-term memory (LSTM), bi-directional long short-term memory (biLSTM) and gated recurrent unit (GRU) networks. We develop three types of NARX models: NARX-LSTM, NARX-biLSTM and NARX-GRU. We evaluate the three models and compare their performances with LSTM, biLSTM and GRU network models. It turns out that the proposed MIMO NARX based RNN models, especially NARX-LSTM and NARX-GRU have better performance in comparison with their RNN counterparts (i.e., LSTM, biLSTM, and GRU). The NARX-GRU model shows the best performance for one step and three step ahead prediction in terms of RMSE in each location and average RMSE, while NARX-LSTM performs better for two steps ahead prediction in terms average RMSE. The results also show that the mixture of RNN and NARX improves the performance of RNN model for all the four tasks at four locations in the UK (Wick, Workington, Ullapol and New Heaven) and for the three time horizons (i.e., 1, 2 and 3 steps ahead). © 2022 IEEE.

关键词： Forecasting

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：