检索结果-内蒙古大学图书馆

ieee symposium Series on computational intelligence (SSCI)

作者： Chen, Canhui Ling, Yihong Zhang, Deyang Shi, Nini Zhang, Yunong Sun Yat Sen Univ SYSU Sch Data & Comp Sci Guangzhou 510006 Peoples R China Sun Yat Sen Univ Shenzhen Res Inst Shenzhen 518057 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China

ISBN: (纸本)9781728124858

This paper handles the noise-free or noisy synchronization control of Genesio chaotic (GC) system. To do so, Zhang dynamics (ZD) method is presented and exploited, and thus the ZD controllers, noise-free or noisy, are theoretically researched. Firstly, the presented ZD controller for GC system synchronization with no noise perturbation is analyzed, and the synchronization error as a whole (i.e., in the form of vector norm) between the drive GC system and the response GC system converges globally exponentially to zero. Secondly, the presented ZD controller for GC system synchronization with noise perturbation is analyzed as well, and detailed theoretical analyses (i.e., proofs) and results show that the synchronization error as a whole (i.e., in the form of vector norm) converges globally to a small bound of error. So, the ZD controllers provided in this paper (including the ones with unequal parameters) are not only simple and effective but also quite robust for the GC system synchronization.

关键词： noisy Zhang dynamics (ZD) Genesio chaotic (GC) system synchronization analyses unequal parameters

来源：评论

学校读者我要写书评

暂无评论

Parallel Ant Colony Optimization for the Electric Vehicle Routing Problem

Parallel Ant Colony Optimization for the Electric Vehicle Ro...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Mavrovouniotis, Michalis Li, Changhe Ellinas, Georgios Polycarpou, Marios Univ Cyprus KIOS Res & Innovat Ctr Excellence Dept Elect & Comp Engn Nicosia Cyprus China Univ Geosci Sch Automat Wuhan Peoples R China China Univ Geosci Hubei Key Lab Adv Control & Intelligent Automat C Wuhan Peoples R China

ISBN: (纸本)9781728124858

Parallelizing metaheuristics has become a common practice considering the computation power and resources available nowadays. The aim of parallelizing a metaheuristic is either to increase the quality of the generated output, given a fixed computation time, or to reduce the required time in generating an output. In this work, we parallelize one of the best-performing ant colony optimization (ACO) algorithms and apply it to the electric vehicle routing problem (EVRP). EVRP is more challenging than the conventional vehicle routing problem, as with the consideration of electric vehicles additional hard constraints arise within the EVRP due to their limited driving range (e.g., the consideration whether electric vehicles need to visit a charging station during their daily operation). The proposed parallel ACO algorithm with several colonies also uses a migration policy to allow communication between the different colonies. From the simulation studies it is shown that parallelizing ACO algorithms, both with and without a migration policy, is highly effective.

关键词： Ant colony optimization electric vehicle vehicle routing problem

来源：评论

学校读者我要写书评

暂无评论

Parallel Building: A Complex System Approach for Smart Building Energy Management

引用

ieee/CAA Journal of Automatica Sinica 2019年第6期6卷 1452-1461页

作者： Abdulaziz Almalaq Jun Hao Jun Jason Zhang Fei-Yue Wang Department of Electrical Engineering Engineering CollegeUniversity of HailHail 55476Saudi Arabia Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer ScienceUniversity of DenverDenverCO 80208 USA State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 and also with the Research Center for Military Computational Experiments and Parallel Systems TechnologyNational University of Defense TechnologyChangsha 410073China

These days' smart buildings have high intensive information and massive operational parameters, not only extensive power consumption. With the development of computation capability and future 5 G, the ACP theory(i.e., artificial systems,computational experiments, and parallel computing) will play a much more crucial role in modeling and control of complex systems like commercial and academic buildings. The necessity of making accurate predictions of energy consumption out of a large number of operational parameters has become a crucial problem in smart buildings. Previous attempts have been made to seek energy consumption predictions based on historical data in buildings. However, there are still questions about parallel building consumption prediction mechanism using a large number of operational parameters. This article proposes a novel hybrid deep learning prediction approach that utilizes long short-term memory as an encoder and gated recurrent unit as a decoder in conjunction with ACP theory. The proposed approach is tested and validated by real-world dataset, and the results outperformed traditional predictive models compared in this paper.

关键词： ACP theory artificial intelligence data acquisition deep learning(DL) energy consumption machine learning parallel energy prediction prediction algorithms smart grid

来源：评论

学校读者我要写书评

暂无评论

Investigation of Noise-sensitivity of a Fixed Point Iteration-based Adaptive controller for a Pendulum-like Electric Cart 13

Investigation of Noise-sensitivity of a Fixed Point Iteratio...

引用

ieee 13th International symposium on Applied computational intelligence and Informatics (SACI)

作者： Redjimi, Hemza Tar, Jozsef K. Obuda Univ Doctoral Sch Appl Informat & Appl Math Budapest Hungary Obuda Univ Univ Res & Innovat Ctr Antal Bejczy Ctr Intelligent Robot ABC iRob Budapest Hungary

ISBN: (纸本)9781728106854

In this paper the preliminary results obtained for a Fixed Pint Iteration-based adaptive control of a pendulum-like mobile robot are further investigated. The main idea in [1] was the application of a very simple adaptive solution that would be realizable by an embedded controller due to omitting the complicated calculation of the order 3 Lie derivatives occurring in the electro-mechanical dynamic model of the cart. In [1] promising simulation results were obtained but the noise-sensitivity of the relative order 3 control task was not investigated. In the present paper the originally suggested control algorithm is equipped with two different and simple algorithms that were developed for noise reduction in the time domain that can be simply applied in a combined way. Realistic sensor noise data were taken into consideration in the measurement of the tilting angle of the steering arm of the cart observed by rotational encoders. It was found via sequential Julia code-based numerical simulation that the suggested control method can be realized because the incorporated simple noise reduction algorithms can handle the expected noise which originates from the measurement of the rotational angle. The situation can be further improved by replacing the encoders with inertial measurement units (IMU acceleration sensors).

关键词： Adaptive control Fixed Point Iteration Banach Space Noise Filtering Time Domain

来源：评论

学校读者我要写书评

暂无评论

The Effects of Adaptive control on Learning Directed Locomotion

The Effects of Adaptive Control on Learning Directed Locomot...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Fuda van Diggelen Robert Babuska A.E. Eiben Technische Universiteit Delft The Netherlands Vrije Universiteit Amsterdam The Netherlands

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

This study is motivated by evolutionary robot systems where robot bodies and brains evolve simultaneously. In such systems robot `birth' must be followed by `infant learning' by a learning method that works for various morphologies evolution may produce. Here we address the task of directed locomotion in modular robots with controllers based on Central Pattern Generators. We present a bio-inspired adaptive feedback mechanism that uses a forward model and an inverse model that can be learned on-the-fly. We compare two versions (a simple and a sophisticated one) of this concept to a traditional (open-loop) controller using Bayesian optimization as a learning algorithm. The experimental results show that the sophisticated version outperforms the simple one and the traditional controller. It leads to a better performance and more robust controllers that better cope with noise.

关键词： Robots Feedback control Erbium Adaptation models Neurons Morphology Process control

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Spatial Extension of Traffic Sensor Points in Urban Road Network 13

Deep Learning Approach for Spatial Extension of Traffic Sens...

引用

ieee 13th International symposium on Applied computational intelligence and Informatics (SACI)

作者： Piazzi, Arthur Couto Tettamanti, Tamas Budapest Univ Technol & Econ Dept Control Transportat & Vehicle Syst Budapest Hungary

ISBN: (纸本)9781728106854

Real-time monitoring of road traffic variables is essential for any effective control strategy in Intelligent Transportation Systems. Network-wide monitoring has increased importance in the current and future panorama due to the verge of adoption of smart mobility technologies, i.e. monitoring all links in a network is a general desired goal. However, installation and maintenance of sensors across the whole network are not cost-effective. Therefore, traffic networks are frequently suffering from the lack of well-operating and reliable traffic detectors. The paper proposes the employment of neural networks based models to virtualize the measurements on road links without detectors. The proposed method applies the measurements of monitored links as input to the deep learning model in order to estimate virtual measurements on the unmonitored road links. Several neural network models differing in architecture (Artificial Neural Network, Time Lagged Neural Network and Long Short Term Memory Neural Network) have been implemented and their hyper-parameterization were optimized using Bayesian search. The prediction techniques were developed and tested by using microscopic road traffic simulation.

关键词： traffic sensors artificial neural networks LSTM spatial extension

来源：评论

学校读者我要写书评

暂无评论

Design a New Intelligent control for a Class of Nonlinear Systems 6

Design a New Intelligent Control for a Class of Nonlinear Sy...

引用

6th International Conference on control, Instrumentation and automation (ICCIA)

作者： Tavoosi, Jafar Mohammadi, Fazel Ilam Univ Dept Elect Engn Ilam Iran Univ Windsor Elect & Comp Engn ECE Dept Windsor ON N9B 1K3 Canada

ISBN: (纸本)9781728158150

This paper presents a new method based on computational intelligence for precise control of a class of nonlinear systems. In this method, the Radial Basis Function Neural Networks (RBFNN) is used to approximate the uncertain functions in the system dynamics. In addition, a constraint is considered on the input. The Backstepping method is used for improving the overall accuracy of the control process. To evaluate the performance of the proposed method, a single-link robot arm with nonlinear dynamics and input saturation constraint is investigated. The simulation results show the performance of the proposed method.

关键词： Backstepping Method Input Saturation Constraint Nonlinear Systems Radial Basis Function Neural Networks (RBFNN)

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Quantification of Bearing Remaining Useful Life Based on Convolutional Neural Network

Uncertainty Quantification of Bearing Remaining Useful Life ...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Huanjie Wang Xiwei Bai Jie Tan Chinese Academy of Sciences Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

Remaining useful life (RUL) prediction is critical for predictive maintenance of machinery. Data-driven prognostics methods centered on deep learning are attracting ever-increasing attention. However, most existing methods mainly provide point estimates about RUL without quantifying predictive uncertainty. In contrast, Bayesian models can offer a reliable framework for estimating predictive uncertainty, but these models require expensive computation cost. In this paper, we present a Bayesian framework based convolutional neural network (BCNN) that is easy to implement and can provide high-quality predictive uncertainty of RUL. The variational inference is adopted to approximate the posterior distribution over the model parameters. Then the approximating probability distribution is used for subsequent inference of newly observed data. The proposed method is validated using vibration signals obtained from the accelerated degradation of rolling element bearings. The time-frequency domain features are extracted from raw vibration signals using continuous wavelet transform. The results of the experiments show the effectiveness of the RUL prediction of machinery.

关键词： Bayes methods Uncertainty Feature extraction Degradation Predictive models Neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control of Heating Process with Weather Forecast Compensation

Model Predictive Control of Heating Process with Weather For...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Jiang Ping Ju Chenxi Li Shi Xu Wenxue Qin Yu Univ Jinan Sch Elect Engn Jinan Peoples R China Diehl Metering Jinan Co Ltd Jinan Peoples R China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124858

This paper deals with a first-principle modeling and model predictive control strategy of heating process. The first principle model based on energy conservation is proposed, the model parameters are estimated using field data of heat supply station. The nonlinear model can be seen as a state-space model with time varying parameters. Then, a model predictive control algorithm based on time varying parameter state space model with weather temperature forecast compensation is proposed. In the MPC algorithm proposed in this paper, the consideration of future weather forecast is added, so that the indoor temperature control effect can be ensured while minimizing energy consumption.

关键词： heating process model predictive control first-principle model weather forecast compensation control

来源：评论

学校读者我要写书评

暂无评论

Weighted Failure Probability Calculation of Overhead Distribution Line in Random Wind Field

Weighted Failure Probability Calculation of Overhead Distrib...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Zhiwei Zhang Hui Hou Min Li Yufeng Xie Ling Zhu Yong Huang School of Automation Wuhan University of Technology Wuhan China Guangdong Power GRID Co. Ltd. Guangzhou China Guangdong Power Grid Corporation Electric Power Research Institute Guangzhou China

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

As a high-risk and small-probability event, typhoon disaster causes great damage to distribution system. A more accurate calculation of failure probability in power system under typhoon disaster can improve the accuracy of risk assessment. However, the existing research used a fixed value when considering load effect to calculate probabilities. Even if randomness was introduced, the solution method was complicated. This paper established a failure probability model of overhead distribution lines under typhoon disasters considering the randomness of load effect. A simpler and faster mathematical statistics method is used to solve the distribution function of the root bending moment of poles. It is concluded that collapsed poles has a more significant impact on failure probability and the introduction of randomness avoids the overestimation of failure probability. Finally, some windproof measures are proposed.

关键词： Conductors Tropical cyclones Wind speed Load modeling Bending Probability Mathematical model

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：