检索结果-内蒙古大学图书馆

12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020

作者： Suzuki, Takahiro Koyama, Masaki Nagata, Syuhei Hatsuse, Wataru Takemoto, Masatsugu Ogasawara, Satoshi Hitachi Ltd. Drive System Control Research Dept. Hitachi Japan Hitachi Ltd. Reliability Science Research Dept. Hitachinaka Japan Okayama University Graduate School of Natural Science and Technology Okayama Japan Hokkaido University Graduate School of Information Science and Technology Sapporo Japan

ISBN: (纸本)9781728158266

This paper proposes a drive control method for a linear compressor driven by a linear motor. Generally, the efficiency of a linear motor itself is relatively lower than that of a rotational motor. However, higher efficiency should be achievable by adding assist springs and driving at the resonant frequency. We have developed a novel resonant frequency estimation method that calculates the phase difference between a supplied voltage and a mover position. Since the phase difference changes according to the drive frequency with respect to the resonant frequency, our method calculates the phase difference by using the arctangent of a Fourier coefficient, which controls the drive frequency to keep the phase difference at 90°. Experimental results show that the proposed method can successfully track to the resonant frequency dynamically even if the mechanical condition is changed. © 2020 IEEE.

关键词： Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

Applying Predictive Machine Learning Algorithms to Petroleum Refining Processes as Part of Intelligent Automation

Applying Predictive Machine Learning Algorithms to Petroleum...

引用

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Ivan S. Nekrasov Vadim S. Tynchenko Vladimir B. Bukhtoyarov Vera A. Kachaeva Kirill A. Bashmur Aleksandra E. Sinitskaya Laboratory of Biofuel Composition Siberian Federal Univercity Krasnoyarsk Russian Federation dept. of Technological Machines and Equipment of Oil and Gas Complex Siberian Federal Univercity Krasnoyarsk Russian Federation Information-Control Systems Department Institute of Computer Science and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk Russian Federation

ISBN: (数字)9781665498043

ISBN: (纸本)9781665498050

Intelligent automation is a term that can be applied to the more complex field of workflow automation, consisting of robotic workplace automation, robotic process automation, machine learning, and artificial intelligence. Depending on the type of business, companies often use one or more types of automation to improve efficiency or effectiveness. As you move from process-driven automation to more flexible data-driven automation, additional costs arise in the form of training datasets, technical development, infrastructure, and expertise. But the potential benefits in terms of new ideas and financial development can increase significantly. The development of mechanized oil production in recent years has been accompanied by significant achievements in the field of digitalization. Machine learning, as an important element of digitalization, can successfully solve many production problems. The paper describes the application of some machine learning algorithms for solving the problem of classifying and predicting failures of hydrocracking process equipment that occur during oil refining and diesel fuel production. The application of random forest, principal component analysis and hyperparameter tuning methods is considered. The effectiveness of their application is compared.

关键词： Radio frequency Intelligent automation Machine learning algorithms Biological system modeling Oils Refining Production

来源：评论

学校读者我要写书评

暂无评论

A strategy of multi-UAV cooperative path planning based on CCPSO

A strategy of multi-UAV cooperative path planning based on C...

引用

2019 IEEE International Conference on Unmanned systems, ICUS 2019

作者： Liu, Yuanna Lu, Hao Northwestern Polytechnical University Dept. School of Electronics and Information Xi'an China Intelligent Agent Cooperation Laboratory Dept. Science and Technology on Complex System Control Beijing China

ISBN: (纸本)9781728137926

Multi-UAV cooperative formation flying has significant advantages in broadening the scope of UAV operations and improving combat effectiveness. How to realize the cooperative path planning of multi-UAV is an open issue. In order to solve the search performance degradation as dimension increases, a strategy of multi-UAV cooperative path planning based on Cooperative Coevolution Particle Swarm Optimization (CCPSO) is proposed in this paper. Firstly, the initial Dubins path is generated for each UAV in the formation, of which the longest one is selected as the reference path. Intermediate waypoints are designed to modify the initial paths to avoid collisions with obstacles. Then, CCPSO algorithm is applied to optimize path parameters and adjust the path length to be equal to the reference path to ensure time coordination. Collision avoidance between UAVs is achieved in the collaborative evaluation phase. Finally, an formation rendezvous example and comparison with CCGA are given to explain the validity and excellent search ability of the proposed method. © 2019 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Improved Template Matching Based Stereo Vision Sparse 3D Reconstruction Algorithm

Improved Template Matching Based Stereo Vision Sparse 3D Rec...

引用

Chinese control and Decision Conference, CCDC

作者： Zhiyuan Liu Bin Song Yanning Guo Hang Xu Dept. of Control Science and Engineering Harbin Institute of Technology Harbin Aerospace System Engineering Shanghai Shanghai Engieering Research Center of Space Robotics Shanghai

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Stereo vision 3D reconstruction using keypoints matching methods can bring up problems, such as uneven distribution of points, or even mismatches. To solve the problems, we proposed a novel stereo vision 3D reconstruction algorithm based on template matching. First, considering that the similarity between left and right image of binocular camera can be high, template matching can be brought in to minify the searching range of every keypoint, thus enhance the accuracy of matches and make the reconstruction result more complete. The specific process of the proposed method includes the following steps: templates extraction, keypoint density index calculation, template matching, keypoint matching within template matched areas, point cloud generation, and point cloud stitching. Furthermore, a simulation environment was built up in Gazebo, and 3D reconstruction was carried out using the proposed method. Comparison experiment was carried out using brute force keypoint matching method and FLANN. Simulation results showed that the proposed method performed better and improved in both utilization of keypoints and reconstruction result.

关键词： Three-dimensional displays Cameras Stereo vision Mathematical model Indexes Solid modeling Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Economic Equilibrium with Random Transactions

Economic Equilibrium with Random Transactions

引用

International Conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Aleksandra Zhukova Igor G. Pospelov Federal Research Center Computer Science and Control of RAS Moscow Institue of Physics and Technology Moscow Russia dept. of mathematical modelling of complex systems and optimization Moscow Russia

ISBN: (数字)9781728188409

ISBN: (纸本)9781728181134

This paper presents the advances in modelling the system of agents under the conditions of random transactions between them. We face certain challenges in this project which we would like to highlight in this presentation. The agents in the modelled system are a large number of consumers, a large number of producers and the bank as the intermediary. Consumers take loans from the bank to spend on consumption goods and producers borrow to make investment at random moments of time. The moments of time the agents deal form the Poisson flow. We present the approach to agents' optimal control problems by the Lagrange method instead of dynamic programming. This enables us obtaining the expressions for the optimal feedback control which appear to be linear in state variables. The solution to the optimal control problems are obtained using asymptotic methods assuming large frequency of transactions. Using the linearity of the agents' optimal control, we may aggregate description of agents, stock-flow consistent on the average. Instead of an ensemble of independent random transactions by agents, the description of the aggregate dynamics is deterministic. The system of equations for the aggregate dynamics is reduced to one equation. There are two cases of this equation, depending on the description of the bank. The equation has a specific form, its numerical analysis is challenging. We provide numerical results and discuss further directions of research.

关键词： Numerical analysis Aggregates Optimal control Process control Linearity Numerical models Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A strategy of multi-UAV cooperative path planning based on CCPSO

A strategy of multi-UAV cooperative path planning based on C...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yuanna Liu Hao Lu dept. School of Electronics and Information Northwestern Polytechnical University Xi’an China dept. Science and Technology on Complex System Control Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781728137933

关键词： Path planning Optimization Particle swarm optimization Safety Unmanned aerial vehicles Collision avoidance Planning

来源：评论

学校读者我要写书评

暂无评论

Improved Positioning of Delivery Quad copter Using GPS - Accelerometer Multimode controller and Unscented Kalman Filter

引用

IOP Conference Series: Materials science and Engineering 2020年第1期745卷

作者： Ahmed Abdulmahdi Abdulkareem Alawsi Basil H Jasim Safanah Mudheher Raafat College of Science Physics Dept. University of Wasit Wasit Iraq Electrical Engineering Dept. University of Basra Basra Iraq Control and System Engineering Dept. University of Technology Baghdad Iraq

In last area of technology, the quadrotor helicopter became essential equipment of everyday man use. Delivery by quadcopter has increased significantly in the last few years in different private and military fields because of its indispensable features such as autonomous flight, vertical take-off and landing. Most quadcopters used for delivery service utilize GPS signal for its autonomous flight to control itself and follow the desired path to the destination. Despite the prevalence of autonomous flight, it produces many challenges. GPS signal denial is one of the most critical challenges that may occur. GPS signal denial problem leads to affect the quadcopter control and potentially get lost. Many studies have tried to provide a solution toward this issue, yet, most solutions focused on specific applications and terms rather than achieving a general solution. In this paper, a multimode control algorithm is proposed as a solution for GPS signal denied through the autonomous flight. The algorithm consists of two control modes: GPS and accelerometer modes with Unscented Kalman Filter (UKF). The results show that the proposed algorithm is reliable and suitable for various applications of the quadcopter in different environments. The proposed algorithm can keep the quadcopter under control during GPS signal denial period and continue moving toward the desired path.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maintaining Diversity in an SVM integrated Case Based GA for Solar Flare Prediction

Maintaining Diversity in an SVM integrated Case Based GA for...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Yoshio Taniguchi Yoshihiko Kubota Setsuo Tsuruta Yoshiyuki Mizuno Takayuki Muranushi Yuko Hada Muranushi Yoshitaka Sakurai Rainer Knauf Andrea Kutics Hitachi Industry & Control Solutions Ltd. Yokohama Japan School of System Design and Technology Tokyo Denki University Tokyo Japan Faculty for the Study of Contemporary Society Kyoto Women’s University Kyoto Japan RIKEN Advanced Institute of Computational Science Kobe Japan Kwasan and Hida Observatories Kyoto University Kyoto Japan School of Interdisciplinary Sciences Meiji University Tokyo Japan Dept. of Computer Science and Automation Technische Universität Ilmenau Ilmenau Germany Dept. of Natural Sciences International Christian University Tokyo Japan

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Unusually intense solar flares may cause serious calamities such as damages of electric/nuclear power plants. It is thereupon highly demanded, but is quite difficult, to predict intense solar flares due to the imbalanced character of the available data. To cope with this problem, we have heretofore developed and applied a Case Based Genetic Algorithm (CBGALO) that contains a Local Optimizer, which is a Support Vector Machine (SVM). However, the prediction performance significantly depends on input data for learning. Hereupon, CBGALO is further extended by a Case Based automatically restartable Good combination searching GA for both learning features and input data (CBRsGcmbGA). Even the powerful but computationally expensive Deep Learning cannot automatically (evolutionarily, in our approach) search the learning data. Our approach solved this problem a little better by the case-based approach. However, it became obvious that even this work suffers from the typical GA effect in falling into local optima. To improve the results, we hence developed newly a diversity maintenance approach that inserts good individuals with large Hamming distance into the case base as elite individuals in GA's population. In 2 out of 3 classes of solar flares, the performance of our new approach became as high as the best ones among the conventional world top records. Namely, even in those ≥ C class solar flares, our approach applying the Hamming distance to increase diversity had as high a performance 0.662 as compared with the conventional world top record 0.650.

关键词： Genetic algorithms Support vector machines Evolutionary computation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Lazy and Decision Tree Classifier: A Data Mining Approach for Global Celebrity's Death Analysis

Performance Evaluation of Lazy and Decision Tree Classifier:...

引用

International Conference on Research in Intelligent and Computing in Engineering (RICE)

作者： Vivek Kumar Roman Zinovyev Abhishek Verma Prayag Tiwari Dept. of Automated Control System National University of Science & Technology-MiSiS Moscow Russian Federation Dept.of Semiconductor Electronic National University of Science & Technology-MiSiS Moscow Russian Federation Dept.of CSE Malaviya National Institute of Technology Jaipur India Dept.of Information Engineering University of PaPadova Italy

In present world data is a valuable asset. The best utilization of this asset by means of technology gives an upper hand to an organization. Technologies like machine learning, data mining, and artificial intelligence are no exception to this either. Celebrities influence common people behaviors through biological, psychological and social processes to a great extent. Simultaneously there is vast disparity amongst their demise over the cause, region, and age. Therefore, it is a challenging and interesting endorsement to work upon. The objective of this work is to come up with the comprehensive result to understand the celebrity deaths by investigating the incidence happened over the decade. The database for training is created from the public and open access databases for years 2006-2016 comprising of 11, 200 reported deaths over the globe. Findings of the work are year by year extraction of death, the cause behind it, age, gender, and place. Lazy and decision tree classifier model of data mining is being used for the analysis based on the profession as evaluation class.

关键词： Decision trees Entropy Support vector machines Text mining Information retrieval Machine learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of arterial travel time considering delay in vehicle re-identification

引用

Transportation Research Procedia 2017年 22卷 625-634页

作者： Xiaoliang Ma Fadi Al Khoury Junchen Jin System Simulation & Control Dept. of Transport Science KTH Royal Institute of Technology Teknikringen 10 Stockholm 10044 Sweden

Travel time is important information for management and planning of road traffic. In the past decades, automated vehicle identification (AVI) systems have been deployed in many cities for collecting reliable travel time data. The fast technology advance has made the budget cost of such data collection system much cheaper than before. For example, bluetooth and WiFi-based systems have become economically a more feasible way for collecting interval travel time information in urban area. Due to increasing availability of such type of data, this paper aims to develop a travel time prediction approach that may take into account both online and historical measurements. Indeed, a statistical prediction approach for real-time application is proposed, modeling the deviation of live travel time from historical distribution estimated per time interval. An extended Kalman Filter (EKF) based algorithm is implemented to combine online travel time with historical patterns. In particular, the system delay due to vehicle re-identification is considered in the algorithm development. The methods are evaluated using Automated Number Plate Recognition (ANPR) data collected in Stockholm. The results show that the prediction performance is good and reliable in capturing major trends during congestion buildup and dissipation.

关键词： Travel time real-time prediction Automated Vehicle Identification extended Kalman filter data fusion historical percentiles

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：