检索结果-内蒙古大学图书馆

IOP Conference Series: Materials Science and engineering 2020年第1期844卷

作者： BE Romero-Tarazona CL Rodriguez-Sandoval JG Villabonai-Ascanio A D Rincón-Quintero Automation and Control Energy Systems Research Group (GISEAC) Design and materials research group (DIMAT) Electromechanical Engineering Faculty of Natural Sciences and Engineering Technological Units of Santander (UTS) Road No 9-82 students 680005 Bucaramanga Colombia. Energy in Building research group (ENEDI) Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV/EHU) Engineer Torres Quevedo Plaza 1 48013 Bilbao BI España

A computing tool based on an intelligent algorithm generates new alternatives for an early crack detection on flat concrete slab in a surface testing. First, a system able to autonomously detect a surface crack, by means of a digital image processing system has been developed. This system carries on an effective selection of data by an algorism bound to a specialized MATLAB software that can assess in full detail the surface conditions of a concrete slab, and finding out any affected spot.

关键词：

Characterization of the mechanical vibration signals associated with unbalance and misalignment in rotating machines, using the cepstrum transformation and the principal component analysis

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and engineering 2020年第1期844卷

作者： C L Sandoval-Rodriguez J G Ascanio Villabona C G Cárdenas-Arias A D Rincon-Quintero B E Tarazona-Romero Energy Systems Automation and Control Research Group (GISEAC) Design and materials research group (DIMAT) Electromechanical Engineering Faculty of Natural Sciences and Engineering Technological Units of Santander (UTS) Road No 9-82 students 680005 Bucaramanga Colombia. Energy in Building Research Group (ENEDI) Doctoral Program in Energy Efficiency and Sustainability in Engineering and Architecture Department of Machines and Thermal Engines University of the Basque Country (UPV / EHU) Engineer Torres Quevedo Square 1 48013 Bilbao BI Spain.

In the present document, the Cepstrum transform and the analysis of principal components were used to differentiate amplitudes in the mechanical vibrations produced by unbalance and misalignment with respect to a reference group. This document requires three stages. It begins with levelling in order to establish the control group. The unbalancing was carried out with a known mass located in the two radial distances of the first and second flywheels. The misalignment was made by running the sliding supports back 0.5, 1.0 and 1.5 degrees. In the second stage, Matlab algorithms were created for both cepsctrum and main component analysis. In the last stage the obtained data were analyzed identifying the differences that may exist in the analyzed records. The project focused on the use of Matlab to find differences at a frequency of 30 Hz. The results obtained made it possible to determine that it is possible to find differences with the proposed methodology.

关键词：

PID2018 benchmark challenge: Learning feedforward control

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhao, Yang Dehghan, Sina Ates, Abdullah School of Control Science and Engineering Center for Robotics Shandong University Jinan Shandong250061 China University of California Merced MercedCA95340 United States School of Automation Southeast University Nanjing210096 China Engineering Faculty Computer Engineering Department Inonu University Malatya44280 Turkey

The design and application of learning feedforward controllers (LFFC) for the one-staged refrigeration cycle model described in the PID2018 Benchmark Challenge is presented, and its effectiveness is evaluated. The control system consists of two components: 1) a preset PID component and 2) a learning feedforward component which is a function approximator that is adapted on the basis of the feedback signal. A B-spline network based LFFC and a low-pass filter based LFFC are designed to track the desired outlet temperature of evaporator secondary flux and the superheating degree of refrigerant at evaporator outlet. Encouraging simulation results are included. Qualitative and quantitative comparison results evaluations show that, with little effort, a high-performance control system can be obtained with this approach. Our initial simple attempt of low-pass filter based LFFC and B-spline network based LFFC give J=0.4902 and J=0.6536 relative to the decentralized PID controller, respectively. Besides, the initial attempt of a combination controller of our optimized PI controller and low-pass filter LFFC gives J=0.6947 relative to the multi-variable PID controller. Copyright © 2018, The Authors. All rights reserved.

关键词： Feedforward control

Active learning for regression using greedy sampling

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Dongrui Lin, Chin-Teng Huang, Jian Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan430074 China Faculty of Engineering and Information Technology University of Technology Sydney Australia

Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a large number of unlabeled samples, but time-consuming or expensive to label them. Active learning for regression (ALR) is a methodology to reduce the number of labeled samples, by selecting the most beneficial ones to label, instead of random selection. This paper proposes two new ALR approaches based on greedy sampling (GS). The first approach (GSy) selects new samples to increase the diversity in the output space, and the second (iGS) selects new samples to increase the diversity in both input and output spaces. Extensive experiments on 12 UCI and CMU StatLib datasets from various domains, and on 15 subjects on EEG-based driver drowsiness estimation, verified their effectiveness and robustness. Copyright © 2018, The Authors. All rights reserved.

关键词： Regression analysis

Optimal boundary control of 1D colloid transport in a dead-end channel 36

学校读者我要写书评

暂无评论

Optimal boundary control of 1D colloid transport in a dead-e...

第36届中国控制会议

作者： Tehuan Chen Chao Xu Zhigang Ren Qinfang Qian Faculty of Mechanical Engineering and Mechanics Ningbo University State Key Laboratory of Industrial Control Technology Zhejiang University School of Automation Guangdong University of Technology Operating Theatre Zhejiang Hospital

ISBN: (纸本)9781538629185

Diffusiophoresis occurs when colloids are placed in the non-uniform solute concentration. The colloids will be propelled in the direction of higher or lower concentration of the solute. In this paper, we consider the optimal boundary control of 1D colloid transport in a dead-end channel, which has a wide range of applications such as drug delivery, biology transport,oil recovery system and so on. Thus, we introduce a coupled system describing the colloid transport process and formulate an optimal control problem, in which the goal is to minimize colloid density distribution deviation between the computational one and the target at a pre-specified terminal time. To solve this optimal problem, we derive the gradient of the objective function based on the control parameterization method with respect to the decision parameters, which depends on the solution of the coupled system and the costate system. Finally, we propose an effective computational method and a gradient-based optimization algorithm to solve the optimal control problem numerically.

关键词： Diffusiophoresis Dead-end channel Colloid transport control parameterization PDE-constrained optimization Computational optimal control

Simulation on model predictive control for PMSM drive system based on double extended state observer

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2018年第4期9卷 380-387页

作者： CUI Hong-wei TENG Qing-fang ZHU Jian-guo GUO You-guang Department of Automation & Electrical Engineering Lanzhou Jiaotong University Lanzhou 730070 China Key Laboratory of Opto-technology and Intelligent Control (Lanzhou Jiaotong University) Ministry of Education Lanzhou 730070 China Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia

A novel double extended state observer(DESO)based on model predictive torque control(MPTC)strategy is developed for three-phase permanent magnet synchronous motor(PMSM)drive system without current *** general,to achieve high-precision control,two-phase current sensors are necessary for successful implementation of *** this purpose,two ESOs are used to estimate q-axis current and stator resistance respectively,and then based on this,d-axis current is ***,to reduce torque and flux ripple and to improve the performance of the torque and speed,MPTC strategy is *** simulation results validate the feasibility and effectiveness of the proposed scheme.

关键词： double extended state observer(DESO) model predictive torque control(MPTC) permanent magnet synchronous motor(PMSM)drive system without current sensor

Pneumatic muscle-based actuator for industrial robotic applications 7

学校读者我要写书评

暂无评论

Pneumatic muscle-based actuator for industrial robotic appli...

2017 7th International Workshop on Computer Science and engineering, WCSE 2017

作者： Pitel, Ján Líška, Ondrej Janáčová, Dagmar Technical University of Kosice Faculty of Manufacturing Technologies Department of Industrial Engineering and Informatics Bayerova 1 Prešov080 01 Slovakia Technical University of Kosice Faculty of Mechanical Engineering Department of Automation Control and Human-Machine Interaction Letná 9 Košice042 00 Slovakia Tomas Bata University in Zlin Faculty of Applied Informatics Department of Automation and Control Engineering Nad Stráněmi 4511 Zlín760 05 Czech Republic

ISBN: (纸本)9789811136719

The outstanding feature of the pneumatic artificial muscle is its high power to weight ratio vastly outperforming both pneumatic cylinder and DC motor. This feature is very important for using of pneumatic muscle-based actuators in industrial robotic systems where high forces and stiffness of mechanism are often required. The most common so far produced and used type of pneumatic artificial muscle is McKibben muscle and it is now made commercially available by different companies (e.g. Festo). In the paper there are described some of its characteristics and principles of control important for using as actuator for industrial robotic applications.

关键词： Pneumatic actuators

Perceptual visual interactive learning

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Shenglan Liu, Xiang Liu, Yang Feng, Lin Qiao, Hong Zhou, Jian Wang, Yang Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian Liaoning116024 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Supervised learning methods are widely used in machine learning. However, the lack of labels in existing data limits the application of these technologies. Visual interactive learning (VIL) compared with computers can avoid semantic gap, and solve the labeling problem of small label quantity (SLQ) samples in a groundbreaking way. In order to fully understand the importance of VIL to the interaction process, we re-summarize the interactive learning related algorithms (e.g. clustering, classification, retrieval etc.) from the perspective of VIL. Note that, perception and cognition are two main visual processes of VIL. On this basis, we propose a perceptual visual interactive learning (PVIL) framework, which adopts gestalt principle to design interaction strategy and multi-dimensionality reduction (MDR) to optimize the process of visualization. The advantage of PVIL framework is that it combines computer's sensitivity of detailed features and human's overall understanding of global tasks. Experimental results validate that the framework is superior to traditional computer labeling methods (such as label propagation) in both accuracy and efficiency, which achieves significant classification results on dense distribution and sparse classes dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

Robust medical instrument segmentation challenge 2019

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Roβ, Tobias Reinke, Annika Full, Peter M. Wagner, Martin Kenngott, Hannes Apitz, Martin Hempe, Hellena Filimon, Diana Mindroc Scholz, Patrick Tran, Thuy Nuong Bruno, Pierangela Arbelaéz, Pablo Bian, Gui-Bin Bodenstedt, Sebastian Bolmgren, Jon Lindström Bravo-Sánchez, Laura Chen, Hua-Bin González, Cristina Guo, Dong Halvorsen, Pål Heng, Pheng-Ann Hosgor, Enes Hou, Zeng-Guang Isensee, Fabian Jha, Debesh Jiang, Tingting Kirtac, Kadir Jin, Yueming Kletz, Sabrina Leger, Stefan Li, Zhixuan Maier-Hein, Klaus H. Ni, Zhen-Liang Riegler, Michael A. Schoeffmann, Klaus Shi, Ruohua Speidel, Stefanie Stenze, Michael Twick, Isabell Wang, Gutai Wang, Jiacheng Wang, Liansheng Wang, Lu Zhang, Yujie Zhou, Yan-Jie Zhu, Lei Wiesenfarth, Manuel Kopp-Schneider, Annette Müller-Stich, Beat P. Maier-Hein, Lena Heidelberg Germany University of Heidelberg Germany Heidelberg Germany Department of General Heidelberg University Hospital Visceral and Transplant Surgery Heidelberg Germany caresyntax Berlin Germany University of Chinese Academy Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China SimulaMet Oslo Norway Tromsø Norway Oslo Norway School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China Partner Site Dresden Heidelberg Germany Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden Germany Dresden Germany Universidad de Los Andes Bogotá Colombia Peking University Peking China Department of Computer Science School of Informatics Xiamen University Xiamen China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong German Cancer Research Center Division of Biostatistics Heidelberg Germany Institute of Information Technology Klagenfurt University Austria

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and roboticassisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization;algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts). Copyright © 2020, The Authors. All rights reserved.

关键词： Endoscopy

Relation Model of Burden Operation and State Variables of Blast Furnace Based on Low Frequency Feature Extraction*

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 13796-13801页

作者： Zhang, Kexin Wu, Min An, Jianqi Cao, Weihua Liu, Zhentao Ning, Fulong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Faculty of Engineering China University of Geosciences wuhan430074 China Department of Computer Science School of Computing Tokyo Institute of Technology Yokohama226-8502 Japan

In the blast furnace ironmaking process, the running state of the blast furnace can be directly adjusted by the burden operation. Therefore, the explicit relation between the burden operation and the running state variables is vital for the blast furnace operators. However, the state variables of the blast furnace are affected by many factors and the burden matrix is complicated. In this paper, a support vector regression(SVR) predicting model based on low frequency feature extraction is proposed to solve these problems. First, the low frequency components of state variables time series which are mostly affected by the burden operation are extracted. Then, the dimensions of the burden matrix are reduced by a devised simple expression method. Finally, the relation model based on SVR is proposed to predict the values of the expected state variables according to the simplified burden matrix and the value of initial state variables. The simulation on real factory data indicates that the model reflects the accurate quantitative relation between the burden operation and the state variables. © 2017

关键词： Blast furnaces Blast furnace practice Extraction Feature extraction Support vector regression Blast furnace iron making Blast furnace operators burden operation Initial state variables Low frequency components Relation models State variables Support vector regression (SVR)