检索结果-内蒙古大学图书馆

Data Driven Control and Learning systems (DDCLS)

作者： Xueyan Zhong Long Chen Zhongyang Han Jun Zhao Wei Wang School of Control Science and Engineering Dalian University of Technology Dalian China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian China

Industrial time series data are usually time-varying due to multiple factors such as environmental and human disturbances. As traditional time series predicting methods are often based on offline training ignoring the changes in working conditions, the prediction results may be inaccurate. In this paper, a time series prediction model based on incremental DBSCAN and KNN with self-learning scheme is proposed to address the problem of time-varying working conditions. The proposed model uses the incremental DBSCAN to automatically identify and expand working conditions with adjusting the number of clusters automatically, and then employs the KNN model to make predictions under different working conditions. Compared with the existing methods, the proposed method is more stable and improves the prediction accuracies of the model under different working conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Liquid Level Control of Unmanned Platform Closed Drainage Based on Improved Particle Swarm optimization

Research on Liquid Level Control of Unmanned Platform Closed...

引用

Energy, Power and Electrical Technology (ICEPET), International Conference on

作者： Xiaoyong He Boying Liu Yuqing Chen Han Pang State Key Laboratory of Offshore Oil and Gas Exploitation Beijing China CNOOC Research Institute Ltd Beijing China China University of Petroleum Qingdao China

ISBN: (数字)9798350352658

ISBN: (纸本)9798350352665

In order to obtain a control scheme for the liquid level of unmanned platform closed drainage with good performance indicators, this paper proposes a PID control method based on the optimization of Improved Particle Swarm optimization (IPSO). On the basis of analyzing the principle of closed drainage liquid level control, a liquid level control model of unmanned platform closed drainage based on Improved Particle Swarm optimization was constructed, and simulation was carried out on the closed drainage liquid level control of four methods: conventional PID, Z-N tuning method, standard Particle Swarm optimization (PSO), and IPSO algorithm, using Simulink. The results show that the IPSO optimization algorithm has shorter adjustment time, smaller overshoot, and smaller steady-state error than the conventional PID, Z-N tuning, and PSO algorithms, with higher control accuracy, faster convergence speed, and stronger stability.

关键词： Analytical models PI control Mathematical models Steady-state PD control Particle swarm optimization Level control

来源：评论

学校读者我要写书评

暂无评论

A hybrid intelligent soft computing method for ammonia nitrogen prediction in aquaculture

引用

Information Processing in Agriculture 2021年第1期8卷 64-74页

作者： Huihui Yu Ling Yang Daoliang Li Yingyi Chen School of Information Science and Technology Beijing Forestry UniversityBeijing 100083PR China College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083PR China Key Laboratory of Agricultural Information Acquisition Technology Ministry of AgricultureBeijing 100083PR China Beijing Engineering and Technology Research Center for Internet of Things in Agriculture Beijing 100083PR China

Ammonia nitrogen is one of the key parameters in determining the aquaculture water quality condition in *** high level of ammonia nitrogen is likely to cause deterioration of water quality and mass death of cultured ***,accurate detection of the cultured water ammonia nitrogen content is crucially important for aquaculture ***,at present,the accuracy of equipment for measuring the ammonia nitrogen content of aquaculture water in real time cannot meet the requirements for *** this paper,the soft computing method is firstly proposed to predict the ammonia nitrogen content in aquaculture water in real *** method includes empirical mode decomposition(EMD),improved particle swarm optimization(IPSO)and extreme learning machine(ELM).To evaluate the performance of the soft computing techniques,three different statistic indicators were used,including root mean square error(RMSE),the mean absolute error(MAE),and the mean absolute percentage error(MAPE)to compare three artificial soft computing *** showed that the EMD-IPSO-ELM soft computing method showed the best performance among other studied methods in the ammonia nitrogen real time *** EMD-IPSO-ELM model provides moderately and roughly accurately real time prediction value of ammonia nitrogen in aquaculture water.

关键词： Ammonia nitrogen prediction Extreme learning machine Soft computing Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Flux Limiters

arXiv

引用

arXiv 2024年

作者： Nguyen-Fotiadis, Nga Chiodi, Robert McKerns, Michael Livescu, Daniel Sornborger, Andrew Information Sciences CCS-3 Los Alamos National Laboratory Los AlamosNM87545 United States Computational Physics and Methods CCS-2 Los Alamos National Laboratory Los AlamosNM87545 United States

The stable numerical integration of shocks in compressible flow simulations relies on the reduction or elimination of Gibbs phenomena (unstable, spurious oscillations). A popular method to virtually eliminate Gibbs oscillations caused by numerical discretization in under-resolved simulations is to use a flux limiter. A wide range of flux limiters has been studied in the literature, with recent interest in their optimization via machine learning methods trained on high-resolution datasets. The common use of flux limiters in numerical codes as plug-and-play blackbox components makes them key targets for design improvement. Moreover, while aleatoric (inherent randomness) and epistemic (lack of knowledge) uncertainty is commonplace in fluid dynamical systems, these effects are generally ignored in the design of flux limiters. Even for deterministic dynamical models, numerical uncertainty is introduced via coarse-graining required by insufficient computational power to solve all scales of motion. Here, we introduce a conceptually distinct type of flux limiter that is designed to handle the effects of randomness in the model and uncertainty in model parameters. This new, probabilistic flux limiter, learned with high-resolution data, consists of a set of flux limiting functions with associated probabilities, which define the frequencies of selection for their use. Using the example of Burgers’ equation, we show that a machine learned, probabilistic flux limiter may be used in a shock capturing code to more accurately capture shock profiles. In particular, we show that our probabilistic flux limiter outperforms standard limiters, and can be successively improved upon (up to a point) by expanding the set of probabilistically chosen flux limiting functions. © 2024, CC BY.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Multi -View Clustering Using Sparse Non-Negative Matrix Factorization for Recommendation systems

Multi -View Clustering Using Sparse Non-Negative Matrix Fact...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Khalil Bachiri Faouzi Boufares Maria Malek Nicoleta Rogovschi Ali Yahyaouy ETIS Laboratory CY Cergy Paris University LISAC Laboratory Sidi Mohamed Ben Abdellah University La Maison des Sciences Numeriques Cergy France Laboratory LIPN-UMR 7030-CNRS La Maison des Sciences Numeriques University Sorbonne Paris Nord Villetaneuse France ETIS Laboratory CY Cergy Paris University Cergy France LIPADE Laboratory University of Paris Descartes Paris France LISAC Laboratory Sidi Mohamed Ben Abdellah University Fez Morocco

Real-world datasets often comprise multiple views or representations, such as user profiles, comments, and preferences. Integrating information from these multi-view datasets can significantly enhance recommendation performance. Consequently, several multi-view clustering (MVC) approaches have been proposed and extensively applied to exploit the compatibility of diverse data sources. Among these methods, Non-negative Matrix Factorization (NMF) has garnered significant attention due to its ability to process high-dimensional data. However, most NMF-based MVC methods suffer from two critical drawbacks: the similarity matrices constructed using traditional methods fail to fully exploit neighborhood information among data points, and they are highly sensitive to noise, missing values, and outliers. Additionally, existing NMF-based clustering methods often do not generate sparse coefficient matrices, leading to suboptimal data representation based on the basis matrix. To address these challenges and enhance the accuracy and efficiency of recommendation algorithms, we propose a novel approach called Multi-View Clustering based on Sparse Non-Negative Matrix Factorization (MVC-SNMF). This method leverages the manifold structure of multi-view data and incorporates a sparsity constraint to effectively handle noise while preserving the geometric structure. Furthermore, we introduce a sparsity constraint on the rows of the coefficient matrix to enhance the visibility of clustering structures. To efficiently solve the proposed non-convex optimization problem, we devise an iterative update scheme. Our experimental results on real datasets from *** and Yelp demonstrate the effectiveness of our approach in improving clustering performance, surpassing most existing clustering algorithms. The proposed method not only enhances the clustering accuracy but also exhibits robustness to noise and missing values, making it a promising solution for practical recommendation systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Modeling and Analysis Method of Dynamic Contact Stress Inside an Automotive Ball Joint

A Modeling and Analysis Method of Dynamic Contact Stress Ins...

引用

SAE 2021 WCX Digital Summit

作者： Feng, Huayuan Xihua, Li South China University of Technology JI HUA Laboratory

A ball joint is an important component of the automotive drive shaft system, as well the contact stress inside the ball joint is an important optimization goal in the design of ball joints. At present, the analysis of the contact stress inside the ball joint mainly focuses on the static contact stress analysis. The static contact stress analysis, however, cannot reflect the change of the contact stress inside the ball joint. In order to analyze the contact stress of the ball joint more effectively, a hybrid flexible and rigid bodies dynamics (HFRBD) model of the ball joint for studying the dynamic contact stress inside the ball joint is proposed. In the HFRBD model, the balls are regarded as the rigid body, while the cage, the inner race and the outer race are regarded as the flexible body. The contact parameters of the contact pairs in the model are determined on the basis of Hertz contact theory. Through the destruction test of the ball joint and the numerical example, the effectiveness of the HFRBD model and the method for the analysis of the dynamic contact stress inside the ball joint is verified. Based on the proposed HFRBD model, the stress distributions of the cage, the inner race and the outer race under different rotation angles are analyzed subsequently. The presented modeling and analysis methods for the dynamic contact stress inside the ball joint in this paper have an important reference for the design of a ball joint. © 2021 SAE International. All Rights Reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of Multi-video Synopsis Based on NSGA-III 8

Multi-objective Optimization of Multi-video Synopsis Based o...

引用

8th International Conference on Virtual Reality, ICVR 2022

作者： Chen, Xiaoxiao Xie, Yujia Wang, Xing Nanjing University of Finance and Economics College of Information Engineering Jiangsu Key Laboratory of Grain Big-data Mining Nanjing China Nanjing China

ISBN: (数字)9781665479110

ISBN: (纸本)9781665479110

Multi-video synopsis can display all information of surveillance video and show all sports solution of moving objects in the sight of multi-cameras. However, most of the existing multi-video synopsis can't achieve these functions. This is because these approaches do not comprehensively consider these factors: video target display timing, maximum target display number, target display consistency, maximum moving target display density, and compression ratio. To address the comprehensive optimization problem of multiple elements for multi-video synopsis, a multi-objective optimization algorithm for multi-video synopsis is proposed. The proposed approach differs significantly from the existing methods and has several appealing properties. First, we propose five objective functions, which are consistent in time sequence, coherent in cross-camera pedestrian display, largest in number of moving objects displayed, smallest in density of moving objects, and smallest in compression ratio, then, establish a multi-objective optimization model based on the five objective functions. Second, we build a model for multi-video synopsis. Third, we use the non-dominated sorting genetic algorithm NSGA-III to optimize the multi-object model of the multi-video synopsis. Through such a solution, the poor performance of multi-video synopsis can be avoided by comprehensively considering the main influencing factors of multi-video synopsis. Besides, we present extensive experiments that demonstrate the effectiveness and efficiency of the proposed approach. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

AI Surrogate Model for Distributed Computing Workloads

AI Surrogate Model for Distributed Computing Workloads

引用

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： David K. Park Yihui Ren Ozgur O. Kilic Tatiana Korchuganova Sairam Sri Vatsavai Joseph Boudreau Tasnuva Chowdhury Shengyu Feng Raees Khan Jaehyung Kim Scott Klasky Tadashi Maeno Paul Nilsson Verena Ingrid Martinez Outschoorn Norbert Podhorszki Frederic Suter Wei Yang Yiming Yang Shinjae Yoo Alexei Klimentov Adolfy Hoisie Brookhaven National Laboratory Upton NY USA University of Pittsburgh Pittsburgh PA USA Carnegie Mellon University Pittsburgh PA USA Oak Ridge National Laboratory Oak Ridge TN USA University of Massachusetts Amherst MA USA SLAC National Accelerator Laboratory Menlo Park CA USA

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

Large-scale international scientific collaborations, such as ATLAS, Belle II, CMS, and DUNE, generate vast volumes of data. These experiments necessitate substantial computational power for varied tasks, including structured data processing, Monte Carlo simulations, and end-user analysis. Centralized workflow and data management systems are employed to handle these demands, but current decision-making processes for data placement and payload allocation are often heuristic and disjointed. This optimization challenge potentially could be addressed using contemporary machine learning methods, such as reinforcement learning, which, in turn, require access to extensive data and an interactive environment. Instead, we propose a generative surrogate modeling approach to address the lack of training data and concerns about privacy preservation. We have collected and processed real-world job submission records, totaling more than two million jobs through 150 days, and applied four generative models for tabular data— TVAE, CTAGGAN+, SMOTE, and TabDDPM—to these datasets, thoroughly evaluating their performance. Along with measuring the discrepancy among feature-wise distributions separately, we also evaluate pair-wise feature correlations, distance to closest record, and responses to pre-trained models. Our experiments indicate that SMOTE and TabDDPM can generate similar tabular data, almost indistinguishable from the ground truth. Yet, as a non-learning method, SMOTE ranks the lowest in privacy preservation. As a result, we conclude that the probabilistic-diffusion-model-based TabDDPM is the most suitable generative model for managing job record data.

关键词： Training Correlation Computational modeling Collaboration Data collection Diffusion models Data models Distributed computing optimization Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Global Sizes and Cylindricity Errors Based on fminimax optimization Function

Evaluation of Global Sizes and Cylindricity Errors Based on ...

引用

Automation, Robotics and Computer Engineering (ICARCE), International Conference on

作者： Xinyu Zhao Zexiang Zhao Dongxu Ren School of Computer Science Zhongyuan University of Technology Zhengzhou China School of Mechatronics Engineering Zhongyuan University of Technology Zhengzhou China Key Laboratory of Optical Sensing and Testing Technology for Mechanical Industry Zhengzhou China

Based on the evaluation definitions of minimum circumscribed, maximum inscribed and minimum zone methods for global sizes and cylindricity errors of cylinder, the optimization objective function of the axis parameters of the reference cylindrical surfaces and the evaluation models of global sizes and cylindricity errors were built. The subprograms for the optimization objective functions of the axis parameters of the reference cylindrical surfaces and the evaluation of global sizes and cylindricity errors were written by using Matlab language. The roundness profiles of four cylindrical samples were extracted, and their global sizes and cylindricity errors were evaluated based on least square, minimum circumscribed, maximum inscribed and minimum zone methods. The evaluation results of the optimization characteristic values of fminimax optimization function were compared with those evaluated by using other optimization methods, and it turned out that the accuracy of the optimization objective characteristic values of fminimax optimization function are higher or equal to those evaluated by other optimization methods, which is suitable to the application in the evaluation of global sizes and cylindricity errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Dynamic Response optimization of Linear Regulators Based on Predictive Compensation

Research on Dynamic Response Optimization of Linear Regulato...

引用

Electrical, Electronic Information and Communication Engineering (EEICE), International Conference on

作者： Yuekang Qian Yang Zuo Sheng Qin Shengkai Jiang Wenhua Gu School of Microelectronics (School of Integrated Circuits) Nanjing University of Science and Technology Key Laboratory of Near-Range RF Sensing ICs & Microsystems (Nanjing University of Science and Technology) Ministry of Education Nanjing China

ISBN: (数字)9798331532598

ISBN: (纸本)9798331532604

The issue of output voltage fluctuations in Low Dropout Regulators (LDOs) under high-frequency dynamic loads severely restricts their application in precision systems such as fiber optic gyroscopes. Traditional compensation techniques exhibit significant limitations in effectively suppressing ripple noise caused by high-frequency load transients due to the lag in feedback loops. For example, fiber optic gyroscopes require maintaining output voltage fluctuations below 1 mV within a 10 MHz bandwidth, whereas traditional compensation methods typically yield measured values ranging from 10 to 100 mV. This paper proposes a dynamic response optimization method for LDOs based on predictive compensation. By establishing a load current time-series prediction model and integrating a feedforward control strategy, a compensation voltage Vcomp is generated prior to load transients to directly adjust the gate state of the power transistor, enabling predictive compensation for dynamic load changes. LTspice simulation results demonstrate that the proposed scheme reduces the output ripple amplitude caused by a dynamic load (0.2 A step current with a 30 ns edge time) from 7.2 mV to 0.36 mV, achieving a reduction of 26 dB. Experimental verification shows that under a 5V output voltage and an actual dynamic load (50 Ω step), the peak-to-peak ripple is significantly reduced from 10.64 mV to 2.64 mV (a decrease of approximately 12 dB). The stability of the output voltage is notably improved, with the undershoot settling time shortened from 2.5 μs to within 300 ns and the overshoot settling time optimized from 7 μs to below 500 ns. Theoretical analysis indicates that as the matching accuracy of the compensation voltage increases, the system’s steady-state time can further approach zero. This study provides a new approach for the design of high-performance LDOs, particularly suitable for power noise suppression in high-speed data converters and precision sensing systems.

关键词： Dynamic response Regulators Voltage measurement Voltage fluctuations Fluctuations Gyroscopes Voltage control Transient analysis Feedforward systems Fiber optics

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：