检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2022年第1期23卷 14032-14081页

作者： Tenghui Li Guoxu Zhou Yuning Qiu Qibin Zhao School of Automation Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangdong University of Technology Guangzhou China School of Automation Key Laboratory of Intelligent Detection and The IoT in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou China Guangdong Key Laboratory of IoT Information Technology Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou China RIKEN Center for Advanced Intelligence Project Tokyo Japan and School of Automation Guangdong University of Technology Guangzhou China

We make an attempt to understand convolutional neural network by exploring the relationship between (deep) convolutional neural networks and Volterra convolutions. We propose a novel approach to explain and study the overall characteristics of neural networks without being disturbed by the horribly complex architectures. Specifically, we attempt to convert the basic structures of a convolutional neural network (CNN) and their combinations to the form of Volterra convolutions. The results show that most of convolutional neural networks can be approximated in the form of Volterra convolution, where the approximated proxy kernels preserve the characteristics of the original network. Analyzing these proxy kernels may give valuable insight about the original network. Based on this setup, we present methods to approximate the order-zero and order-one proxy kernels, and verify the correctness and effectiveness of our results.

关键词： convolutional neural network Volterra convolution order-n convolution unified neural network proxy kernel

来源：评论

学校读者我要写书评

暂无评论

Optimization of Extreme Learning Machine Based on Improved Beetle Antennae Search for Slot Die Coating Prediction

Optimization of Extreme Learning Machine Based on Improved B...

引用

第35届中国控制与决策会议

作者： Haonan Yang Ding Liu Jun-Chao Ren Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology

In the actual production of slot die coating,the minimum coating thickness and the maximum substrate moving speed could only be judged by production experience,and there was no accurate prediction model due to the nonlinear characteristics of fluid ***,building a reasonable and efficient prediction model for slot die coating is now an urgent and challenging *** this paper,an optimized extreme learning machine(ELM) based on improved beetle antennae search(IBAS) algorithm is proposed for slot die coating *** optimized ELM model can well learn the nonlinear characteristics of the system and make accurate predictions,thus solving the traditional inaccurate empirical *** the prediction accuracy of ELM depends on the selection of weights and biases,the IBAS optimization algorithm is used to quickly search for the optimal value of weights and biases in the ELM *** algorithm improves the generation mechanism of antennae on the basis of the original algorithm,so that the algorithm can converge *** the same time,the search strategy of the algorithm is improved to avoid falling into the local optimal *** predicting the production data of slit coating,the feasibility and effectiveness of IBAS-ELM model are proved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Support Vector Regression Modeling based Data-Driven Iterative Learning Control for Czochralski Crystal Growth Process

Support Vector Regression Modeling based Data-Driven Iterati...

引用

第三十八届中国控制会议

作者： Junchao Ren Ding Liu Yin Wan Ni Zhang National & Local Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

In view of the previous Czochralski(Cz) monocrystalline silicon growth control method based on mechanism model, it is difficult to accurately reflect the nonlinear and real-time variation characteristics of crystal growth process. This paper proposes a data-driven iterative learning control method based on support vector regression, which combines crystal diameter prediction model by support vector regression(SVR) off-line training with crystal growth mechanism model, and then control the crystal diameter and output key variable information in the framework of iterative learning algorithm. Simulation results for diameter control of crystal growth process and the analysis of key variable information show that the proposed method is effective and has a fast crystal diameter learning speed, and good performances of setpoint tracking and disturbance rejection, high crystal growth speed.

关键词： Data-Driven Czochralski Monocrystalline Silicon Support Vector Regression Iterative Learning Control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sparse Coding-Based Value Estimation Network for Deep Reinforcement Learning

SSRN

引用

SSRN 2023年

作者： Zhao, Haoli Li, Zhenni Su, Wensheng Xie, Shengli School of Automation Guangdong University of Technology Guangzhou510006 China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology GDUT Guangzhou510006 China Key Laboratory of Intelligent Detection The Internet of Things in Manufacturing GDUT Ministry of Education Guangzhou510006 China Key Laboratory of Intelligent Information Processing and System Integration of IoT GDUT Ministry of Education Guangzhou510006 China

Deep Reinforcement Learning (DRL) is one powerful tool for varied control automation problems. Performances of DRL highly depend on the accuracy of value estimation for states from environments. However, the Value Estimation Network (VEN) in DRL can be easily influenced by the phenomenon of catastrophic interference from environments and training, and moreover, the efficiency of DRL is restricted by the training with redundant parameters. In this paper, we propose a Dynamic Sparse Coding-based (DSC) DRL model to obtain precise sparse representations and sparse parameters in VEN through training, i.e., DSC-VEN, to improve the control performance, which is not only applicable in Q-learning but also in actor-critic structured DRL. In detail, to alleviate interference in VEN, we propose to employ dynamic sparse coding to learn sparse representations for accurate value estimation with a dynamic sparsity regularizer. To avoid influences from redundant parameters, we employ dynamic sparse coding to prune weights with dynamic thresholds. Therefore, we develop a dynamic sparse coding-based VEN algorithm, which can improve control performances not only for Q-learning structured discrete-action DRL but also actor-critic structured continuous-action DRL. We have validated the proposed DSC-VEN in both discrete and continuous action benchmark environments. Experiments demonstrate that the proposed algorithms with dynamic sparse coding can obtain higher control performances than existing benchmark DRL algorithms in both discrete-action and continuous-action environments, e.g., over 25% increase in Puddle World and about 10% increase in Hopper. Moreover, the proposed algorithm can reach convergence efficiently with fewer episodes in different environments. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Non-Fourier Heat Conduction based on Self-Adaptive Weight Physics-Informed Neural Networks

Non-Fourier Heat Conduction based on Self-Adaptive Weight Ph...

引用

第40届中国控制会议

作者： Shuyan Shi Ding Liu Zhongdan Zhao National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shananxi Key Laboratory of Complex System Control and Intelligent Information Processing

This paper establishes the non-Fourier heat conduction model to describe the heat transfer process of mono-crystalline silicon under the condition of unstable thermal field and thermal shock in the Czochralski method.A novel differential equations solver called Physics-Informed Neural Networks（PINN） algorithm was *** with finite element method（FEM）,this method has some advantages like no grid requirement and easily *** order to deal with the unbalance of constraint condition and speed up the convergence,we propose a novel method called Self-Adaptive Weight Physics-Informed Neural Networks（SWPINN）.The comparison of the experimental results of SWPINN and COMSOL verifies the effectiveness of *** modifying the parameter of non-Fourier heat conduction model,this paper obtains the temperature distribution under different heat relaxation ***,comparison between SWPINN and PINN shows that the proposed method has faster convergence speed and higher accuracy.

关键词： Non-Fourier Heat Conduction Physics-Informed Neural Networks Partial Differential Equation Monocrystalline Silicon Czochralski Method

来源：评论

学校读者我要写书评

暂无评论

Diameter Detection of Silicon Single Crystal Based on Brain Storm Optimization Algorithm Hough Transform

Diameter Detection of Silicon Single Crystal Based on Brain ...

引用

第三十八届中国控制会议

作者： Lu Kang Ding Liu National and Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

In order to improve the speed and accuracy of silicon single crystal diameter detection, this paper proposes an ellipse detection method based on brain storm optimization algorithm Hough transform, this method uses brain storm optimization algorithm to search ellipse parameters that make the accumulator obtains the maximum value after using Hough transform, then the accurate measurement value of silicon single crystal diameter is obtained. The proposed algorithm is simulated on the complete ellipse with Gaussian white noise and silicon single crystal diameter detection engineering experiments, and the results are compared with other intelligent optimization algorithms. Experimental results show that the proposed algorithm can effectively improve the speed and accuracy of ellipse detection with Hough transform, thereby verify the feasibility and effectiveness of the proposed algorithm, and improve the speed and accuracy of silicon single crystal diameter detection.

关键词： Silicon single crystal Diameter detection Ellipse detection Brain storm optimization algorithm Hough transform

来源：评论

学校读者我要写书评

暂无评论

Silicon Melt Liquid Level Detection Based on Improved Laser Trigonometry

Silicon Melt Liquid Level Detection Based on Improved Laser ...

引用

第37届中国控制会议

作者： Xinyu Zhang Ding Liu Simi Wang Xiaoguo Zhao Lei Jiang National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

In order to improve the robustness of laser triangulation to detect the liquid level of silicon melt, this paper firstly proposes a method of calculating the laser spot coordinates based on the voting mechanism. The vote is taken according to the coordinates of small laser spots, which are formed by the effect of liquid surface fluctuation on the line laser in the liquid level measurement image. Secondly, the Kalman filter method is used to correct the liquid level measurement data and compensate the missing data. Then the linear conversion is performed to obtain the liquid level value. Finally, the experimental results show that this method can effectively improve the robustness of the liquid level measurement by the laser triangulation method, and avoid the generation of impulse noise. The introduction of the Kalman filter can accurately correct the level measurement data and compensate for missing data.

关键词： Single crystal furnace Liquid level detection Coordinate calculation Voting mechanism Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Distributed MPC Algorithm for Linear Discrete systems with Communication Noise

Distributed MPC Algorithm for Linear Discrete Systems with C...

引用

第40届中国控制会议

作者： Duqiao Zhao Ding Liu Linxiong Liu Xia Zhang National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xian University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

In this paper, a distributed MPC algorithm is proposed for linear discrete systems with bounded communication noise and random communication failure. Based on the characteristics of time-varying directed graphs, the convergence of the algorithm is analyzed in the case of communication noise and random communication failure. This algorithm uses the distributed projection dual subgradient algorithm to solve the dual problem and replaces the double stochastic condition of the traditional algorithm with row stochastic condition. The exponential stability of the system is guaranteed. Finally, an example is given to illustrate the performance of the algorithm.

关键词： Distributed MPC Bounded Communication Noise Random Communication Faults Distributed Projection Dual Subgradient Row Stochastic

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Algorithm for Distributed Multi-agent Convex Optimization

Asynchronous Algorithm for Distributed Multi-agent Convex Op...

引用

第三十九届中国控制会议

作者： Duqiao Zhao Ding Liu Xia Zhang National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

This paper proposes an asynchronous algorithm for distributed optimization problem(Asy-DOP) in multi-agent network with gradient *** algorithm can be implemented in an asynchronous distributed *** objective function of the algorithm is the sum of the local functions of multiple nodes in the network,each node only knows its own local objective function and can exchange information with its *** addition,the algorithm is based on the undirected connected graph and requires the objective function is Lipschitz *** step-size of the proposed algorithm is homogeneous and when the step-size is in a suitable range,it is proved that the convergence rate of the proposed algorithm is O(1/(?)),where the k is the number of iterations.

关键词： asynchronous algorithm distributed optimization multi-agent gradient method

来源：评论

学校读者我要写书评

暂无评论

Research on Algorithm for Model Predictive Control Based on Robust Optimizition

Research on Algorithm for Model Predictive Control Based on ...

引用

第三十八届中国控制会议

作者： Xia Zhang Ding Liu Fei Yu National and Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xian University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

The practicality of model predictive control(MPC) is partially limited by its ability to solve optimization problems in real time. The robust model prediction algorithm based on linear matrix inequality is divided into online and offline parts. In order to improve the response speed and control precision of the system, the upper bound of the objective function obtained by the off-line algorithm is taken as a known quantity, and a series of large asymptotically stable invariant elliptic sets are obtained by re-optimization. The state variables can be determined-lying between two ellipsoid sets within the ellipsoid set sequence, on the basis of online measured state variables. By adding an adjacent small ellipse set, the state variables are precisely located by three ellipse sets optimization, and the system control quantity is obtained. The simulation results show that this algorithm is better than the traditional algorithm. Finally, this algorithm is applied to identify parameters of silicon single crystal thermal field temperature model and the simulation results prove its excellent ability of parameters identification.

关键词： Robust optimization Model predictive control Uncertainty Online optimization

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：