检索结果-内蒙古大学图书馆

Chinese Control and Decision Conference, CCDC

作者： Jian Zhang Jianbo Yu Gang Yu Rongcheng Sun Jian Tang School of Computer Science Nanjing University of Information Science & Technology Nanjing China NUIST-TianChang Research Institute Nanjing University of Information Science & Technology Nanjing China State & Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The municipal solid waste incineration has great advantages for resource recovery and utilization, and the stability of its combustion state is of great significance to the control process. However, the problem of low accuracy still exists in the classification of the images of municipal solid waste incineration (MSWI). For this reason, this paper proposes an image classification algorithm for MSWI based on attention module. The framework of ResNet is employed to improve the depth and accuracy of the network, which solves the problem of insufficient depth of the traditional network while suffering from the deficiency of slow convergence speed. Consequently, the attention module is embedded to solve the problem of different importance of different parts in the incineration flame image. The results show that the algorithm improves the recognition accuracy of municipal solid waste incineration flame images to 96.7%, and the convergence speed is significantly improved compared to other basic neural network models.

关键词： Waste management Training Waste materials Accuracy Image recognition Incineration Fires

来源：评论

学校读者我要写书评

暂无评论

An improved normalized mutual information variable selection algorithm for neural networks 3

An improved normalized mutual information variable selection...

引用

3rd IEEE International Conference on Electronic Information Technology and Computer Engineering, EITCE 2019

作者： Tian, Pengxin Wu, Hao Wang, Hongxun Sun, Kai School of Electrical Engineering and Automation Jinan China State Key Laboratory of Process Automation in Mining and Metallurgy Ganization Beijing China Beijing Key Laboratory of Process Automation in Mining and Metallurgy Beijing China

ISBN: (纸本)9781728135847

In this paper, normalized mutual information feature selection (NMIFS) and tabu search (TS) are integrated to develop a new variable selection algorithm for neural networks. NMIFS is applied to select influential variables that contribute to the output variable, and avoids selecting redundant variables by calculating mutual information. TS based strategy is designed to prevent NMIFS from falling into local optimal situation. The proposed algorithm performs the variable selection by combining entropy information, mutual information, and validating error information of neural networks. Therefore, the algorithm proposed in this paper has more advantages than previous mutual information based variable selection algorithms. Several simulation datasets with different scale, correlation and noise are implemented to compare the performance of the proposed algorithm with several classical algorithms. The experiments show that developed algorithm present better model accuracy with fewer variables selected, compared to other state-of-art methods. © 2019 IEEE.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

Condition Identification of Copper Flotation process based on Foam Image and VGG16 Network

Condition Identification of Copper Flotation Process based o...

引用

第33届中国控制与决策会议

作者： Zhiqiang Wang Qiang Li Xu Wang Dakuo He Xiang Ma School of Information Science and Engineering Northeastern University Beijing Key Laboratory of Automation of Mining and Metallurgy Process State Key Laboratory of Synthetical Automation for Process Industries Northeastern University SINTEF Industry

In the flotation process,the foam in the flotation tank can reflect the characteristic information of the flotation condition *** on the characteristic information of the foam,the identification of working conditions and the operational optimization can be carried *** this paper,the research on image processing and working condition recognition based on deep learning is ***,the flotation foam image is preprocessed through the gray scale,image size processing and filtering ***,the neural network visual geometry group(VGG) is built and trained to realize the recognition of flotation foam image *** VGG16 network is based on the Sequential model in the Keras *** main structure of the network consists of 13 convolutional layers,5 pooling layers and 3 fully connected *** VGG16 data set is a collection of 43,800 foam images under six conditions,dividing the data set into a training set,a validation set,and a test ***,the VGG16 network is used for image feature learning to realize six classifications of bubble images and working condition *** is verified that the proposed neural network has high precision and can be used in flotation industrial process.

关键词： copper flotation process bubble image gray scale Gaussian filtering VGG16

来源：评论

学校读者我要写书评

暂无评论

Stochastic configuration networks with robust supervised least squares regression

引用

Neurocomputing 2025年 647卷

作者： Chu, Fei Sun, Zihang Wang, Yu Zhang, Yong School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The State Key Laboratory of Process Automation in Mining and Metallurgy/Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing100160 China Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou221116 China

Stochastic Configuration Networks (SCNs) are widely used in regression modeling to fit data distributions due to their fast convergence and powerful learning capabilities. However, in practical industrial applications, labeled outliers in the dataset inevitably appear, which can destroy the internal structure and connection of the data, and not only seriously reduce the prediction accuracy of SCNs, but may also increase the risk of overfitting. To cope with this problem, this paper proposes a new algorithm - Robust Supervised Stochastic Configuration Networks (RSSCNs). In this paper, firstly, the loss function is constructed based on the concave function of the error, which extends the applicability of the robust supervised least squares regression. Second, robust supervised least squares regression is introduced into the SCN algorithm for the first time, which enhances the robustness of the model and reduces the risk of model overfitting. Finally, the inequality constraint of the SCN algorithm is reconstructed according to the loss function, which optimizes the parameter selection and accelerates the convergence of the model. In the experimental section, RSSCNs are applied to a function fitting experiment, several benchmark datasets, and an industrial dataset from a dense medium coal preparation process, and the performance is compared with other algorithms. The experimental results show that for these datasets, RSSCNs perform favorably in terms of accuracy and robustness, validating the effectiveness of the algorithm. © 2025

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Novelty Detection for Multimode process Using GANs with Learning Disentangled Representation

Novelty Detection for Multimode Process Using GANs with Lear...

引用

第32届中国控制与决策会议

作者： Daoming Li Huangang Wang Junwu Zhou Department of Automation Tsinghua University State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy

Modern industrial processes often need to switch between multiple modalities,but there is often a lack of sufficient label samples in modeling,which makes traditional data-driven novelty detection methods face many *** adversarial networks(GANs) have demonstrated excellent feature extraction and pattern description capabilities on unsupervised learning *** paper proposes a novel GAN model for multimodal novelty detection called *** can learn the multimodal distribution by maximizing the mutual information between latent category code variables and generated data,and learn disentangled representation in latent space of the original data through an auto-encoder *** mine the information from local modals structure and common modal structure,and build a global detection method integrating multimodal local *** experiments on Tennessee Eastman benchmark process verify the advantages of our method.

关键词： Generative Adversarial Network Multimode process Novelty Detection Disentangled Representation

来源：评论

学校读者我要写书评

暂无评论

Novelty Detection for Multimode process Using GANs with Learning Disentangled Representation

Novelty Detection for Multimode Process Using GANs with Lear...

引用

Chinese Control and Decision Conference, CCDC

作者： Daoming Li Huangang Wang Junwu Zhou Department of Automation Tsinghua University Beijing State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Modern industrial processes often need to switch between multiple modalities, but there is often a lack of sufficient label samples in modeling, which makes traditional data-driven novelty detection methods face many challenges. Generative adversarial networks (GANs) have demonstrated excellent feature extraction and pattern description capabilities on unsupervised learning tasks. This paper proposes a novel GAN model for multimodal novelty detection called MMNDGAN. MMNDGAN can learn the multimodal distribution by maximizing the mutual information between latent category code variables and generated data, and learn disentangled representation in latent space of the original data through an auto-encoder structure. We mine the information from local modals structure and common modal structure, and build a global detection method integrating multimodal local information. The experiments on Tennessee Eastman benchmark process verify the advantages of our method.

关键词： Gallium nitride Generators Mutual information Monitoring Data models Training Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Operating Performance Assessment of Complex Industrial process Based on Kernel Locally Linear Embedding PLS

Operating Performance Assessment of Complex Industrial Proce...

引用

第32届中国过程控制会议(CPCC2021)

作者： Chu Fei Mo Shuangshuang Wang Fuli Lu Ningyun Ma Xiaoping Research Center of Underground Space Intelligent Control Engineering of the Ministry of Education China University of Mining and Technology School of Information and Control Engineering China University of Mining and Technology State Key Laboratory of Automatic Control Technology for Mining and Metallurgy Process Beijing General Research Institute of Mining & Metallurgy State Key Laboratory of Integrated Automation for Process Industries Northeastern University College of Automation Engineering Nanjing University of Aeronautics and Astronautics

Due to the process disturbances and uncertainties,the operating performance of industrial process may deviate from the optimal operating point along with ***,non-optimal operation may lead to decline production quality and economic *** it is significant to implement online assessment strategy and further analyze the actual process operating performance,so as to make the production process in the best operating performance as far as *** process data is strongly nonlinear due to the change of system state caused by the change of machine performance or operation *** this time,the relationship between the local nearest neighbor samples is ***,the existing methods of operating performance assessment for solving nonlinear problems only focus on the global structure of data,i.e.,the variance,while ignoring the local neighborhood structure in each performance ***,a new method called kernel locally linear embedding PLS(KLLEPLS) is developed and applied for operating performance *** includes offline modeling,online evaluation and non-optimal cause *** algorithm not only has concise expression and similar analytical solutions for PLS,but also retains the original geometric structure of strongly nonlinear data when extracting the maximum correlation information between process ***,the practice and effectiveness of the proposed method are demonstrated by the dense medium coal preparation process and Tennessee Eastman(TE) process.

关键词： Complex industrial process operating performance assessment kernel locally linear embedding PLS non-optimal cause identification

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Delay Estimation Based on Dynamic Characteristic Analytics

Multivariate Time Delay Estimation Based on Dynamic Characte...

引用

第三十九届中国控制会议

作者： Xu Chen Chunhui Zhao State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining &Metallurgy

Time delay widely exists among industrial process variables, which may lead to invalid description of systems and reduce the model accuracy for soft sensor, process monitoring etc. Therefore, it is crucial to estimate time delay for improving model accuracy. In traditional research, time delay estimation（TDE） algorithm for two variables is fully investigated, but little research pays attention to multivariate. The method of pairwise comparison may not only cause high calculation complexity but also cut off the correlation between multivariate. In this work, a new TDE algorithm is proposed to estimate time delay between multivariate, which extracts dynamic latent variable to represent the process using improved dynamic inner PCA algorithm（DiPCA）. Dynamic latent variable extracts the autocorrelation and cross-correlation between process variables. Take it as a standard and analyze the time delay, so that the influence of multivariate variables could be comprehensively considered. Since there may be non-linear variables, the significant factor（SF） is used for variable selection, and the multivariate variables are divided into multiple linear subgroups, which makes the analysis result more reasonable. The effectiveness is illustrated with two numerical examples and the Tennessee Eastman process.

关键词： Time delay estimation process dynamics dynamic latent variable variable selection multivariate

来源：评论

学校读者我要写书评

暂无评论

Incremental Gaussian Mixture Model for Time-varying process Monitoring

Incremental Gaussian Mixture Model for Time-varying Process ...

引用

Data Driven Control and Learning Systems (DDCLS)

作者： Qingyang Dai Chunhui Zhao State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing

ISBN: (数字)9781728159225

ISBN: (纸本)9781728159232

With the increasing complexity of industrial production, data-driven based monitoring methods attract more attention. However, the conventional static process monitoring methods may show poor performance for the time-varying processes since they fail to track the time-varying characteristics. As Gaussian Mixture Model (GMM) has been widely used for process monitoring, this paper presents a new incremental GMM model for monitoring time-varying processes. First, an incremental GMM (IGMM) model is proposed, which can recursively update model parameters, adaptively add new Gaussian components and discard the irrelevant component based on the shifting samples online. Then the Bayesian Inference Probability (BIP) is introduced for monitoring statistics and a two-level partition strategy that can separate normal shifting samples from fault samples is proposed, which reduces the possibility of adding fault samples to the model. On the basis of IGMM model, an adaptive monitoring scheme is developed, which can track the time-varying characteristics of processes. Finally, a time-varying numerical example and the Tennessee Eastman process are adopted to validate the feasibility of the proposed monitoring model. Experimental results clearly demonstrate the adaptiveness of the monitoring model to time-varying processes and the ability to avoid false updates.

关键词： Adaptation models process monitoring Mathematical model Gaussian mixture model Numerical models Data models Production

来源：评论

学校读者我要写书评

暂无评论

Bayesian Network-based Technical Index Estimation for Industrial Flotation process under Incomplete Data

Bayesian Network-based Technical Index Estimation for Indust...

引用

第32届中国控制与决策会议

作者： Hao Yan Jin Zhu Fuli Wang Dakuo He Qingkai Wang College of Information Science and Engineering Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University State Key Laboratory of Process Automation in Mining and Metallurgy

Due to the lack of detection instruments or long measurement cycles in the industrial flotation process,accurate and real-time estimation of the technical index is of great significance for optimizing flotation performance and operational *** the real-world flotation process,incomplete data is a widespread phenomenon owing to hardware sensor failures and other *** this end,this paper proposes a Bayesian network（BN）-based concentrate grade estimation method under incomplete *** real-time froth image information and the concentrate grades of the previous periods are taken as the input of the BN model,and the current concentrate grade is the output of the BN *** expectation maximum（EM） algorithm is used to estimate the model *** application results show the proposed method can accurately estimate the concentrate grade even if some data are missing.

关键词： Industrial flotation process Bayesian network Incomplete data Concentrate grade Estimation

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：