检索结果-内蒙古大学图书馆

Multivariate Molten Iron Quality Modeling Based on Improved Incremental Random Vector Functional-link Networks

IFAC-PapersOnLine 2018年第21期51卷 290-294页

作者： Jiang, Y. Zhou, P. Yu, G. The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102628 China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing102628 China

Aiming at the problems that the model structure is complex and the training time is too long for traditional incremental random vector functional-link networks (I-RVFLNs), this paper proposes an improved incremental random vector functional-link networks (Improved I-RVFLNs). Compared with the traditional I-RVFLNs, this algorithm changes the mode of constructing network. First, the number of hidden layer nodes is fixed in advance, and then the output weights of all nodes are changed in sequence. Finally, based on the actual data of a large blast furnace in Southern China, a nonlinear auto-regressive exogenous (NARX) model of multivariate molten iron quality (MIQ) is established by using the improved I-RVFLNs, and then it is compared with other modeling algorithms. The results show that compared with other quality modeling algorithms, the proposed method not only has higher model accuracy and shorter test time, but also solves the problem that the number of optimal hidden layer nodes in the conventional RVFLNs algorithm is difficult to choose, and the network is too complicated due to too many hidden nodes in the traditional I-RVFLNs. © 2018

关键词： Blast furnaces Iron Vectors Blast furnace iron making Data driven model Functional link network Molten iron NARX modeling

来源：评论

学校读者我要写书评

暂无评论

A time-delay analysis method for the variables of grinding process

引用

IFAC-PapersOnLine 2018年第21期51卷 88-93页

作者： Yu, Gang Zhou, Junwu Wang, Qingkai Zhao, Jianjun Department of IT & Automation BGRIMM Technology Group Beijing102600 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China Beijing Key Laboratory of Automation of Mining and Metallurgy Process Beijing102600 China

Data based expert knowledge mining is very important for intelligent and optimal grinding process control. However, the original process data includes noise, and there is a certain time delay between the variables of grinding process. These factors bring some difficulties to the extraction of expert knowledge based on data analysis. To solve this problem, a method of combining wavelet de-noising with cross-correlation is proposed for the time-delay analysis of variables in grinding process. The case study on the grinding process shows the effectiveness of the proposed method. © 2018

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Combining Active Learning and Fisher Discriminant Analysis for the Semi-supervised process Monitoring

引用

IFAC-PapersOnLine 2018年第21期51卷 147-151页

作者： Yin, Lili Wang, Huangang Fan, Wenhui Zhou, Junwu Yu, Gang Department of Automation Tsinghua University Beijing100084 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China Beijing Key Laboratory of Automation of Mining and Metallurgy Process Beijing102600 China

Fault detection and fault classification are two extremely important parts in process monitoring. However, obtaining the true labels of the industrial data is often time-consuming and expensive in practice, which brings great difficulties to the fault classification. To solve this problem, a new semi-supervised fault classification method is proposed, which combines the active learning and fisher discriminant analysis (FDA). The limited capacity of FDA can be effectively improved by integrating the active learning for semi-supervised fault classification. The experiments on the Benchmark of Tennessee Eastman process (TEP) prove the effectiveness of the proposed method. © 2018

关键词： Semi-supervised learning Discriminant analysis Fault detection Fisher information matrix process control process monitoring Active Learning Fault classification Fisher discriminant analysis In process monitoring Industrial datum Limited capacity Semi supervised Tennessee Eastman process

来源：评论

学校读者我要写书评

暂无评论

Selective Ensemble Least Square Support Vector Machine with Its Application

引用

IFAC-PapersOnLine 2018年第18期51卷 631-636页

作者： Tang, J. Qiao, J.F. Liu, Z. Wu, Z.W. Zhou, X.J. Yu, G. Zhao, J.J. Faculty of Information Technology Beijing University of Technology Beijing China State Key Laboratory of Synthetical Automation for Process Industries Northeaster University Shenyang110004 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

Kernel-based modeling methods have been used widely to estimate some difficulty-to-measure quality or efficient indices at different industrial applications. Least square support vector machine (LSSVM) is one of the popular ones. However, its learning parameters, i.e., kernel parameter and regularization parameter, are sensitive to the training data and the model's prediction performance. Ensemble modeling method can improve the generalization performance and reliability of the soft measuring model. Aim at these problems, a new adaptive selective ensemble (SEN) LSSVM (SEN-LSSVM) algorithm is proposed by using multiple learning parameters. Candidate regularization parameters and candidate kernel parameters are used to construct many of candidate sub-sub-models based on LSSVM. These sub-sub-models based on the same kernel parameter are selected and combined as candidate SEN-sub-models by using branch and bound-based SEN (BBSEN). By employing BBSEN at the second time, these SEN-sub-models based on different kernel parameters are used to obtain the final soft measuring model. Thus, multiple kernel and regularization parameters are adaptive selected for building SEN-LSSVM model. UCI benchmark datasets and mechanical frequency spectral data are used to validate the effectiveness of this method. © 2018

关键词： Learning systems Parameterization Support vector machines Generalization performance Learning parameters Least square support vector machines Mechanical frequency Prediction performance Regularization parameters Selective ensemble modeling soft measuring

来源：评论

学校读者我要写书评

暂无评论

Mill Load Parameter Forecasting Based on Multi-source Single-scale Mechanical Frequency Spectral Multiple feature Subsets

引用

IFAC-PapersOnLine 2018年第21期51卷 53-58页

作者： Tang, J. Qiao, J.F. Liu, Z. Zhou, Z.X.J. Yu, G. Zhao, J.J. Faculty of Information Technology Beijing University of Technology Beijing China State Key Laboratory of Synthetical Automation for Process Industries Northeaster University Shenyang110004 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

Multi-source mechanical signals at different locations of the ball mill system have different contributions for constructing mill load parameter forecasting (MLPF) model. It is necessary to select suitable multi-source mechanical signals and their frequency spectral feature subsets. Aim at these problems, a new MLPF approach based on LASSO algorithm and selective ensemble (SEN) modeling strategy by using multi-source single-scale mechanical frequency spectrum is proposed. At first, Fast Fourier transformer (FFT) is used to obtain single-scale frequency spectrum of these multi-source (channel) mechanical signals. Then, SEN-LASSO modeling approach based on candidate regularization parameter set is used to obtain single-scale frequency spectral feature subsets and to build single-channel SEN MLPF model jointly. Finally, SEN strategy is employed again to construct the final MLPF model by selecting and combining these single-channel SEN MLPF models. Simulation results based on a laboratory-scale ball mill validate effectiveness of this approach. © 2018

关键词： Ball mills Feature extraction Forecasting Regression analysis Spectroscopy Frequency spectra Measuring model Mechanical frequency Mechanical signals Mill loads Regularization parameters Selective ensemble modeling Selective ensembles

来源：评论

学校读者我要写书评

暂无评论

process Modelling and Univariate Analysis of Comminution Circuits

引用

IFAC-PapersOnLine 2018年第21期51卷 19-23页

作者： Song, T. Yang, T.H. Zhou, J.W. Wang, Q.K. BGRIMM Technology Group Beijing100160 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing100160 China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing100160 China

BGRIMM Technology Group developed a process simulation software to mass balance, model fit and simulate crushing, grinding and classification circuits. This paper presents the structure and some modelling method details of the simulation tool. An industrial grinding and classification circuit was modelled, and the modelling parameters were verified by plant survey data. Then the model predicted the effects on the circuit of changing operating conditions and feed ore hardness. Univariate analysis of the comminution circuit for water feed to SAG mill, water feed to sump, the rolling speed of SAG mill and the percentage of ball filling in SAG mill was put into practice based on the simulation results. And the results of analysis were set as the knowledge library for the comminution circuit expert control strategy. © 2018

关键词： Grinding (comminution)

来源：评论

学校读者我要写书评

暂无评论

Estimation of copper concentrate grade for copper flotation

引用

IFAC-PapersOnLine 2018年第21期51卷 94-98页

作者： Yan, Hao Wang, Qingkai Wang, Zhiqiang Wang, Xu Yu, Feng College of Information Science and Engineering Northeastern University Shenyang110819 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China Beijing Key Laboratory of Automation of Mining and Metallurgy Process Beijing102600 China

This paper develops a comparative study based on several modeling methods for estimating the copper concentrate grade in the copper flotation process. Back propagation neural network (BPNN) method, partial least squares (PLS) method, just-in-time learning partial least squares (JIT-PLS) method, adaptive-PLS method and window-adaptive-PLS method are proposed respectively. The prediction effects and test errors of these modeling methods are compared and analysed by using the measurement data of copper grade from X fluorescent grade analyzer in the dressing plant. The result is that window adaptive partial least squares method is the most accurate method, which can accurately predict the copper concentrate grade of the next measurement period in advance and can be used to guide operations. © 2018

关键词： Least squares approximations Backpropagation Copper Copper metallurgy Copper smelting Estimation Flotation Just in time production Models Back propagation neural networks Comparative studies Copper concentrates Copper flotation Just in time learning Measurement data Partial least square (PLS) Partial least squares method

来源：评论

学校读者我要写书评

暂无评论

Single-mode Sub-signal Selection Method Based on VMD and Predic Performance for Multi-component Mechanical Signal 39

Single-mode Sub-signal Selection Method Based on VMD and Pre...

引用

39th Chinese Control Conference, CCC 2020

作者： Tang, Jian Zhu, Hongjuan Li, Dong Zhang, Jian Yu, Gang Beijing University of Technology Faculty of Information Technology Beijing100124 China Pla Navy Beijing100129 China Joint Staff of the Central Military Commission 55th Institute Beijing100128 China Nanjing University of Information Science and Technology College of Computer and Software Nanjing210044 China State Beijing Key Laboratory of Process Automation in Mining Metallurgy Beijing100160 China

ISBN: (纸本)9789881563903

The mapping relationship between the mill load and the multi-component mechanical signals generated by the ball mill of the mineral grinding process is non-deterministic and complex. With the inherent filtering function of the human ear, the operating expert can effectively estimate the mill load and its internal parameters for their familiar mill in the actual industrial process. In order to obtain multiple single-mode sub-signals with physical meaning and complementary characteristic, this paper proposes a single-mode sub-signal selection method based on variational modal decomposition (VMD) and predictive performance. At first, based on prior knowledge, the value of decomposition layers required to perform VMD is determined. Then, VMD is used to decompose the original mechanical signal into multiple time-domain single-mode sub-signals with different bandwidths and time scales, and further are transformed to the frequency domain to obtain candidate single-mode sub-signal frequency spectrum. Finally, based on these candidate spectral data, a serial of candidate sub-models for mill load parameter prediction are constructed, and a series of selective ensemble models are built for obtaining reduced single-mode sub-signal frequency spectrum, The final single-mode sub-signals with the biggest complementary characteristics are selected based on the practical requirement. The effectiveness of the method is demonstrated by comparative experiment simulations based on the shell vibration signal of a laboratory-scale ball mill. © 2020 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Operating performance assessment for industrial process with hybrid qualitative and quantitative information using modified fuzzy probabilistic rough set

Operating performance assessment for industrial process with...

引用

Chinese automation Congress (CAC)

作者： Xiaoyu Zou Fuli Wang Yuqing Chang Jie Pan School of Mechatronic Engineering China University of Mining and Technology Xuzhou China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China College of Information Science & Engineering Northeastern University Shenyang China School of Information and Control Engineering Xuzhou China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Since satisfactory operating performance helps guarantee high comprehensive economic benefit under normal working condition for industrial processes, it is crucial to conduct accurate performance assessment on the degree of optimality for modern industry. process online assessment judges how well the process is working. However, the coexistence of the qualitative and quantitative information renders the conventional performance assessment approaches inappropriate. To solve the above problem, a modified version of fuzzy probabilistic rough set (FPRS) is proposed for performance assessment in this research. The modified FPRS is employed to establish a valid online assessment strategy of operating performance for complicated industrial processes with the coexistence of both the qualitative and quantitative information. The proposed technique is finally validated by a gold hydrometallurgy process.

关键词： Rough sets Probabilistic logic Uncertainty Production process control Indexes Gold

来源：评论

学校读者我要写书评

暂无评论

Single-mode Sub-signal Selection Method Based on VMD and Prediction Performance for Multi-component Mechanical Signal

Single-mode Sub-signal Selection Method Based on VMD and Pre...

引用

第三十九届中国控制会议

作者： Jian Tang Hongjuan Zhu Dong Li Jian Zhang Gang Yu Faculty of Information Technology Beijing University of Technology PLA Navy 55th Institute Joint staff of the Central Military Commission College of computer and software Nanjing University of Information Science and Technology State (Beijing) Key Laboratory of Process Automation in Mining & Metallurgy

The mapping relationship between the mill load and the multi-component mechanical signals generated by the ball mill of the mineral grinding process is non-deterministic and complex. With the inherent filtering function of the human ear, the operating expert can effectively estimate the mill load and its internal parameters for their familiar mill in the actual industrial process. In order to obtain multiple single-mode sub-signals with physical meaning and complementary characteristic, this paper proposes a single-mode sub-signal selection method based on variational modal decomposition（VMD） and predictive performance. At first, based on prior knowledge, the value of decomposition layers required to perform VMD is determined. Then, VMD is used to decompose the original mechanical signal into multiple time-domain single-mode sub-signals with different bandwidths and time scales, and further are transformed to the frequency domain to obtain candidate single-mode sub-signal frequency spectrum. Finally, based on these candidate spectral data, a serial of candidate sub-models for mill load parameter prediction are constructed, and a series of selective ensemble models are built for obtaining reduced single-mode sub-signal frequency spectrum, The final single-mode sub-signals with the biggest complementary characteristics are selected based on the practical requirement. The effectiveness of the method is demonstrated by comparative experiment simulations based on the shell vibration signal of a laboratory-scale ball mill.

关键词： Variational modal decomposition（VMD） decomposition layer single-mode sub-signal prediction performance

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：