检索结果-内蒙古大学图书馆

A denoising shrinkage stacked autoencoder method for fault detection in industrial beneficiation ILAB process with uncertainty

引用

Measurement 2025年 256卷

作者： Wei Zhang Yunpeng Gao Yongbin Zhou Fei Teng Haili Zhao Jianjun Zhao Department of College of Electrical and Information Engineering Hunan University Lushan South Road Changsha 410012 China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing 102628 China BGRIMM Technology Group West South Fourth Ring Road Beijing 102628 China

The intelligent laboratory (ILAB) is used in industrial beneficiation processes to replace manual laboratory testing and enhance quality control. Fault detection is crucial for ensuring reliable operation. However, uncertainties in sampling, preparation, measurement, and environmental conditions degrade fault detection performance. Conventional methods for uncertainty-aware fault detection typically assume the same level of uncertainty for all variables, which oversimplifies the complexity of real industrial processes. In real industrial processes, uncertainties are interrelated, and considering them in isolation does not accurately reflect the true state of the system. To address this issue, a denoising shrinkage stacked autoencoder (DSSAE) fault detection method is proposed. First, a combined uncertainty degree is constructed to accurately represent uncertainty by integrating multiple sources such as sampling, preparation, measurement, and acid corrosion aging. Second, the shrinking blocks embedded in the stacked autoencoder adaptively adjust the thresholds using a soft thresholding mechanism to set near-zero feature values to zero, reducing irrelevant features layer by layer while enhancing important features. Third, the redefined loss function constrains the reconstruction error within an allowable range, which reduces the sensitivity of uncertainty and prevents overfitting to uncertain data. The proposed method is validated on the benchmark Tennessee Eastman (TE) process, industrial beneficiation ILAB process, and wastewater treatment plant (WWTP) process. Experimental results show that the proposed method exhibits good comprehensive performance.

关键词： Combined uncertainty degree Denoising shrinkage stacked autoencoder (DSSAE) Fault detection Industrial beneficiation process Intelligent laboratory (ILAB)

来源：评论

学校读者我要写书评

暂无评论

Efficient Ensemble Broad Learning System Based on Dropout and Dropconnect

引用

The International Journal of Intelligent control and Systems 2024年第2期29卷 79-87页

作者： Yiwan Cao Fei Chu Shuai Li C.L.Philip Chen Jun Fu School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110004China

Broad learning system(BLS)is an emerging neural network characterized by its rapid processing and robust generalization ***,determining the appropriate structure for broad learning system is also a *** addition,broad learning system may perform overfitting due to the dependence between nodes in processing fully connected *** deal with these problems,an efficient ensemble broad learning system based on Dropout and Dropconnect is proposed in this *** proposed Dropout ensemble broad learning system randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction *** Dropconnect ensemble broad learning system randomly drops connection weights to generate more complementary models by adding input attribute *** experimental results on the UCI datasets confirm that the method proposed in this paper can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning *** proposed algorithm outperforms the original BLS in terms of prediction stability and classification accuracy.

关键词： Broad learning system ensemble learning Dropout Dropconnect

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

Gas-solid flow characteristics in downstream reactor

引用

Powder technology 2025年 464卷

作者： Zhiming Li Yuexin Han Yongsheng Sun Peng Gao Zhidong Tang Chuanwei Li School of Resources and Civil Engineering Northeastern University Shenyang 110819 PR China National-local Joint Engineering Research Center of High-efficient Exploitation Technology for Refractory Iron Ore Resources Shenyang 110819 PR China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing 100160 PR China

Gas-solid flow is the basic condition for the reactor to achieve its functions. This article conducted cold state experiments on a Single-layer Downstream Reactor, based on which, the gas-solid flow characteristics inside the reaction chamber were revealed and analyzed. The results indicate that the occurrence of an “inflection point” in the bed pressure drop pulsation signal is a key characteristic to achieve bed flow; The particle concentration in the feed end, middle area, and discharge end of the reaction chamber decreases sequentially. Compared to simple fluidization, the energy concentration frequency domain under gas-solid flow expands to 0–3.5 Hz. The apparent particle concentration in the reactor increases with the increase of feed rate and decreases with the increase of fluidization gas velocity. This study reveals the gas-solid flow behavior in downstream reactor, which has certain guiding significance for the process control of Downstream Hydrogen Mineral Phase Transformation Equipment.

关键词：

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

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

Mechanical Frequency Spectrum Sub-band Feature Estimation Based on Multiple Types Correlation Analysis

Mechanical Frequency Spectrum Sub-band Feature Estimation Ba...

引用

第三十九届中国控制会议

作者： Jian Tang Meiying Jia Fupeng Wang Jian Zhang Gang Yu Faculty of Information Technology Beijing University of Technology 55th Institute Joint staff of the Central Military Commission 91411 Unit PLA College of computer and software Nanjing University of Information Science and Technology State Key Laboratory of Process Automation in Mining & Metallurgy

Mill load is one of the key factors that affects the operation optimization and control of grinding process. It is difficult to detect accurately in real time. The mill load relates to multiple channel mechanical signals, such as the mill shell vibration signals, the shaft seat front and rear vibration signals, the acoustic signals near to the shell surface and under the grinding area, *** to evaluate these sub-band feature of the mechanical spectrum of the above channels is a difficult problem. It can help to clarify the ball mill grinding mechanism and the mechanical signal generation mechanism. To solve these problems, this paper proposes a multi-channel mechanical frequency spectrum sub-band feature evaluation method based on multiple types correlation analysis. Firstly, the multi-channel mechanical signals are transformed from time domain to frequency domain to obtain the frequency spectrum data, which are divided into several sub-bands to extract features. Then, the normalized correlation coefficients between the multi-channel sub-band feature and the mill load are calculated. Thirdly, based on the partial least square algorithm, the variable projection importance（VIP） value of sub-band features are also calculated. The VIPs are normalized same as that of correlation coefficient. Finally, a new index is calculated by using normalized correlation coefficient and VIP value and the model’s prediction performance. These sub-band features of single channel and all channel mechanical signals are measured based on the new defined combined evaluation index. The multi-channel mechanical signals of a laboratory-scale ball mill are used to verify the effectiveness of the proposed method.

关键词： Multiple channel mechanical signals mechanical frequency spectrum sub-band features correlation coefficient variable projection importance（VIP）

来源：评论

学校读者我要写书评

暂无评论

Mechanical Frequency Spectrum Sub-band Feature Estimation Based on Multiple Types Correlation Analysis

Mechanical Frequency Spectrum Sub-band Feature Estimation Ba...

引用

Chinese control Conference (CCC)

作者： Jian Tang Meiying Jia Fupeng Wang Jian Zhang Gang Yu Faculty of Information Technology Beijing University of Technology Beijing China Joint staff of the Central Military Commission 55th Institute Beijing China 91411 Unit PLA Dalian China College of computer and software Nanjing University of Information Science and Technology Nanjing China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

Mill load is one of the key factors that affects the operation optimization and control of grinding process. It is difficult to detect accurately in real time. The mill load relates to multiple channel mechanical signals, such as the mill shell vibration signals, the shaft seat front and rear vibration signals, the acoustic signals near to the shell surface and under the grinding area, etc. How to evaluate these sub-band feature of the mechanical spectrum of the above channels is a difficult problem. It can help to clarify the ball mill grinding mechanism and the mechanical signal generation mechanism. To solve these problems, this paper proposes a multi-channel mechanical frequency spectrum sub-band feature evaluation method based on multiple types correlation analysis. Firstly, the multi-channel mechanical signals are transformed from time domain to frequency domain to obtain the frequency spectrum data, which are divided into several sub-bands to extract features. Then, the normalized correlation coefficients between the multi-channel sub-band feature and the mill load are calculated. Thirdly, based on the partial least square algorithm, the variable projection importance (VIP) value of sub-band features are also calculated. The VIPs are normalized same as that of correlation coefficient. Finally, a new index is calculated by using normalized correlation coefficient and VIP value and the model's prediction performance. These sub-band features of single channel and all channel mechanical signals are measured based on the new defined combined evaluation index. The multi-channel mechanical signals of a laboratory-scale ball mill are used to verify the effectiveness of the proposed method.

关键词： Vibrations Feature extraction Correlation coefficient Shafts Acoustics Electronic mail Frequency-domain analysis

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

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

引用

Chinese control Conference (CCC)

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

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

关键词： Vibrations Time-domain analysis Predictive models Time-frequency analysis Prediction algorithms Electronic mail Minerals

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：