检索结果-内蒙古大学图书馆

Stochastic configuration networks with robust supervised least squares regression

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

The Prediction Model of SAG Mill Load Based on Industrial Big-data mining

The Prediction Model of SAG Mill Load Based on Industrial Bi...

引用

第43届中国控制会议

作者： Guicheng Wang Changyu Wang Zhicheng Bai Changliang Guan Min Zhang Xiaobin Li School of Electrical and Electronics Engineering Shanghai Institute of Technology State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process and Beijing Key Laboratory of Process Automation in Mining & Metallurgy

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Regarding the modeling problem of grinding process in mining,taking the operating load of semi-automatic grinding mill as the research object,starting from industrial big data analysis,using data mining methods to establish decision tree models and random forest models,and evaluating and predicting the constructed *** testing,decision tree models with different effects can be obtained,indicating that the decision tree model has a certain degree of flexibility,and selecting parameters can lead to a model with good *** addition,under the same conditions,a random forest model was constructed,and simulation results showed that the combination model constructed using the random forest algorithm was superior to a single decision tree model,with better prediction performance.

关键词： SAG mill data mining big-data analysis decision tree random forest

来源：评论

学校读者我要写书评

暂无评论

Intelligent expert control method and application in SABC grinding circuit based on hybrid model

Intelligent expert control method and application in SABC gr...

引用

第35届中国控制与决策会议

作者： Guobin Zou Junwu Zhou Daoxi Liu Tao Song Kang Li College of Information Science and Engineering Northeastern University State Key Laboratory of Process Automation in Mining and Metallurgy BGRIMM Technology Group State Key Laboratory of Process Automation in Mining and Metallurgy

SABC grinding circuit(Semi Autogenous+Ball mill+Crushing circuit) is an important typical configuration in comminution production,which has control problems such as uncertainty and strong *** this paper,an intelligent expert control method for grinding process based on hybrid model is ***,a hybrid model driven by mechanism and data is proposed to realize online perception of production indicators such as particle size in cyclone overflow;then,the application scope of expert rules is improved by intelligent correction of uncertainties;finally,the process mechanism knowledge and the online perception data of the hybrid model are integrated to realize the coordinated production of each sub process in the target SABC *** method proposed in this paper has been applied in an intelligent expert control system of SABC circuit in a concentrator to meet the production target.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Heterogeneous Ensemble Learning Algorithm Based on MLP-SVR-LGBM

A Two-stage Heterogeneous Ensemble Learning Algorithm Based ...

引用

International Conference on Industrial Artificial Intelligence (IAI)

作者： Chunpeng Yang Xurui Zhang Yiping Wang Jianjun Zhao Kai Sun School of Information and Automation Qilu University of Technology (Shandong Acadamy of Sciences) Jinan China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

A single machine learning approaches often encounter numerous challenges and limitations when addressing complex problems. In this study, we propose a novel stacking ensemble learning model for heterogeneous soft sensors, utilizing multi-layer perceptron (MLP), support vector regression (SVR), and light gradient boosting machine (LGBM) as base learners, with gradient boosting decision tree (GBDT) as the meta-learner. First, the proposed heterogeneous soft sensor model fully considers the diversity of the base learners and their learning performance to effectively exploit the advantages of various machine learning methods. Second, the meta-learner, GBDT, is an integrated learning algorithm that can better handle different data of the base learners and improve the performance of the overall model. Subsequently, we demonstrate the superiority of the proposed method is confirmed through an artificial dataset case study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Sparse Optimization Algorithm for Gated Recurrent Units Estimators

A Two-stage Sparse Optimization Algorithm for Gated Recurren...

引用

International Conference on Industrial Artificial Intelligence (IAI)

作者： Xurui Zhang Chunpeng Yang Lei Zhao Jianjun Zhao Kai Sun School of Information and Automation Qilu University of Technology (Shandong Acadamy of Sciences) Jinan China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

Industrial processes are always with sophisticated characteristics in particular highly nonlinear, multivariate coupling, and dynamic time lag. To overcome these dilemmas, a gated recurrent unit (GRU) neural network based on ℓ p - regularization is proposed to design effective prediction algorithms for the processes. Firstly, a primordial GRU model is trained from the given data. Secondly, a two-stage regularization algorithm is integrated into the fundamental model to simplify the input gate and the hidden layers of the GRU, respectively, which simultaneously achieves input variable selection and structural optimization. Finally, the performance of the proposed double ℓ p -regularized GRU is verified through a practical industrial dataset and compared with other machine learning algorithms. Experimental results demonstrate that the proposed algorithm can extract relevant features and simplify the model structure, therefore improving the prediction accuracy of the model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NeuroVI-based snow ruts and drivable area detection on snow-covered road 5

NeuroVI-based snow ruts and drivable area detection on snow-...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Liu, Xiangyong Yin, Fengfeng Zhuo, Guirong Yang, Zhixin Jiang, Wei College of Automotive Studies Tongji University Shanghai201804 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing Key Laboratory of Process Automation in Mining & Metallurgy Bgrimm Technology Group Beijing100160 China Department of Electromechanical Engineering University of Macau 999078 China Linyi Engineering Branch China Railway Jinan Group Co. Ltd. Shandong Linyi276000 China

ISBN: (纸本)9781510668621

Detection of safe driving areas on the road surface is a necessary prerequisite for path planning in snow-covered scenarios. The snow rut trajectory of snow-covered roads can provide the consultation of safe zones’ detection. This study proposed to use a Neuromorphic vision (NeuroVI) sensor to detect snow ruts and predict the safe driving area. We establish an image clustering method based on NeuroVI event points’ thickness and make a rut dataset under snow scenes. This dataset not only includes the recognition of optimal safe ruts but also includes adjacent boundary points and remote preview points. Then, a feature fusion model with a detection head is designed to output the recognition results, which can provide the safe zones’ position in snow-covered autonomous driving. © 2023 SPIE.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

RIS-assisted Channel Prediction Model for Mine V2X Systems

RIS-assisted Channel Prediction Model for Mine V2X Systems

引用

Computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Yuanxun Cheng Qingsong Hu Yujia Luo Yuansheng Zhang School of Information and Control Engineering China University of Mining and Technology Xuzhou China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

The complex and dynamic environment of mines leads to time-variability and uncertainty in channel propagation, which affects the stability and reliability of Vehicle-to-Everything (V2X)communication in mine networks. Channel prediction can help mitigate these issues. Introducing reconfigurable intelligence surface (RIS) into the mine V2X system can enhance signal coverage and quality in the complex mine environment. To address the issue of long-term error accumulation in existing channel prediction models, this paper analyzes the prediction error of channel state information (CSI) in mine V2X systems. It was observed that the error distribution exhibits characteristics of an approximate normal distribution, revealing its predictability. Utilizing this characteristic, this paper proposes an error correction strategy to suppress long-term error accumulation during the prediction process. Furthermore, an adaptive method for optimizing RIS phases is designed based on the Snow Ablation Optimizer. Specifically, this paper utilizes a metaheuristic optimization algorithm and deep learning techniques to propose a mine V2X channel prediction model that incorporates the error correction strategy. Experimental results show that optimizing the RIS phase can effectively enhance channel gain, and the mine V2X channel prediction model incorporating the error correction strategy can effectively suppress cumulative errors during the prediction process, thereby improving prediction accuracy.

关键词： Deep learning Adaptation models Accuracy Predictive models Reconfigurable intelligent surfaces Gaussian distribution Prediction algorithms Approximation algorithms Error correction Vehicle-to-everything

来源：评论

学校读者我要写书评

暂无评论

An Improved MOEA Based on Adaptive Adjustment Strategy for Optimizing Deep Model of RFID Indoor Positioning 26

An Improved MOEA Based on Adaptive Adjustment Strategy for O...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Jiahui Yang, Lvqing Chen, Sien Dong, Wensheng Yu, Bo Wang, Qingkai Xiamen University School of Informatics Xiamen361005 China Information Technology Co. Ltd. Xiamen361005 China Jimei University School of Navigation Xiamen361021 China Technology Co. Ltd. Xiamen361005 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China

ISBN: (纸本)9798350331684

Nowadays, IoT technology is developing rapidly and RFID (Radio Frequency Identification) based indoor positioning problems can be performed using deep learning and intelligent optimization algorithms. Deep models can analyze and predict the localization problem as a regression problem to achieve high accuracy positioning. Meanwhile, to ensure the accuracy of the model, we need to find excellent hyperparameters, which requires the support of optimization algorithms, but existing optimization algorithms do not allow flexible adaptation according to the optimization phase and there is room for improvement. In this paper, we propose a deep model, called CTT, and a multi-objective evolutionary algorithm (MOEA) based on a neighborhood adaptive adjustment strategy, called MOEA-NAAS. The experimental results show that CTT optimized by the NAAS algorithm is significantly more accurate and stable in the localization problem, with significant improvements in the three main metrics, proving the usability of the optimization algorithm. At the same time, the localization effect of the CTT also shows obvious advantages. In the future, the optimized algorithm can be combined with other deep models and widely used in various high-precision indoor positioning. © 2023 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-condition flotation process condition recognition method based on deep learning and multivariate data pre-processing

Multi-condition flotation process condition recognition meth...

引用

Chinese Control and Decision Conference, CCDC

作者： Yicheng Wang Shu Wang Kang Li College of Information Science and Engineering Northeastern University Shenyang China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The state and trend of flotation surface foam play a crucial role in flotation operations as they provide important indications of working conditions, index predictions, and operational volume adjustments. While researchers have focused on manual feature design of froth images or automatic extraction of depth features and their relationship to flotation conditions, the information contained in the flotation process variables and the importance of data pre-processing are usually overlooked. To address these shortcomings, this study proposes an integrated framework for flotation process data preprocessing and condition recognition. It includes a fast imputation algorithm based on multi-condition data center of mass (FCKNN) for overcoming the challenges of imputing missing values in on-line industrial processes, as well as a high-precision work condition recognition method that fuses deep visual features with key process variables. Finally, the framework was applied to the gold flotation process. The experimental results show that the proposed framework can perform work condition recognition with high accuracy and solve the challenge of online missing value imputation.

关键词： Employee welfare Visualization Image recognition Accuracy process control Manuals Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Trend-Aware Patch Feature Fusion Transformer for Fault Diagnosis of Vibration Signals

引用

IEEE Sensors Journal 2025年

作者： Zhang, Ruicong Chu, Fei Qiu, Yazhi He, Dakuo Wang, Fuli China University of Mining and Technology School of Information and Control Engineering Xuzhou221000 China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing100160 China Northeastern University College of Information Science and Engineering State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Northeastern University College of Information Science and Engineering Shenyang110000 China

The Vision Transformer (ViT) has demonstrated reliable performance in industrial equipment fault diagnosis by capturing global features and long-range dependencies in vibration signals. Nonetheless, when processing vibration signals, ViT primarily focuses on the correlations between patches, while neglecting the trend variation information hidden between signal units. This limitation hinders the model’s ability to extract latent fault information. To address this issue, we propose a trend-aware patch feature fusion Transformer (TAPformer) for fault diagnosis of vibration signals. Specifically, we design both patch-level and signal-level trend-aware self-attention blocks and adopt a weighted approach to integrate coarse-grained patch-level trend features with fine-grained signal-level trend features at the output of each self-attention head. This approach enables the model to capture fault information hidden within trend variations, effectively enhancing its fault detection capabilities. TAPformer establishes optimal weighted fusion hyperparameters through ablation experiments and is tested on four public datasets. Compared to eight advanced models, TAPformer achieves the highest accuracy across all four datasets, demonstrating the effectiveness and generalization capability of the proposed method. © 2001-2012 IEEE.

关键词： Fault detection

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：