检索结果-内蒙古大学图书馆

An empirical study on prediction of seismic activity using stochastic configuration networks

Neural Computing and Applications 2024年第31期36卷 19435-19448页

作者： Qiu, Yuanhang Wang, Dianhui Artificial Intelligence Research Institute China University of Mining and Technology Jiangsu Xuzhou221116 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Liaoning Shenyang110819 China

Predicting seismic events has long been a huge challenge due to intricate nature of the underlying occurrence mechanisms. The traditional approach to estimating recurrence intervals is highly reliant on prior knowledge and expert experience, which often leads to considerable error margins. Recent advances in high-performance monitoring systems and artificial intelligence (AI) achieving great successes in various areas have renewed interest in identifying failure precursors and predicting seismic events. In this paper, we propose a genetic algorithm wrapped stochastic configuration networks (GAWSCN) approach to explore seismic physics for time-to-failure prediction. Specifically, stochastic configuration networks (SCN), a novel randomized learning paradigm, is utilized to learn essential seismic information from acoustic emission signals. To further enhance the generalization capability and alleviate overfitting, a regularization technique is imposed during the SCN training to establish a robust seismic prediction model. In particular, a genetic algorithm is integrated with SCN to optimize the selection of pertinent seismic features and further improve prediction performance. The experimental results demonstrate that our GAWSCN method outperforms other machine learning methods across evaluation metrics. This study offers promising insights for geophysical hazards assessment. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Output Regulation of Interconnected Singularly Perturbed Systems With Application to Power Systems

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 595-607页

作者： Jianguo Zhao Chunyu Yang Weinan Gao Linna Zhou Xiaomin Liu the Engineering Research Center of Intelligent Control for Underground Space Ministry of EducationChina University of Mining and TechnologyXuzhou 221116 the School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116 IEEE the State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819China

This article studies the adaptive optimal output regulation problem for a class of interconnected singularly perturbed systems(SPSs) with unknown dynamics based on reinforcement learning(RL).Taking into account the slow and fast characteristics among system states,the interconnected SPS is decomposed into the slow time-scale dynamics and the fast timescale dynamics through singular perturbation *** the fast time-scale dynamics with interconnections,we devise a decentralized optimal control strategy by selecting appropriate weight matrices in the cost *** the slow time-scale dynamics with unknown system parameters,an off-policy RL algorithm with convergence guarantee is given to learn the optimal control strategy in terms of measurement *** combining the slow and fast controllers,we establish the composite decentralized adaptive optimal output regulator,and rigorously analyze the stability and optimality of the closed-loop *** proposed decomposition design not only bypasses the numerical stiffness but also alleviates the *** efficacy of the proposed methodology is validated by a load-frequency control application of a two-area power system.

关键词： Adaptive optimal control decentralized control output regulation reinforcement learning(RL) singularly perturbed systems(SPSs)

来源：评论

学校读者我要写书评

暂无评论

DeepMultiple: A Deep Learning Model for RFID-based Multi-object Activity Recognition 35

DeepMultiple: A Deep Learning Model for RFID-based Multi-obj...

引用

35th International Conference on Software Engineering and Knowledge Engineering, SEKE 2023

作者： Shen, Shunwen Yang, Lvqing Chen, Sien Dong, Wensheng Yu, Bo Wang, Qingkai School of Informatics Xiamen University Xiamen China School of Navigation Jimei University Xiamen China School of Management Xiamen University Xiamen China Technology Co. Ltd. Xiamen China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

Wireless sensing techniques for Human Activity Recognition (HAR) have been widely studied in recent years. At present, the research on HAR based on Radio Frequency Identification (RFID) is changing from the tag attachment method to the tag non-attachment method. Affected by multipath, the current solutions in tag non-attachment scenarios mainly focus on single-object activity recognition, which is not suitable for multi-object scenarios. To address these issues, we propose DeepMultiple, a novel tag non-attachment activity recognition model for multi-object. The model first preprocesses the raw signal with filter and phase calibration, then it applies dilated convolution in the frequency domain to extract multi-object activity features, finally ProbSparse is used to optimize the vanilla Transformer-based Encoder to enhance the activity recognition ability. We deployed a single reader and antenna for multi-object activity tracking during the experiments to reduce deployment difficulties. Extensive experimental results show that DeepMultiple can recognize ten types of multi-object activities with 98.12% precision under different challenging settings, which has excellent performance compared with several state-of-the-art methods. © 2023 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Bearing Remaining Life Prediction Method Based on Wavelet Transform Denoising and Feature Preservation CycleGAN under Unbalanced Samples 3

Bearing Remaining Life Prediction Method Based on Wavelet Tr...

引用

3rd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022

作者： Wang, Songyang Yu, Jun Zhao, Kun Guo, Zhenyu School of Automation Harbin University of Science and Technology Harbin China School of Automation State Key Laboratory of Process Automation in Mining & Metallurgy Harbin University of Science and Technology Harbin China Cixing Group Co Ltd Beijing China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (纸本)9781665492812

With the rapid development of industrialization today, mechanical equipment has undergone significant development and progress in terms of type and quality. Rolling bearings are the key components of mechanical transmission and the most vulnerable mechanical components. Only 10% of rolling bearings can operate as designed. Exploring more scientific and reasonable test methods to predict the remaining service life of rolling bearings can not only reduce operating costs, but also prevent accidents. Life prediction models can be divided into three categories: statistical models, dynamic models, and data-driven prediction models. The existing life prediction models based on statistics, dynamics, etc. continue to increase the workload and difficulty of life prediction in the case of increasingly complex, time-consuming and labor-intensive mechanical equipment. With the rapid development of information technology, industrial process data collection has become efficient and convenient, providing sufficient data resources for data-driven intelligent life prediction technology, and gradually showing great development potential. The remaining life prediction mainly includes two key parts: the feature extraction of bearing vibration data and the construction of life prediction model. Therefore, this paper takes the rolling bearing as the research object, and carries out the remaining life prediction research from the two directions of feature extraction and prediction model construction. In the bearing operation monitoring data, the proportion of the fault data relative to the normal operation data is very small, forming a typical data imbalance phenomenon, and the traditional life prediction is not ideal when dealing with such data. In this paper, a secondary filtering method combining wavelet transform and parameter adaptive variational modal decomposition is used to preprocess the data and enhance the features;and fully consider the influence of unbalanced cluster data, a l

关键词： deep neural network remaining useful life prediction rolling bearing

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

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

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

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：