检索结果-内蒙古大学图书馆

Industrial Cyber-Physical systems (ICPS)

作者： Huimin Ou Jianqi An Xing-ao Wang Jianru Xiong Xin Chen Qingyi Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

Deep learning is currently the mainstream method for ceramic defect detection, and it requires a large number of defect samples to train the network. However, collecting these defect samples is very time-consuming and deep learning suffers from few-shot learning problems. In this study, a StyleGAN3-based data augmentation method for ceramic defect detection was proposed which can generate ceramic defect samples and thus reduce the data collection work. Experiments show that our method uses less training time, has a more stable training process, and can improve the accuracy of the detection network.

关键词： Training Deep learning Image synthesis Data collection Cyber-physical systems Data models Ceramics

来源：评论

学校读者我要写书评

暂无评论

That-Net: Two-Layer Hidden State Aggregation Based Two-Stream Network for Traffic Accident Prediction

SSRN

引用

SSRN 2023年

作者： Liu, Wei Zhang, Tao Lu, Yisheng Chen, Jun Wei, Longsheng School of Automation China University of Geosciences Wuhan430074 China Key Laboratory of Geological Survey and Evaluation Ministry of Education Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

With the bursting of autonomous and assistant driving systems, traffic accident prediction has attracted increasing attention during the past few years. However, predicting traffic accidents is extremely challenging due to the complexity of traffic scenarios and the variability of traffic object's motion states. Existing algorithms contain all traffic objects and all video frames indiscriminately in the prediction model, which correspondingly reduces the prediction accuracy. To solve this problem, we propose a two-layer hidden state aggregation based two-stream network (THAT-Net) to construct a more accurate prediction model. The proposed model fuses two streams to achieve complementary spatio-temporal information, in which optical flow features are introduced to 'remove' irrelevant objects of accident. Furthermore, two-layer hidden state aggregation structure is adopted to reintegrate the hidden state weights of gated recurrent units to reduce the influence of irrelevant frames. Comprehensive experimental results on both benchmark datasets demonstrate state-of-the-art performance of THAT-Net, especially on the challenging Dashcam Accident dataset. Our code is available at: https://***/redeyezt/THAT-Net. © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Design and application of a one-stop mobile application sharing platform for steel enterprises

Design and application of a one-stop mobile application shar...

引用

第42届中国控制会议

作者： Xinzhe Chen Luefeng Chen Jie Hu Qingfeng Yang Min Wu Witold Pedrycz School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Department of Electrical and Computer Engineering University of Alberta

As China's steel production accounts for an increasing share of the world's output, the intelligent transformation of the steel industry is becoming increasingly urgent. To address issues such as low levels of mobile informationization in steel enterprises and the lack of an industry-specific mobile application platform, it is of great significance to establish a shared mobile application platform for the steel industry. In this paper, the requirements of the platform were analyzed, and the platform's functions were designed. The software design of the platform was then carried out, and the entire mobile application sharing platform was developed, effectively improving the production management efficiency of steel enterprises. The results indicate that the platform can effectively meet the needs of steel enterprises and has significant engineering significance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Model for Online Prediction of Rate of Penetration (ROP) in Drilling Process

A Novel Hybrid Model for Online Prediction of Rate of Penetr...

引用

Chinese automation Congress (CAC)

作者： Yao Wang Chao Gan Weihua Cao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

In this paper, a novel hybrid model is proposed for online prediction of rate of penetration (ROP) in drilling process, which including two parts (online data pre-processing and online hybrid modeling). In the first part, threshold filtering and Savitzky Golay (SG) filtering are both employed to enhance the quality of drilling data considering the expert experience and data characteristics. In the next part, a novel hybrid model with error compensation is established, which is combined the Bingham sub-model and gradient boosting decision tree (GBDT) sub-model. To better capture the dynamic changes of ROP, the hybrid model is updated with moving window strategy. Finally, compared simulation results with well-known ROP prediction models indicate the efficiency of the hybrid model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Displacement Prediction of Landslide Using SARIMA Model Based on Seasonal Characteristic

Displacement Prediction of Landslide Using SARIMA Model Base...

引用

Chinese control Conference (CCC)

作者： Ruoxi Wu Chengda Lu Wanke Yu Min Wu Xuzhi Lai School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

Landslide displacement prediction is an important and indispensable part of landslide monitoring and warning. The change of the displacement is always considered being related to inducing factors, which are aimed at improving accuracy of the predicted model. However, the seasonal characteristic of the displacement, which has not been carefully analyzed, reveals the law of inducing factors. In order to gain a deeper understanding of characteristics, the Baijiabao landslide is taken as an example. The variational mode decomposition (VMD) method, which can extract effective information well, is introduced to decompose the displacement. Introducing the seasonal parameters, the seasonal autoregressive integrated moving average (SARIMA) model is established to predict the displacement subseries. Finally, accumulative displacement prediction values are obtained by superimposing the predicted subseries. With higher accuracy and lower error, the VMD-SARIMA model proves a better option in application compared with VMD-ARIMA, SARIMA and ARIMA models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Silicon Content in Molten Iron of Blast Furnace Based on Multi-dimensional Sequential Characteristic Reconstruction

Prediction of Silicon Content in Molten Iron of Blast Furnac...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Zhuofu Zhang Weihua Cao Jie Hu Qifu Chen Min Wu School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

Molten iron is the primary output of blast furnace production. The content of silicon in molten iron clearly correlates with blast furnace temperature. However, due to the intricate conditions of blast furnace production, the silicon content in molten iron is nonlinear and unstable. Therefore, this paper adopts variational mode decomposition (VMD) to decompose and extract the feature information of the real silicon content data of LY Steel in March 2022, then uses Grey Wolf optimization (GWO) algorithm to optimize the parameters of the support vector regression (SVR) prediction model, and takes the decomposed data as model input for experimental verification. By comparing the predicted results with the real historical data of blast furnace production, it is found that the degree of fit is about 94.2%, which offers a new idea for the prediction of silicon content.

关键词： Support vector machines Production Predictive models Blast furnaces Prediction algorithms Feature extraction Silicon

来源：评论

学校读者我要写书评

暂无评论

Template Matching and Trend Feature Analysis-Based Data Pre-Processing Method for Seismic Wave Detection

Template Matching and Trend Feature Analysis-Based Data Pre-...

引用

Chinese automation Congress (CAC)

作者： Zheng Xu Chao Gan Weihua Cao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

In this paper, a template matching and trend feature analysis-based data pre-processing method for seismic wave detection is proposed with two stages. In the first stage, it involves extracting the rock physical parameters from seismic wave detection results using OCR (Optical Character Recognition) method, and extracting the original rock physical parameters from the raw rock property table using keyword matching method. Using the rock physical parameters as a template, a template matching approach is employed to eliminate abnormal values from the original rock physical parameters. In the next stage, a technique is proposed to extract trend features of rock physical parameters for conducting advanced geological forecasting, which considered the expertise of experts in interpreting seismic wave detection data. Finally, the effectiveness of the proposed method is verified by the compared simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Finite-Time Stabilization of Stochastic Parabolic PDE systems via Non-Fragile Spatial Sampled-Data control

Robust Finite-Time Stabilization of Stochastic Parabolic PDE...

引用

IEEE Conference on Decision and control

作者： Xiaofang Hu Feida Song Leimin Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

This paper addresses the robust finite-time stabi-lization (FTS) issue for stochastic parabolic PDE systems via non-fragile spatial sampled-data control scheme. First, a class of distributed parameter systems characterized by the delayed stochastic parabolic partial differential equation is developed for analyzing the effects of stochastic disturbance, structural uncertainty, and discrete delay on the system performance. Then, a non-fragile spatial sampled-data control scheme is established by setting sampling points in the spatial domain, which effectively saves communication resources and ensures that the closed-loop system maintains good performance when the controller is perturbed. Moreover, based on the partial differential equation theory, stochastic analysis approach, and the extended Wirtinger's inequality technique, several criteria are provided to ensure the robust FTS of stochastic parabolic PDE systems in the mean square sense. Lastly, a numerical example is provided to verify the feasibility of the suggested stabilization criteria and control scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamics Modeling Method of Offshore Drilling Experimental system Based on Double-Layer Stewart Parallel Mechanism

Dynamics Modeling Method of Offshore Drilling Experimental S...

引用

第42届中国控制会议

作者： Chenxuan Wang Zhejiaqi Ma Chengda Lu Sheng Du Min Wu School of Future Technology China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences

Establishing the dynamics model of the offshore drilling experimental system can better complete the offshore drilling test in the laboratory environment and reduce the cost of testing.A dynamical modeling method for the offshore drilling experimental system built on the double-layer Stewart parallel mechanism is ***,the kinematic and dynamical characteristics of the double-layer Stewart parallel mechanism are combined with the Lagrange method and the virtual work method to establish the dynamics model of the *** a parameter identification scheme is designed using a nonlinear gray system estimation method based on the trust-domain reflection algorithm,and the model parameters are *** model is downscaled to improve the feasibility of the identification scheme and the accuracy of the identified *** actual experimental system data verify this model's correctness and the model parameters' accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Feature Difference Network for Defect Detection on the Surface with complex Pattern of Ceramic Tile

A Feature Difference Network for Defect Detection on the Sur...

引用

Chinese control Conference (CCC)

作者： Jianru Xiong Jianqi An Xing-ao Wang Huimin Ou Xin Chen School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo- Exploration Ministry of Education Wuhan China

The surface defects of ceramic tile greatly affect the service life of ceramic tile. At present, many detection methods of ceramic tile surface defects are mostly used for ceramic tiles with monochrome background or simple texture. However, many tiles with complex and irregular surface patterns are used in practical applications, but many methods cannot effectively detect surface defects in such tiles. This paper presents a double input feature difference network structure to overcome the limitation. First, a double input channel is constructed to extract features from the template image and the defect image respectively. Next, a method of feature difference is performed at different depths to suppress the background interference and prevent misclassification between different defect categories. Then a parameter-free attention module is embedded in the backbone to improve the ability of feature extraction. Experimental results show that this model effectively improves the mean average accuracy of 8.3% and the recall rate of 11.7%.

关键词：

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：