检索结果-内蒙古大学图书馆

10th International Symposium on Test Automation & Instrumentation (ISTAI 2024)

作者： Peixin Xing Ran Jia Tao Chen Guangxin Sun Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing University of Information Science and Technology Beijing 100192 People's Republic of China Beijing Machinery and Equipment Research Institute Beijing 100120 People's Republic of China

ISBN: (数字)9781837241910

With the rapid advancement of industrial technology, the structure of transmission systems has become increasingly complex, posing more severe challenges to their real-time monitoring and anomaly detection systems. To address these challenges, this paper proposes a novel comprehensive transmission sequence anomaly detection method. Firstly, the method employs Recursive Feature Elimination (RFE) to select the most relevant temporal features for precise identification of the anomaly detection target variables. Subsequently, Piecewise Aggregate Approximation (PAA) is utilized for effective dimensionality reduction of the time series data to simplify the subsequent processing steps. Finally, by integrating Bidirectional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN), a deep anomaly detection model is constructed to identify abnormal states efficiently. An example analysis of time series anomaly detection in transmission system oil leakage demonstrates the significant advantages of this method in improving the accuracy and efficiency of anomaly detection. The results indicate that this method can provide a new, reliable, and efficient technical solution for anomaly detection in complex transmission systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Gear Shifting Strategy of Mining Truck Based on Deep Learning and Real-Time Vehicle Condition

SSRN

引用

SSRN 2023年

作者： Su, Qinghua Xu, Xiaoyu Wang, Liyong Zhang, Dingge Xie, Min Zhang, Pengbo Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China Laboratory for Visual Perception and Intelligent Systems School of Control Science and Engineering Shandong University Shangdong Province Jinan250100 China

Mining areas are characterized by complex driving conditions, making automatic gear shift strategies specifically suited for mine trucks are critical. Nevertheless, development of automatic gear shifting strategy is under challenging, as it relies on experience and historical experiment data which is the top classified commercial secret of the manufacturers. Recently, some gear shifting strategies have been implemented based on artificial intelligent technology. However, many of them shift the gear based on vehicle current status and ignore the influences of historical data. It has potential risk by making wrong shift when receiving abnormal sensor data accidentally. Besides that, it also causes the gear continuous shifting within short time, which increases the chance of transmission damage and influences the driving experience. Consequently, a novel method based on Bi-directional Long Short-Term Memory(Bi-LSTM) network with multiple parameters from continuous time spans for gear prediction is proposed. The real-time vehicle status data is becaptured from CAN-bus, and 9 types of parameters with positive relation for gear shifting are chosen by R/S analysis. By inputting values of 9 paramters from continuous time spans to our Bi-LSTM based machine learning model, gear prediction target is achieved. The experimental records show that our network outputs the gears best suited to the current vehicle state with 96.85% accuracy. Its average prediction time consumption is around 3.86ms, which fits the real-time processing requirement in driving. Our network not only has advantages in balancing prediction correct rate and time consumption, but also maintains high accuracy when overcoming the influence of transient abnormal sensor data. Hence, it has the potential to be widely applied to the fields that prediction model is based on the data with temporal characteristic. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

INFRARED NON-UNIFORMITY CORRECTION MODEL VIA DEEP CONVOLUTIONAL NEURAL NETWORK 9

INFRARED NON-UNIFORMITY CORRECTION MODEL VIA DEEP CONVOLUTIO...

引用

9th International Symposium on Test Automation and Instrumentation, ISTAI 2022

作者： Chen, Shiqiang Deng, Feng Zhang, Hongyan Lyu, Suhuan Kou, Zongchun Yang, Jingjing Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science & Technology University Beijing100192 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science & Technology University Beijing100192 China School of Automation Beijing Information Science & Technology University Beijing100192 China State Key Laboratory of Nickel and Cobalt Resources Comprehensive Utilization Jinchang737104 China Jinchuan Group Co. Ltd Jinchang737104 China

ISBN: (纸本)9781839538391

Constrained by the limitation of the manufacturing engineering of the infrared thermal imaging detector, the non-uniformity problem is reflected as the periodical fixed pattern noise (FPN) in the images, which leads to a serious decline in the image quality. In order to solve this problem, this paper proposes an infrared non-uniformity correction model via a deep convolutional neural network (NUC-DCN). The residual learning technology is used to learn the residual information between the noisy infrared image and the latent clean one, which can accelerate the training process. A cubic polynomial is used to simulate the FPN to improve the generalization performance of the model. In addition, a wider convolutional kernel is used in the feature extraction to obtain the global noise feature representation. Furthermore, a combination of pooling layer and deconvolution layer is used to reduce the feature dimension, reduce the amount of computation, and then restore the feature map size to reconstruct the image. Finally, the feature maps of feature extraction and nonlinear mapping are fused to reconstruct the denoised image. The results of experiments show that our model outperforms the compared method in removing non-uniform noise and preserving the original structure and detail information of the image. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Uplink Spectrum Efficiency and UAV Trajectory in Cell-Free UAV Networks

Joint Optimization of Uplink Spectrum Efficiency and UAV Tra...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Jian He Chunyu Pan Qian Chen The Key Laboratory of Information and Communication Systems Ministry of Information Industry and the Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin China

The flexible mobility characteristics of unmanned aerial vehicle (UAV) lead to frequent handover and inter cell interference issues in traditional cellular based UAV assisted communication systems. Establishing cell-free UAV (CF-UAV) networks without cell boundaries will effectively alleviate this problem and has been an important research. However, the movement of the UAV results in time-varying channels. Therefore, the joint dynamic and reasonable UAV trajectory optimization and power allocation are very important for in CF-UAV networks. The expression of pilot transmission, channel estimation, uplink transmission spectrum efficiency (SE) have been derived based on the assumption of Rician channel between UAVs and access point (AP). SE optimization algorithm for CF-UAV networks combined with the Angle search and multi-UAV trajectory optimization strategy has been proposed in this paper. Simulation results show that the proposed algorithm performs better performance than comparison schemes, which SE improves by 37% compared with Angle search.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Security Risk Assessment Method for Connected and Automated Vehicles

Data Security Risk Assessment Method for Connected and Autom...

引用

IEEE International Conference on Intelligent Transportation Engineering (ICITE)

作者： Shiying Zhou Xuezhu Yang Muxi Li Huawei Yang Haojie Ji State Key Laboratory of Comprehensive Technology on Automobile Vibration and Noise & Safety Control Changchun China Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China

Considering the data security problems of connected and automated vehicles (CAVs), this paper analyzes the security vulnerability and risk challenges for the communication data in vehicles. Based on state of the art technical manuals, we explore the security reverse engineering technology, and propose the risk assessment method for data security of CAVs. Considering the impact level of data security for the national security, public interests, personal legitimate rights and privacy, we present the possibility evaluation level of data security and get the security risk value of ICVs. The proposed method has been verfied and provides risk assessment results of the vehicle component, i.e., T-box. Finally, the suggestion to construct an effective security protection policies for data security is put forward, and the method for the research of ICV data security is provided to push the development of automotive security system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A study of aircraft skin assembly gap measurement based on point cloud data

A study of aircraft skin assembly gap measurement based on p...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： Y. Liu G. Wu X. He Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing People's Republic of China

Aircraft skin is an important large thin-walled component of the fuselage and its high quality assembly is essential to ensure the safety and reliability of the aircraft. Aiming at the problems of high accuracy requirements for measurement of skin assembly gap, low efficiency of manual measurement and difficult to maintain accuracy. Based on contactless digital measurement technology, this paper proposes a method to process and analyse the point cloud data that forms the 3D model of the component, so as to realize the assembly gap measurement. Firstly, a statistical filter is used to remove the outlier noise in the part point cloud model away from the main point cloud; secondly, a voxel filter is used to remove the small-scale noise mixed in the main point cloud; thirdly, the part edge feature points are extracted based on the normal vector information of the point cloud, and finally, the multilinear gap measurement is implemented based on the short distance finding algorithm proposed in this paper, and the results are briefly analysed. Experiments have been conducted using actual data combined with simulation data to verify the feasibility of the method and to provide an outlook on it.

关键词： edge detection feature extraction solid modelling

来源：评论

学校读者我要写书评

暂无评论

Research on slam improvement method based on cartographer

Research on slam improvement method based on cartographer

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： Y. Huang G. Wu Y. Zuo Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing People's Republic of China

Cartographer is a SLAM (simultaneous localization and map building) algorithm based on graph optimization, which is commonly used for building maps of mobile robots in large indoor scenes, but there are problems of point cloud data feature loss and motion distortion caused by low frame rate LIDAR in data processing of LIDAR. In this paper, an improved algorithm based on Cartographer algorithm is proposed to address these problems. First, a voxel filtering method with downsampling of neighboring points is used for k-neighborhood search to improve the map building accuracy and computation rate. Then, a wheeled odometer-assisted algorithm is used to remove motion distortions and reduce the cumulative errors that occur in a large scale environment, thus improving the map building effect. Finally, the two algorithms are tested separately by simulating experiments in the gazebo simulation environment in the robot operating system, and the experimental results show that the improved algorithm builds the map trajectory with less error, thus verifying its effectiveness and feasibility.

关键词： control engineering computing distance measurement feature extraction mobile robots optical radar path planning robot vision SLAM (robots)

来源：评论

学校读者我要写书评

暂无评论

The two-factor damage threshold and proprotion of friction component in wet clutch

The two-factor damage threshold and proprotion of friction c...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： R. Chen L. Li L. Wang J. Wu J. Li Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing People's Republic of China

Frictional thermal load and wear have a complex influence relationships on the wet clutch working performance, and jointly cause damage to the friction ***,the two-factor threshold model of thermal load and wear is constructed using the neural network, and their optimal weights under damage conditions are obtained by training damage threshold data sets. Then, the difference on the weight of two factors is analysed under three specific operating conditions. Finally, the damage causes of wet clutch friction pairs are explained in detail. Research indicates that, the threshold model training error of 3.47 × 10 −4 is much smaller than the target error of 6.5 × 10 −4 , which is providing a high accuracy degree. Specifically, wear is the main influence on damage under the heavy load and low speeds conditions. While thermal loading is the main influence on damage under the high speeds and light loads conditions. Both thermal loads and wear have a huge impact on the damage under the high speed and heavy load conditions.

关键词： ageing computerised monitoring condition monitoring failure analysis fault diagnosis fission reactor safety hazards nuclear power stations

来源：评论

学校读者我要写书评

暂无评论

Research on building algorithm of indoor dense map based on ORB-SALM2

Research on building algorithm of indoor dense map based on ...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： P. Zhang Z. Zhang B. Ding X. Xu C. Wang Q. Su Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science & Technology University Beijing People's Republic of China

The purpose of visual SLAM (Simultaneous Localization and Mapping) technology is building accurate map and estimating correct camera pose. Since the sparse point cloud map generated by the traditional ORB-SLAM2 algorithm can not be directly applied to the 3D path planning for mobile robots due to inability to generate grid maps, this paper proposes a novel method which improves traditional ORB-SLAM2 algorithm for building more detialed 3D map. The ORB (Oriented FAST and Rotated BRIEF) algorithm is used to detect the image feature points in the front end, and the extracted feature points are processed by using the quad tree based homogenization strategy. At the back end, EPnP (Effective Perspective-n-Point) and ICP (Iterative Closest Point) algorithms are comprehensively used to optimize camera pose and to improve the pose estimation accuracy. Based on ORB-SLAM2, the proposed method adds dense mapping threads to build dense 3D point cloud maps. The experimental results show that the method presented in this paper is effective and robust in both common datasets and realscenes, and the root mean square error of the trajectory under two closed-loop datasets is less than 0.1 m, which can be used for robot navigation and path planning.

关键词： feature extraction iterative methods mobile robots navigation path planning pose estimation robot vision SLAM (robots)

来源：评论

学校读者我要写书评

暂无评论

A robust visual-inertial odometry with patch optical flow

A robust visual-inertial odometry with patch optical flow

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： C. Wang L. Wang Q. Su B. Ding Z. Zhang X. Xu P. Zhang M. Xie Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing People's Republic of China

In this paper, we propose a vision-inertial system(VIO) based on patch optical flow tracking. For the visual front-end, the input image is divided into uniform grid cells, FAST feature corners with the highest confidence are detected in the grid cells, and Gaussian kernel convolution is used to downsample the input image to build an image pyramid. Re-detecte FAST corners from grid cells where corner features are not detected in low resolution layers until all grid cells are filled. We calculate the feature optical flow movement from the top to the bottom of the pyramid. Unlike other methods, we consider the invariance of the light intensity scale. During the optical flow tracking, we estimate the SE(2) of the patch-to-patch, instead of the point-topoint, we consider both the translation and rotation of the patch. Calculating more pixel gradients around feature corners is helpful to maintain the consistency of photometric intensity *** experiments on a public datasets, we validate the performance of our VIO system and compare with other approaches the results show that our proposed method has superior localization accuracy.

关键词： distance measurement feature extraction Gaussian distribution image resolution mobile robots robot vision

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：