检索结果-内蒙古大学图书馆

An Adaptive multi-sensor data fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox

引用

sensorS 2017年第2期17卷 414页

作者： Jing, Luyang Wang, Taiyong Zhao, Ming Wang, Peng Tianjin Univ Sch Mech Engn Tianjin 300354 Peoples R China Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Peoples R China

A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment.

关键词： fault diagnosis multi-sensor data fusion deep convolutional neural networks feature learning planetary gearbox

来源：评论

学校读者我要写书评

暂无评论

A multi-sensor data fusion Approach for Atrial Hypertrophy Disease Diagnosis Based on Characterized Support Vector Hyperspheres

引用

sensorS 2017年第9期17卷 2049-2049页

作者： Zhu, Yungang Liu, Dayou Grosu, Radu Wang, Xinhua Duan, Hongying Wang, Guodong Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Coll Comp Sci & Technol Changchun 130012 Jilin Peoples R China Vienna Univ Technol Dept Comp Engn A-1040 Vienna Austria Chinese Acad Sci State Key Lab Appl Opt Changchun 130012 Jilin Peoples R China

Disease diagnosis can be performed based on fusing the data acquired by multiple medical sensors from patients, and it is a crucial task in sensor-based e-healthcare systems. However, it is a challenging problem that there are few effective diagnosis methods based on sensor data fusion for atrial hypertrophy disease. In this article, we propose a novel multi-sensor data fusion method for atrial hypertrophy diagnosis, namely, characterized support vector hyperspheres (CSVH). Instead of constructing a hyperplane, as a traditional support vector machine does, the proposed method generates "hyperspheres" to collect the discriminative medical information, since a hypersphere is more powerful for data description than a hyperplane. In detail, CSVH constructs two characterized hyperspheres for the classes of patient and healthy subject, respectively. The hypersphere for the patient class is developed in a weighted version so as to take the diversity of patient instances into consideration. The hypersphere for the class of healthy people keeps furthest away from the patient class in order to achieve maximum separation from the patient class. A query is labelled by membership functions defined based on the two hyperspheres. If the query is rejected by the two classes, the angle information of the query to outliers and overlapping-region data is investigated to provide the final decision. The experimental results illustrate that the proposed method achieves the highest diagnosis accuracy among the state-of-the-art methods.

关键词： multi-sensor data fusion support vector hypersphere computer-aided diagnosis trial hypertrophy

来源：评论

学校读者我要写书评

暂无评论

Research for multi-sensor data fusion based on Huffman tree clustering algorithm in greenhouses

引用

INTERNATIONAL JOURNAL OF EMBEDDED SYSTEMS 2016年第1期8卷 34-38页

作者： Xu, Yang Chen, BaoZhan Hu, ZhiChen Northwest A&F Univ Coll Informat 3 Taicheng Rd Yangling Shanxi Peoples R China

Information monitoring system in the greenhouse will often deploy multiple redundant collection nodes in the same region in order to gather environmental parameters. It will improve data collection accuracy and enhance system stability through data fusion. This paper proposes a multi-sensor data fusion algorithm for greenhouse environment monitoring. First, triple exponential smoothing is applied to a variety of greenhouse environmental parameters. Then the smoothed data are sent to a router or gateway, removing invalid data, then idea of the Huffman tree is introduced to determine the order of the integration of each sensor, so as to realise multi-sensor data fusion. In the Institute for Farmland Irrigation Chinese Academy of Agricultural Sciences, the tests indicated that three exponential smoothing fluctuations significantly reduce the data to improve the accuracy of the data fusion, meanwhile, running time of data fusion algorithm was significantly shorter, and better than weighted average method.

关键词： multi-sensor data fusion distributed Huffman tree greenhouse monitor embedded systems embedded systems

来源：评论

学校读者我要写书评

暂无评论

multi-sensor Optimal data fusion Based on the Adaptive Fading Unscented Kalman Filter

引用

sensorS 2018年第2期18卷 488-488页

作者： Gao, Bingbing Hu, Gaoge Gao, Shesheng Zhong, Yongmin Gu, Chengfan Northwestern Polytech Univ Sch Automat Xian 710072 Shaanxi Peoples R China RMIT Univ Sch Engn Bundoora Vic 3083 Australia

This paper presents a new optimal data fusion methodology based on the adaptive fading unscented Kalman filter for multi-sensor nonlinear stochastic systems. This methodology has a two-level fusion structure: at the bottom level, an adaptive fading unscented Kalman filter based on the Mahalanobis distance is developed and serves as local filters to improve the adaptability and robustness of local state estimations against process-modeling error;at the top level, an unscented transformation-based multi-sensor optimal data fusion for the case of N local filters is established according to the principle of linear minimum variance to calculate globally optimal state estimation by fusion of local estimations. The proposed methodology effectively refrains from the influence of process-modeling error on the fusion solution, leading to improved adaptability and robustness of data fusion for multi-sensor nonlinear stochastic systems. It also achieves globally optimal fusion results based on the principle of linear minimum variance. Simulation and experimental results demonstrate the efficacy of the proposed methodology for INS/GNSS/CNS (inertial navigation system/global navigation satellite system/celestial navigation system) integrated navigation.

关键词： multi-sensor data fusion adaptive fading unscented Kalman filter process-modeling error Mahalanobis distance linear minimum variance

来源：评论

学校读者我要写书评

暂无评论

multi sensor data fusion for 6D pose estimation and 3D underground mine mapping using autonomous mobile robot

引用

INTERNATIONAL JOURNAL OF IMAGE AND data fusion 2017年第2期8卷 173-187页

作者： Ghosh, Dibyendu Samanta, Biswajit Chakravarty, Debashish Intel Labs ADR STPL Bangalore Karnataka India IIT Dept Min Engn Kharagpur W Bengal India

Simultaneous localisation and mapping by using a robot is indeed a challenging and critically important problem for an accurate 3D underground mine mapping. Using 6D pose information of a robot (x, y and z coordinates and the yaw, pitch and roll angles), the robot vehicle can be tracked, which is very crucial for an accurate mine mapping. The estimation of 6D robot pose on the ground surface is easy and generally accomplished by either the Global Positioning System (GPS) or by putting some artificial visual landmarks. However, in the underground mining environment, the estimation of pose becomes difficult due to the unavailability of the GPS signal and the identification of landmarks (as surface wall of the underground mine is rough). In this paper, an attempt has been made to construct a 3D underground mine map using a prototype mine robot. For this purpose, a strategy for the underground mine robot pose estimation is devised with the help of multi-sensor data fusion techniques. A shaft-encoder (wheel odometry), Inertial Measurement Unit (IMU) and a rotated 2D Laser Scanner is used to improve and rectify the 6D robot pose as well as 3D mine map. An autonomous prototype robot is built up and allowed to navigate in a real underground mine gallery to validate our algorithm. Generated 3D map has been compared with the actual map available. The outputs of this study are highlighted in this paper.

关键词： multi-sensor data fusion EKF 6D pose estimation scan matching SLAM underground mine mapping

来源：评论

学校读者我要写书评

暂无评论

Energy Aware Routing Based on multi-sensor data fusion for Wireless sensor Networks 1st

Energy Aware Routing Based on Multi-sensor Data Fusion for W...

引用

1st International Conference on Smart Trends for Information Technology and Computer Communications (SmartCom)

作者： Das, Soumitra Barani, S. Wagh, Sanjeev Sonavane, S. S. Sathyabama Univ Dept CSE Madras Tamil Nadu India Sathyabama Univ Dept Elect & Control Engn Madras Tamil Nadu India KJCOEMR Dept Comp Engn Pune Maharashtra India Dr DY Patil Sch Engn Dept E&TC Pune Maharashtra India

ISBN: (纸本)9789811034336;9789811034329

In this paper a multi-sensor data fusion approach for wireless sensor system based on Bayesian strategies and Ant Colony Optimization procedures have been recommended. In this methodology, every node is furnished with various sensors (i.e. temperature and humidity sensors). Usage of more than one sensor gives additional information about the environmental conditions. The data fusion based on the competitive type hierarchical processing has been considered for experimentation. In the data fusion, the data gathered by the sensors are set in the sensing fields and afterward the data fusion probabilities are registered. In our suggested approach, the gathered temperature and humidity information are prepared by multi-sensor data fusion strategies, which then helps in diminishing the energy utilization and also communication cost through accumulation of the repetitive information. The multiple information merging process is reliable and accurate in addition to being energy-efficient which our primary goal is. The proposed algorithms were simulated utilizing Matlab. The implementation of the proposed algorithms were conducted with and without multi-sensor data fusion and the outcomes demonstrate that the proposed algorithms could reduce the energy-consumption, rather save additional energy, thus enhance the entire lifetime of the system.

关键词： multi-sensor data fusion Optimization techniques Energy aware routing ACO WSN

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based multi-sensor data fusion Method for Degradation Monitoring of Ball Screws 7

A Deep Learning-Based Multi-Sensor Data Fusion Method for De...

引用

Prognostics and System Health Management Conference (PHM-Chengdu)

作者： Zhang, Li Gao, Hongli Southwest Jiaotong Univ Dept Mech Engn Chengdu 610031 Peoples R China

ISBN: (纸本)9781509027781

As ball screw has complex structure and long range of distribution, single signal collected by one sensor is difficult to express its condition fully and accurately. multi-sensor data fusion usually has a better effect compared with single signal. multi-sensor data fusion based on neural network(BP) is a commonly used multi-sensor data fusion method, but its application is limited by local optimum problem. Aiming at this problem, a multi-sensor data fusion method based on deep learning for ball screw is proposed in this paper. Deep learning, which consists of unsupervised learning and supervised learning, is the development and evolution of traditional neural network. It can effectively alleviate the optimization difficulty. Parallel superposition on frequency spectra of signals is directly done in the proposed deep learning-based multi-sensor data fusion method, and deep belief networks(DBN) are established by using fused data to adaptively mine available fault characteristics and automatically identify the degradation condition of ball screw. Test is designed to collect vibration signals of ball screw in 7 different degradation conditions by using 5 acceleration sensors installed on different places. The proposed fusion method is applied in identifying the degradation degree of ball screw in the test to demonstrate its efficacy. Finally, the multi-sensor data fusion based on neural network is also applied in degradation degree monitoring. The monitoring accuracy of deep learning-based multi-sensor data fusion is higher compared with that of neural network-based multi-sensor data fusion, which means the proposed method has more superiority.

关键词： multi-sensor data fusion deep learning ball screw degradation monitoring

来源：评论

学校读者我要写书评

暂无评论

multi-sensor Adaptive data fusion with Colored Measurement Noise 29

Multi-sensor Adaptive Data Fusion with Colored Measurement N...

引用

第29届中国控制与决策会议

作者： Yao Wu Meng Cai Jianxun LI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Satellite Marine Tracking & Control Department of China Luoyang Institute of Electro-optical Equipment AVIC

ISBN: (纸本)9781509046584

As one of the key theories of target tracking,multi-sensor data fusion(MSDF) is widely utilized in engineering ***,the research of MSDF is under the hypothesis that the measurement systems of sensors are only influenced by white noise and their priori knowledge is obtained,which is not appropriate for practical *** these situations,a white noise model convention and adaptive measurement noise adjustment is added into the two proposed fusion methods called centralized measurement fusion(CMF) and decentralized state fusion(DSF).The equations of fusion estimation results are derived both with and without white noise *** method of adaptive covariance adjustment based on artificial neural network(ANN) is *** simulation results show that the measurement model is estimated more precisely by denoting the colored noise with white noise,the adaptive variance adjustment method contributes to overcoming the priori information deficiency of noise and keep the tracking precision,and the DSF has higher tracking accuracy than the local filter based on each sensor but lower than the CMF.

关键词： multi-sensor data fusion Target tracking Colored measurement noise Centralized measurement fusion Decentralized state fusion Adaptive weighting

来源：评论

学校读者我要写书评

暂无评论

multi-sensor data fusion Algorithm for Automobile Anti-theft System 5

Multi-sensor Data Fusion Algorithm for Automobile Anti-theft...

引用

Fifth International Conference on Instrumentation & Measurement, Computer, Communication, and Control (IMCCC)

作者： Dong, Jingwei Xu, Qi Harbin Univ Sci & Technol Sch Measurement & Control Technol & Commun Engn Harbin Peoples R China

ISBN: (纸本)9781467377232

Automobile anti-theft system need to use multisensor data fusion. For the problems in the process of multisensor data fusion, D-S evidence theory based on the weight distribution is corrected using the theory of matrix analysis. After verification, the algorithm can deal with the integration process operation problem of excessive very well. In the case of failure of one or more sensors this algorithm can ensure the accuracy of the results of the integration.

关键词： multi-sensor data fusion D-S evidence theory Matrix analysis

来源：评论

学校读者我要写书评

暂无评论

3D Buried Utility Location Using A Marching-Cross-Section Algorithm for multi-sensor data fusion

引用

sensorS 2016年第11期16卷 1827-1827页

作者： Dou, Qingxu Wei, Lijun Magee, Derek R. Atkins, Phil R. Chapman, David N. Curioni, Giulio Goddard, Kevin F. Hayati, Farzad Jenks, Hugo Metje, Nicole Muggleton, Jennifer Pennock, Steve R. Rustighi, Emiliano Swingler, Steven G. Rogers, Christopher D. F. Cohn, Anthony G. Univ Leeds Sch Comp Leeds LS2 9JT W Yorkshire England Univ Birmingham Sch Elect Elect & Comp Engn Birmingham B15 2TT W Midlands England Univ Birmingham Sch Civil Engn Birmingham B15 2TT W Midlands England Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England Univ Bath Sch Elect & Elect Engn Bath BA2 7AY Avon England Univ Southampton Inst Sound & Vibrat Res Southampton SO17 1BJ Hants England

We address the problem of accurately locating buried utility segments by fusing data from multiple sensors using a novel Marching-Cross-Section (MCS) algorithm. Five types of sensors are used in this work: Ground Penetrating Radar (GPR), Passive Magnetic Fields (PMF), Magnetic Gradiometer (MG), Low Frequency Electromagnetic Fields (LFEM) and Vibro-Acoustics (VA). As part of the MCS algorithm, a novel formulation of the extended Kalman Filter (EKF) is proposed for marching existing utility tracks from a scan cross-section (scs) to the next one;novel rules for initializing utilities based on hypothesized detections on the first scs and for associating predicted utility tracks with hypothesized detections in the following scss are introduced. Algorithms are proposed for generating virtual scan lines based on given hypothesized detections when different sensors do not share common scan lines, or when only the coordinates of the hypothesized detections are provided without any information of the actual survey scan lines. The performance of the proposed system is evaluated with both synthetic data and real data. The experimental results in this work demonstrate that the proposed MCS algorithm can locate multiple buried utility segments simultaneously, including both straight and curved utilities, and can separate intersecting segments. By using the probabilities of a hypothesized detection being a pipe or a cable together with its 3D coordinates, the MCS algorithm is able to discriminate a pipe and a cable close to each other. The MCS algorithm can be used for both post- and on-site processing. When it is used on site, the detected tracks on the current scs can help to determine the location and direction of the next scan line. The proposed "multi-utility multi-sensor" system has no limit to the number of buried utilities or the number of sensors, and the more sensor data used, the more buried utility segments can be detected with more accurate location and orientation.

关键词： buried utility location marching-cross-section algorithm multi-sensor data fusion

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：