检索结果-内蒙古大学图书馆

A novel framework for bearing fault diagnosis across working conditions based on time-frequency fusion and multi-sensor data fusion

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第12期35卷 126205-126205页

作者： Lin, Bo Zhu, Guanhua Zhang, Qinghua Sun, Guoxi Guangdong Univ Petrochem Technol Sch Automat Maoming 525000 Guangdong Peoples R China South China Univ Technol Sch Automat Sci & Engn Guangzhou 510641 Guangdong Peoples R China Guangdong Univ Petrochem Technol Guangdong Prov Key Lab Petrochem Equipment & Fault Maoming 525000 Guangdong Peoples R China

The condition of bearings significantly impacts the healthy operation of rotating machinery. However, bearings are prone to failure under a harsh working environment and alternating load. Integrating time-domain, frequency-domain, and multi-sensor data information has been a remarkable way to improve the accuracy and robustness of bearing fault diagnosis. How to combine these pieces of information remains a significant challenge. A novel network architecture called time-frequency multi-sensor fusion network is developed to address this issue. Firstly, a multi-scale feature extraction module based on a one-dimensional convolutional neural network is proposed for extracting multi-scale information from time-domain signals. Secondly, a multi-sensor data fusion strategy based on scaled dot product attention is applied to facilitate feature interaction among multi-sensor data. Thirdly, a time-frequency fusion module is designed to fuse the time-domain and frequency-domain features from multi-sensor. Finally, the effectiveness and superiority of the proposed method are validated on the Paderborn dataset.

关键词： bearing fault diagnosis time-frequency fusion multi-sensor data fusion deep learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Aspects of Solving Rail-Track multi-sensor data fusion 6th

Collaborative Aspects of Solving Rail-Track Multi-sensor Dat...

引用

33rd International Conference on database and Expert Systems Applications (DEXA)

作者： Kromp, Florian Hinterberger, Fabian Konanur, Datta Wieser, Volkmar Software Competence Ctr Hagenberg GmbH Hagenberg Austria TMC Linz Austria

ISBN: (纸本)9783031143434;9783031143427

multi-sensor data fusion depicts a challenge if the data collected from different remote sensors present with diverging properties such as point density, noise and outliers. To overcome a time-consuming, manual sensor-registration procedure in rail-track data, the TransMVS COMET project was initiated in a joint collaboration between the company Track Machines Connected and the research institute Software Competence Center Hagenberg. One of the project aims was to develop a semi-automated and robust data fusion workflow allowing to combinemulti-sensor data and to extract the underlying matrix transformation solving the multi-sensor registration problem. In addition, the buildup and transfer of knowledge with respect to 3D point cloud data analysis and registration was desired. Within a highly interactive approach, a semi-automated workflow fulfilling all requirements could be developed, relying on a close collaboration between the partners. The knowledge gained within the project was transferred inmultiple partner meetings, leading to a knowledge leap in 3D point cloud data analysis and registration for both parties.

关键词： Remote sensing Point cloud analysis multi-sensor data fusion Interactive collaboration Knowledge buildup and transfer

来源：评论

学校读者我要写书评

暂无评论

Edge Computing-Enabled multi-sensor data fusion for Intelligent Surveillance in Maritime Transportation Systems 20

Edge Computing-Enabled Multi-Sensor Data Fusion for Intellig...

引用

IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech)

作者： Qu, Jingxiang Liu, Ryan Wen Nie, Jiangtian Deng, Xianjun Xiong, Zehui Zhang, Yang Yu, Han Niyato, Dusit Wuhan Univ Technol Sch Nav Wuhan 430063 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Singapore Univ Technol & Design Informat Syst Technol & Design Pillar Singapore Singapore Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China

ISBN: (数字)9781665462976

ISBN: (纸本)9781665462976

With the rapid development of navigation technologies, maritime transportation has become one of the mainstream international trade channels. However, a large number of maritime traffic accidents still occur every year, which cause significant economic losses and environmental damage. Intelligent and efficient surveillance in maritime transportation systems is essential for avoiding accidents. This paper proposes an edge computing-enabled multi-sensor data fusion method for intelligent maritime surveillance, which achieves efficient perception of maritime traffic information by receiving and processing visual and Automatic Identification System (AIS) data simultaneously. We first propose an anti-occlusion algorithm for vessel tracking based on visual trajectory analysis to mitigate missing detection caused by overlapping vessels. We then leverage the Hungarian algorithm driven by multidimensional feature analysis to match data collected by different sensors. The matched AIS information is eventually fused into the visual target of interest. Extensive experiments illustrate that our method can achieve effective information perception in different maritime environments with 91.67% accuracy and superior robustness.

关键词： Intelligent maritime surveillance multi-sensor data fusion vessel trajectory prediction anti-occlusion tracking Hungarian algorithm

来源：评论

学校读者我要写书评

暂无评论

multi-sensor data fusion BASED ON GCN-LSTM

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2022年第5期18卷 1363-1381页

作者： Xiao, Bohuai Xie, Xiaolan Yang, Chengyong Guilin Univ Technol Guangxi Key Lab Embedded Technol & Intelligent Sys 319 Yanshan St Guilin 541004 Peoples R China Guilin Univ Technol Sch Informat Sci & Engn 319 Yanshan St Guilin 541004 Peoples R China Guilin Univ Technol Network & Informat Ctr 319 Yanshan St Guilin 541004 Peoples R China

Due to the constraints of traditional multi-sensor systems with multiple sources and heterogeneity, the common fusion model is inefficient and error-prone, which is difficult to meet the demand for multi-sensor data fusion. To cope with this problem, this paper proposes a combined graph convolutional network (GCN) and long short-term memory (LSTM) algorithm to construct a feature-level fusion model for sensor data. The model uses GCN to extract features of multi-source heterogeneous data, which solves the problem of difficult fusion of heterogeneous data caused by differences in data types, and LSTM for feature extraction of time series, which solves the problem of gradient disappearance. Finally, the proposed model is validated on an industrial-grade data set, and the test results show the model's effectiveness.

关键词： multi-sensor data fusion Graph convolutional network Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A multi-sensor data fusion Method for Intelligent Aging Condition Identification of Viscoelastic Sandwich Structure

引用

IEEE ACCESS 2021年 9卷 63029-63042页

作者： Qu, Jinxiu Shi, Changquan Xian Technol Univ Sch Mech & Elect Engn Xian 710021 Peoples R China Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Peoples R China

Viscoelastic sandwich structure is playing an important role in mechanical equipment. The aging condition identification of viscoelastic sandwich structure is essential for monitoring structural health condition and guaranteeing the safe operation of mechanical equipment. The development of a reliable intelligent aging condition identification method is an ongoing attempt. By analyzing vibration response signals, a multi-sensor data fusion method using multi-scale permutation entropy (MPE) and ensemble-based incremental support vector machine (EISVM) is proposed in this paper. In this method, for obtaining complementary information, multiple sensors are mounted on the different locations of viscoelastic sandwich structure. For extracting effective feature information, MPE is introduced to reflect the structural aging condition change, and multiple feature sets of multiple sensors are obtained. With distance evaluation technique, multiple sensitive feature sets are respectively selected from the multiple original feature sets to discard irrelevant or redundant features. Based on ensemble learning and incremental learning, EISVM is developed to fuse all sensitive feature sets from different sensors for reliable intelligent classification. The proposed method is verified with a well-designed viscoelastic sandwich structure in which the viscoelastic layer subjected to accelerated aging. The testing results show the outstanding performance of the proposed method.

关键词： Feature extraction Aging Sandwich structures Vibrations Support vector machines Intelligent sensors data integration Viscoelastic sandwich structure aging condition identification multi-sensor data fusion multi-scale permutation entropy ensemble-based incremental support vector machine

来源：评论

学校读者我要写书评

暂无评论

Saliency area detection algorithm of electronic information and image processing based on multi-sensor data fusion

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2021年第1期2021卷 1-16页

作者： Zhang, Xinyu Ye, Kai Xian Univ Sch Informat Engn Xian 710065 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Automat Sci & Technol Xian 710049 Shaanxi Peoples R China

Researched in the 1980s, multi-sensor data convergence has become a hot issue. Not only does it differ from general signal processing, or single to multiple sensor surveillance and measurement, on the other hand, it is a higher level of integrated decision-making processes based on multiple sensor measurement outcomes, this paper is based on the study of the saliency area detection algorithm of electronic information and image processing based on multi-sensor data fusion, based on the improved FT algorithm and LC algorithm using multi-sensor data fusion technology, a new LVA algorithm is proposed, and these three algorithms are evaluated in an all-round way through various algorithm evaluation indicators such as PR curve, PRF histogram, MAE index, and recognition image rate. The research results show that the LVA algorithm proposed in this paper improves the detection rate of saliency maps by 5-10%.

关键词： multi-sensor data fusion Electronic information Image processing Saliency detection

来源：评论

学校读者我要写书评

暂无评论

Sanda training program based on multi-sensor data fusion in the internet of things environment

引用

INTERNET TECHNOLOGY LETTERS 2024年第2期7卷

作者： Zhou, Bin Harbin Sport Univ Harbin Peoples R China Harbin Sport Univ Harbin 150008 Peoples R China

Sanda, also known as Chinese kickboxing, is a Wushu that combines elements of traditional Kung Fu, kickboxing, and grappling. Considering that the use of action recognition can effectively improve the level of Sanda players, this study uses inertial sensors and visual sensors to collect the motion data of Sanda. A federated Kalman filter with time-varying parameters is designed according to the error form of each sensor to complete the data fusion. The main idea is that the whole system is divided into several local filtering systems, and a primary filter is designed for these systems. The main structure of the filter is a cascaded decentralized filtering structure composed of several local filters and a primary filter. The experimental results show that the proposed Sanda training scheme based on multi-sensor data fusion under the Internet of Things environment has high action recognition accuracy, and the joint inertial-vision model produces significantly better results than the other two models.

关键词： federated Kalman filter IoT multi-sensor data fusion Sanda

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis method of drum bearing based on multi-sensor data fusion under small samples

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第5期36卷

作者： Du, Xiangjun Zhang, Hongjie Yu, Ling Yang, Dengjie Tiangong Univ Sch Mech Engn Tianjin 300387 Peoples R China Tianjin Light Ind Vocat Tech Coll Tianjin 300380 Peoples R China

With the increasing complexity of industrial equipment, the fault diagnosis of rolling bearings, which are important rotating mechanical components, is particularly critical. Rolling bearing fault diagnosis under small-sample conditions faces challenges of data scarcity and insufficient model validity. In this paper, a fault diagnosis method based on multi-sensor data fusion is proposed to solve the problem of rolling bearing fault diagnosis under small-sample conditions. First, the multi-sensor time-frequency image fusion module is designed to convert the multi-source 1D vibration signals into multi-source 2D fused images by short-time Fourier transform, preserving the time-frequency characteristics of the original signals. Second, the expansion residual shrinkage weighting module is constructed to extract multi-scale features from multi-source information by using multi-scale expansion convolution and improved residual shrinkage module, while the global information selection mechanism is designed to allow the network to focus on key features. Finally, a pyramid feature fusion network is constructed to minimize the information loss phenomenon, and the identification of different states is performed using Softmax classifiers. Experimental validation was performed using the Case Western Reserve University bearing dataset bearing dataset and Southeast University bearing dataset bearing dataset, and the results show that the proposed method has excellent fault diagnosis and good generalization ability under small-sample conditions.

关键词： fault diagnosis multi-sensor data fusion expansion residual shrinkage weighting module global information selection mechanism

来源：评论

学校读者我要写书评

暂无评论

A New Evidence Weight Combination and Probability Allocation Method in multi-sensor data fusion

引用

sensorS 2023年第2期23卷 722-722页

作者： Ma, Li Yao, Wenlong Dai, Xinguan Jia, Ronghao Xian Univ Sci & Technol Coll Commun & Informat Engn Xian 710054 Peoples R China Xian Key Lab Heterogeneous Network Convergence Com Xian 710054 Peoples R China

A single sensor is prone to decline recognition accuracy in the face of a complex environment, while the existing multi-sensor evidence theory fusion methods do not comprehensively consider the impact of evidence conflict and fuzziness. In this paper, a new evidence weight combination and probability allocation method is proposed, which calculated the degree of evidence fuzziness through the maximum entropy principle, and also considered the impact of evidence conflict on fusing results. The two impact factors were combined to calculate the trusted discount and reallocate the probability function. Finally, Dempster's combination rule was used to fuse every piece of evidence. On this basis, experiments were first conducted to prove that the existing weight combination methods produce results contrary to common sense when handling high-conflicting and high-clarity evidence, and then comparative experiments were conducted to prove the effectiveness of the proposed evidence weight combination and probability allocation method. Moreover, it was verified, on the PAMAP2 data set, that the proposed method can obtain higher fusing accuracy and more reliable fusing results in all kinds of behavior recognition. Compared with the traditional methods and the existing improved methods, the weight allocation method proposed in this paper dynamically adjusts the weight of fuzziness and conflict in the fusing process and improves the fusing accuracy by about 3.3% and 1.7% respectively which solved the limitations of the existing weight combination methods.

关键词： D-S evidence theory maximum entropy multi-sensor data fusion the weight combination trust discount

来源：评论

学校读者我要写书评

暂无评论

Application Research and Improvement of Weighted Information fusion Algorithm and Kalman Filtering fusion Algorithm in multi-sensor data fusion Technology

引用

SENSING AND IMAGING 2023年第1期24卷 43-43页

作者： Liu, Qiuxia Heze Univ Coll Phys & Elect Engn Heze 274015 Shandong Peoples R China

In order to improve the accuracy and reliability of the collected data, the weighted information fusion algorithm and the Kalman filtering fusion algorithm in multi-sensor data fusion technology are researched and improved. Firstly, the definition of multi-sensor data fusion and the basic working principle of multi-sensor data fusion are expounded. Structural models of multi-sensor data fusion are introduced, the existing problems of multi-sensor data fusion are analyzed, the development trend of data fusion is pointed out. Secondly, the multi-sensor data fusion algorithms are analyzed, the weighted information fusion fusion algorithm and Kalman filtering algorithm in multi-sensor data fusion technology are focused on. Aiming at the deficiency of the weighted information fusion algorithm, an information fusion algorithm combining the jackknife method and the adaptive weighted method is proposed, and the basic steps of the improved fusion algorithm are given. The algorithm makes full use of the observed values and the estimated values of each historical moment, Quenouille estimation on the estimated values is performed by constructing pseudo-values. On the basis of the traditional Kalman filtering algorithm, an improved filtering algorithm is proposed, and a new state estimation equation is derived, which both treats the field value to prevent the filtering divergence, and introduces the observed value at the next moment to the state estimate at the current moment. Finally, improved fusion algorithms are applied and simulated in intelligent monitoring systems. Application and simulation results show that improved fusion algorithms are effective and superior, they have high reliability and anti-interference performances, the accuracy of the data is greatly increased, and they play a positive role in promoting the wide application of multi-sensor data fusion technology.

关键词： multi-sensor data fusion fusion algorithm data accuracy Intelligent monitoring system Simulations and analyses

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：