Papers by Keyword: Information Fusion

Paper TitlePage

Authors: Xiu Hu Tan
Abstract: For the multisensor systems with unknown noise variances, by the statistics method, the mathematical model and the noise statistics are essential, and this limitation was settled by adaptive algorithm. The adaptive Kalman filter was proposed to solve the filtering problem of the system with unknown mathematical model or noise statistics in information fusion. Based on the probability method and the scalar weighting optimal information fusion criterion in the minimum variance sense, the algorithm can not only optimize the multi-channel data, but also obtain the minimum mean square error (MMSE) by introducing fusion equation, namely the algorithm is optimal under the sense of MMSE, and the error is the least than the original Kalman information fusion algorithm. The test result shows that the algorithm can precede information fusion effectively under the distributed acquisition system.
Authors: Jun Hua Li, Hong Wei Quan, Xiu Yin Xue
Abstract: The simulation system for passive acoustic sensor network is an important part of information fusion system. Its main function is to simulate the detection process of acoustic sensor network and produce the simulation data which is needed for testing and evaluating the target tracking algorithms. For implementation of simulation system, the target motion model and the measurement model of passive acoustic sensor must be built, and a scenario will be defined in advance when it is running. This paper discussed the passive acoustic sensor network model and gave an information fusion system structure for passive acoustic sensor network. Then the basic principle of target detection for acoustic sensor is stated. Finally, we illustrated the operation process of a simulation system for passive acoustic sensor network.
Authors: Hong Xian Tian, Yun Ling Sun, Shu Yong Liu
Abstract: Rotor rub-impact fault may be diagnosed through several kind signal such as rotor vibration, stator vibration and rotor transient speed, and every signal include fault features of different side, so it is possible to improve diagnosis successful probability by mul-information fusing method. The fault identifying frame and combination diagnosis rules are determined using stator vibration and rotor transient speed signals. It is adopted to determine mass function by the S-function, and the deducing method is put up. After peak value of stator resonance demodulation and rotor transient speed fluctuation amplitude information are fused, the method is applied to diagnose rotor rub-impact fault successfully.
Authors: Hai Feng Li, Hui Zuo, Xu Feng Hua
Abstract: This paper issues the D-S evidence theory and modifies the fusion rule according to the relation of time and the NH3 content in water. A few concepts of D-S evidence theory and D-S evidence combination rule are presented. The modified D-S algorithm is simulated in time and space fusion of multi-sensor measurement system information. It could distinguish the main factor that changing the NH3 content in water. The measurement system cost could be decreased.
Authors: Yong Hong Zhu, Yan Fang Liu
Abstract: Roller kiln is a kind of advanced fast sintering kiln. In production process of roller kiln, materials sintering of burning zone is the key working procedure which affects product quality directly. Hence, the temperature detection process of burning zone became the key link in roller kiln control system. This paper proposed a kind of fusion method of both temperature point detection and flame image recognition of imitating ‘artificial-look-fire’. Flame image processing-based temperature detection scheme was also given. In the scheme, expert system fuses temperature data detected by the thermocouple with flame image data of burning zone detected by CCD so as to obtain the actual temperature of burning zone. The method proposed greatly improves the temperature detection precision of burning zone working conditions. The experimental results show that the proposed method is feasible and effective.
Authors: Yong Feng Zhang, Ren Bin Zhou, Jie Min Yang, Zheng Zhang
Abstract: In order to diagnose the fault, the fault of the unnormal automatic shift function of tracked vehicle is diagnosed by the FTA-FMEA method, according to the step of determine the top event, FTA(Fault Tree Analysis) qualitative analysis, self-checking and self-repairing by the user unit, FMEA(Failure Mode and Effects Analysis) analysis and locate the fault. The conclusion of the study can be conveniently guiding self-repairing by the user unit or repairing by the next higher level repair unit. Practice has proved, this method is simple and feasible, with high accuracy, has very important significance to guide the tracked vehicle repair.
Authors: Xu De Cheng, Hong Li Wang, Bing Xu, Xue Dong Xue
Abstract: Research and development of fault diagnosis system in application of integrated neural network information fusion is based on information fusion technology, with which preliminary analysis of equipment fault is made in different perspectives in terms of neural network, so as to identify the fault on the basis of fusion outcome. This technique is applied in fault diagnosis of one type of missile launching control unit, leading to sufficient use of various information and substantially increased fault diagnosis rate.
Authors: Zhong Qi Sheng, Chang Ping Tang, Hua Tao Fan, Chao Biao Zhang
Abstract: The structure and applications of multi-sensor information fusion technology are introduced systematically in this paper. Main fusion algorithms are summarized. The fusion applications are pointed out in machine-tool monitoring. The structure and information process of monitor system are discussed in the machine-tool monitoring.
Authors: Hua Ping Zhou, Bo Jie Xiong, Cheng Jun Wang
Abstract: In order to reduce the false alarm rate in coal mine fire warning system, we apply information fusion technology to the system and propose a fire forecast algorithm based on Rough Set Support Vector Machine ( RS-SVM ). Firstly, we map the feature description of coal mine fires to the knowledge representation system described by rough set; Secondly, we discrete the continuous attributes and eliminate the redundant information for attribute reduction to form a rule set of this knowledge representation system; At last, we use the above rule set as the training sample to optimize the parameters for the fire warning support vector machine. The experimental results show that the accuracy of the algorithm is very high. It can make timely and accurate prediction of coal mine fire.
Authors: Xiang Qi Liu, Xiang Ting Chong, Cheng Gang Zhen
Abstract: nformatization construction is a major issue of current social construction, and the technology of multi-source information fusion is an integral part of the information construction. This paper provides an overview of the technology of the multi-source information fusion, gives an introduction of the application of the technology of multi-source information fusion in industrial monitoring and fault diagnosis, and gives the direction of development and trends of the technology in the future according to the main problems in the research of the technology of multi-source information fusion.
Showing 21 to 30 of 148 Paper Titles