Papers by Keyword: DS Evidence Theory

Abstract: BP neural network and evidence theory data fusion technology can be used in troubleshooting electronic equipment, from the simulation results show that the fault diagnosis method based on evidence theory and BP neural network can effectively diagnose faults in analog circuit, and it has automated intelligent characteristics.

Abstract: As a common fault of motor, the short circuit of rotor winding is important for the accurate diagnosis. In this article, the author collected every status parameter of motor by different sensors, using two BP neural networks to partly diagnose the motor and fusing the results of partly diagnosis by D-S evidence theory. The author increases the creditability of diagnosis results by practices and decreases uncertainty, showing the efficiency of this method.

Abstract: According to the problem that the difference of test mode, mixed quantitative and qualitative information of electromechanical equipment state prediction, a state prediction method based on information fusion was proposed in this paper. It was used DS evidence theory to fuse decision level information of electromechanical equipments at this method. Simulation results showed that it is feasible and effective that information fusion technology is applied on the state prediction for mechanical and electrical equipment. Information for decision-making integrated repeatedly by different forecasting methods, can greatly reduce the blindness of judgment and improve the accuracy of state prediction.

Abstract: The hydraulic cylinder is an important actuator in hydraulic system, and its leakage has a great influence on the performance of the hydraulic system. Therefore, researching the accurate identification of hydraulic cylinder leakage fault is very important to eliminate leakage fault as soon as possible. Based on the fault mechanism, the paper proposes a fault diagnosis method for hydraulic cylinder based on displacement signal and pressure signal fusion. BP neural network and DS evidence theory are respectively used for fault mode identification. Through the research, it is found that combining the two methods can improve the identification accuracy of hydraulic cylinder leakage failure mode.

Abstract: Focuses on how to dispose the multi-source uncertain information and promote the testability evaluation and fault diagnosis capability of the electronic equipment, this paper uses fuzzy theory in the uncertain information description and modeling. Based on the fuzzy set description of fuzzy target, new method is proposed to obtain fuzzy evidences from fuzzy fault features, and then, Dempster-Shafer combination rule are used to fuse multi-source fuzzy evidence to get diagnosis results. The proposed method of fuzzy evidence extraction can reduces uncertainties in fusion makings and improves fault identifications, and the fusion diagnosis method based on multi fuzzy evidence matching enhances the precision and reliability of the system fault diagnosis decision furthermore.

Abstract: This paper presents a model by combining BP neural network and DS evidential reasoning, which not only achieves the feature level fusion of all subjective and objective evidences in various domains and layers, but also makes distinct models complement each other. By the experiment, this method improves classification precision by 7.9 percent and reduces the time complexity of algorithm. The model solves the problems such as high complexity of algorithms and low accuracy rate of classifications lie in the flood prediction using single models.

Abstract: The study on driver’s intention recognition is useful to improve the conclusion accuracy of the risk assessment in current vehicle driving safety precaution system. DS evidence theory is used to study a recognition method for driver’s intention. In order to improve the accuracy of driver’s intention recognition, the driving sequential actions and the driver’s characteristics are also taken into account. The detailed steps of the recognition method for driver’s intention are presented. And the experimental result shows that the recognition method is feasible and effective.

Abstract: As only using Euclidean distance KNN algorithm has its limits, many researchers use other distance calculation methods as the replacement it to improve the accuracy of Data Classification. While combining the DS evidence theory with a series of KNN algorithm which discussed in this paper, we found that every algorithm has their merits. All of them ignore the analysis of the data set, through deeply analysis we found that the actual distance is determined by the larger value when two attribute values are in great difference. Therefore, what we do next is to compress the large-dimensional numerical data values. By this way, the accuracy of KNN, VSMKNN, KERKNN algorithm are obviously improved after experiment and then these new methods are called CDSKNN, CDSVSMKNN, CDSKERKNN.

Abstract: Factors that affect the safety of coal mine roof is a multi-faceted, information fusion technology can take full advantage of multi-source information complementary, comprehensive, and improving information quality and credibility of coal mine roof safety. In analyzing the current monitoring means, a coal mine roof safety evaluation model is presented based on information fusion, and given information processing steps of multi-sensor data analysis, processing, distribution and integration based on Dempster-Shafer evidence theory; For the elimination of multi-source data fusion of uncertain factors, proposed coal mine roof safety decision-making rules; The simulation analysis shows that the validity of the model and practicality.

Abstract: Outer space target recognition is one of kernel functions of space-based surveillance system. This paper presents a new method on space target recognition based on image sequence using wavelet moments and DS evidence theory. Experimental results show our recognition system has a good performance (100%) which achieves need of practical application.