Abstract:

The fuzzy transition region of the overlapping between each level of the equipment status can lead to the problem of the subjectivity of the state division. At the same time, in order to improve the accuracy of the state estimation method based on multipul feature parameter fusion, Dezert-Smarandache (DSm) evidence modeling and condition assessment method based on cloud matter element model is proposed. Firstly, the characteristic parameters are assigned to the DSm membership based on the cloudmatter element model. Then a modified formula of evidence source based on the grey target contribution rate is proposed. According to the relationship between the membership and basic probability assignment (BPA), the BPA of the DSm model is obtained. Finally, the different characteristic parameters of BPA are fused to get the evaluation results by DSm theory+proportional conflict redistribution rules (DSmT+PCR5). The effectiveness and superiority of the new method are verified by analyzing the condition assessment of the radar seeker.