Weighted assignment fusion algorithm of evidence conflict based on Euclidean distance and weighting strategy, and application in the wind turbine system

Abstract

In the process of intelligent system operation fault diagnosis and decision making, the multi-source, heterogeneous, complex, and fuzzy characteristics of information make the conflict, uncertainty, and validity problems appear in the process of information fusion, which has not been solved. In this study, we analyze the credibility and variation of conflict among evidence from the perspective of conflict credibility weight and propose an improved model of multi-source information fusion based on Dempster-Shafer theory (DST). From the perspectives of the weighting strategy and Euclidean distance strategy, we process the basic probability assignment (BPA) of evidence and assign the credible weight of conflict between evidence to achieve the extraction of credible conflicts and the adoption of credible conflicts in the process of evidence fusion. The improved algorithm weakens the problem of uncertainty and ambiguity caused by conflicts in the information fusion process, and reduces the impact of information complexity on analysis results. And it carries a practical application out with the fault diagnosis of wind turbine system to analyze the operation status of wind turbines in a wind farm to verify the effectiveness of the proposed algorithm. The result shows that under the conditions of improved distance metric evidence discrepancy and credible conflict quantification, the algorithm better shows the conflict and correlation among the evidence. It improves the accuracy of system operation reliability analysis, improves the utilization rate of wind energy resources, and has practical implication value.

E-Commerce Fraud Detection Model by Computer Artificial Intelligence Data Mining

“…This level includes machine learning (ML), platforms, and application technologies (computer vision (CV), speech recognition (SR), natural language processing (NLP)). Also, recent years have witnessed China's extensive research and development efforts of vertical technologies, resulting in mature technologies and obvious competitive advantages CV and SR. On the other hand, IFT can collect and integrate various information sources, multimedia, and multiformat information to generate a complete, accurate, timely, effective, and comprehensive information process [ 22 , 23 ]. Figure 2 gives the working principle of a multisource information fusion system (IFS).…”

Research on mechanical fault diagnosis based on MADS evidence fusion theory

“…To further validate the robustness and reliability of the model, random error data were added to the original data to The improved MADS algorithm is tested now, and the results showed that the diagnosis results of the evidence fusion theory algorithm proposed in this work had a higher accuracy rate of 99.80% compared with the diagnosis results of a single vibration signal; the measured height conflict rate was 0.91%, When there is a high degree of conflict, this model handles highly conflicting data better, and the algorithm can throw an exception while giving the diagnosis result to prevent misjudgment; when there is no high degree of conflict, the accuracy rate is as high as 99.91%, which proves the effectiveness of the evidence fusion algorithm. Even if the random error rate reaches 15% during the robustness test, the classification accuracy [39] 0.5218 0.7934 0.8328 Gou et al [40] 0.5597 0.6048 0.8744 Our MADS 0.8698 0.9775 0.9932 DS S({F 6 }) 0.3245 0.5424 0.5582 Ghosh et al [28] 0.4524 0.8257 0.8553 Ma et al [39] 0.5177 0.7729 0.7418 Gou et al [40] 0.5269 0.5967 0.8523 Our MADS 0.8378 0.9675 0.9835 DS S({F 9 }) 0.3048 0.5298 0.5582 Ghosh et al [28] 0.4496 0.8037 0.8553 Ma et al [39] 0.5165 0.7579 0.7418 Gou et al [40] 0.5129 0.5563 0.8523 Our MADS 0.8251 0.9543 0.9749 remains over 95%. The findings of the confusion matrix test demonstrate that the UVTM technique can successfully exclude samples from uncertain categories and enhance the model's capacity to discriminate diagnostic results with low confidence.…”

Design and Development of Map Vertical Social Platform Based on LBS

“…By collecting the tags of users' historical participation activities and the personalized tags filled by users themselves, we learn to calculate users' preferred interests, and based on this, we calculate the similarity between users and each item in the set of items to be recommended, and then sort and recommend them to the users according to the similarity calculation results. Since the data of this system are mainly low-dimensional data and need more accurate results, we compare several distance calculation formulas and finally use Euclidean Metric to calculate the similarity, which has the advantages of easy understanding and simple calculation, and the formula for calculating the distance between two points in n-dimensional space is shown in equation (1) [10][11][12] .…”