High-conflict evidence fusion method based on fuzzy reasoning

Abstract

The invention discloses a high-conflict evidence fusion method based on fuzzy reasoning, relates to a road condition assessment method based on an automobile physical information fusion system, and belongs to the technical field of multi-sensor data fusion. The method is based on the VCPS technology. The method comprises the steps of acquiring real-time operation information of an automobile, forming evidence for judging the current road condition by multiple automobiles, calculating support probability distribution of an evidence source through a support probability function, further obtaining a maximum distance and an average distance of probability distribution between evidences, and performing effective measurement on a conflict degree between the evidences through a fuzzy reasoning mechanism. And on the basis, the support degree and the credibility of the evidence can be obtained. The method also considers the uncertain information of the evidence at the same time, and calculatesthe relative importance of the evidence through Dane entropy. And the weight of the evidence is obtained by combining the credibility and the importance, and finally weighted average is performed on the evidence to obtain an average evidence. And finally, the average evidence is integrated for multiple times by utilizing a DS combination rule to obtain a reliable assessment evidence.

Description

technical field [0001] The invention relates to a high-conflict evidence fusion method based on fuzzy reasoning, in particular to a road condition evaluation method based on a vehicle physical information fusion system (VCPS), and belongs to the technical field of multi-sensor data fusion. Background technique [0002] With the development of sensor technology, the research of multi-sensor data fusion technology has also developed rapidly. The existing data fusion techniques include statistical reasoning method, estimation theory method, information theory method, and artificial intelligence method. Among them, the most widely used data fusion technology is DS evidence theory. [0003] With the development of CPS, intelligent transportation has taken a big step, and the research of automobile CPS has been widely concerned by many scholars. Among them, the traffic road condition assessment method based on automobile CPS has become a hot research direction. Due to the compl...

AI Technical Summary

Problems solved by technology

Due to the complexity and diversity of traffic equipment, the mass data of traffic road network monitoring will be redundant, missing, and wrong due to random factors and internal factors of equipment (such as monitoring equipment damage), which greatly reduces the quality of data sources. , the traditional road condition evaluation method based on traffic equipment is becoming less and less suitable for the development of today's intelligent transportation

At the same time, the traditional traffic road condition evaluation method often only considers a state index of the traffic operation state, such as judging the congestion state based on the speed of the road section, or judging the congestion state based on the traffic density. However, these single indexes can no longer correctly describe and evaluate the road condition state.

Therefore, a multi-sensor-based traffic road condition assessment method was proposed, but because the sensor equipment also faces the same problem, the collected data also has uncertainty and conflict, resulting in poor reliability of the fusion results obtained in the final fusion assessment.

The fundamental reason is that the current traffic condition assessment method cannot effectively deal with multi-source high-conflict data. Although the fusion of DS evidence theory can handle uncertain data well, it will produce counter-intuitive results when high-conflict evidence is fused. , which cannot meet the reliability requirements of the application system

Images