Markov jump based distributed event triggered filtering system and design method thereof

Abstract

The invention relates to a Markov jump based distributed event triggered filtering system and a design method thereof. The system comprises N filtering links, and is characterized in that each filtering link comprises a sensor, an event trigger, a zero-order retainer and a filter which are sequentially connected, the sensors are connected with a measured object, the filter in each filtering link further performs communication connection with the other neighbor filters, the communication topology among the N filters in the system is of a non-homogeneous Markov jump mode, the mutually connected filters perform information exchange under each type of non-homogeneous Markov link topology, and the filter in each filtering link is further connected with the corresponding event trigger in the filtering link. Compared with the prior art, the Markov jump based distributed event triggered filtering system has good anti-noise capacity, effectively reduces the number of data transmission times under the premise of ensuring the filtering performance and saves network resources.

Description

technical field [0001] The invention relates to a filtering system and a design method, in particular to a Markov jump-based distributed event-triggered filtering system and a design method. Background technique [0002] Most of people's daily life behaviors are closely related to the development, collection, transmission and processing of information resources. Especially in the 21st century, people put forward higher standards for the way of obtaining information, and the standard requires more accurate information. Accurate real-time dynamic information collection is the premise of precise analysis. Although the commonly used data collection system is effective, with the ever-increasing high-precision requirements, increasingly complex experimental environment and interference from measurement noise, the existing data collection methods can no longer meet the requirements. people's demands. [0003] As a new way of information acquisition in wireless sensor network, its...

AI Technical Summary

Problems solved by technology

However, due to the complexity and variability of the objective environment, it is difficult for the transition probability of the actual system to remain stable for a long time. Therefore, it is necessary to consider the time-varying and uncertainties of the transition probability in the estimation process

Images