Multi-source data fusion method in clustering wireless sensor network

Abstract

The invention discloses a multi-source data fusion method in a clustering wireless sensor network, which comprises the following specific contents: a distributive data fusion structure is adopted; at all cluster-head nodes, an evidence set is preprocessed according to reliability degree of the member nodes in the cluster; based on the consistent intensity and the value of primitive supporting degree of the evidence, the evidence conflicts are distributed, the evidence combination sequence is optimized, the rules of conflicting evidence combination are established to synthesize all evidences; in connection with the evidence combination results, the value of the fine confidence interval of the primitive proposition is obtained by utilizing the uncertainty measure and the property supporting degree of the set; and then an evidence decision model is constructed based on the priority sequence of the fine confidence interval, and the final diagnosis is made. The method can improve the identifying accuracy ratio of the detected goal by the clustering wireless sensor network, and simultaneously and effectively reduce the transmitting volume of redundant data in the network and satisfy the application demands of the clustering wireless sensor network in the fields such as pipe leakage diagnosis, target tracking, environment detecting and the like.

Description

technical field [0001] The invention relates to the technical field of wireless sensor networks, in particular to a multi-source data fusion method in a clustered wireless sensor network. Background technique [0002] Wireless sensor network (WSN) is composed of a large number of micro sensor nodes deployed in the monitoring area, and forms a multi-hop, self-organizing network system through wireless communication. The sensor nodes in the wireless sensor network cooperatively perceive, collect and process the information of the sensing objects in the network coverage area, and transmit the information to the user terminal in a multi-hop relay mode, which has been widely used in military, environmental detection, fine-grained fields such as agriculture and intelligent transportation. Since the network may contain hundreds or even thousands of sensor nodes, in order to increase the scalability of the network and reduce the complexity of management, the network structure desig...

AI Technical Summary

Problems solved by technology

The form of the weighted average method is relatively simple and easy to implement, but its weight is not easy to determine, and it will produce certain errors; the Bayesian inference method is intuitive and has an axiom basis, which is suitable for the fusion processing of redundant data. However, the disadvantage is that it is required to give the assumption of prior probability and probability independence, which is highly subjective and cannot distinguish between "uncertain" or "unknown" information; fuzzy reasoning is the reasoning and fusion of fuzzy data acquired by multiple sensors, which can fully Using the fuzzy characteristics of real things, but the determination of the fuzzy membership function is more difficult, and its calculation is more complicated; the artificial neural network has strong self-learning, self-adaptive and self-fault-tolerant capabilities, which can solve the problem of mathematical construction in the process of information fusion. Difficult models, insufficient information, and poor real-time performance have been successfully applied in many fields; however, due to the influence of factors such as training sample selection, background interference noise, and time-varying effects of sensors, the diagnostic results of neural networks have certain limitations. the ambiguity of

Images