Bridge state evaluation method based on discrete dynamic Bayesian network

Abstract

The invention relates to the technical field of bridge structure state evaluation, discloses a bridge state evaluation method based on a discrete dynamic Bayesian network, and solves the defect that the existing bridge structure state evaluation method cannot be updated through detection information. The method comprises the following steps: establishing a bridge state assessment system frameworkby utilizing an analytic hierarchy process, setting each component element in an assessment system as a node in a discrete dynamic Bayesian network, endowing the node with a discrete value domain according to the division level of a structure state, and establishing a dynamic Bayesian network model suitable for bridge structure state assessment according to a time sequence; learning a discrete state sample generated by using an analytic hierarchy process to obtain model parameters. According to the method, the model is updated by comprehensively utilizing the detection information of the actual condition of the specific structure, the structural problem of the complex relationship of the bridge state is solved through the dynamic Bayesian network of the Bayesian theory, and the bridge structure state is effectively evaluated.

Description

technical field [0001] The present invention relates to the technical field of bridge structure state evaluation, in particular to a bridge state evaluation method based on a discrete dynamic Bayesian network, in particular to a bridge state using a discrete dynamic Bayesian network with span concrete girder bridges as state evaluation objects assessment method. Background technique [0002] In recent years, researchers have made many achievements in the evaluation of bridge structure status based on theoretical research, experimental research, and measured data, and proposed many methods, such as: expert evaluation method, gray system evaluation method, fuzzy theory evaluation method, Analytic Hierarchy Process, Reliability Evaluation Method, etc. The common problem with the above evaluation methods is that no matter which method or model is placed on a certain fixed formula, it cannot be effectively combined with reality, and the existing method or model cannot be updated...

AI Technical Summary

Problems solved by technology

The common problem with the above evaluation methods is that no matter which method or model is placed on a certain fixed formula, it cannot be effectively combined with reality, and the existing method or model cannot be updated through detection information, so it is impossible to make comprehensive use of structural degradation. Prior understanding of general laws and detection information reflecting the actual situation of specific structures

Images