Offshore channel risk early warning method based on dynamic Bayesian network

A dynamic Bayesian, risk early warning technology, applied in probabilistic networks, based on specific mathematical models, data processing applications, etc., can solve the complexity of risk source factors, the difficulty of obtaining risk source factor data, and the uncertainty of sea channel risks. And other issues

Pending Publication Date: 2022-06-24
ZHEJIANG SCI RES INST OF TRANSPORT
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved in the present invention is to construct a sea channel risk early warning model based on a dynamic Bayesian network, aiming at the characteristics of the uncertainty of the risk of the sea channel, the complexity of the risk source factors, and the difficulty in obtaining the data of the risk source factors. Introduce the DBN model into the field of sea channel risk early warning, and provide early warning of sea channel risk when some data are missing

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Offshore channel risk early warning method based on dynamic Bayesian network
  • Offshore channel risk early warning method based on dynamic Bayesian network
  • Offshore channel risk early warning method based on dynamic Bayesian network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] Example 1: Take the Indian Ocean waters from 20 to 80 east longitude and 40 north latitude to 40 south latitude as the research object of sea channel risk warning, select 298 emergencies from 2007 to 2016 as the parameter learning samples, and 259 emergencies from 2008 to 2017. incidents as risk warning samples. The specific data in the emergency sample comes from the wind speed data from Remote Sensing Systems, the weather forecast data for the sea area released by the Meteorological Center, the statistical data of ship traffic, the data of military exercises, and the "Hull War, Piracy, Terrorism and Related Perils" report; and discretize the data, after processing, the state description and discretization value of each node data are obtained as shown in Table 3 below.

[0088] Table 6. Classification description and discretization results of dynamic Bayesian network node variables

[0089]

[0090]

[0091] like image 3 and Figure 4 As shown, after applying...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an offshore channel risk early warning method based on a dynamic Bayesian network. The method comprises the following steps: identifying offshore channel risk influence factors and establishing a dynamic Bayesian risk early warning model; according to the method, main risk source factors influencing the safety of the offshore channel are systematically analyzed and counted according to the emergency of the offshore channel, and an offshore channel risk early warning model based on the dynamic Bayesian network is established; a risk early warning comparison model is carried out, the effectiveness and accuracy of the DBN model are verified, and the comparison result shows that the accuracy and the F value of the DBN model are better than those of the comparison model, which indicates that the offshore channel risk early warning model based on the DBN can accurately early warn the offshore channel risk condition; a sensitivity analysis method is applied to identify key influence factors influencing offshore channel risks, and related suggestions are provided for ship navigation according to a sensitivity analysis result.

Description

technical field [0001] The invention relates to the technical field of emergency management systems, in particular to a sea passage risk early warning method based on a dynamic Bayesian network. Background technique [0002] A Dynamic Bayesian Network (DBN) is a Bayesian network that associates different variables with adjacent time steps. This is often referred to as a "two time slice" Bayesian network, because the DBN at any time point T, the value of the variable can be computed from the intrinsic regressor and the direct prior (time T-1). [0003] Expectation-Maximization algorithm (EM), or Dempster-Laird-Rubin algorithm [1], is a class of optimization algorithms for Maximum Likelihood Estimation (MLE) through iteration [2], usually as An alternative to the Newton-Raphson method is used for parameter estimation of probabilistic models containing latent variables or incomplete-data. [0004] The Viterbi algorithm (Viterbi) is a dynamic programming algorithm used to find...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q10/08G06N7/00
CPCG06Q10/0635G06Q10/083G06N7/01
Inventor 蒋美芝郝英君曹更永
Owner ZHEJIANG SCI RES INST OF TRANSPORT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products