A method and system for ship collision risk assessment based on data mining

Abstract

This disclosure is about a method and system for assessing the risk of ship collision based on data mining. According to the statistical historical data of ship collision, the cumulative autoregressive moving average model is used to predict the occurrence times of the causative factors, and the principal component analysis method is used to analyze the Carry out dimensionality reduction calculations, use the obtained principal components as the input of the first neural network, and predict the probability of collision; use decision tree analysis to find high-confidence, frequent accident sequences, and use the neural network model to calculate the number of injuries, deaths and property losses , and carry out standardization and normalization processing to eliminate the influence of magnitude and dimension; use expert system and fuzzy analytic hierarchy process to assign different weights to the indicators to quantify the consequences of collisions. According to the above content, developing a ship collision risk assessment system based on data mining can quantitatively predict the ship collision risk and provide real-time guidance for ship maneuvering, collision avoidance emergency and on-site disposal, which can effectively reduce losses.

Description

technical field [0001] The present disclosure relates to the technical field of traffic management, in particular to a data mining-based ship collision risk assessment method and system. Background technique [0002] Among the many modes of transportation, waterway transportation is generally recognized and accepted for its low cost and large transportation volume. Water transportation has developed rapidly. occurred, resulting in varying degrees of property damage, casualties and environmental pollution. [0003] Because there are many factors that lead to ship collision accidents: including ship factors, environmental factors, and human factors, it is difficult to fully quantify the risk of collision due to the uncertainty of these causative factors. At present, qualitative or semi-quantitative methods are usually used to evaluate the risk of ship collision, so that corresponding ship management measures can be taken according to the evaluation results to prevent the occu...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a data mining-based ship collision risk assessment method and its system to solve the problems in the prior art that the accuracy of risk assessment is poor and the risk of ship collision cannot be reduced

Images