Unlock instant, AI-driven research and patent intelligence for your innovation.

New algorithm for sensitivity analysis of ship data

A sensitivity analysis and data technology, applied in computing, computer components, instruments, etc., can solve the problem of high cost of conditional density function estimation, and achieve the effect of improving efficiency

Inactive Publication Date: 2019-01-01
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the variance-based sensitivity analysis method is not applicable to the case where the output distribution is highly skewed and multi-modal, and the density-based sensitivity analysis method is that the conditional density function estimation cost is too large

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
  • New algorithm for sensitivity analysis of ship data
  • New algorithm for sensitivity analysis of ship data
  • New algorithm for sensitivity analysis of ship data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Such as figure 1 Shown: A new algorithm for sensitivity analysis of ship data, including the following steps: ① preprocess the collected raw sensor data, remove noise data and normalize the data; ② divide the preprocessed data into For training samples and test samples, use SVM to train to obtain an optimal ship motion model; ③ use the sensitivity analysis method PAWN based on cumulative distribution function, use the trained model to analyze the sensor data of the ship, and get each input The proportion of the parameters that affect the ship's motion, that is, the sensitivity index, is finally visualized to show the results.

[0028] Here we only study one ship motion parameter (ship heading)

[0029] Specific steps are as follows:

[0030] 1. Preprocess the collected raw sensor data, including data cleaning and normalization:

[0031] ① Data cleaning Data Cleaning: Use hierarchical clustering algorithm to delete outliers (noise). If the distance between an object a...

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

A novel algorithm for sensitivity analysis of ship data includes the following steps: (1) preprocessing the collected original sensor data; 12) dividing the preprocessed data into a training sample and a test sample, and training the data with SVM to obtain an optimal ship motion model; (3) the sensitivity analysis method PAWN based on cumulative distribution function being used to analyze the sensor data of the ship, and the sensitivity index, which is the influence ratio of each input parameter on the ship motion, is obtained; (4), the results being displayed vividly by visualization. The algorithm is used to find the input parameters which have a great influence on the ship motion, and provides a good reference standard for the future control and prediction of ship motion.

Description

technical field [0001] The invention belongs to an algorithm for data, in particular to a novel algorithm for ship data sensitivity analysis. Background technique [0002] With the increase of offshore operations, the reliability and safety of ship maneuverability has become increasingly important, which has also aroused great concern in the marine field. Since ships are affected by various factors at sea, such as human factors, and external disturbances such as sea wind and waves, in order to ensure the safety of ships, various sensors will be installed on the hull, such as radar, laser and GPS / INS. These sensors have collected data for a long time to form very large big data (Big Data), which has the characteristics of high dimensionality, nonlinearity and noise, so it is necessary to carry out sensitivity analysis on ship data and filter out Those parameters that have a greater impact on ship motion are beneficial to control and predict ship motion. [0003] However, ...

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): G06K9/62
CPCG06F18/23G06F18/2411G06F18/214
Inventor 赵萌陈胜勇王春林程徐
Owner TIANJIN UNIVERSITY OF TECHNOLOGY