Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hybrid navigation mark alarm intelligent detection method

An intelligent detection and hybrid technology, applied to alarms, ship traffic control, instruments, etc., can solve problems such as inability to judge data, poor flexibility, poor alarm effect, etc., and achieve the effect of interpretability advantages

Active Publication Date: 2017-08-01
广州数字方舟信息技术股份有限公司 +1
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, the abnormality of some aids to navigation is regional, and the calculation at the RTU end cannot be judged by combining the data of adjacent RTUs
Secondly, the abnormality of some navigation marks is a gradual change process (such as the position deviation of the navigation mark), but the rule-based method is less flexible, and the alarm effect is poor in such scenarios

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
  • Hybrid navigation mark alarm intelligent detection method
  • Hybrid navigation mark alarm intelligent detection method
  • Hybrid navigation mark alarm intelligent detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

[0036] The present invention provides a hybrid intelligent detection method for navigation mark alarm, please refer to figure 1 with figure 2 , The steps include:

[0037] 1. Find similar sites based on historical data; it specifically includes the following steps:

[0038] 1.1 Regarding historical timing data, each site is taken as an element of the cluster, the basic information characteristics and historical timing data characteristics of each site are selected, and the values ​​(or numerical values) of each feature corresponding to each site are calculated according to the selected characteristics. group). The basic information features include the longitude, latitude, historical water level, historical temperature and other information of the site. The histo...

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 provides a hybrid navigation mark alarm intelligent detection method comprising the steps that 1) similar stations are discovered according to historical timing data and historical alarm data so as to obtain similar station division and similar station data; 2) alarm model training is performed according to the similar station division and similar station data, the historical alarm data and the historical timing data of a previous period of time of the alarm moment so as to generate a secondary alarm model; 3) the real-time alarm data and the historical timing data of a previous period of time of the alarm moment are inputted to the secondary alarm model so as to perform alarm result judgment; and 4) the alarm model in the step 2) is corrected according to the alarm result and the artificial feedback alarm result. According to the method, the navigation mark abnormity can be alarmed through combination of the data mining method and the artificial feedback under the premise of fully using the domain knowledge. Besides, the accuracy of alarm judgment can be effectively enhanced by the method.

Description

Technical field [0001] The invention relates to the field of waterways and water transportation, and in particular to a hybrid type navigation mark alarm intelligent detection method. Background technique [0002] The navigation mark telemetry and remote control system based on the Internet of Things and big data analysis, comprehensively using wireless digital communication GPRS technology, Beidou and GPS positioning technology, microprocessor technology, embedded system and other modern information processing technologies to realize automatic monitoring of navigation lights. And analysis, automatic monitoring and analysis of high-precision navigation mark displacement positioning, automatic monitoring and analysis of the working condition of navigation mark accessory equipment. [0003] In the remote control navigation system, the remote terminal unit (RTU) can collect the status of the navigation mark in real time and return it to the control center regularly. However, due to f...

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): G08G3/00G08B29/18
CPCG08B29/18G08G3/00
Inventor 陶永陈金柱邓仕戈杜一沈志宏吴章生
Owner 广州数字方舟信息技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com