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

Abnormality detection method, system and equipment for ocean timing sequence observation data

A technology for observational data and anomaly detection, applied in electrical digital data processing, design optimization/simulation, climate sustainability, etc., to solve problems such as limited effective application and lack of contextual modeling capabilities for time series data

Active Publication Date: 2021-04-20
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These traditional machine learning methods have limited their effective application due to the lack of contextual modeling capabilities for time series data.

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
  • Abnormality detection method, system and equipment for ocean timing sequence observation data
  • Abnormality detection method, system and equipment for ocean timing sequence observation data
  • Abnormality detection method, system and equipment for ocean timing sequence observation data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] An anomaly detection system for ocean time series observation data, including

[0062] The data acquisition module is configured to collect ocean observation data; the ocean observation data includes one or more of chlorophyll content, dissolved oxygen content, colored dissolved organic matter content, and turbidity.

[0063] The preprocessing module is configured to preprocess the ocean observation data, and obtain the target data points and target data point sequences of the ocean observation data within the preset time period. The preset time period can be 5min, 10min, 30min, etc. The detection environment is determined; the preprocessing includes numerical normalization and time series segmentation of the ocean observation data, and scaling the target data to between 0 and 1, which is convenient for the learning, training and reasoning of the LSTM model. The RRCF model does not clearly stipulate whether the numerical range of the data needs to be scaled, so it can b...

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 anomaly detection method, system and device for ocean timing sequence observation data. The anomaly detection method for the ocean timing sequence observation data comprises the following steps of the ocean observation data being collected and preprocessed; a CoDisp value being calculated; obtaining a predicted value of the marine observation data at the moment t based on the predicted data point sequence; subtracting the predicted value from a target data point x value actually measured at the moment t, and calculating an absolute value to obtain a PredDiff value; and respectively carrying out statistical modeling on the CoDisp value and the PredDiff value within a preset duration, obtaining probability distribution of the CoDisp value and the PredDiff value, and calculating an abnormal probability of each target data point in the detection window based on the obtained probability distribution. The dynamic anomaly probability determination method based on the sliding window can solve a problem that a manually set threshold value lacks a scientific basis, and plays an anomaly detection role in practical application.

Description

technical field [0001] The invention relates to intelligent quality control of marine data, in particular to an anomaly detection method, system and equipment for marine time-series observation data. Background technique [0002] The 21st century is the "ocean century", and the competition among world powers has extended to the field of marine science, especially in the field of marine information. Countries have accelerated and increased investment in scientific research and infrastructure in related directions, with the goal of mining marine big data And build smart ocean applications. However, ocean observation data include data inconsistency, data redundancy, data missing, and data type confusion. Data mining is carried out from these large amounts of incomplete, fuzzy, and noisy ocean observation data to extract hidden potential information. Valuable oceanographic information and knowledge presents great challenges. Quality control of these noise observation data is a...

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
IPC IPC(8): G06F30/27G06F119/02
CPCY02A90/10
Inventor 李响赵志刚潘景山郭莹王春晓刘召远霍吉东张俭
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN