Time Series Parameter Correlation Analysis for Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing time series data from systems like satellites or space probes are labor-intensive and prone to overlooking correlations between time series parameters and anomalies or operation states, requiring manual guesswork and extensive analysis.
Innovation Solution
A method that automatically determines which time series parameters are correlated with a specific operation state by comparing characteristic parameters across multiple time periods, using statistical and mathematical parameters to identify similarities and differences, thereby reducing the reliance on engineer knowledge and increasing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual analysis methods are used to identify correlated time series parameters, then analysis can be performed with existing tools, but the process becomes labor-intensive and time-consuming
Solution Approach 1:
The system automatically performs anomaly detection and correlation analysis without requiring manual engineer intervention. The computer automatically identifies time series parameters correlated with anomalies by comparing characteristic parameters across multiple time periods, enabling the system to analyze itself and reduce dependency on manual labor
Solution Approach 2:
The patent replaces manual mechanical analysis processes with automated computational methods. Instead of engineers manually examining time series data and guessing correlations, the system uses automated algorithms to calculate characteristic parameters and statistically determine correlations between time series parameters and operation states
2Reliability
If manual guesswork is used to identify correlated parameters, then analysis can proceed without automated tools, but correlations may be overlooked and reliability decreases
Solution Approach 1:
The system uses feedback loops where characteristic parameters are calculated from time series data, compared across multiple time periods, and used to determine correlations. The process iteratively refines identification of correlated parameters by continuously comparing operation states and parameter behaviors, ensuring reliable detection without overlooking correlations
Solution Approach 2:
The patent transforms the analysis approach by changing from manual parameter inspection to automated characteristic parameter calculation. By defining specific characteristic parameters (such as statistical measures like mean, standard deviation, or other temporal characteristics) and systematically comparing them across different operation states, the system reliably identifies correlations that would be difficult to detect manually
3Productivity
If automated analysis methods are implemented, then productivity and reliability improve, but the system requires more complex processing and computation
Solution Approach 1:
The patent segments the complex analysis task into distinct computational steps: (1) identifying multiple time periods with different operation states, (2) calculating characteristic parameters for each time series parameter in each time period, (3) comparing characteristic parameters across time periods, and (4) determining correlations based on comparisons. This segmentation makes the automated system more manageable and implementable despite the overall complexity
Data Source
Figure 1
Figure 2
Figure 2
AI summary
The present invention relates to a method and an apparatus for determining which one or more time series parameters of a plurality of time series parameters relating to operation of a system are correlated with a first operation state of the system. According to the invention, the method comprises providing time series data including data relating to a time series of each of the plurality of time series parameters; determining at least two first time periods, wherein the system is in the first operation state during the at least two first time periods; determining at least one second time period, wherein the system is in a second operation state during the at least one second time period; determining, for each respective time series parameter of the plurality of time series parameters, a first characteristic parameter relating to a first characteristic of the time series of the respective time series parameter for each of the at least two first time periods and the at least one second time period; and determining which one or more time series parameters of the plurality of time series parameters relating to the operation of the system are correlated with the first operation state of the system by determining, for each respective time series parameter of the plurality of time series parameters, whether or not the respective time series parameter is correlated with the first operation state of the system based on the first characteristic parameters of the respective time series parameter determined for each of the at least two first time periods and the at least one second time period.