Time sequence key value type industrial process data parallel analysis method
A technology of industrial process and analysis method, which is applied in the field of parallel analysis of time series key-value industrial process data, and can solve the problems of long time series data and lack of consideration of time series trend characteristics
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0045] Example: such as figure 1 Shown; A time series key-value type industrial process data parallel analysis method, it includes:
[0046] S1: Obtain time series data;
[0047] S2: data preprocessing;
[0048] S3: Split the time series data in parallel, obtain the turning points and corresponding slopes as key data points, and construct the key data points as a new time series.
[0049] S4: Based on the dynamic time warping method, the improved distance measure and the parallel calculation of the curved path matrix are used for similarity discrimination and classification, as shown in Table 1.
[0050] Table 1 Parallel computing curved path table
[0051]
[0052] Among them, S1, S2, and S3 are subsequences of the time series S, and C is the time series. The shortest curved path is: The font in bold in Table 1, namely (S 2 , C)=(71,69) is 2 and 3; (S 2 , C)=(73,73) is 5; (S 2 , C)=(73,75) is 4; (S 2 , C)=(80,79) is 35; (S 2, C)=(80,80) is 35; (S 2 , C)=(80,79) i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More