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

Model training and abnormal data identification method and device, equipment and medium

An abnormal data and model training technology, applied in the field of data processing, can solve problems such as abnormal oil chromatographic data of oil-immersed transformers, and achieve high accuracy, precise identification, and high-quality results

Pending Publication Date: 2022-07-29
上海思源弘瑞自动化有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the application scenario of oil-immersed transformers, it is necessary to use the oil color acquisition device to collect the oil chromatographic data of the oil-immersed transformer, but when the oil color acquisition device fails, the collected oil-immersed transformer oil chromatogram data will be abnormal

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
  • Model training and abnormal data identification method and device, equipment and medium
  • Model training and abnormal data identification method and device, equipment and medium
  • Model training and abnormal data identification method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Figure 1A A flowchart of a model training method provided in Embodiment 1 of the present invention, Figure 1B This is a schematic structural diagram of a model provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of training the abnormal data identification model, wherein the abnormal data in the oil color spectrum data is caused by the failure of the oil color collection device. The method may be performed by a model training apparatus, which may be implemented in software and / or hardware. like Figure 1A As shown, the method specifically includes:

[0035] S101. According to the existing eigenvalues ​​of at least two groups of samples in the sample oil chromatographic data, determine the expanded eigenvalues ​​corresponding to the existing eigenvalues ​​of each group of samples.

[0036] The sample oil chromatographic data refers to data including at least two groups of existing eigenvalues ​​of the sample and expanded eigen...

Embodiment 2

[0053] figure 2 It is a flowchart of a model training method provided in the second embodiment of the present invention. On the basis of the above-mentioned embodiment, this embodiment further performs the following steps: "According to the existing characteristic values ​​of at least two groups of samples in the sample oil chromatography data, determine each group Existing eigenvalues ​​of the sample corresponding to the extended eigenvalues” for a detailed explanation, such as figure 2 As shown, the method specifically includes:

[0054] S201. Determine a first expanded eigenvalue corresponding to the existing eigenvalues ​​of each group of samples according to the correlation between the existing eigenvalues ​​of each group of samples in the sample oil chromatographic data.

[0055] The correlation between existing eigenvalues ​​refers to a numerical relationship between at least two existing eigenvalues. The first extended eigenvalue refers to the extended eigenvalue c...

Embodiment 3

[0069] image 3 It is a flowchart of a model training method provided in the third embodiment of the present invention. On the basis of the above-mentioned embodiment, this embodiment further determines the content value of each gas according to the corresponding content values ​​of the same gas in the existing characteristic values The second expanded eigenvalue corresponding to the existing eigenvalue of the group sample” will be explained in detail, such as image 3 As shown, the method specifically includes:

[0070] S301. Determine a first expanded eigenvalue corresponding to the existing eigenvalues ​​of each group of samples according to the correlation between the existing eigenvalues ​​of each group of samples in the sample oil chromatographic data.

[0071] S302. Determine the absolute growth rate and / or relative growth rate of the target gas according to the corresponding content values ​​of the target gas in the existing characteristic values ​​of the first group of...

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 a model training and abnormal data identification method and device, equipment and a medium. The method comprises the following steps: determining an expanded characteristic value corresponding to an existing characteristic value of each group of samples according to the existing characteristic values of at least two groups of samples in sample oil chromatographic data; wherein the existing characteristic values of different groups of samples are the content values of at least two gases in the transformer oil collected at different time points; and training an abnormal data identification model according to the existing feature values of the at least two groups of samples, the expanded feature values corresponding to the existing feature values of the at least two groups of samples and the abnormal data labels associated with the sample oil chromatographic data, so as to identify abnormal data in the oil chromatographic data. According to the technical scheme provided by the embodiment of the invention, the accuracy of the trained abnormal data identification model is higher, so that the abnormal data in the oil chromatography data can be identified more accurately based on the model.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of data processing, and in particular, to a method, apparatus, device, and medium for model training and abnormal data identification. Background technique [0002] With the development of transformer technology, oil-immersed transformers have been widely used. The body of oil-immersed transformers is often installed in an oil tank filled with transformer oil, and the oil tank is welded with steel plates. In the application scenario of oil-immersed transformers, the oil color acquisition device needs to be used to collect the oil chromatographic data of the oil-immersed transformer. However, when the oil color acquisition device fails, the collected oil chromatographic data of the oil-immersed transformer will be abnormal. [0003] Therefore, how to perform abnormal detection on oil chromatographic data of oil-immersed transformers and provide higher-quality oil chromatographic data is ...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06F18/214
Inventor 马坤鹏翟志祥刘寒寒杨浩巍
Owner 上海思源弘瑞自动化有限公司