Power system fault type analysis method and device based on three-layer data mining
A fault type, power system technology, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as grid faults, affect timely processing, expand the scope of fault losses, and achieve the effect of improving safety.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0070] Embodiment 1 of the present invention provides a power system fault type analysis method based on three-layer data mining, including:
[0071] S1: Obtain a first original data sample library, the original data sample library is used to establish a power system fault prediction model, and perform preprocessing and data fusion on the first original data sample library to obtain a second original data sample library;
[0072] Specifically, after the above data collection, data preprocessing and data fusion are completed, the source data sample library is extracted in the following form: {X, F}, where X={X 1 ,X 2 ,...,X i ,...} are the data samples in the source sample library except the fault information, F={F 1 , F 2 ,...,F i ,...} is a sample of fault information. Will F i Defined as the fault type label of each group of samples during training, the present invention takes the most frequently occurring short-circuit faults of the power system as an example, but is ...
Embodiment 2
[0115] Embodiment 2 of the present invention explains the steps of constructing a power grid fault type prediction model based on the second sample database to judge the faults that occur in the power grid:
[0116] Specifically, the fault type prediction model satisfies the linear relationship:
[0117] f(XII j )=w T (XII j )+b
[0118] w—model parameter vector;
[0119] b—intercept;
[0120] w T (XII j )—sample group vector XII j and the inner product of the model parameter vector w;
[0121] Use the gradient descent method to obtain the optimal solution of the fault type model:
[0122] The SVM-type loss function is constructed as follows:
[0123]
[0124] Among them, E(w,b)—empirical risk (that is, the expectation of the loss function);
[0125] αR(w)—structural risk;
[0126] L(F j ,f(XII j ))=log(1+exp(-F j f(XII j ))) — loss function
[0127] f j -actual value
[0128] The regular term R(w) can take the following form:
[0129]
[0130] The op...
Embodiment 3
[0137] The present invention implements three pairs of steps to construct a power grid fault type prediction model based on the second sample database to determine another implementation mode of the fault type that occurs in the power grid, specifically:
[0138] The types of faults that occur in the power grid satisfy the following prediction model:
[0139] f(a,x)=a 1 x n +a 2 x n-1 +...+a n x+a n+1
[0140] 5.2 In the nonlinear prediction model (4-2), the optimization objective function is to obtain the following χ 2 The smallest coefficient (a 1 , a 2 ,...,a n )
[0141]
[0142] the y j ---actual value.
[0143] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system and device can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap