Distribution transformer type selection recommendation method based on data driving
A distribution transformer, data-driven technology, applied in data processing applications, electrical digital data processing, digital data information retrieval, etc., can solve the problem of not considering the difference in the selection of distribution transformers, and cannot provide a recommended method for user station selection. and other problems to achieve the effect of improving the reliability of power supply
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0035] like figure 1 As shown, a data-driven distribution transformer selection recommendation method includes the following steps:
[0036] S1: Divide the application scenarios of distribution transformers, and determine the types of distribution transformers to be selected;
[0037] S2: Calculate the average value of the historical state scores of all distribution transformers of this type in S1 in the past 1 year;
[0038] S3: Calculate the average scores of various types of distribution transformers in S2 within one year according to the difference in the time of commissioning;
[0039] S4: The distribution transformer models with an average score of more than 90 points in the statistical operation time of 1 to 5 years; the distribution transformer models with an average operation time of 6 to 10 years and an average score of more than 85 points; the statistical operation time in 10 Models of distribution transformers with an average score of more than 80 points over the...
Embodiment 2
[0045] like figure 2 , image 3 As shown, the data-driven distribution transformer selection recommendation method according to the embodiment of the present invention is different from the first embodiment in that:
[0046] The method for dividing the application scenarios of distribution transformers includes the following steps:
[0047] Step (1): First, according to different types of distribution transformers and different regional characteristics, preliminarily classify the application scenarios of distribution transformers; Step (2): Extract features for clustering, and reduce the dimensionality of these features; Step (3): Use the improved K-means clustering algorithm to further divide the second type of application scenarios; Step (4): Use the CH index method to evaluate the clustering effect; Step (5): Analyze the evaluation results Finally, the final division result of the distribution transformer application scenario is obtained.
[0048] In step (2), the secon...
Embodiment 3
[0051] The data-driven distribution transformer selection recommendation method in the embodiment of the present invention is different from Embodiments 1 and 2 in that: when making selection recommendation for a distribution transformer in a certain application scenario, if the statistics are If there are more than 2 types of distribution transformers that meet the requirements in a certain commissioning time, the 2 distribution transformer models with higher scores in the commissioning period are recommended; otherwise, all distribution transformers that meet the requirements in the commissioning period are recommended. model.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


