Method for determining fluid density of fluid in an encapsulated electrical device

By using machine learning and digital models to correct the measured values ​​of fluid density in electrical equipment, the problem of measurement deviation under the influence of weather conditions has been solved, enabling accurate and rapid monitoring of fluid density and improving the safety and maintainability of electrical equipment.

CN115516592BActive Publication Date: 2026-01-16SIEMENS ENERGY GLOBAL GMBH & CO KG
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202180034088.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-04-09
Filing Date
2021-03-11
Publication Date
2026-01-16
Estimated Expiration
2041-03-11

AI Technical Summary

Technical Problem

Existing technologies are insufficient to reliably monitor and correct changes in fluid density in electrical equipment in the short term, especially due to measurement deviations caused by weather conditions, which affect the operational safety and maintainability of electrical equipment.

Method used

Machine learning methods are employed to collect measurement data using sensors and train a digital model by combining it with weather data. The measured fluid density is then corrected using an artificial neural network (such as a recurrent neural network LSTM). The influence of weather conditions on the measurement is taken into account, and data cloud is used for calculation and correction.

Benefits of technology

It significantly improves the accuracy and speed of fluid density measurement, enabling timely detection of fluid density changes and enhancing the operational safety and maintainability of electrical equipment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115516592B_ABST
    Figure CN115516592B_ABST
Patent Text Reader

Abstract

The invention relates to a method for determining a fluid density of a fluid in an encapsulated electrical device (1). In the method, measurement data (5) are acquired with a sensor unit (3), a measured value (9) of the fluid density is derived from the measurement data, and weather data (13) about weather conditions in the environment of the electrical device (1) are collected. By means of machine learning, a digital model (15) of the influence of the weather conditions on a measurement deviation of the measured value (9) from the correct fluid density is produced. With the digital model (15), a correction value (17) for the measured value (9) is calculated from the weather data (13), and the measured value (9) is corrected with the correction value (17).
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Gas compensation based full-temperature SF6 gas density relay checking device

    CN102879733A

  • Wind power prediction method and system

    CN104200280A