Magnetic field signal-based current calculation method suitable for multiple scenes
A technology of current calculation and magnetic field signal, applied in the direction of calculation, neural learning method, computer-aided design, etc., can solve the problem of difficult to achieve ideal conditions, and achieve the effect of high-precision current calculation
Active Publication Date: 2021-11-05
GUIZHOU POWER GRID CO LTD +1
View PDF1 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Considering the limitations of the widely used optimization algorithms, the advantages of machine learning methods, and the interference of various factors such as installation deviation and wire position movement in actual use, the ideal condition that the sensor array plane is completely perpendicular to the current wire is difficult. Realized; therefore, this application proposes a current calculation method based on magnetic field signals suitable for multiple scenarios
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0071] See figure 1 Distance figure 1 A flow schematic diagram of a current calculation method suitable for use in a multi-scene-based magnetic field signal provided by the embodiment of the present invention.
[0072] According to the applicant, it has been found that the current size inversion of magnetic field data is calculated, and the current optimization algorithm is solved. The traditional optimization algorithm global search ability is unstable, and the result is strongly dependent on the initial value; the heuristic optimization algorithm is strong, but the amount of calculation is large, the accuracy is unstable. It can be seen that the use of optimization algorithms to solve this problem is often difficult to combine efficiency and accuracy. Compared to the traditional optimization algorithm, the advantage of the machine learning algorithm is that once enough data sample training, the model can be directly calculated using the model each time the measurement is calcula...
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
Login to View More Abstract
The invention provides a magnetic field signal-based current calculation method suitable for multiple scenes, which is applied to a circular magnetic field sensor array measurement system consisting of giant magnetoresistance sensors, and comprises the following steps of: quantitatively calculating a magnetic field vector generated around a long straight wire; establishing a first electrified long straight wire magnetic field model in which a current wire is perpendicular to a sensor array plane and a second electrified long straight wire magnetic field model in which the current wire is not perpendicular to the sensor array plane; obtaining a training set based on the first electrified long straight wire magnetic field model; obtaining a test set based on the second electrified long straight wire magnetic field model; importing a training set into a MLP neural network model for training, and importing a test set to test the error of the MLP neural network model; and performing current calculation by using the trained MLP neural network model. The calculation method provided by the invention has very high calculation precision under the condition of multiple scenes, the calculation amount during single measurement is greatly reduced through machine learning, and the real-time performance of a measurement result can be ensured.
Description
Technical field [0001] The present invention relates to the field of power grid failure measurement, and in particular, the current calculation method of magnetic field signals suitable for use in multi-scenes. Background technique [0002] In recent years, with the continuous emergence of new measurement techniques, the sensor technology has developed rapidly, and the construction of smart grids has been unprecedented development. The development goal of the smart grid is to enable the Internet to cover every link of the power system, including sending delivery or the like. In order to make the smart grid can be stably operated, each node in the network needs to provide the corresponding data support. This puts higher requirements for information acquisition accuracy and real-time performance of each link. In order to achieve an energy Internet characterized by "Internet + Energy Network", the information measurements in the grid are required to be more comprehensive and real-ti...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06N3/08G06F113/04
CPCG06F30/27G06N3/08G06F2113/04Y02A90/30
Inventor 徐长宝辛明勇高吉普王宇吕黔苏吕前程田兵刘仲骆柏锋王志明陈仁泽孙宏棣张佳明尹旭
Owner GUIZHOU POWER GRID CO LTD