A ground-based augmentation system for high-precision prediction of tropospheric refractivity
A ground-based enhancement system and refractive index technology, applied in the field of ground-based enhancement systems, can solve problems such as poor accuracy of the refractive index of the fluid layer.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0092] In this embodiment, a BP neural network is established to predict the future tropospheric refractivity under normal weather conditions and a large amount of meteorological data.
[0093] The data processing of the present invention mainly concentrates on the processor of ground base station to carry out, as figure 2 As shown in the flow chart of predicting the refractive index in the embodiment of the present invention, the processor includes executing the following instructions:
[0094] Step S101, acquiring meteorological data.
[0095] Call historical data from the database to obtain meteorological parameters.
[0096] The ground collection device 101 collects local meteorological data such as temperature, humidity, and air pressure, and uses the collected meteorological parameters as historical data. The processor 102 invokes the historical data collected by the ground collection equipment to obtain meteorological data such as temperature, humidity, and air press...
Embodiment 2
[0149] In this embodiment, under normal weather conditions and with less meteorological data, a BP neural network is established to predict the future tropospheric refractivity.
[0150] The difference between the first implementation in this embodiment is that the processor executes step S31 of the instruction for processing data. The processor in this embodiment executes the following instructions in detail below:
[0151] Step S101, acquiring meteorological data.
[0152] Call historical data from the database to obtain meteorological parameters. Under normal weather conditions and when the weather data is less, the training set and the test set are relatively small. In this embodiment, the two parts are no longer used as the training set and the test set, and the cross-validation method is used to expand the amount of data. .
[0153] Step S102, calculating the refractive index.
[0154] The refractive index is calculated from the acquired meteorological parameters.
...
Embodiment 3
[0202] In this embodiment, for the situation of meteorological data under abnormal weather, a BP neural network is established to predict the future tropospheric refractivity. Abnormal weather generally refers to an abnormal phenomenon with small spatial scale, short life history and obvious suddenness, or the change trend of meteorological parameters is different from the normal situation. Such as temperature inversion, short-term heavy rainfall, typhoon, high temperature, heavy fog and other weather.
[0203] According to the present invention, the difference between this embodiment and Embodiment 1 and Embodiment 2 is that the database is formed by updating the meteorological data of abnormal weather, the refractive index is calculated, and the BP neural network is established to predict the refractive index.
[0204] Specifically, such as Figure 4 The flow chart of predicting the refractive index under abnormal weather conditions in the embodiment of the present inventio...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


