Application system for guaranteeing spaceflight launch task by using meteorological elements

Abstract

The invention provides an application system for guaranteeing a spaceflight launch task by using meteorological elements. The application system comprises a spaceflight launch first area multi-source data fusion processing subsystem which provides a more accurate weather forecast release product for influence analysis returned by a spacecraft by using meteorological data; the spaceflight launch first area high-rise meteorological element influence analysis subsystem is configured to dynamically optimize meteorological forecast parameters based on a reinforcement learning model; the spaceflight launch numerical prediction interpretation application subsystem is used for analyzing the influence of meteorological conditions on spacecraft return, evaluating the influence of marine conditions on marine measurement and control and analyzing the influence of space weather on spaceflight launch; the space launch navigation zone space weather monitoring and early warning subsystem is used for monitoring the space weather of the navigation zone, including monitoring solar flares and solar proton events so as to provide space launch guarantee information.

Description

Technical Field

[0001] The invention belongs to the technical field of aerospace weather forecasting, and in particular relates to an application system that utilizes meteorological elements to ensure aerospace launch missions. Background Art

[0002] Existing space launch mission support technologies mainly include multi-source meteorological data fusion processing, high-level meteorological element impact analysis, numerical forecast interpretation and application, space weather monitoring and early warning, and launch window selection and support. These technologies integrate and analyze meteorological data from different sources to evaluate the impact of meteorological conditions on space launches and provide important weather warnings and launch window recommendations. However, existing technologies still have some shortcomings. First, there may be problems of data inconsistency and error accumulation in the fusion and analysis of multi-source data. Second, in the application of numerical forecast interpretation, the accuracy and reliability of forecast products still need to be improved. In addition, space weather monitoring and early warning technology has limited prediction capabilities for events such as solar activity and geomagnetic storms, and the launch window selection and support technology needs to be strengthened in its ability to cope with complex weather conditions. Summary of the invention

[0003] In view of this, the present invention aims to propose an application system for ensuring space launch missions by using meteorological elements, so as to provide support information for space launch missions.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows: An application system that uses meteorological elements to ensure space launch missions, including a multi-source data fusion processing subsystem for the first space launch area, an impact analysis subsystem for high-level meteorological elements in the first space launch area, a space launch numerical forecast interpretation application subsystem, and a space weather monitoring and early warning subsystem for the space launch area; The multi-source data fusion processing subsystem of the first space launch area uses meteorological data to provide more accurate meteorological forecast interpretation products for the impact analysis of spacecraft return; The subsystem for analyzing the impact of high-level meteorological elements in the first space launch area is configured to dynamically optimize meteorological forecast parameters based on a reinforcement learning model; The space launch numerical prediction interpretation application subsystem is used to analyze the impact of meteorological conditions on the return of spacecraft, evaluate the impact of ocean conditions on offshore measurement and control, and analyze the impact of space weather on space launch; The space weather monitoring and early warning subsystem for the space launch area is used to monitor the space weather in the area, including monitoring solar flares and solar proton events to provide space launch support information.

[0005] Furthermore, the space launch numerical forecast interpretation application subsystem analyzes meteorological conditions including hourly temperature, precipitation, high wind area, shallow wind, atmospheric density, and atmospheric refractive index.

[0006] Furthermore, the hourly temperature is calculated using the following formula: ; In the formula, T 1 For the previous moment t 1 The corresponding temperature is T 2 For the next moment t 2 The corresponding temperature is Any moment between the two interpolated moments t The corresponding temperature value, a is the weight coefficient adjusted according to the season and geographical location.

[0007] Furthermore, precipitation is calculated using the following formula: ; In the formula, For the previous moment The corresponding precipitation value is For the next moment The corresponding precipitation value is Any moment between the two interpolated moments t The corresponding precipitation value.

[0008] Furthermore, the high wind area is calculated by the following formula: ; In the formula, For the previous moment The corresponding wind speed, For the next moment The corresponding wind speed is Any moment between the two interpolated moments t The corresponding wind speed value.

[0009] Furthermore, the shallow wind is calculated by the following formula: ; In the formula, V 1 For a certain layer height z 1 The corresponding wind speed, V 2 For the previous level z 2 The corresponding wind speed is V Any height between the two interpolated levels z The corresponding wind speed value.

[0010] Furthermore, the atmospheric density is calculated by the following formula: ; In the formula, P k for k The corresponding air pressure value at the altitude, P 0 The standard physical atmospheric pressure is 1013.25hPa. T k for k The actual temperature at altitude and E is the water vapor pressure.

[0011] Furthermore, the atmospheric refractive index is calculated by the following formula: ; ; ; In the formula, T is the temperature corresponding to each layer, e , e s are water vapor pressure and saturated water vapor pressure, respectively. r h is the relative humidity, p is the air pressure value corresponding to each layer, C is the concentration of atmospheric pollutants, and k is the correction coefficient.

[0012] Furthermore, the reinforcement learning model optimizes meteorological parameters by the following steps: The reinforcement learning model optimizes meteorological parameters through the following steps: a. State space construction: define the state vector S t =[v t ,T t ,H t ,P t ,R hist ,E status ],in: v t is the surface wind speed at the current moment, T t is the temperature of the first emission zone, H t is the relative humidity, P t is the sea level pressure, R hist is the mission success rate under similar meteorological conditions in the past 30 days, E status is the equipment state vector, including launcher inclination, fuel pressure, and tracking and control link availability; b. Action space definition: Set parameters to adjust the action set A = {ΔP thresh ,ΔT offset ,Δv max},in: ΔP thresh is the pressure threshold adjustment, ΔT offset is the temperature compensation offset, Δv max is the maximum allowable wind speed correction; c. Reward function design: define the immediate reward R t = -log(MSE t )+γ×S safe ,in: MSE t is the mean square error of meteorological parameter prediction; S safe =α×I 风速<阈值 +β×I 温度∈安全范围 ; S safe is the task safety factor, γ is the safety weight, α and β are the expert experience weights; dQ-learning algorithm iteration: Initialize the Q table Q(S,A), where Q(S,A) is the benchmark value of the historical optimal parameter combination; According to the current state S t Select Action A t , adopting the ε-greedy strategy; After executing the action, observe the new state S t+1 And calculate the reward R t ; Update Q value: Q(S t ,A t )←Q(S t ,A t )+a[R t +bmax A Q(S t+1 ,A)-Q(S t ,A t )]; The learning rate a=0.05, the discount factor b=0.9; When the Q value change rate is less than 10 for 10 consecutive iterations -4 Or the training is terminated when the maximum number of iterations reaches 100,000.

[0013] Compared with the prior art, the application system for ensuring space launch missions by using meteorological elements described in the present invention has the following beneficial effects: An application system that uses meteorological elements to ensure space launch missions has significantly improved the safety and success rate of space launch missions by integrating multiple subsystems such as multi-source data fusion processing, high-level meteorological element impact analysis, numerical forecast interpretation and application, and space weather monitoring and early warning. The system provides more reliable meteorological information for the return of spacecraft through accurate meteorological forecast interpretation products, ensuring the safe return of spacecraft under complex meteorological conditions. At the same time, the system comprehensively considers the meteorological, oceanic and space weather conditions in the first space launch area, providing comprehensive support for space launch missions. Through the calculation and analysis of parameters such as hourly temperature, precipitation, high wind area, shallow wind, atmospheric density and atmospheric refractive index, the system can more accurately evaluate the impact of meteorological conditions on the return of spacecraft, evaluate the impact of oceanic conditions on offshore measurement and control, and analyze the impact of space weather on space launches. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings: Figure 1 The present invention is a schematic diagram of an application system structure for utilizing meteorological elements to ensure space launch missions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0016] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0017] An application system that uses meteorological elements to ensure space launch missions, such as Figure 1 The multi-source data fusion processing subsystem in the first space launch area shown uses meteorological data to provide more accurate meteorological forecast interpretation products for the impact analysis of spacecraft return; The subsystem for analyzing the impact of high-level meteorological elements in the first space launch area is configured to dynamically optimize meteorological forecast parameters based on a reinforcement learning model; The space launch numerical prediction interpretation application subsystem is used to analyze the impact of meteorological conditions on the return of spacecraft, evaluate the impact of ocean conditions on offshore measurement and control, and analyze the impact of space weather on space launch; The space weather monitoring and early warning subsystem for the space launch area is used to monitor the space weather in the area, including monitoring solar flares and solar proton events to provide space launch support information.

[0018] The space launch numerical forecast interpretation and application subsystem analyzes meteorological conditions including hourly temperature, precipitation, strong wind area, shallow wind, atmospheric density, and atmospheric refractive index, and interprets and applies forecasts of conventional elements, weather phenomena, and special elements based on T1279 numerical forecast data.

[0019] Specifically, the reinforcement learning model optimizes meteorological parameters through the following steps: The reinforcement learning model optimizes meteorological parameters through the following steps: a. State space construction: define the state vector S t =[v t ,T t ,H t ,P t ,R hist ,E status ],in: v t is the surface wind speed at the current moment, T t is the temperature of the first emission zone, H t is the relative humidity, P t is the sea level pressure, R hist is the mission success rate under similar meteorological conditions in the past 30 days, E status is the equipment state vector, including launcher inclination, fuel pressure, and tracking and control link availability; b. Action space definition: Set parameters to adjust the action set A = {ΔP thresh ,ΔT offset ,Δv max},in: ΔP thresh is the pressure threshold adjustment, ΔT offset is the temperature compensation offset, Δv max is the maximum allowable wind speed correction; c. Reward function design: define the immediate reward R t = -log(MSE t )+γ×S safe ,in: MSE t is the mean square error of meteorological parameter prediction; S safe =α×I 风速<阈值 +β×I 温度∈安全范围 ; S safe is the task safety factor, γ is the safety weight, α and β are the expert experience weights; dQ-learning algorithm iteration: Initialize the Q table Q(S,A), where Q(S,A) is the benchmark value of the historical optimal parameter combination; According to the current state S t Select Action A t , adopting the ε-greedy strategy; After executing the action, observe the new state S t+1 And calculate the reward R t ; Update Q value: Q(S t ,A t )←Q(S t ,A t )+a[R t +bmax A Q(S t+1 ,A)-Q(S t ,A t )]; The learning rate a=0.05, the discount factor b=0.9; When the Q value change rate is less than 10 for 10 consecutive iterations -4 Or the training is terminated when the maximum number of iterations reaches 100,000.

[0020] Specifically, the hourly temperature is obtained by linear interpolation of the three-hourly temperature output by the T1279 numerical forecast model. The hourly temperature is calculated using the following formula: ; In the formula, T1 is the corresponding temperature at the previous moment t1, and T2 is the corresponding temperature at the next moment t2. is the temperature value corresponding to any time t between the two interpolated times, and a is the weight coefficient adjusted according to the season and geographical location.

[0021] Specifically, the precipitation is interpolated after weighting according to the size of the cumulative precipitation value of the adjacent 3 hours. Since the precipitation usually changes nonlinearly, when the 3-hour cumulative precipitation is processed into 1-hour cumulative precipitation, the size of the cumulative precipitation value of the adjacent 3 hours is used as the weight to interpolate the cumulative precipitation in time. The precipitation is calculated by the following formula: ; In the formula, For the previous moment The corresponding precipitation value is For the next moment The corresponding precipitation value is Any moment between the two interpolated moments t The corresponding precipitation value.

[0022] Specifically, the strong wind is judged based on the ground wind speed output by the T1279 numerical model, and the hourly strong wind identification product is produced through the interpolation algorithm and threshold judgment. The strong wind area is calculated by the following formula: ; In the formula, For the previous moment The corresponding wind speed, For the next moment The corresponding wind speed, Any moment between the two interpolated moments t The corresponding wind speed value.

[0023] Specifically, the shallow wind is obtained by linear interpolation of the 10m wind speed and 925hPa wind speed based on the T1279 numerical forecast product. The height of 925hPa is recorded as 800m. The vertical interpolation is performed based on the 10m wind speed and the 925hPa wind speed. The high-altitude wind is output according to the results of the T1279 numerical forecast product. The shallow wind is calculated by the following formula: ; In the formula, V 1 For a certain layer height z 1 The corresponding wind speed is V 2 For the previous level z 2 The corresponding wind speed, V Any height between the two interpolated levels z The corresponding wind speed value.

[0024] Specifically, the atmospheric density is calculated from the sea level pressure field and the temperature of each layer output by the T1279 numerical model. The hourly atmospheric density data is obtained by interpolating and calculating the sea level pressure and temperature data of each layer. The atmospheric density is calculated by the following formula: ; In the formula, P k for k The corresponding air pressure value at the altitude, P 0 The standard physical atmospheric pressure is 1013.25hPa. T k for k The actual temperature at altitude and E is the water vapor pressure.

[0025] The atmospheric refractive index is calculated from temperature and relative humidity. The hourly atmospheric refractive index data is obtained by interpolating and calculating the temperature and relative humidity data of each layer. The saturated water vapor pressure is first calculated by temperature, and then the water vapor pressure is calculated by saturated water vapor pressure and relative humidity. Finally, the atmospheric refractive index is calculated. The atmospheric refractive index is calculated by the following formula: ; ; ; In the formula, T is the temperature corresponding to each layer, e , es are water vapor pressure and saturated water vapor pressure, respectively. rh is the relative humidity, p is the air pressure value corresponding to each layer.

[0026] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0027] In the several embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the division of the units described above is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The above-mentioned units may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0028] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

[0029] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An application system for ensuring space launch missions using meteorological factors, characterized in that: It includes the multi-source data fusion processing subsystem of the first space launch area, the high-level meteorological element impact analysis subsystem of the first space launch area, the space launch numerical forecast interpretation and application subsystem, and the space weather monitoring and early warning subsystem of the space launch area; The multi-source data fusion processing subsystem of the first space launch area uses meteorological data to provide more accurate meteorological forecast interpretation products for the impact analysis of spacecraft return; The subsystem for analyzing the impact of high-level meteorological elements in the first space launch area is configured to dynamically optimize meteorological forecast parameters based on a reinforcement learning model; The space launch numerical prediction interpretation application subsystem is used to analyze the impact of meteorological conditions on the return of spacecraft, evaluate the impact of ocean conditions on offshore measurement and control, and analyze the impact of space weather on space launch; The space weather monitoring and early warning subsystem for the space launch area is used to monitor the space weather in the area, including monitoring solar flares and solar proton events to provide space launch support information.

2. The application system for ensuring space launch missions by using meteorological elements according to claim 1, characterized in that: The space launch numerical forecast interpretation application subsystem analyzes meteorological conditions including hourly temperature, precipitation, high wind area, shallow wind, atmospheric density, and atmospheric refractive index.

3. The application system for ensuring space launch missions by using meteorological elements according to claim 2, characterized in that: The hourly temperature is calculated using the following formula: ； In the formula, T 1 For the previous moment t 1 The corresponding temperature is T 2 For the next moment t 2 The corresponding temperature is Any moment between the two interpolated moments t The corresponding temperature value, a is the weight coefficient adjusted according to the season and geographical location.

4. The application system for ensuring space launch missions by using meteorological elements according to claim 2 is characterized in that: Precipitation is calculated using the following formula: ； In the formula, For the previous moment The corresponding precipitation value is For the next moment The corresponding precipitation value is Any moment between the two interpolated moments t The corresponding precipitation value.

5. The application system for ensuring space launch missions by using meteorological elements according to claim 2, characterized in that: The high wind area is calculated by the following formula: ； In the formula, For the previous moment The corresponding wind speed is For the next moment The corresponding wind speed, Any moment between the two interpolated moments t The corresponding wind speed value.

6. The application system for using meteorological elements to ensure space launch missions according to claim 2, characterized in that: Shallow wind is calculated using the following formula: ； In the formula, V 1 For a certain layer height z 1 The corresponding wind speed, V 2 For the previous level z 2 The corresponding wind speed, V Any height between the two interpolated levels z The corresponding wind speed value.

7. The application system for ensuring space launch missions by using meteorological elements according to claim 2, characterized in that: The atmospheric density is calculated using the following formula: ； In the formula, P k for k The corresponding air pressure value at the altitude, P 0 The standard physical atmospheric pressure is 1013.25hPa. T k for k The actual temperature at altitude and E is the water vapor pressure.

8. The application system for ensuring space launch missions by using meteorological elements according to claim 2 is characterized in that: The atmospheric refractive index is calculated using the following formula: ； ； ； In the formula, T is the temperature corresponding to each layer, e , e s are water vapor pressure and saturated water vapor pressure, respectively. r h is the relative humidity, p is the air pressure value corresponding to each layer, C is the concentration of atmospheric pollutants, and k is the correction coefficient.

9. The application system for ensuring space launch missions by using meteorological elements according to claim 1, characterized in that: The reinforcement learning model optimizes meteorological parameters through the following steps: The reinforcement learning model optimizes meteorological parameters through the following steps: a. State space construction: define the state vector S t =[v t ,T t ,H t ,P t ,R hist ,E status ],in: v t is the surface wind speed at the current moment, T t is the temperature of the first emission zone, H t is the relative humidity, P t is the sea level pressure, R hist is the mission success rate under similar meteorological conditions in the past 30 days, E status is the equipment state vector, including launcher inclination, fuel pressure, and tracking and control link availability; b. Action space definition: Set parameters to adjust the action set A = {ΔP thresh ,ΔT offset ,Δv max },in: ΔP thresh is the pressure threshold adjustment, ΔT offset is the temperature compensation offset, Δv max is the maximum allowable wind speed correction; c. Reward function design: define the immediate reward R t = -log(MSE t )+γ×S safe ,in: MSE t is the mean square error of meteorological parameter prediction; S safe =α×I 风速<阈值 +β×I 温度∈安全范围 ; S safe is the task safety factor, γ is the safety weight, α and β are the expert experience weights; dQ-learning algorithm iteration: Initialize the Q table Q(S,A), where Q(S,A) is the benchmark value of the historical optimal parameter combination; According to the current state S t Select Action A t , adopting the ε-greedy strategy; After executing the action, observe the new state S t+1 And calculate the reward R t ; Update Q value: Q(S t ,A t )←Q(S t ,A t )+a[R t +bmax A Q(S t+1 ,A)-Q(S t ,A t )]; The learning rate a=0.05, the discount factor b=0.9; When the Q value change rate is less than 10 for 10 consecutive iterations -4 Or the training is terminated when the maximum number of iterations reaches 100,000.

Images