Multi-source high-energy particle detection data fusion method and device

Abstract

The embodiment of the invention provides a multi-source high-energy particle detection data fusion method and device, and the method comprises the steps: obtaining initial detection data, carrying out the geomagnetic coordinate conversion based on the initial detection data, and determining a coordinate conversion result; determining a baseline model based on the coordinate conversion result, and determining a fluctuation model based on the baseline model; establishing a data calibration model based on the baseline model and the fluctuation model; determining calibration data based on the data calibration model, and determining a calibration coefficient based on the calibration data; and performing data conversion based on the calibration coefficient and the data calibration model, and determining fusion data. By adding the calibration of the fluctuation data in the data calibration level, the fluctuation detection data can be reserved in the aspect of data fusion, and the method has a wider application scene.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of particle detection technology, and in particular to a multi-source high-energy particle detection data fusion method. Background Art

[0002] High-energy particles in the Earth's orbit are affected by the Earth's magnetic field and solar activity, resulting in a near-Earth high-energy particle environment distribution with multiple superpositions of different change periods and dynamic changes. Different on-orbit particle detection data will also be affected by these factors. Excluding the differences in the design and hardware of each detector, the data detected at different spatial positions and different space environment conditions will still be affected by the environment and spatial position, resulting in certain differences. According to current technology, the data fusion calibration of high-energy particle detection data is mainly based on the following process: 1. Based on the geomagnetic adiabatic invariant relationship, data comparison and calibration are performed in geomagnetic coordinates: Since high-energy particles in the Earth's orbit are affected by the Earth's magnetic field, based on the assumption of the geomagnetic adiabatic invariant relationship, it can be assumed that the particle distribution obeys the same law in the geomagnetic BL coordinate system. Therefore, even if the detectors on satellites with different longitudes, latitudes and altitudes in real space positions are relatively consistent, their detection data can be calibrated if the B / B0 and L values ​​of the geomagnetic coordinate system are relatively consistent; 2. The calibration data needs to be cleaned. Due to the design of each detector, the background noise may be different. The data needs to be cleaned before calibration.

[0003] 3. The specific calibration is to select basically consistent BL positions in geomagnetic space according to the BL coordinate system results of the cleaned detection data, and perform linear regression on the data of two different satellite detectors to obtain the slope coefficient, R2, p value and other parameters that characterize the calibration effect.

[0004] The above methods have the following problems: 1. In the traditional calibration process, only the endogenous geomagnetic field is generally considered. Therefore, for satellites with higher orbital altitudes or satellites passing through the Earth's polar regions at higher latitudes, the weight of their magnetic field B value affected by the external magnetic field increases. Traditional calibration will discard the data with excessively fluctuating BL values ​​and only use the relatively stable BL value part; 2. In the traditional calibration process, the fluctuation of data will be eliminated during data cleaning, so that the results of calibration and data fusion lack the data of environmental disturbance; 3. The traditional calibration process usually only considers data from a quiet period or an event (such as a solar proton event or a high-energy electron burst event), and generally does not consider long-term processes.

[0005] Therefore, a better solution is urgently needed. Summary of the invention

[0006] In view of this, the embodiments of this specification provide a multi-source high-energy particle detection data fusion method. One or more embodiments of this specification also involve a multi-source high-energy particle detection data fusion device, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0007] According to a first aspect of an embodiment of this specification, a multi-source high-energy particle detection data fusion method is provided, comprising: Acquire initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine the coordinate conversion result; Determine a baseline model based on the coordinate transformation result, and determine a fluctuation model based on the baseline model; Establish a data calibration model based on the baseline model and fluctuation model; Determine calibration data based on the data calibration model, and determine calibration coefficients based on the calibration data; Data conversion is performed based on the calibration coefficient and data calibration model to determine the fused data.

[0008] In a possible implementation, performing geomagnetic coordinate conversion based on the initial detection data and determining a coordinate conversion result includes: Determine the internal magnetic field and the external magnetic field, and determine a mapping relationship based on the internal magnetic field and the external magnetic field; The coordinate transformation result is determined based on the mapping relationship.

[0009] In a possible implementation, determining a baseline model based on a coordinate transformation result includes: Determine baseline data based on the coordinate transformation result; Build regularity models corresponding to various energy parameters based on baseline data; Based on the regular model, weighted superposition is performed to determine the baseline model.

[0010] In a possible implementation, determining a fluctuation model based on a baseline model includes: Determine fluctuation data based on the baseline model; The data model is constructed based on the fluctuation data and machine learning model to determine the fluctuation model.

[0011] In a possible implementation, a data calibration model is established based on a baseline model and a fluctuation model, including: The baseline model and the fluctuation model are superimposed to obtain the data calibration model.

[0012] In a possible implementation, determining a calibration coefficient based on calibration data includes: Determine the calibration object based on the calibration data; The calibration coefficients are determined by linear regression based on the calibration object.

[0013] In a possible implementation, the initial detection data includes detection data corresponding to at least two proton detectors; Accordingly, data conversion is performed based on the calibration coefficient and the data calibration model to determine the fused data, including: Determine a first calibration coefficient and a first data calibration model corresponding to a first detector in the proton detector, convert the detection data of the first detector based on the first calibration coefficient and the first data calibration model, and determine the first detection data; Determine a second calibration coefficient and a second data calibration model corresponding to a second detector in the proton detector, convert the detection data of the second detector based on the second calibration coefficient and the second data calibration model, and determine the second detection data; The fused data is determined based on the first detection data and the second detection data.

[0014] According to a second aspect of an embodiment of this specification, a multi-source high-energy particle detection data fusion device is provided, comprising: A coordinate conversion module is configured to obtain initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine a coordinate conversion result; A fluctuation model module is configured to determine a baseline model based on the coordinate transformation result and determine a fluctuation model based on the baseline model; A calibration model module is configured to establish a data calibration model based on a baseline model and a fluctuation model; A calibration coefficient module is configured to determine calibration data based on a data calibration model and to determine a calibration coefficient based on the calibration data; The data fusion module is configured to perform data conversion based on the calibration coefficient and the data calibration model to determine the fused data.

[0015] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the multi-source high-energy particle detection data fusion method are implemented.

[0016] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned multi-source high-energy particle detection data fusion method are implemented.

[0017] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned multi-source high-energy particle detection data fusion method.

[0018] The embodiments of this specification provide a multi-source high-energy particle detection data fusion method and device, wherein the multi-source high-energy particle detection data fusion method includes: obtaining initial detection data, performing geomagnetic coordinate conversion based on the initial detection data, and determining the coordinate conversion result; determining a baseline model based on the coordinate conversion result, and determining a fluctuation model based on the baseline model; establishing a data calibration model based on the baseline model and the fluctuation model; determining calibration data based on the data calibration model, and determining a calibration coefficient based on the calibration data; performing data conversion based on the calibration coefficient and the data calibration model, and determining fused data. By adding calibration to the fluctuation data at the data calibration level, the fluctuating detection data can be retained in data fusion, which has a wider range of application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a multi-source high-energy particle detection data fusion method provided by an embodiment of this specification; Figure 2 It is a structural schematic diagram of a multi-source high-energy particle detection data fusion device provided by an embodiment of this specification; Figure 3 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0020] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0021] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0022] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0023] In this specification, a multi-source high-energy particle detection data fusion method is provided. This specification also involves a multi-source high-energy particle detection data fusion device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0024] See also Figure 1 , Figure 1 A flow chart of a multi-source high-energy particle detection data fusion method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0025] Step 101: Acquire initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine the coordinate conversion result.

[0026] In a possible implementation, geomagnetic coordinate conversion is performed based on initial detection data to determine the coordinate conversion result, including: determining an endogenous magnetic field and an exogenous magnetic field, determining a mapping relationship based on the endogenous magnetic field and the exogenous magnetic field; and determining the coordinate conversion result based on the mapping relationship.

[0027] In practical applications, since charged particles in the Earth's orbital space basically follow three geomagnetic adiabatic invariants, it is necessary to convert the latitude, longitude, and altitude parameters into geomagnetic coordinates for a more accurate description. When converting geomagnetic coordinates, it is necessary to combine the endogenous magnetic field model with the exogenous magnetic field model. That is, construct a mapping relationship {Lat(t), Long(t), Alt(t)}→{B→ inner (t)+ B→ outer (t)}→{|B|(t),B0(t),L(t)}. Where B→ is the magnetic field vector at the corresponding position, which is respectively composed of the internal magnetic field B→ inner With external magnetic field B→ outerThe magnetic field model is superimposed and is calculated by the endogenous magnetic field model and the exogenous magnetic field model. The endogenous magnetic field can adopt the geomagnetic field model such as IGRF, and the exogenous magnetic field can adopt the magnetic field model such as T96 and TA16. |B| is the modulus of the magnetic field strength at the location, B0 is the magnetic field strength from the magnetic field line at the location to the magnetic equator, and L is the distance from the magnetic field line at the location to the center of the earth at the magnetic equator. B0 and L need to be calculated by magnetic field line tracking.

[0028] Specifically, based on the detection data obtained by two on-orbit high-energy proton detectors, the high-energy particle detection data set DF is formed by processing the data using the geometric factors of the detectors. i =Data(UT(time),>Energy, Counts i , {X Positions}). Where i={1,2}. The position coordinate data set DP can be extracted i =Data(UT(time), {X Positions})= Data(UT(time), {Lat,Long,Alt}). Use various spatial environment data to construct a spatial environment dataset containing time stamps DE=Data(UT(time), {X Environments}).

[0029] To convert geomagnetic coordinates, use X Positions Information, using the endogenous field model to obtain B→ inner For example, when using the IGRF13 geomagnetic field model, DM1 i = Data (UT(time), IGRF({Lat,Long,Alt}, Year(time))); use the external field model to obtain B→ outer For example, when using the T96 external source field model, {X Environments}Including Dst index, solar wind speed, and solar wind dynamic pressure at each UT (time). For missing or low-resolution spatial environment data, interpolation can be used to obtain the corresponding value at the corresponding time. That is, DM2 i = Data (UT(time), T96({Lat,Long,Alt}, Dst, SW speed , S.W. preasure )) Integration of DM1 i and DM2 i Data that forms the magnetic field B → value: DM i (B)=DM1 i (B)+DM2 i (B) and based on the constructed global geomagnetic field DM iThe vector B→data is used to track the magnetic field lines to obtain the distance between the magnetic field lines at the magnetic equator and the center of the earth, which is recorded as L value. The ratio of |B| to the magnetic field |B0| at this position can be used to obtain B / B0, thus constructing DM i (B, L)={B, L, B / B0}.

[0030] Step 102: Determine a baseline model based on the coordinate transformation result, and determine a fluctuation model based on the baseline model.

[0031] In a possible implementation, determining a baseline model based on a coordinate transformation result includes: determining baseline data based on the coordinate transformation result; constructing a regular model corresponding to each energy parameter based on the baseline data; and performing weighted superposition based on the regular model to determine the baseline model.

[0032] In practical applications, by performing coordinate transformation, the data of high-energy charged particles becomes Flux base (E, t, B / B0, L), therefore, according to the Kolmogorov-Arnold superposition theorem, we can construct the regularity model of each energy E under B / B0 or ​​L coordinate transformation, and perform weighted superposition to form the final high-energy particle environment change model with geomagnetic coordinates Fit base (E,B / B0,L).

[0033] Specifically, add DM i Update the detection data set to DF1 i = Data(UT(time),>Energy,Counts, B / B0, L, Lat,Long,Alt). Construct a generalized linear correlation model so that Fit i : DF1 i (Counts i )~DF1 i (>Energy, B / B0, L, Lat, Long, Alt), for model Fit i Iterative optimization is performed based on AIC (Akaike Information) or other similar features to reduce irrelevant position factors, and finally the high-energy particle environment baseline model Fit is obtained. base_i .

[0034] In a possible implementation, determining a fluctuation model based on a baseline model includes: determining fluctuation data based on the baseline model; and constructing a data model based on the fluctuation data and a machine learning model to determine the fluctuation model.

[0035] In practical applications, it can be considered that the high-energy particle environment is formed by the superposition of the baseline environment and the fluctuation environment, so the high-energy particle fluctuation part data Flux can be extracted env =Flux all -Flux base . And through machine learning models, such as generalized linear correlation, random forest and other methods, we build Fit:F env ~{e rel} model, where e rel It is an environmental parameter with a high correlation to the fluctuation data. Use the existing data to obtain the relevant weights of the model and establish Flux env (E,t)=Fit env (E, e rel (t)).

[0036] Specifically, through the high-energy particle environment baseline model Fit base_i Can calculate the fluctuation data Flux env_i (>Energy,time)= DF i (>Energy,Counts i )- Fit base_i (>Energy, B / B0, L, Lat, Long, Alt). And use machine learning models to perform Flux env_i Training. In the embodiment, the random forest algorithm is used for training, the number of trees in the forest is 100, and the eigenvalue M is 3. Finally, the high-energy particle environment fluctuation model Fit is obtained. env_i .

[0037] Step 103: Establish a data calibration model based on the baseline model and the fluctuation model.

[0038] In a possible implementation, a data calibration model is established based on a baseline model and a fluctuation model, including: superimposing the baseline model and the fluctuation model to obtain the data calibration model.

[0039] In practical applications, combining the above two parts of data, we can get Fit all (E,B / B0,L,e rel (t)) = Fit base (E,B / B0,L)+ Fit env (E, e rel (t)).

[0040] Specifically, build a particle data calibration model Fit i (E,B / B0,L,e rel (t)) = Fit base_i (E,B / B0,L)+Fit env_i(E, e rel (t)).

[0041] Step 104: Determine calibration data based on the data calibration model, and determine calibration coefficients based on the calibration data.

[0042] In a possible implementation, determining a calibration coefficient based on the calibration data includes: determining a calibration object based on the calibration data; and determining the calibration coefficient through linear regression based on the calibration object.

[0043] In practical applications, for each detector data, a set of Fit i (E,B / B0,L,e rel (t)). i=[1,..,n], where n is the number of satellite payloads that need to be calibrated.

[0044] For each load's raw data DF i =Data(UTtime,Pos,E,Count), where UTtime is the universal time stamp, Pos is the latitude and longitude position information, E is the energy channel information, and Count is the particle count information. i Transform the data: DF i '=Data(E,Count i ', B / B0(Grid),L(Grid),e rel (UTtime))= Data(E, Fit i (E, B / B0(Grid), L(Grid), e rel (UTtime))). Grid is a sequence formed by discretizing the maximum range of B / B0, L covered by multiple detector payload tracks.

[0045] Furthermore, for DF i 'Data Count i 'Perform calibration, at this time each DF i The technical correction value of ' has three main dimensions: B / B0, L, e rel Since B / B0 and L are discretized by the same set of Grids, they have the same calibration standard. rel Due to the difference in time, there are multiple states, but when the detection time span is relatively long (generally not less than 1 year), the distribution of environmental data is basically consistent. rel Fit i The transformation process is equivalent to dimensionality reduction, so the transformed Count i'Data is used as the calibration object. Assuming that the detector data with number i=1 is used as the benchmark, all detectors with number i=[2,..,n] need to be calibrated with it. Then, linear regression is used to construct Count i '~w i Count1'+ε i , the calibration coefficient A can be obtained i =[w i , ε i ], where A1=[1,0].

[0046] Specifically, generate particle calibration data for each detector: DF1'=Data(E,Count1', B / B0(Grid),L(Grid),e rel (Uttime1))= Data(E, Fit1(E,B / B0(Grid), L(Grid), e rel (Uttime1))), DF2'=Data(E,Count2', B / B0(Grid), L(Grid),e rel (Uttime2)) = Data(E, Fit2(E, B / B0(Grid), L(Grid), e rel (Uttime2))).

[0047] Furthermore, data calibration is performed: taking Count1' as the benchmark and setting A1=[1,0], the linear regression Count2'~w2·Count1' + ε2 is performed to obtain A2=[w2, ε2].

[0048] Step 105: Perform data conversion based on the calibration coefficient and the data calibration model to determine fused data.

[0049] In a possible implementation, the initial detection data includes detection data corresponding to at least two proton detectors; accordingly, data conversion is performed based on calibration coefficients and data calibration models to determine fusion data, including: determining a first calibration coefficient and a first data calibration model corresponding to a first detector in the proton detector, converting the detection data of the first detector based on the first calibration coefficient and the first data calibration model to determine the first detection data; determining a second calibration coefficient and a second data calibration model corresponding to a second detector in the proton detector, converting the detection data of the second detector based on the second calibration coefficient and the second data calibration model to determine the second detection data; and determining the fusion data based on the first detection data and the second detection data.

[0050] In practical applications, after obtaining the calibration coefficient A iAfter that, the normalized model Fit obtained by each detector can be used i Combined with A i To convert the data: DF i =Data(UTtime,Pos,E,Count)→DF i '=Data(E,Count i ', B / B0(UTtime),L(UTtime),e rel (UTtime)) →DF i ' fix =Data(E,(Count i '-ε i ) / w i , B / B0(UTtime),L(UTtime),e rel (UTtime)). Finally, the fused data DF is formed total =Data(DF i ' fix ), i=[1,..,n].

[0051] Specifically, data fusion is performed: DF1' fix = DF1', DF2' fix =Data(E,(Count2'-ε2) / w i , B / B0(Uttime2), L(Uttime2), e rel (Uttime2)), DF total = Data(DF1' fix , DF2' fix ) .

[0052] The embodiments of this specification do not directly select the data with consistent benchmarks from the existing data for calibration, but use the existing data to form a continuous response model, and use the model to generate more secondary data with consistent benchmarks for calibration; there is no need to remove the fluctuating and inconsistent benchmark data during calibration, and more data can provide information for calibration; the calibrated data fusion can contain more data, and there is no need to remove and discard the fluctuating or inconsistent benchmark data. Therefore, on the one hand, the basic data of the original calibration can be retained, and the calibration and fusion of data in the case of inconsistent benchmarks (such as inconsistent geomagnetic B / L coordinate ranges, inconsistent space environments, etc.) can also be expanded, so as to more effectively utilize the on-orbit detection data.

[0053] The embodiments of this specification provide a multi-source high-energy particle detection data fusion method and device, wherein the multi-source high-energy particle detection data fusion method includes: obtaining initial detection data, performing geomagnetic coordinate conversion based on the initial detection data, and determining the coordinate conversion result; determining a baseline model based on the coordinate conversion result, and determining a fluctuation model based on the baseline model; establishing a data calibration model based on the baseline model and the fluctuation model; determining calibration data based on the data calibration model, and determining a calibration coefficient based on the calibration data; performing data conversion based on the calibration coefficient and the data calibration model, and determining fused data. By adding calibration to the fluctuation data at the data calibration level, the fluctuating detection data can be retained in data fusion, which has a wider range of application scenarios.

[0054] Corresponding to the above method embodiment, this specification also provides a multi-source high-energy particle detection data fusion device embodiment, Figure 2 FIG. 1 is a schematic diagram showing the structure of a multi-source high-energy particle detection data fusion device provided by an embodiment of the present specification. Figure 2 As shown, the device comprises: The coordinate conversion module 201 is configured to obtain initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine a coordinate conversion result; The fluctuation model module 202 is configured to determine a baseline model based on the coordinate transformation result, and determine a fluctuation model based on the baseline model; The calibration model module 203 is configured to establish a data calibration model based on the baseline model and the fluctuation model; A calibration coefficient module 204 is configured to determine calibration data based on a data calibration model, and to determine calibration coefficients based on the calibration data; The data fusion module 205 is configured to perform data conversion based on the calibration coefficient and the data calibration model to determine fused data.

[0055] In a possible implementation, the coordinate conversion module 201 is further configured as follows: Determine the internal magnetic field and the external magnetic field, and determine a mapping relationship based on the internal magnetic field and the external magnetic field; The coordinate transformation result is determined based on the mapping relationship.

[0056] In a possible implementation, the fluctuation model module 202 is further configured to: Determine baseline data based on the coordinate transformation result; Build regularity models corresponding to various energy parameters based on baseline data; Based on the regular model, weighted superposition is performed to determine the baseline model.

[0057] In a possible implementation, the fluctuation model module 202 is further configured to: Determine fluctuation data based on the baseline model; The data model is constructed based on the fluctuation data and machine learning model to determine the fluctuation model.

[0058] In a possible implementation, the calibration model module 203 is further configured to: The baseline model and the fluctuation model are superimposed to obtain the data calibration model.

[0059] In a possible implementation, the calibration coefficient module 204 is further configured to: Determine the calibration object based on the calibration data; The calibration coefficients are determined by linear regression based on the calibration object.

[0060] In a possible implementation, the data fusion module 205 is further configured to: The initial detection data includes detection data corresponding to at least two proton detectors; Accordingly, data conversion is performed based on the calibration coefficient and the data calibration model to determine the fused data, including: Determine a first calibration coefficient and a first data calibration model corresponding to a first detector in the proton detector, convert the detection data of the first detector based on the first calibration coefficient and the first data calibration model, and determine the first detection data; Determine a second calibration coefficient and a second data calibration model corresponding to a second detector in the proton detector, convert the detection data of the second detector based on the second calibration coefficient and the second data calibration model, and determine the second detection data; The fused data is determined based on the first detection data and the second detection data.

[0061] The embodiments of this specification provide a multi-source high-energy particle detection data fusion method and device, wherein the multi-source high-energy particle detection data fusion device includes: obtaining initial detection data, performing geomagnetic coordinate conversion based on the initial detection data, and determining the coordinate conversion result; determining a baseline model based on the coordinate conversion result, and determining a fluctuation model based on the baseline model; establishing a data calibration model based on the baseline model and the fluctuation model; determining calibration data based on the data calibration model, and determining a calibration coefficient based on the calibration data; performing data conversion based on the calibration coefficient and the data calibration model, and determining fused data. By adding calibration to the fluctuation data at the data calibration level, the fluctuating detection data can be retained in data fusion, which has a wider range of application scenarios.

[0062] The above is a schematic scheme of a multi-source high-energy particle detection data fusion device of this embodiment. It should be noted that the technical scheme of the multi-source high-energy particle detection data fusion device and the technical scheme of the multi-source high-energy particle detection data fusion method described above belong to the same concept, and the details of the technical scheme of the multi-source high-energy particle detection data fusion device that are not described in detail can all be referred to the description of the technical scheme of the multi-source high-energy particle detection data fusion method described above.

[0063] Figure 3 The block diagram of a computing device 300 according to an embodiment of the present specification is shown. The components of the computing device 300 include but are not limited to a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and the database 350 is used to store data.

[0064] The computing device 300 also includes an access device 340 that enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 340 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0065] In one embodiment of the present specification, the above components of the computing device 300 and Figure 3 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 3 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0066] The computing device 300 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 300 may also be a mobile or stationary server.

[0067] The processor 320 is used to execute the following computer executable instructions, which implement the steps of the multi-source high-energy particle detection data fusion method when executed by the processor. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above belong to the same concept. For the details not described in detail in the technical scheme of the computing device, please refer to the description of the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above.

[0068] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the multi-source high-energy particle detection data fusion method.

[0069] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above.

[0070] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned multi-source high-energy particle detection data fusion method.

[0071] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the multi-source high-energy particle detection data fusion method mentioned above.

[0072] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0074] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A multi-source high-energy particle detection data fusion method, characterized in that: include: Acquire initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine a coordinate conversion result; Determine a baseline model based on the coordinate transformation result, and determine a fluctuation model based on the baseline model; Establishing a data calibration model based on the baseline model and the fluctuation model; Determine calibration data based on the data calibration model, and determine calibration coefficients based on the calibration data; Data conversion is performed based on the calibration coefficient and the data calibration model to determine fused data.

2. The method according to claim 1, characterized in that The performing geomagnetic coordinate conversion based on the initial detection data and determining the coordinate conversion result comprises: Determining an endogenous magnetic field and an exogenous magnetic field, and determining a mapping relationship based on the endogenous magnetic field and the exogenous magnetic field; A coordinate transformation result is determined based on the mapping relationship.

3. The method according to claim 1, characterized in that The determining of the baseline model based on the coordinate transformation result comprises: Determine baseline data based on the coordinate transformation result; Constructing a regularity model corresponding to each energy parameter based on the baseline data; A baseline model is determined by performing weighted superposition based on the regular model.

4. The method according to claim 1, characterized in that The determining of the fluctuation model based on the baseline model comprises: determining fluctuation data based on the baseline model; A data model is constructed based on the fluctuation data and the machine learning model to determine the fluctuation model.

5. The method according to claim 1, characterized in that A data calibration model is established based on the baseline model and the fluctuation model, including: The baseline model and the fluctuation model are superimposed to obtain the data calibration model.

6. The method according to claim 1, characterized in that The step of determining the calibration coefficient based on the calibration data comprises: Determining a calibration object based on the calibration data; The calibration coefficients are determined by linear regression based on the calibration object.

7. The method according to claim 1, characterized in that The initial detection data includes detection data corresponding to at least two proton detectors; Accordingly, performing data conversion based on the calibration coefficient and the data calibration model to determine fused data includes: Determine a first calibration coefficient and a first data calibration model corresponding to a first detector in the proton detector, and convert detection data of the first detector based on the first calibration coefficient and the first data calibration model to determine first detection data; Determine a second calibration coefficient and a second data calibration model corresponding to a second detector in the proton detector, and convert the detection data of the second detector based on the second calibration coefficient and the second data calibration model to determine second detection data; Fused data is determined based on the first detection data and the second detection data.

8. A multi-source high-energy particle detection data fusion device, characterized in that: include: A coordinate conversion module is configured to obtain initial detection data, perform geomagnetic coordinate conversion based on the initial detection data, and determine a coordinate conversion result; A fluctuation model module, configured to determine a baseline model based on the coordinate transformation result, and determine a fluctuation model based on the baseline model; A calibration model module, configured to establish a data calibration model based on the baseline model and the fluctuation model; A calibration coefficient module, configured to determine calibration data based on the data calibration model, and to determine calibration coefficients based on the calibration data; The data fusion module is configured to perform data conversion based on the calibration coefficient and the data calibration model to determine fused data.

9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the multi-source high-energy particle detection data fusion method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the multi-source high-energy particle detection data fusion method as described in any one of claims 1 to 7.

Images