CN117607913A - High-precision positioning method and system based on ionosphere real-time perception - Google Patents
High-precision positioning method and system based on ionosphere real-time perception Download PDFInfo
- Publication number
- CN117607913A CN117607913A CN202311618974.1A CN202311618974A CN117607913A CN 117607913 A CN117607913 A CN 117607913A CN 202311618974 A CN202311618974 A CN 202311618974A CN 117607913 A CN117607913 A CN 117607913A
- Authority
- CN
- China
- Prior art keywords
- model
- positioning
- satellite
- offset
- fuzzy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000005433 ionosphere Substances 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000008447 perception Effects 0.000 title claims abstract description 20
- 230000000694 effects Effects 0.000 claims abstract description 75
- 230000008859 change Effects 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 55
- 238000012549 training Methods 0.000 claims description 53
- 230000008569 process Effects 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000004043 responsiveness Effects 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000010295 mobile communication Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 101100259947 Homo sapiens TBATA gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000005358 geomagnetic field Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/21—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/20—Integrity monitoring, fault detection or fault isolation of space segment
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/40—Correcting position, velocity or attitude
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The application provides a high-precision positioning method and a system based on ionosphere real-time perception, and relates to the technical field of satellite positioning, wherein the method comprises the following steps: acquiring an ionosphere activity index set and satellite positioning information; the ionospheric activity index set comprises at least one of: the change rate of the total electron content of the ionized layer, the vertical total electron content and the vertical gradient of the electron density of the ionized layer; inputting the ionosphere liveness index set into a preset positioning calibration model to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models; and calibrating the satellite positioning information according to the positioning offset to determine target positioning information. Therefore, the positioning offset is predicted by utilizing the mixed fuzzy model, the positioning interference of ionosphere flicker to the satellite signal receiver is compensated, and the positioning accuracy and reliability are improved.
Description
Technical Field
The application relates to the technical field of satellite high-precision positioning, in particular to a high-precision positioning method and system based on ionosphere real-time perception.
Background
In recent years, along with the continuous promotion of unmanned aerial vehicle autonomous inspection large-scale application in the power industry, the application coverage rate of unmanned aerial vehicle autonomous inspection in power transmission and distribution lines, 110 kilovolts and above transformer substations and converter stations is continuously improved, and the large-scale application of the unmanned aerial vehicle in a power grid is basically realized.
The high-precision positioning of the power grid unmanned aerial vehicle is a necessary condition that the power grid unmanned aerial vehicle can successfully complete an autonomous inspection task, so that the power grid unmanned aerial vehicle is also assisted with various signal enhancement stations and positioning optimization algorithms on the basis of positioning data by using a Beidou satellite system, and the positioning precision level is improved.
However, since the ionosphere swells due to solar radiation, the size, shape and strength of the ionosphere change from moment to moment. In particular, the electron liveness effect on the ionosphere is particularly strong when solar activity such as earth magnetic storm, sun blackness, flare and the like occurs. However, the ionosphere is mainly located about 60 to 1000 km above the earth's surface, and is not separated from the ionosphere for daily communication, broadcasting, navigation and positioning, and has important influence on radio communication, satellite navigation positioning and radar detection. For example, when the activity of the power layer reaches more than 120, the positioning accuracy of the power grid unmanned aerial vehicle deviates greatly, so that the power grid unmanned aerial vehicle cannot finish the autonomous inspection task well, and even accidents occur in the autonomous inspection process of the power grid unmanned aerial vehicle.
In addition, ionospheric disturbances exhibit multi-scale, irregular, complex, varying features due to the complex spatio-temporal variability of the ionosphere. When ionosphere disturbance occurs, the electronic density changes, which has serious influence on satellite navigation positioning and communication. Studying the nature and modeling of ionospheric disturbances is essential to maintaining safety of human spatial activity, reducing and avoiding economic damage to spatial weather events. Ionosphere flicker is one of important ionosphere disturbance effects, and can reflect an irregular plasma structure and physical characteristics of the plasma structure in an ionosphere, and distortion and error code of signals received by a satellite receiver can be caused, so that reliability and accuracy of a satellite navigation and communication system are affected.
Disclosure of Invention
The application provides a high-precision positioning method and a high-precision positioning system based on ionosphere real-time perception, which are used for at least solving the problem of positioning precision of an ionosphere scintillation interference satellite signal receiver in the prior art.
The application provides a high-precision positioning method based on ionosphere real-time perception, which is applied to a satellite signal receiver and comprises the following steps: acquiring an ionosphere activity index set and satellite positioning information; the ionospheric activity index set includes at least one of: the change rate of the total electron content of the ionized layer, the vertical total electron content and the vertical gradient of the electron density of the ionized layer; inputting the ionosphere liveness index set into a preset positioning calibration model to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models; and calibrating the satellite positioning information according to the positioning offset to determine target positioning information.
Optionally, the satellite signal receiver is provided in a power grid drone for performing autonomous patrol tasks.
Optionally, the calibrating the satellite positioning information according to the positioning offset to determine target positioning information includes: taking a preset ground signal enhancement base station as a differential source, and detecting communication signals aiming at the ground signal enhancement base station in real time; according to the signal flight time corresponding to the communication signal, calculating the relative distance between the power grid unmanned aerial vehicle and the ground signal enhancement base station; determining differential positioning coordinates of the power grid unmanned aerial vehicle according to pre-stored base station coordinates of the ground signal enhancement base station and the relative distance; and calibrating the satellite positioning information according to the differential positioning coordinates and the positioning offset to determine target positioning information.
Optionally, for the acquiring of the ionospheric activity index set, the acquiring includes: acquiring latitude and time parameters of a geographic area and a satellite sight angle; the latitude of the geographic area comprises dimension information of a target geographic area in which the satellite signal receiver is located, and the satellite sight angle comprises a satellite side view angle and a satellite pitch angle of the target geographic area relative to a Beidou satellite; inputting the geographic area latitude, the time parameter and the satellite line-of-sight angle into a pre-constructed index prediction model to determine an ionospheric activity index set for the target geographic area by the index prediction model.
Optionally, the index prediction model adopts an adaptive multi-output gaussian model, and the step of constructing the gaussian model includes: acquiring a training sample set; each training sample in the training sample set is provided with unique geographic area information, and the training sample comprises geographic area latitude, time parameters, satellite sight angles and corresponding real ionosphere activity index sets; determining regional sector information corresponding to geographic area information in the training samples aiming at each training sample, and enriching the training samples based on the regional sector information; normalizing each training sample, and training the self-adaptive multi-output Gaussian model based on each normalized training sample; the adaptive multi-output gaussian model is defined by:
wherein k is {a} Representing a set of predicted ionospheric activity indicators; x represents the latitude of a geographic area, y represents regional sector information, t represents a time parameter, and angle1 and angle2 respectively represent a satellite side view angle and a satellite pitch angle; h. u and l represent model parameters determined from the training sample set through model training, respectively.
Optionally, the hybrid model is defined by:
wherein { A } represents the ionospheric activity index set entered into the hybrid model, and f ({ A } represents the corresponding positioning offset; m is M i Model weight for the ith fuzzy model to characterize the influence degree of the fuzzy model on the whole mixed model; f (f) i ({ A }) describes the positioning offset determined by the ith fuzzy model.
Optionally, the fuzzy model comprises a fuzzy hyperbolic tangent model module, and the fuzzy hyperbolic tangent model module is defined by:
P＝f({A})＝α*tanh(β*{A})+γ*δ；
wherein P is a positioning offset, and alpha, beta, gamma and delta are model parameters;
alpha is the sensitivity of the model to the ionospheric activity index set, which determines the degree of responsiveness of the model to { A } changes;
beta is a parameter of the hyperbolic tangent function that determines how smooth the model is to the { A } variations.
Gamma is a constant term for the position offset, which represents the expected offset of the positioning coordinates without ionospheric activity;
delta is an error term for the position offset, which represents the extra error caused by the actual ionospheric activity;
wherein the values of α, β, γ and δ are according to the data sample set { { { B 1 },{B 2 },…,{B N The loss function of the fuzzy hyperbolic tangent model module is determined in the training process, and a dynamic loss function is adopted by the loss function of the fuzzy hyperbolic tangent model module; each data sample in the data sample set comprises an ionosphere liveness index set marked with a true positioning offset;
the dynamic loss function is defined by:
L hyperbolic tangent Is a loss function value, Y j Representing any one of the data samples B in the set of data samples j Corresponding true positioning offset, p j Representing the prediction of data sample B by the fuzzy hyperbolic tangent model module j The corresponding positioning coordinate offset; n represents the total amount of data samples in the data sample set; d is the number of iterations, where the total number of iterations for the same data sample is G, G is determined from the user input information, and G is greater than or equal to 1.
Optionally, the fuzzy model further comprises a probability map model module, and the probability map model module comprises an input layer, a hidden layer and an output layer, wherein the input layer is used for carrying out characterization processing on an ionospheric activity index set, the hidden layer adopts a cyclic neural network, and the output layer adopts a fully-connected network; the probability map model module uses the mean square error as a loss function to measure the coordinate difference between the predicted positioning offset and the actual positioning offset; the probability map model module performs model training by using a back propagation algorithm based on a regularization method; the probability map model module is constructed by:
Input layer: x= [ { B 1 },{B 2 },…,{B N }}，Y]＝[x 1 ,...,x n ]Wherein x is n Representing an n-th ionospheric activity index, Y being an actual positioning offset;
hidden layer: h=c (x·w) h ) Where c () is the activation function of the hidden layer, W h Is a weight matrix of the hidden layer;
output layer: o=g (h·wo), where g () is the activation function of the output layer, W o Is the weight matrix of the output layer;
loss function:wherein L is Probability map Using absolute difference loss function e j Predicting data sample B by a probabilistic graphical model module j The corresponding positioning coordinate offset;
in the process of training the probability map model module based on the sample data set, the weight matrix W is continuously updated h And W is o To minimize the loss function L Probability map 。
Alternatively, the loss function of the hybrid model employs a mean square error loss function and may be defined by:
wherein L is Mixing A loss function value representing the whole of the hybrid model, N representing the total amount of data samples in the data sample set; { y 1j ,…,y nj The expression of each fuzzy model is directed to data sample B j The outputted predicted positioning offset; in the process of fusion training of the mixed models on the fuzzy models, the model weight { M > of each fuzzy model is continuously updated 1 …M n To minimize the loss function L Mixing 。
The application also provides a high-precision positioning system based on ionosphere real-time perception, which comprises: the acquisition unit is used for acquiring the ionosphere activity index set and satellite positioning information; the ionospheric activity index set includes at least one of: the change rate of the total electron content of the ionized layer, the vertical total electron content and the vertical gradient of the electron density of the ionized layer; the input unit is used for inputting the ionosphere liveness index set into a preset positioning calibration model so as to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models, and the fuzzy models comprise a fuzzy hyperbolic tangent model module and a probability map model module; and the calibration unit is used for calibrating the satellite positioning information according to the positioning offset to determine target positioning information.
The application also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the high-precision positioning method based on ionosphere real-time perception when executing the program.
The present application also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a high precision positioning method based on ionospheric real-time perception as described in any of the above.
The present application also provides a computer program product comprising a computer program which when executed by a processor implements a method of ionospheric real-time perception based high accuracy positioning as described in any of the above.
According to the high-precision positioning method, system, electronic equipment and non-transitory computer readable storage medium based on ionosphere real-time perception, in the method, when a satellite signal receiver requests positioning, an ionosphere activity index set and satellite positioning information are acquired, the ionosphere activity index set is input into a positioning calibration model, so that corresponding positioning offset is determined by the positioning calibration model, and then the satellite positioning information is calibrated, and therefore positioning deviation caused by an ionosphere scintillation phenomenon is compensated by using an intelligent model technology. In addition, a positioning calibration model is constructed based on a fuzzy model, and the influence of various uncertainty and random factors (namely ionospheric activity indexes) on the positioning accuracy of the satellite signal receiver is predicted based on a probability and statistics method. Further, in the embodiment of the application, the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models, so that the advantages and characteristics of different fuzzy models can be fully utilized, and the accuracy and reliability of the positioning offset predicted under the action of ionosphere liveness variables with various uncertainties are effectively improved.
Drawings
For a clearer description of the present application or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 illustrates a flow chart of an example of a ionospheric real-time perception based high-precision positioning method in accordance with an embodiment of the present application;
FIG. 2 illustrates an operational flow diagram according to an example of step S130 in FIG. 1;
FIG. 3 illustrates an operational flow diagram of one example of acquiring an ionospheric activity index set;
FIG. 4 illustrates a flowchart of one example of a construction operation for an index prediction model according to an embodiment of the present application;
FIG. 5 illustrates a block diagram of an example of a positioning calibration model according to an embodiment of the present application;
FIG. 6 illustrates a block diagram of an example of an ionospheric real-time perception based high-precision positioning system in accordance with an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
FIG. 1 illustrates a flow chart of an example of a ionosphere real-time perception based high accuracy positioning method according to an embodiment of the present application.
The implementation main body of the method of the embodiment of the application can be any electronic equipment with a satellite navigation positioning module, such as a satellite signal receiver, so as to realize real-time sensing of ionosphere activity of the electronic equipment and corresponding calibration of satellite positioning signals, thereby realizing the goal of high-precision navigation positioning.
As shown in fig. 1, in step S110, an ionospheric activity index set and satellite positioning information are acquired.
Here, the ionospheric activity index set comprises at least one of: a total electron content rate of change (ROTI) of the ionosphere to reflect dynamic changes in the concentration of electrons in the ionosphere, a Vertical Total Electron Content (VTEC) to reflect a distribution of electrons in the ionosphere in a vertical direction, and a vertical gradient of ionosphere electron Density (DVOR) to reflect a disturbance of the ionosphere. In addition, according to the requirements of the test scene, such as task type or regional environment, other relevant parameters of the ionospheric activity index set can be selected, such as ionospheric delay time (IFT) for reflecting the change condition of the electron density and the ion temperature of the ionosphere, ionospheric reflection index (RAR) for reflecting the reflection condition of the ionosphere, and the like.
In one example of an embodiment of the present application, the satellite signal receiver may obtain the ionospheric activity index set described above from a weather station server. However, due to service limitations and lack of dimensionality of part of the index, the satellite signal receiver may not be able to obtain the complete ionospheric index from the weather station, and thus, in another example of an embodiment of the present application, the satellite signal receiver may predict and analyze the ionospheric index, as will be described in more detail below in connection with other examples.
In step S120, the ionospheric activity index set is input to a preset positioning calibration model to determine a corresponding positioning offset from the positioning calibration model.
Here, the positioning calibration model adopts a hybrid model in which a plurality of blur models are fused. It should be noted that in the satellite positioning field, ionospheric activity is an important uncertainty factor, which affects the propagation time and phase of satellite signals, and thus the positioning accuracy. Therefore, in the embodiment of the application, the influence of ionosphere liveness indexes with strong randomness and uncertainty on positioning accuracy is predicted by using a fuzzy model based on a probability and statistics method so as to compensate satellite navigation signals and improve positioning accuracy and reliability.
It should be noted that the fuzzy model may employ various non-limiting types of mathematical models that describe the ambiguity or uncertainty of a system or process because it allows for the ambiguous or uncertain description of certain variables or parameters, and thus the fuzzy model is effective in addressing and learning problems that are difficult to describe with accurate mathematical models, by which the ionospheric activity index of the system input, such as uncertainty factors, and the corresponding system output positioning offset, can be modeled, and then these uncertainties are processed using fuzzy logic or fuzzy reasoning to compensate for deviations in positioning information of the signal receiver caused by the ionospheric activity variables.
In addition, the positioning calibration model adopts a mixed model, and different fuzzy models can be used for processing and learning different characteristic information in the sample data. The fuzzy models can independently run, and then the output results are comprehensively analyzed by the fusion module, so that the satellite positioning information of the satellite positioning receiver is calibrated in a model fusion mode, and the accuracy and reliability of the positioning information of the satellite signal receiver are improved.
In step S130, the satellite positioning information is calibrated according to the positioning offset to determine target positioning information.
In some embodiments, the positioning offset and the satellite positioning information are directly subjected to mathematical superposition operation so as to calibrate the satellite positioning information.
In some examples of embodiments of the present application, the satellite signal receiver is disposed in a power grid drone for performing autonomous patrol tasks. Therefore, aiming at ionosphere scintillation, the positioning accuracy of the power grid unmanned aerial vehicle when the autonomous patrol task is executed is enhanced, the reliability of the power grid unmanned aerial vehicle for completing the autonomous patrol task is improved, and the probability of continuous error reporting of the autonomous navigation patrol of the unmanned aerial vehicle caused by satellite positioning accuracy deviation in the autonomous patrol task can be effectively reduced.
Fig. 2 shows an operation flowchart according to an example of step S130 in fig. 1.
As shown in fig. 2, in step S210, a preset ground signal enhancement base station is used as a differential source, and a communication signal for the ground signal enhancement base station is detected in real time.
Here, the ground signal enhancing base station is used as a reliable differential source to provide accurate positioning data therefrom.
In step S220, according to the signal flight time corresponding to the communication signal, the relative distance between the power grid unmanned aerial vehicle and the ground signal enhancement base station is calculated.
In this way, the relative distance between the power grid unmanned aerial vehicle and the ground signal enhancement base station is determined by a time difference method (TOF).
In step S230, differential positioning coordinates of the power grid unmanned aerial vehicle are determined according to the pre-stored base station coordinates and relative distances of the ground signal enhancement base station.
In combination with the service application scene, the power grid unmanned aerial vehicle starts to execute the cruising task after being triggered by the ground signal enhancement base station, and then the differential positioning coordinates of the power grid unmanned aerial vehicle can be obtained according to the cruising direction of the power grid unmanned aerial vehicle and the relative distance of the ground signal enhancement base station.
In step S240, the satellite positioning information is calibrated according to the differential positioning coordinates and the positioning offset to determine target positioning information.
Therefore, the mixed fuzzy model is further combined with the differential positioning technology, and the positioning precision and reliability of the satellite signal receiver can be further ensured.
In some embodiments, the receiver compensates the satellite positioning information with a positioning offset to obtain positioning coordinates based on the hybrid fuzzy model, compares the positioning coordinates with differential positioning coordinates determined based on the differential source, and then optimizes the positioning information according to the comparison result. Here, a diversified positioning information optimization manner may be employed, for example, by a weighted average manner. More preferably, the neural network is also used for learning the relationship among the differential positioning coordinates, the positioning coordinates based on the mixed fuzzy model and the real positioning coordinates, so that the positioning accuracy can be further improved, and the occurrence probability of the risk power grid frying machine can be effectively reduced.
FIG. 3 illustrates an operational flow diagram of an example of acquiring an ionospheric activity index set.
As shown in fig. 3, in step S310, a geographical area latitude, a time parameter, and a satellite line-of-sight angle are acquired.
Here, the geographical area latitude includes dimension information of a target geographical area in which the satellite signal receiver is located, and the satellite line of sight angle includes a satellite side view angle and a satellite pitch angle of the target geographical area with respect to the beidou satellite.
It should be noted that, the satellite side view angle refers to an angle between the satellite and the receiver, that is, an angle between the satellite and the receiver from the side, and the satellite pitch angle refers to an angle between the satellite and a plane of the receiver, that is, an angle between the satellite and the receiver from above, which may be measured and adjusted by software or hardware devices provided by the satellite navigation system. The larger the satellite side view angle is, the weaker the satellite signal is received by the receiver, and the lower the positioning accuracy is. In addition, if the pitch angle of the satellite is too small, the satellite signal is affected by the geomagnetic field, resulting in a decrease in positioning accuracy. Thus, both the satellite side view angle and the satellite pitch angle have an effect on the satellite positioning accuracy of the signal receiver.
Furthermore, ionospheric level distributions are different for different latitudes. In particular, in low latitude areas, the ionosphere is most active and changes severely irregularly, in mid latitude areas, the ionosphere is calm but changes in characteristics are obvious, in high dimension areas, it is complicated and changeable by polar day and night and the influence of solar wind particles.
In step S320, the geographic area latitude, time parameters, and satellite line-of-sight angles are input to a pre-constructed index prediction model to determine an ionospheric activity index set for the target geographic area from the index prediction model.
According to the method and the device for predicting the ionospheric activity, various parameter information of the satellite equipment parameters, including the coverage time, the coverage space and the coverage time, the coverage space of the satellite equipment parameters possibly affecting the positioning signals of the satellite signal receiver, is collected, and is designed to serve as the characteristic dimension of the index prediction model aiming at the ionospheric activity prediction result, so that the index prediction model can be ensured to reliably and accurately predict various ionospheric activity indexes according to historical sample data.
In some examples of embodiments of the present application, the index prediction model employs an adaptive multi-output gaussian model. FIG. 4 illustrates a flowchart of an example of a construction operation for an index prediction model according to an embodiment of the present application.
As shown in fig. 4, in step S410, a training sample set is obtained, where each training sample in the training sample set has unique geographical area information, and the training sample includes a geographical area latitude, a time parameter, a satellite line of sight angle, and a corresponding real ionospheric activity index set.
In step S420, for each training sample, the region sector information corresponding to the geographical region information in the training sample is determined, and the training samples are enriched based on the region sector information.
It should be noted that ionospheric scintillation corresponding to different regional sectors of the earth is regularized and differentiated. Specifically, the ionospheric scintillation of south america and atlantic sectors at 12 months is most pronounced, the ionospheric scintillation of africa and pacific sectors at 6 months is most pronounced, the variation in scintillation intensity of the 60 ° W-60 ° E longitude zone of the northern hemisphere with solar activity is most pronounced, and so on.
According to the method and the device for predicting the ionosphere activity index, the regional sector information is utilized to further enrich training samples, so that when the index prediction model is predicted, the index prediction model can automatically learn the difference rule of ionosphere flicker of the regional sector corresponding to different geographic area information, the performance of the index prediction model is improved, and then the high accuracy of the prediction result of each ionosphere activity index when the model is applied is guaranteed.
In step S430, normalization processing is performed on each training sample, and the adaptive multi-output gaussian model is trained based on each normalized training sample. Therefore, the dimension of each parameter in the training sample is unified through normalization operation (for example, minimum-maximum normalization is adopted), so that the dimension influence is eliminated, the model training process is simplified, and the model precision is improved.
The adaptive multi-output gaussian model is defined by:
wherein k is {a} Representing a set of predicted ionospheric activity indicators; x represents the latitude of a geographic area, y represents regional sector information, t represents a time parameter, and angle1 and angle2 respectively represent a satellite side view angle and a satellite pitch angle; h. u and l represent model parameters determined from the training sample set through model training, respectively.
Here, the adaptive multi-output gaussian model may employ a loss function of various types to measure a function of a gap between each ionospheric activity index predicted by the model and an actual ionospheric activity index, such as a sum-of-squares difference loss, a polynomial loss, a cross-log loss, etc., which should not be limited herein.
According to the embodiment of the application, the index prediction model is built by taking the self-adaptive multi-output Gaussian model as a framework, and the self-adaptive multi-output Gaussian model can be adjusted according to the change of data, so that the change of the ionospheric activity is better adapted. In addition, the method has the advantage of interpretability, and the influence of various parameters (geographical area latitude, time parameters and satellite line of sight angle) on the total electron content change rate, the vertical total electron content and the ionosphere electron density vertical gradient can be more intuitively understood by using a Gaussian model, so that the change rule of the ionosphere liveness can be better understood. Therefore, fitting of a more accurate variation trend of the ionosphere is facilitated, and the ionosphere activity index set with higher reliability can be predicted by combining with the input information of the unmanned aerial vehicle when the index prediction model is applied to the prediction operation.
FIG. 5 illustrates a block diagram of an example of a positioning calibration model according to an embodiment of the present application.
As shown in FIG. 5, the positioning calibration model 500 is a hybrid model that incorporates multiple fuzzy models, including a fuzzy hyperbolic tangent model module 510, a probability map model module 520, and various non-limiting fuzzy model modules 51n.
More specifically, the hybrid model is defined by:
wherein { A } represents the ionospheric activity index set of the input hybrid model, and f ({ A } represents the corresponding positioning offset; m is M i The model weight of the ith fuzzy model is used for representing the influence degree of the fuzzy model on the whole mixed model; f (f) i ({ A }) describes the positioning offset determined by the ith fuzzy model.
Therefore, by carrying out weighted calculation on the output results of different fuzzy models, the advantages and characteristics of the different fuzzy models can be fully utilized, and the accuracy and reliability of the positioning offset predicted under the action of ionosphere liveness variables with various uncertainties are effectively improved.
With respect to the fuzzy hyperbolic tangent model module 510, which is a predictive model based on a hyperbolic tangent function (also referred to as a hyperbolic function), it may blur the input data to better accommodate the uncertainty data. When the positioning offset is predicted, the model can calculate a predicted value through a hyperbolic tangent function according to the change trend of the ionosphere liveness variable, so that the positioning offset of the satellite positioning signal relative to the real coordinates is obtained.
More specifically, the fuzzy model includes a fuzzy hyperbolic tangent model module, and the fuzzy hyperbolic tangent model module is defined by:
P＝f({A})＝α*tanh(β*{A})+γ*δ；
where P is the positioning offset, { A } is the ionospheric activity index set, α, β, γ and δ are model parameters, α is the sensitivity of the model to the ionospheric activity index set, which determines the degree of responsiveness of the model to { A } changes, β is the parameter of the hyperbolic tangent function, which determines the degree of smoothness of the model to { A } changes, γ is a constant term for the position offset, which represents the expected offset of the positioning coordinates in the absence of ionospheric activity, δ is an error term for the position offset, which represents the additional error caused by the effect of actual ionospheric activity. Wherein the values of α, β, γ and δ are according to the data sample set { { { B 1 },{B 2 },…,{B N And is determined during training. Each data sample in the set of data samples contains a set of ionospheric activity indicators that are labeled with a true positioning coordinate offset (i.e., a tag).
Further, the loss function of the fuzzy hyperbolic tangent model module employs a dynamic loss function, which is defined by:
L hyperbolic tangent Is a loss function value, Y j Representing any one of the data samples B in the set of data samples j Corresponding true positioning offset, p j Representing the prediction of data sample B by the fuzzy hyperbolic tangent model module j The corresponding positioning coordinate offset; n represents the total amount of data samples in the data sample set; d is the number of iterations, where the total number of iterations for the same data sample is G, G is determined from the user input information, and G is greater than or equal to 1.
Therefore, the fuzzy hyperbolic tangent model module adopts a dynamic loss function, so that better adaptability, precision and efficiency can be realized, the condition of over fitting or under fitting is avoided, and the performance and generalization capability of the model are improved.
With respect to the probabilistic graphical model 520, it should be noted that ionospheric activity is a factor of uncertainty that can be modeled by the probabilistic graphical model and that positioning offsets can be predicted by probabilistic reasoning. In particular, the probabilistic graph model may be represented as a probabilistic relationship between a series of nodes (variables) that are connected by edges that represent dependencies between them, in a positioning problem, the nodes may be represented as various ionospheric liveness, etc. variables of the signal receiver. By probabilistic reasoning, the probability distribution between these variables can be calculated, thus predicting the positioning offset.
Specifically, the probability map model module comprises an input layer, a hidden layer and an output layer, wherein the input layer is used for carrying out characteristic processing on the ionosphere liveness index set, the hidden layer adopts a circulating neural network, and the output layer adopts a fully-connected network. The probability map model module uses the mean square error as a loss function to measure the coordinate difference between the predicted and actual positioning offsets.
The probability map model module performs model training by using a back propagation algorithm based on a regularization method, so that the problem of overfitting in a general probability map model can be effectively avoided.
Further, the probability map model module is constructed by:
input layer: x= [ { B 1 },{B 2 },…,{B N }}，Y]＝[x 1 ,...,x n ]Wherein x is n Representing an n-th ionospheric activity index, Y being an actual positioning offset;
hidden layer: h=c (x·w) h ) Where c () is the activation function of the hidden layer, W h Is a weight matrix of the hidden layer;
output layer: o=g (h·wo), where g () is the activation function of the output layer, W o Is the weight matrix of the output layer;
loss function:wherein L is Probability map Using absolute difference loss function e j Predicting data sample B by a probabilistic graphical model module j The corresponding positioning coordinate offset;
in the process of training the probability map model module based on the sample data set, the weight matrix W is continuously updated h And W is o To minimize the loss function L Probability map 。
According to the embodiment of the application, uncertainty factors such as ionosphere liveness and the like are modeled by adopting the probability map model, and the positioning offset is predicted by probability reasoning, so that the positioning precision is improved.
Finally, in the positioning calibration model 500, the prediction results of the fuzzy hyperbolic tangent model module 510 and the probability map model module 520 and the prediction results of other fuzzy models are weighted and summed, so that the characteristic information of each fuzzy model is fully and comprehensively considered, and the high accuracy of the positioning offset finally determined by the positioning calibration model is ensured.
Further, a mean square error loss function is employed for the loss function of the hybrid model, and can be defined by:
wherein L is Mixing A loss function value representing the whole of the hybrid model, N representing the total amount of data samples in the data sample set; { y 1j ,…,y nj The expression of each fuzzy model is directed to data sample B j The outputted predicted positioning offset;
in the process of fusion training of each fuzzy model by the mixed model, the model weight { M } of each fuzzy model is continuously updated 1 …M n To minimize the loss function L Mixing 。
According to the embodiment of the application, after the independent training convergence of each model module, the combination training is carried out on different model modules in the mixed model, and the model weight of each fuzzy model is continuously optimized, so that the model can be better adapted to the diversification of input data, higher prediction precision and fewer errors are obtained, and the risk of overfitting is reduced. In addition, in the training process, the model weights are continuously optimized, and based on comparison of the model weights, the contribution degree of the model module can be easier to explain and understand, so that the correlation degree between ionosphere scintillation and fuzzy models of different types can be further explored.
The high-precision positioning system based on the ionosphere real-time sensing provided by the application is described below, and the high-precision positioning system based on the ionosphere real-time sensing described below and the high-precision positioning method based on the ionosphere real-time sensing described above can be correspondingly referred to each other.
FIG. 6 illustrates a block diagram of an example of an ionospheric real-time perception based high-precision positioning system in accordance with an embodiment of the present application.
As shown in fig. 6, the ionospheric real-time perception based high-precision positioning system 600 includes an acquisition unit 610, an input unit 620, and a calibration unit 630.
An acquiring unit 610, configured to acquire an ionospheric activity index set and satellite positioning information; the ionospheric activity index set includes at least one of: the total electron content change rate of the ionosphere, the vertical total electron content, and the ionosphere electron density vertical gradient.
An input unit 620, configured to input the ionospheric activity index set to a preset positioning calibration model, so as to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models, and the fuzzy models comprise a fuzzy hyperbolic tangent model module and a probability map model module.
And a calibration unit 630, configured to calibrate the satellite positioning information according to the positioning offset, so as to determine target positioning information.
In some embodiments, embodiments of the present application provide a non-transitory computer readable storage medium having stored therein one or more programs including execution instructions that are readable and executable by an electronic device (including, but not limited to, a computer, a server, or a network device, etc.) for performing the ionospheric real-time awareness based high-precision positioning method described herein above.
In some embodiments, embodiments of the present application also provide a computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the ionospheric real-time perception based high accuracy positioning method described above.
In some embodiments, embodiments of the present application further provide an electronic device, including: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a high-precision positioning method based on ionospheric real-time awareness.
Fig. 7 is a schematic hardware structure of an electronic device for performing a high-precision positioning method based on ionosphere real-time sensing according to another embodiment of the present application, as shown in fig. 7, where the device includes:
one or more processors 710, and a memory 720, one processor 710 being illustrated in fig. 7.
The apparatus for performing the ionosphere real-time sensing-based high-precision positioning method may further include: an input device 730 and an output device 740.
Processor 710, memory 720, input device 730, and output device 740 may be connected by a bus or other means, for example in fig. 7.
The memory 720 is used as a non-volatile computer readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs, and modules, such as program instructions/modules corresponding to the ionospheric real-time sensing-based high-precision positioning method in the embodiments of the present application. The processor 710 executes various functional applications of the server and data processing by running non-volatile software programs, instructions and modules stored in the memory 720, i.e. implements the ionospheric real-time aware-based high-precision positioning method of the above-described method embodiments.
Memory 720 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 720 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 720 may optionally include memory located remotely from processor 710, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 730 may receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.
The one or more modules are stored in the memory 720 and when executed by the one or more processors 710 perform the ionospheric real-time awareness based high-precision positioning method of any of the method embodiments described above.
The product can execute the ionosphere real-time perception-based high-precision positioning method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present application.
The electronic device of the embodiments of the present application exist in a variety of forms including, but not limited to:
(1) Mobile communication devices, which are characterized by mobile communication functionality and are aimed at providing voice, data communication. Such terminals include smart phones, multimedia phones, functional phones, low-end phones, and the like.
(2) Ultra mobile personal computer equipment, which belongs to the category of personal computers, has the functions of calculation and processing and generally has the characteristic of mobile internet surfing. Such terminals include PDA, MID, and UMPC devices, etc.
(3) Portable entertainment devices such devices can display and play multimedia content. The device comprises an audio player, a video player, a palm game machine, an electronic book, an intelligent toy and a portable vehicle navigation device.
(4) Other on-board electronic devices with data interaction functions, such as on-board devices mounted on vehicles.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus a general purpose hardware platform, or may be implemented by hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the related art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A high-precision positioning method based on ionosphere real-time perception, applied to a satellite signal receiver, the method comprising:
acquiring an ionosphere activity index set and satellite positioning information; the ionospheric activity index set includes at least one of: the change rate of the total electron content of the ionized layer, the vertical total electron content and the vertical gradient of the electron density of the ionized layer;
inputting the ionosphere liveness index set into a preset positioning calibration model to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models;
and calibrating the satellite positioning information according to the positioning offset to determine target positioning information.
2. The method of claim 1, wherein the satellite signal receiver is disposed in a power grid drone for performing autonomous inspection tasks.
3. The method of claim 2, wherein said calibrating the satellite positioning information according to the positioning offset to determine target positioning information comprises:
taking a preset ground signal enhancement base station as a differential source, and detecting communication signals aiming at the ground signal enhancement base station in real time;
according to the signal flight time corresponding to the communication signal, calculating the relative distance between the power grid unmanned aerial vehicle and the ground signal enhancement base station;
determining differential positioning coordinates of the power grid unmanned aerial vehicle according to pre-stored base station coordinates of the ground signal enhancement base station and the relative distance;
and calibrating the satellite positioning information according to the differential positioning coordinates and the positioning offset to determine target positioning information.
4. The method of claim 1, wherein the obtaining of the ionospheric activity index set comprises:
acquiring latitude and time parameters of a geographic area and a satellite sight angle; the latitude of the geographic area comprises dimension information of a target geographic area in which the satellite signal receiver is located, and the satellite sight angle comprises a satellite side view angle and a satellite pitch angle of the target geographic area relative to a Beidou satellite;
Inputting the geographic area latitude, the time parameter and the satellite line-of-sight angle into a pre-constructed index prediction model to determine an ionospheric activity index set for the target geographic area by the index prediction model.
5. The method of claim 4, wherein the index prediction model employs an adaptive multi-output gaussian model, and the constructing of the adaptive multi-output gaussian model includes:
acquiring a training sample set; each training sample in the training sample set is provided with unique geographic area information, and the training sample comprises geographic area latitude, time parameters, satellite sight angles and corresponding real ionosphere activity index sets;
determining regional sector information corresponding to geographic area information in the training samples aiming at each training sample, and enriching the training samples based on the regional sector information;
normalizing each training sample, and training the self-adaptive multi-output Gaussian model based on each normalized training sample;
the adaptive multi-output gaussian model is defined by:
wherein k is {a} Representing a set of predicted ionospheric activity indicators; x represents the latitude of a geographic area, y represents regional sector information, t represents a time parameter, and angle1 and angle2 respectively represent a satellite side view angle and a satellite pitch angle; h. u and l represent model parameters determined from the training sample set through model training, respectively.
6. The method of claim 1, wherein the hybrid model is defined by:
wherein { A } represents the ionospheric activity index set entered into the hybrid model, and f ({ A } represents the corresponding positioning offset; m is M i Model weight for the ith fuzzy model to characterize the influence degree of the fuzzy model on the whole mixed model; f (f) i ({ A }) describes the positioning offset determined by the ith fuzzy model.
7. The method of claim 6, wherein the fuzzy model comprises a fuzzy hyperbolic tangent model module, and the fuzzy hyperbolic tangent model module is defined by:
P＝f({A})＝α*tanh(β*{A})+γ*δ；
wherein P is a positioning offset, and alpha, beta, gamma and delta are model parameters;
alpha is the sensitivity of the model to the ionospheric activity index set, which determines the degree of responsiveness of the model to { A } changes;
beta is a parameter of the hyperbolic tangent function that determines how smooth the model is to the { A } variations.
Gamma is a constant term for the position offset, which represents the expected offset of the positioning coordinates without ionospheric activity;
delta is an error term for the position offset, which represents the extra error caused by the actual ionospheric activity;
Wherein the values of α, β, γ and δ are according to the data sample set { { { B 1 },{B 2 },…,{B N The loss function of the fuzzy hyperbolic tangent model module is determined in the training process, and a dynamic loss function is adopted by the loss function of the fuzzy hyperbolic tangent model module; each data sample in the data sample set comprises an ionosphere liveness index set marked with a true positioning offset;
the dynamic loss function is defined by:
L hyperbolic tangent Is a loss function value, Y j Representing any one of the data samples B in the set of data samples j Corresponding true positioning offset, p j Representing the prediction of data sample B by the fuzzy hyperbolic tangent model module j The corresponding positioning coordinate offset; n represents the total amount of data samples in the data sample set; d is the number of iterations, where the total number of iterations for the same data sample is G, G is determined from the user input information, and G is greater than or equal to 1.
8. The method of claim 7, wherein the fuzzy model further comprises a probabilistic graph model module and the probabilistic graph model module comprises an input layer, a hidden layer, and an output layer, wherein the input layer is configured to characterize an ionospheric activity index set, the hidden layer employs a recurrent neural network, and the output layer employs a fully connected network; the probability map model module uses the mean square error as a loss function to measure the coordinate difference between the predicted positioning offset and the actual positioning offset;
The probability map model module performs model training by using a back propagation algorithm based on a regularization method;
the probability map model module is constructed by:
input layer: x= [ { B 1 },{B 2 },…,{B N }}，Y]＝[x 1 ,...,x n ]Wherein x is n Representing an n-th ionospheric activity index, Y being an actual positioning offset;
hidden layer: h=c (x·w) h ) Where c () is the activation function of the hidden layer, W h Is a weight matrix of the hidden layer;
output layer: o=g (h·wo), where g () is the activation function of the output layer, W o Is the weight matrix of the output layer;
loss function:wherein L is Probability map Using absolute difference loss function e j Predicting data sample B by a probabilistic graphical model module j The corresponding positioning coordinate offset;
in the process of training the probability map model module based on the sample data set, the weight matrix W is continuously updated h And W is o To minimize the loss function L Probability map 。
9. The method of claim 8, wherein the loss function of the hybrid model employs a mean square error loss function and may be defined by:
wherein L is Mixing A loss function value representing the whole of the hybrid model, N representing the total amount of data samples in the data sample set; { y 1j ,…,y nj The expression of each fuzzy model is directed to data sample B j The outputted predicted positioning offset;
in the process of fusion training of the mixed models on the fuzzy models, the model weight { M > of each fuzzy model is continuously updated 1 …M n To minimize the loss function L Mixing 。
10. A ionosphere real-time perception based high precision positioning system, comprising:
the acquisition unit is used for acquiring the ionosphere activity index set and satellite positioning information; the ionospheric activity index set includes at least one of: the change rate of the total electron content of the ionized layer, the vertical total electron content and the vertical gradient of the electron density of the ionized layer;
the input unit is used for inputting the ionosphere liveness index set into a preset positioning calibration model so as to determine a corresponding positioning offset by the positioning calibration model; the positioning calibration model adopts a mixed model fused with a plurality of fuzzy models, and the fuzzy models comprise a fuzzy hyperbolic tangent model module and a probability map model module;
and the calibration unit is used for calibrating the satellite positioning information according to the positioning offset to determine target positioning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311618974.1A CN117607913B (en) | 2023-11-23 | 2023-11-23 | High-precision positioning method and system based on ionosphere real-time perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311618974.1A CN117607913B (en) | 2023-11-23 | 2023-11-23 | High-precision positioning method and system based on ionosphere real-time perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117607913A true CN117607913A (en) | 2024-02-27 |
| CN117607913B CN117607913B (en) | 2024-08-06 |
Family
ID=89945868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311618974.1A Active CN117607913B (en) | 2023-11-23 | 2023-11-23 | High-precision positioning method and system based on ionosphere real-time perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117607913B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118131267A (en) * | 2024-03-25 | 2024-06-04 | 中国矿业大学 | M-level flare-driven geomagnetic storm, ionosphere scintillation and positioning coupling analysis method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275185A (en) * | 2019-07-11 | 2019-09-24 | 武汉大学 | Ionosphere projection function modeling method based on GNSS and GEO satellite |
| US10852439B1 (en) * | 2020-04-30 | 2020-12-01 | Beihang University | Global ionospheric total electron content prediction system |
| CN116840874A (en) * | 2023-06-28 | 2023-10-03 | 广州导远电子科技有限公司 | Differential data quality monitoring method and device, electronic equipment and storage medium |
-
2023
- 2023-11-23 CN CN202311618974.1A patent/CN117607913B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275185A (en) * | 2019-07-11 | 2019-09-24 | 武汉大学 | Ionosphere projection function modeling method based on GNSS and GEO satellite |
| US10852439B1 (en) * | 2020-04-30 | 2020-12-01 | Beihang University | Global ionospheric total electron content prediction system |
| CN116840874A (en) * | 2023-06-28 | 2023-10-03 | 广州导远电子科技有限公司 | Differential data quality monitoring method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| WENQING SUN等: ""Forecasting of ionospheric vertical total electron content (TEC) using LSTM networks"", 《2017 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC)》, 16 November 2017 (2017-11-16), pages 340 - 344 * |
| 张富彬等: ""基于深度学习的全球电离层TEC 预测"", 《电波科学学报》, vol. 36, no. 4, 31 August 2021 (2021-08-31), pages 553 - 562 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118131267A (en) * | 2024-03-25 | 2024-06-04 | 中国矿业大学 | M-level flare-driven geomagnetic storm, ionosphere scintillation and positioning coupling analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117607913B (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117607913B (en) | High-precision positioning method and system based on ionosphere real-time perception | |
| CN111045046B (en) | Short-term ionosphere forecasting method and device based on NARX | |
| CN112052627A (en) | Method, device, medium and equipment for estimating near-surface ozone space distribution | |
| CN111474529B (en) | Satellite inversion radar echo method, inversion radar echo system and navigation radar | |
| CN111797573A (en) | Ionized layer electron concentration total content time sequence prediction method based on deep learning technology | |
| CN112902989B (en) | Data error calibration method and device, electronic equipment and storage medium | |
| WO2020247721A1 (en) | Systems and methods to improve geo-referencing using a combination of magnetic field models and in situ measurements | |
| Xie et al. | LSTM-based short-term ionospheric TEC forecast model and positioning accuracy analysis | |
| CN114185114B (en) | Correction method and device for rainfall forecast falling area, electronic equipment and medium | |
| CN115545334A (en) | Land use type prediction method, land use type prediction device, electronic device, and storage medium | |
| Carvalho et al. | Nowcasting of amplitude ionospheric scintillation based on machine learning techniques | |
| CN118070843A (en) | Multi-station low-visibility prediction method based on graph recurrent neural network | |
| Zhang et al. | Short-term regional ionospheric TEC forecast using a hybrid deep learning neural network | |
| WO2024152673A1 (en) | Mobile terminal positioning method and apparatus, and device and storage medium | |
| Liu et al. | GNSS-R global sea surface wind speed retrieval based on deep learning | |
| Lu et al. | A new technique for automatically locating the center of tropical cyclones with multi-band cloud imagery | |
| US20210364645A1 (en) | Method for gps spoofing detection with gps receivers leveraging inaccuracies of gps spoofing devices and apparatus therefore | |
| Chen et al. | Global TEC map fusion through a hybrid deep learning model: RFGAN | |
| Lei et al. | Reference source‐aided coordinate registration method for over‐the‐horizon radar using ensemble learning | |
| Maheswaran et al. | Bi-LSTM based vertical total electron content prediction at low-latitude equatorial ionization anomaly region of South India | |
| CN114252871B (en) | Radar measurement precision compensation method based on machine learning | |
| Tian et al. | Estimation model of global ionospheric irregularities: an artificial intelligence approach | |
| CN115062526B (en) | Three-dimensional ionosphere electron concentration distribution model training method based on deep learning | |
| CN113093225B (en) | Wide-area and local-area fused high-precision ionospheric scintillation model establishment method | |
| Cañar et al. | Deep learning to implement a statistical weather forecast for the andean city of quito |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |