GNSS inter-frequency deviation solving method and system based on graph neural network

Abstract

The invention discloses a GNSS inter-frequency deviation solving method and system based on a graph neural network, and the method comprises the steps: obtaining GNSS observation data, and calculating a phase smoothing pseudo-range inter-frequency difference value and puncture point information; inputting the phase smoothing pseudo-range inter-frequency difference value and puncture point information into the trained graph neural network model, and outputting GNSS inter-frequency deviation; training of a graph neural network model: acquiring GNSS observation data and a precision inter-frequency deviation product of global sites, and calculating a phase smoothing pseudo-range inter-frequency difference value and puncture point information site by site; constructing a data set by taking the phase smoothing pseudo-range inter-frequency difference value and puncture point information as input and taking a precise inter-frequency deviation product as output; based on a graph neural network architecture, taking a satellite and a receiver as nodes, and taking puncture point information and a phase smoothing pseudo-range inter-frequency difference value as edge attributes, carrying out embedded transformation, and forming a graph neural network model; and training the graph neural network model by using the constructed data set, and outputting the trained model.

Description

Technical Field

[0001] The present invention belongs to the field of GNSS inter-frequency deviation parameter solution, and specifically relates to a GNSS inter-frequency deviation solution method and system based on graph neural network. Background Art

[0002] In global navigation satellite system (GNSS) positioning, inter-frequency deviation (hereinafter referred to as "DCB") is an error caused by the difference in propagation speed of signals of different frequencies due to the ionosphere. Accurately solving DCB is crucial to improving GNSS positioning accuracy.

[0003] Traditional DCB solution methods usually rely on global GNSS observation data, establish a smooth correction model for ionospheric delay based on phase-smoothed pseudorange frequency difference values ​​and spherical harmonics, and separate the DCB for separate solution while calculating the model coefficients. This method assumes that the ionospheric correction value is smooth in space, but the actual ionospheric correction value often has significant spatiotemporal non-stationarity. Due to this assumption deviation, the traditional method will cause the systematic error of the ionospheric correction model to be absorbed by the DCB during the solution process, thereby affecting the accuracy of the DCB solution, especially when the ionospheric conditions are complex or dynamically changing.

[0004] The terms involved in the specification of the present invention are explained as follows: GNSS: Global Navigation Satellite System; DCB: Differential Code Bias, that is, frequency deviation. Summary of the invention

[0005] In order to solve the problem that the existing methods rely on the smoothness assumption, which affects the accuracy of DCB solutions, the present invention provides a GNSS inter-frequency deviation solution method and system based on graph neural network. By directly using the spatiotemporal dependency relationship between satellites and receivers for modeling and combining graph neural network for node information transmission, accurate DCB prediction is achieved.

[0006] According to one aspect of the present invention, a method for solving GNSS inter-frequency deviation based on a graph neural network is provided, comprising: Acquire GNSS observation data, and calculate phase-smoothed pseudorange inter-frequency difference value and puncture point information according to the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are input into the trained graph neural network model to output the GNSS frequency deviation; wherein the training of the graph neural network model includes: Obtain GNSS observation data and precise inter-frequency deviation products of global sites, and calculate the phase-smoothed pseudo-range inter-frequency difference value and puncture point information for each site based on the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are used as input, and the precise frequency deviation product is used as output to construct a data set; Based on the graph neural network architecture, satellites and receivers are used as nodes, puncture point information and phase-smoothed pseudorange frequency difference values ​​are used as edge attributes, and embedded transformation is performed to form a graph neural network model. Use the constructed dataset to train the graph neural network model and output the trained model.

[0007] As a further technical solution, the calculation of the puncture point information includes: Calculate the latitude and longitude, satellite altitude angle and azimuth of the puncture point.

[0008] As a further technical solution, constructing a data set also includes: A data sample is composed of one day's phase-smoothed pseudorange frequency difference value, puncture point information, and precise frequency deviation product, and a data set is composed of several days' data samples.

[0009] As a further technical solution, the constructed dataset is used to train the graph neural network model, including: The data set is input into the constructed graph neural network model, the mean square error (MSE) is used as the loss function, and the Adam optimization algorithm is used for back propagation to perform model training.

[0010] According to one aspect of the present invention, a GNSS inter-frequency deviation solution system based on a graph neural network is provided, comprising: A first calculation module is used to obtain GNSS observation data and calculate the phase smoothed pseudorange frequency difference value and puncture point information according to the GNSS observation data; The second calculation module is used to input the calculated phase-smoothed pseudorange frequency difference value and puncture point information into the trained graph neural network model, and output the GNSS frequency deviation; wherein the training of the graph neural network model includes: Obtain GNSS observation data and precise inter-frequency deviation products of global sites, and calculate the phase-smoothed pseudo-range inter-frequency difference value and puncture point information for each site based on the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are used as input, and the precise frequency deviation product is used as output to construct a data set; Based on the graph neural network architecture, satellites and receivers are used as nodes, puncture point information and phase-smoothed pseudorange frequency difference values ​​are used as edge attributes, and embedded transformation is performed to form a graph neural network model. Use the constructed dataset to train the graph neural network model and output the trained model.

[0011] According to one aspect of the present invention specification, a GNSS inter-frequency deviation solving device based on a graph neural network is provided, comprising a memory and a processor, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS inter-frequency deviation solving method based on a graph neural network.

[0012] According to one aspect of the present specification, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute the steps of the GNSS inter-frequency deviation solution method based on graph neural network.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention designs a graph neural network suitable for GNSS DCB and implements a high-precision solution method for DCB. This method no longer relies on the smooth assumption of ionospheric correction values, but skips the estimation of ionospheric corrections and directly uses the spatiotemporal dependency between satellites and receivers for modeling. And by utilizing the characteristics of graph neural networks that are naturally suitable for processing such data with strong spatiotemporal correlation, through information transmission between nodes, the deep connection between historical precise DCB data and observations is adaptively learned. Through this data-driven approach, the model can more accurately predict DCB without relying on traditional smooth assumptions, and show higher robustness and adaptability in a dynamic ionospheric environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction is given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A schematic flow chart of a method for solving GNSS inter-frequency deviation based on a graph neural network provided in an embodiment of the present invention.

[0016] Figure 2 A schematic diagram of the training process of the graph neural network model provided in an embodiment of the present invention.

[0017] Figure 3 A schematic diagram of the structure of a GNSS inter-frequency deviation solution system based on a graph neural network provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] It should be noted that: When solving DCB in the prior art, it is assumed that the ionospheric correction value is smooth in space. Due to this assumption deviation, the systematic error of the ionospheric correction model in the solution process is absorbed by DCB, thereby affecting the accuracy of DCB solution, especially when the ionospheric conditions are complex or dynamically changing. In view of this problem, the present invention considers that neural networks, as a powerful data fitting and feature extraction tool, have made significant progress in many fields, and proposes a GNSS inter-frequency deviation solution method based on graph neural network, which solves the problem that the prior art relies on the smooth assumption of ionospheric correction values, resulting in the affected accuracy of DCB solution.

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] The embodiment of the present invention provides a method for solving GNSS inter-frequency deviation based on graph neural network, such as Figure 1 As shown, first, GNSS observation data is obtained, and the phase-smoothed pseudorange inter-frequency difference value and puncture point information are calculated based on the GNSS observation data; then, the calculated phase-smoothed pseudorange inter-frequency difference value and puncture point information are input into the trained graph neural network model to output the GNSS inter-frequency deviation.

[0021] The method provided in the embodiment of the present invention skips the estimation of ionospheric correction, directly utilizes the spatiotemporal dependency between satellite and receiver, and solves the GNSS inter-frequency deviation, i.e., the precise DCB product, in combination with the graph neural network model. This not only avoids the reliance on the smooth assumption, but also demonstrates higher robustness and adaptability in a dynamic ionospheric environment.

[0022] The embodiment of the present invention is based on the IGS global observation station and the precision DCB product to perform model training. Figure 2 As shown, the training of the graph neural network model includes: S1, obtain the GNSS observation data and precise inter-frequency deviation products of global sites, and calculate the phase-smoothed pseudo-range inter-frequency difference value and puncture point information for each site based on the GNSS observation data.

[0023] Specifically, it also includes: S11, download GNSS observation data and precision DCB products of global stations. For example, download GNSS observation data of IGS global stations and daily precision DCB products of CODE Analysis Center from 2020 to 2023.

[0024] S12, calculate the phase-smoothed pseudo-range inter-frequency difference observation value of the GNSS station, as well as the puncture point position at the intersection of the observation ray and the ionosphere, the satellite altitude angle and azimuth angle for each station.

[0025] S2, takes the calculated phase-smoothed pseudorange inter-frequency difference value and puncture point information as input and the precise inter-frequency deviation product as output to construct a data set.

[0026] Specifically, a data sample is constructed with single-day data, and the puncture point information (including the puncture point latitude and longitude, satellite altitude angle, azimuth) and the calculated phase smoothed pseudorange frequency difference value are used as input data, and the precise DCB product is used as output data. The input data and output data of one day constitute a data sample, and the data samples of multiple days constitute the entire data set.

[0027] S3, based on the graph neural network architecture, takes the satellite and receiver as nodes, the puncture point information and the phase-smoothed pseudorange frequency difference value as the observation edge attributes, and constructs the graph neural network model after embedding transformation.

[0028] Specifically, when constructing the graph neural network model, satellites and receivers are used as two types of nodes respectively, and the longitude and latitude of the puncture point, the satellite altitude angle and azimuth, and the frequency difference value are used as edge attributes. An embedding transformation is performed to map these discrete data into a low-dimensional continuous space, so that similar data are close in the embedding space, which facilitates the neural network to capture relationships and perform spatiotemporal data modeling through information transfer and aggregation operations between nodes.

[0029] Graph convolution is expressed as:

[0030] in, is the feature vector of node i at layer t, is the set of neighbor nodes of node i, is the weight matrix, is the bias term, is the activation function (such as ReLU).

[0031] S4, use the constructed data set to train the graph neural network model and output the trained model.

[0032] The data set is divided into training set, validation set and test set, and the graph neural network model is applied to train the graph neural network model according to the training set data input, graph convolution operation feature iteration, minimization of loss function and back propagation algorithm optimization parameters until the training converges.

[0033] Furthermore, the dataset is input into the constructed model, and mean square error (MSE) is used as the loss function, and the Adam optimization algorithm is used for back propagation to train the model.

[0034] In practical applications, the embodiment of the present invention uses the trained graph neural network model and the latest site observation data to calculate spatiotemporal data, and performs reasoning based on the calculated spatiotemporal data to obtain the corresponding DCB. Compared with the existing methods, the DCB obtained by the embodiment of the present invention has higher accuracy and exhibits higher robustness and adaptability in a dynamic ionospheric environment.

[0035] The implementation basis of each embodiment of the present invention is achieved by programmed processing through a device with a processor function. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this reality, on the basis of the above embodiments, an embodiment of the present invention provides a GNSS inter-frequency deviation solution system based on a graph neural network, which is used to execute the GNSS inter-frequency deviation solution method based on a graph neural network in the above method embodiment.

[0036] See also Figure 3 The system includes: a first calculation module, which is used to obtain GNSS observation data, and calculate the phase-smoothed pseudorange frequency difference value and puncture point information according to the GNSS observation data; a second calculation module, which is used to input the calculated phase-smoothed pseudorange frequency difference value and puncture point information into the trained graph neural network model, and output the GNSS frequency deviation; wherein the training of the graph neural network model includes: obtaining GNSS observation data and precise frequency deviation products of global sites, and calculating the phase-smoothed pseudorange frequency difference value and puncture point information for each site based on the GNSS observation data; constructing a data set with the calculated phase-smoothed pseudorange frequency difference value and puncture point information as input and the precise frequency deviation product as output; based on the graph neural network architecture, with satellites and receivers as nodes, and with puncture point information and phase-smoothed pseudorange frequency difference value as edge attributes, embedding transformation is performed to form a graph neural network model; the graph neural network model is trained using the constructed data set, and the trained model is output.

[0037] The GNSS inter-frequency deviation solution system based on graph neural network provided by the embodiment of the present invention aims at the problem that the DCB solution accuracy is affected by the reliance on smoothness assumption in the existing methods. Figure 3 Several modules in the proposed method achieve accurate prediction of DCB by directly utilizing the spatiotemporal dependency between satellites and receivers for modeling and combining graph neural networks for node information transmission.

[0038] It should be noted that the system embodiment provided by the present invention is used to implement the methods in the above method embodiment as well as the methods in other method embodiments provided by the present invention. The only difference is that the corresponding functional modules are set. The principle is basically the same as the principle of the above system embodiment provided by the present invention. As long as the technical personnel in this field refer to the specific technical solutions in other method embodiments on the basis of the above system embodiment, obtain the corresponding technical means and the technical solutions composed of these technical means by combining the technical features, and on the premise of ensuring the practicality of the technical solutions, improve the modules in the above system embodiment to obtain the corresponding system class embodiments, which are used to implement the methods in other method class embodiments. For example: Based on the content of the above system embodiment, as a preferred embodiment, in the GNSS inter-frequency deviation solution system based on graph neural network provided in the embodiment of the present invention, the first calculation module is also used to execute the following instructions: Calculate the latitude and longitude, satellite altitude angle and azimuth of the puncture point.

[0039] Based on the content of the above system embodiment, as a preferred embodiment, in the GNSS inter-frequency deviation solution system based on graph neural network provided in the embodiment of the present invention, the second calculation module is also used to execute the following instructions: A data sample is composed of one day's phase-smoothed pseudorange frequency difference value, puncture point information, and precise frequency deviation product, and a data set is composed of several days' data samples.

[0040] Based on the content of the above system embodiment, as a preferred embodiment, in the GNSS inter-frequency deviation solution system based on graph neural network provided in the embodiment of the present invention, the second calculation module is also used to execute the following instructions: The data set is input into the constructed graph neural network model, the mean square error (MSE) is used as the loss function, and the Adam optimization algorithm is used for back propagation to perform model training.

[0041] Based on the same inventive concept as the above-mentioned embodiment, an embodiment of the present invention also provides a GNSS inter-frequency deviation solving device based on a graph neural network, comprising a memory and a processor, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS inter-frequency deviation solving method based on a graph neural network.

[0042] In an embodiment of the present invention, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or a volatile memory (volatile memory), such as a random-access memory (RAM). The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in an embodiment of the present invention may also be a circuit or any other device that can implement a storage function, for storing program instructions and / or data.

[0043] In the embodiments of the present invention, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0044] Based on the same inventive concept as the above-mentioned embodiment, an embodiment of the present invention also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable the computer to execute the steps of the GNSS inter-frequency deviation solution method based on graph neural network.

[0045] In summary, the present invention designs a graph neural network suitable for GNSS DCB and implements a high-precision solution method for DCB, which has the following advantages: The present invention no longer relies on the smooth assumption of ionospheric correction values, but skips the estimation of ionospheric correction and directly uses the space-time dependency between satellites and receivers for modeling.

[0046] The present invention utilizes the characteristics of graph neural networks that are suitable for processing such data with strong spatiotemporal correlation, and adaptively learns the deep connection between historical precise DCB data and observed values ​​through information transmission between nodes.

[0047] The present invention can more accurately predict DCB without relying on the traditional smooth assumption, and exhibits higher robustness and adaptability in a dynamic ionospheric environment.

[0048] The terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A GNSS inter-frequency deviation solution method based on graph neural network, characterized in that: include: Acquire GNSS observation data, and calculate phase-smoothed pseudorange inter-frequency difference value and puncture point information according to the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are input into the trained graph neural network model to output the GNSS frequency deviation; wherein the training of the graph neural network model includes: Obtain GNSS observation data and precise inter-frequency deviation products of global sites, and calculate the phase-smoothed pseudo-range inter-frequency difference value and puncture point information for each site based on the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are used as input, and the precise frequency deviation product is used as output to construct a data set; Based on the graph neural network architecture, satellites and receivers are used as nodes, puncture point information and phase-smoothed pseudorange frequency difference values ​​are used as edge attributes, and embedded transformation is performed to form a graph neural network model. Use the constructed dataset to train the graph neural network model and output the trained model.

2. According to the method for solving GNSS inter-frequency deviation based on graph neural network in claim 1, it is characterized in that: The calculation of the puncture point information includes: Calculate the latitude and longitude, satellite altitude angle and azimuth of the puncture point.

3. According to the GNSS inter-frequency deviation solution method based on graph neural network according to claim 1, it is characterized in that: Building a dataset also includes: A data sample is composed of one day's phase-smoothed pseudorange frequency difference value, puncture point information, and precise frequency deviation product, and a data set is composed of several days' data samples.

4. The GNSS inter-frequency deviation solution method based on graph neural network according to claim 1 is characterized in that: Use the constructed dataset to train the graph neural network model, including: The data set is input into the constructed graph neural network model, the mean square error (MSE) is used as the loss function, and the Adam optimization algorithm is used for back propagation to perform model training.

5. The GNSS inter-frequency deviation solution system based on graph neural network is characterized by: include: A first calculation module is used to obtain GNSS observation data and calculate the phase smoothed pseudorange frequency difference value and puncture point information according to the GNSS observation data; The second calculation module is used to input the calculated phase-smoothed pseudorange frequency difference value and puncture point information into the trained graph neural network model, and output the GNSS frequency deviation; wherein the training of the graph neural network model includes: Obtain GNSS observation data and precise inter-frequency deviation products of global sites, and calculate the phase-smoothed pseudo-range inter-frequency difference value and puncture point information for each site based on the GNSS observation data; The calculated phase-smoothed pseudorange frequency difference value and puncture point information are used as input, and the precise frequency deviation product is used as output to construct a data set; Based on the graph neural network architecture, satellites and receivers are used as nodes, puncture point information and phase-smoothed pseudorange frequency difference values ​​are used as edge attributes, and embedded transformation is performed to form a graph neural network model. Use the constructed dataset to train the graph neural network model and output the trained model.

6. A GNSS inter-frequency deviation solving device based on graph neural network, characterized in that: It includes a memory and a processor, the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS inter-frequency deviation solution method based on graph neural network as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, which enable the computer to execute the steps of the GNSS inter-frequency deviation solution method based on graph neural network as described in any one of claims 1 to 4.

Images