[go: up one dir, main page]

CN118818540B - A receiver clock bias prediction method, apparatus, device, and storage medium - Google Patents

A receiver clock bias prediction method, apparatus, device, and storage medium

Info

Publication number
CN118818540B
CN118818540B CN202410842927.3A CN202410842927A CN118818540B CN 118818540 B CN118818540 B CN 118818540B CN 202410842927 A CN202410842927 A CN 202410842927A CN 118818540 B CN118818540 B CN 118818540B
Authority
CN
China
Prior art keywords
receiver clock
receiver
clock bias
elevation
time
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.)
Active
Application number
CN202410842927.3A
Other languages
Chinese (zh)
Other versions
CN118818540A (en
Inventor
戴志强
孙思媚
谢婷
翟春磊
朱祥维
何少烽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sun Yat Sen University
Original Assignee
Sun Yat Sen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sun Yat Sen University filed Critical Sun Yat Sen University
Priority to CN202410842927.3A priority Critical patent/CN118818540B/en
Publication of CN118818540A publication Critical patent/CN118818540A/en
Application granted granted Critical
Publication of CN118818540B publication Critical patent/CN118818540B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G01S19/23—Testing, monitoring, correcting or calibrating of receiver elements
    • 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
    • G01S19/24—Acquisition or tracking or demodulation of signals transmitted by the system
    • G01S19/25—Acquisition or tracking or demodulation of signals transmitted by the system involving aiding data received from a cooperating element, e.g. assisted GPS
    • 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
    • G01S19/24—Acquisition or tracking or demodulation of signals transmitted by the system
    • G01S19/27—Acquisition or tracking or demodulation of signals transmitted by the system creating, predicting or correcting ephemeris or almanac data within the receiver
    • 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
    • G01S19/35—Constructional details or hardware or software details of the signal processing chain
    • G01S19/37—Hardware or software details of the signal processing chain
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04J—MULTIPLEX COMMUNICATION
    • H04J3/00—Time-division multiplex systems
    • H04J3/02—Details
    • H04J3/06—Synchronising arrangements
    • H04J3/0635—Clock or time synchronisation in a network
    • H04J3/0638—Clock or time synchronisation among nodes; Internode synchronisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Power Engineering (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention discloses a receiver clock error prediction method, a device, equipment and a storage medium, wherein the method comprises the steps of obtaining satellite navigation information and observation information of a current time node received by a receiver; and inputting the receiver clock difference, the elevation and the time precision attenuation factors into a preset receiver clock difference prediction model, predicting the receiver clock difference of a future time node, and generating the receiver clock difference corresponding to the future time node. The invention can improve the prediction precision of the receiver clock error.

Description

Receiver clock error prediction method, device, equipment and storage medium
Technical Field
The present invention relates to the field of satellite navigation positioning technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting a receiver clock error.
Background
The receiver clock error is an important GNSS parameter, and has important significance for theoretical research and application research of the receiver clock error. At present, a prediction method of the receiver clock error mainly comprises a receiver clock error epoch-by-epoch estimation model and an actual measurement data mathematical modeling method.
The receiver clock error and the three-dimensional coordinates of the receiver acquired in the positioning resolving process are resolved together by the receiver clock error epoch-by-epoch estimating model to form four unknowns, at least 4 satellites are observed at the same time in each epoch to construct a pseudo-range measuring equation set or a carrier phase measuring equation set, and the positioning and clock error estimation of the receiver are realized. The mathematical modeling method of the measured data models the receiver clock error time sequence through a mathematical method, and has higher short-term prediction precision in dynamic positioning, particularly in complex environments such as tunnels, urban canyons and the like, and specifically comprises a quadratic polynomial model, an ARMA model, a gray theoretical model, an extended Kalman filtering model and the like.
However, these models are not very accurate in terms of prediction (1) an epoch-by-epoch estimation model, in which only satellites in the hemisphere above the horizon are observed, and this asymmetry leads to significant correlation between the receiver clock bias, tropospheric parameters and the estimate of the elevation, and thus part of the receiver clock bias estimate contains pseudo errors associated with the elevation. (2) The traditional method is to mine the internal rule of the clock difference sequence based on some physical characteristics (such as noise type and frequency characteristic) of the receiver clock, to make statistical rule assumption to model (such as quadratic polynomial model and extended Kalman filtering model), or to verify that the predictive model obeys an information processing system (such as gray system) which is researched according to experience to model the sequence. The method only models the receiver clock error by a single factor, does not consider the influence of various factors such as elevation, troposphere delay and the like, and is difficult to accurately model and predict an original actual measurement sequence, so that the prediction accuracy is not high.
Disclosure of Invention
The invention provides a receiver clock error prediction method, device, equipment and storage medium, which are used for solving the technical problem that the prediction precision of the existing receiver clock error prediction model is not high.
In order to solve the above technical problems, an embodiment of the present invention provides a method for predicting a receiver clock error, including:
acquiring satellite navigation information and observation information of a current time node received by a receiver;
Standard single-point positioning calculation is carried out on the satellite navigation information and the observation information, and receiver clock error, elevation and time precision attenuation factors corresponding to the current time node are obtained through calculation;
and inputting the receiver clock difference, the elevation and the time precision attenuation factors into a preset receiver clock difference prediction model, predicting the receiver clock difference of the future time node, and generating the receiver clock difference corresponding to the future time node.
Preferably, the satellite navigation information comprises the orbit position and clock error of the satellite;
Standard single-point positioning calculation is carried out on the satellite navigation information and the observation information, and receiver clock difference, elevation and time precision attenuation factors corresponding to the current time node are obtained through calculation, and the method comprises the following steps:
Calculating satellite observation pseudo-range according to the observation information;
And calculating to obtain a receiver clock error and an approximate position coordinate of the receiver corresponding to the current time node according to the satellite observation pseudo-range, the orbit positions and clock errors of at least four satellites, a preset troposphere error model and a preset ionosphere error model, and further calculating to obtain a corresponding receiver elevation and a time precision attenuation factor corresponding to the current time node according to the approximate position coordinate of the receiver.
Preferably, before the receiver clock error, the elevation and the time precision attenuation factors are input into a preset receiver clock error prediction model, the method further comprises:
And preprocessing the clock difference, the elevation and the time precision attenuation factors of the receiver, wherein the preprocessing comprises discontinuous data processing, coarse difference detection and correction and sampling time conversion.
Preferably, the receiver comprises a static base station receiver and a dynamic motion carrier receiver;
The receiver clock error prediction model comprises a static receiver clock error prediction model and a dynamic receiver clock error prediction model;
inputting the receiver clock error, the elevation and the time precision attenuation factors into a preset receiver clock error prediction model, wherein the method comprises the following steps of:
When the receiver is a base station receiver, inputting the receiver clock error, elevation and time precision attenuation factors into the static receiver clock error prediction model; when the receiver is a motion carrier receiver, the receiver clock error, elevation and time precision attenuation factors are input into the dynamic receiver clock error prediction model.
Preferably, the receiver clock error prediction model comprises an LSTM model;
wherein, LSTM model includes a plurality of LSTM unit, and each LSTM unit includes:
ft＝σ(Wf[xt,ht-1]+bf);
it＝σ(Wi[xt,ht-1]+bi);
ot＝σ(Wo[xt,ht-1]+bo);
ht＝ot⊙tanh(ct);
wherein f t represents a forgetting gate indicating a proportion of memory information to be retained in memory cells at a current time, i t represents an input gate indicating a proportion of input information at a current time in memory cells at a current time, c t represents memory cells at a current time t to selectively store past information and current input information, o t represents an output gate indicating that current memory information selectively flows into current output information, h t represents an output at a current time, sigma represents a sigmoid activation function, tan h represents a hyperbolic tangent activation function, W * represents a weight matrix, b * represents a bias vector, and c represents a matrix point product.
Preferably, the generating of the receiver clock difference prediction model includes:
acquiring satellite navigation information and observation information of past time nodes received by a receiver;
Standard single-point positioning calculation is carried out on the satellite navigation information and the observation information, and receiver clock error, elevation and time precision attenuation factors corresponding to past time nodes are obtained;
preprocessing the clock difference, the elevation and the time precision attenuation factors of the receiver, wherein the preprocessing comprises discontinuous data processing, coarse difference detection and correction and sampling time conversion;
respectively carrying out normalization processing on each subsequence in the preprocessed receiver clock difference, elevation and time precision attenuation factors, and dividing the subsequence into a plurality of samples;
dividing the samples into a training set, a verification set and a test set, and training the LSTM model according to the training set, the verification set, the test set, the preset input time step and output time step in each sample and the preset super parameters to obtain a receiver clock error prediction model.
Preferably, after the receiver clock differences, the elevation and the time precision attenuation factors are input into a preset receiver clock difference prediction model, the receiver clock differences of the future time nodes are predicted, and the receiver clock differences corresponding to the future time nodes are generated, the method further comprises:
calculating the average absolute error and the root mean square error of the receiver clock error;
And comparing the average absolute error and the root mean square error of the receiver clock error with the average absolute error and the root mean square error of the receiver clock error based on a preset quadratic polynomial model and a gray theoretical model respectively, and then evaluating the prediction performance of the receiver clock error prediction model according to the comparison result.
On the basis of the above embodiment, another embodiment of the present invention provides an apparatus, including a satellite navigation information and observation information acquisition module, a standard single point positioning calculation module, and a receiver clock prediction module;
the satellite navigation information and observation information acquisition module is used for acquiring satellite navigation information and observation information of the current time node received by the receiver;
The standard single-point positioning resolving module is used for carrying out standard single-point positioning resolving on the satellite navigation information and the observation information, and calculating to obtain receiver clock difference, elevation and time precision attenuation factors corresponding to the current time node;
The receiver clock difference prediction module is used for inputting the receiver clock difference, the elevation and the time precision attenuation factors into a preset receiver clock difference prediction model, predicting the receiver clock difference of the future time node and generating the receiver clock difference corresponding to the future time node.
On the basis of the above embodiment, a further embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes the computer program to implement the receiver clock error prediction method according to the above embodiment of the present invention.
On the basis of the above embodiment, a further embodiment of the present invention provides a storage medium, where the storage medium includes a stored computer program, where the computer program controls a device where the storage medium is located to execute the receiver clock error prediction method according to the above embodiment of the present invention when running.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
The invention provides a receiver clock error prediction method, which comprises the steps of obtaining satellite navigation information and observation information of a current time node received by a receiver, carrying out standard single-point positioning calculation based on the satellite navigation information and the observation information, calculating to obtain receiver clock error, elevation and time precision attenuation factors corresponding to the current time node, inputting the receiver clock error, the elevation and the time precision attenuation factors into a preset receiver clock error prediction model, predicting the receiver clock error of a future time node, and generating the receiver clock error corresponding to the future time node.
The receiver clock error prediction model in the prior art only models the receiver clock error by a single factor, does not consider the influence of various factors such as elevation, troposphere delay and the like, and is difficult to accurately model and predict an original actual measurement sequence. Compared with the prior art, the receiver clock error prediction model is formed by model training of a preset neural network model by taking the receiver clock error, the elevation and the time precision attenuation factors corresponding to the past time nodes as inputs and the receiver clock error corresponding to the future time nodes as outputs. Therefore, the receiver clock error prediction model can automatically learn the correlation between the receiver clock error and the elevation, acquire the uncertainty of the receiver clock error from the time precision attenuation factor, and can model complex nonlinear relations. When the receiver clock error prediction model is used for predicting the receiver clock error, satellite navigation information and observation information received by a receiver are acquired and subjected to standard single-point positioning calculation, so that the receiver clock error, elevation and time precision attenuation factors are obtained and input into the receiver clock error prediction model, the receiver clock error with higher prediction precision can be obtained, and the prediction precision of the receiver clock error is improved.
Drawings
Fig. 1 is a schematic flow chart of a receiver clock error prediction method according to an embodiment of the present invention;
FIG. 2 is a block diagram of the LSTM cell;
FIG. 3 is a diagram of a receiver clock error prediction model;
FIG. 4 is a flow chart of LSTM predicted receiver clock bias and assisted GNSS positioning;
fig. 5 is a schematic structural diagram of a receiver clock error prediction apparatus according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, the terms used herein are for the purpose of describing particular embodiments only and are not intended to be limiting of the application, and the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the above description of the drawings are intended to cover non-exclusive inclusions.
In the description of embodiments of the present application, the technical terms "first," "second," and the like are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present application, the meaning of "plurality" is two or more unless explicitly defined otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In the description of the embodiment of the present application, the term "and/or" is merely an association relationship describing the association object, and indicates that three relationships may exist, for example, a and/or B, and may indicate that a exists alone, while a and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
In the description of the embodiments of the present application, the term "plurality" means two or more (including two), and similarly, "plural sets" means two or more (including two), and "plural sheets" means two or more (including two).
In the description of the embodiments of the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "fixed" and the like are to be construed broadly and include, for example, fixed connection, detachable connection, or integral therewith, mechanical connection, electrical connection, direct connection, indirect connection via an intermediary, communication between two elements, or interaction between two elements. The specific meaning of the above terms in the embodiments of the present application will be understood by those of ordinary skill in the art according to specific circumstances.
Example 1
Referring to fig. 1, a flowchart of a receiver clock error prediction method according to an embodiment of the invention includes the following specific steps:
S1, acquiring satellite navigation information and observation information of a current time node received by a receiver;
The method aims at solving the problems of the prior art that (1) modeling is only carried out on the receiver clock error by a single factor, the influence of various factors such as elevation, troposphere delay and the like is not considered, the modeling and the prediction of an original actual measurement sequence are difficult to accurately model, and (2) based on a fixed function or a system, the complex nonlinear input-output relationship of the receiver clock error is difficult to be represented, and the prediction precision cannot be remarkably improved. The invention constructs a receiver clock error prediction model with strong generalization capability, can realize long-time high-precision prediction, can assist GNSS to realize high-precision positioning when satellite signal quality is poor, and can directly express by using a model with the same structure and super parameters aiming at static and dynamic conditions.
When the receiver clock error prediction model constructed by the invention is used for predicting the receiver clock error, the prediction steps are as follows:
1. firstly, static satellite navigation information and observation information received by a base station receiver (static) and dynamic satellite navigation information and observation information received by a motion carrier receiver (dynamic) are respectively acquired.
S2, carrying out standard single-point positioning calculation on the satellite navigation information and the observation information, and calculating to obtain receiver clock error, elevation and time precision attenuation factors corresponding to the current time node;
The satellite navigation information comprises satellite orbit positions and clock differences, standard single-point positioning calculation is carried out on the satellite navigation information and observation information to obtain receiver clock differences, elevation and time precision attenuation factors corresponding to current time nodes, the satellite navigation information comprises satellite observation pseudo-ranges obtained through calculation according to the observation information, and according to the satellite observation pseudo-ranges, the orbit positions and clock differences of at least four satellites, a preset troposphere error model and a preset ionosphere error model, the receiver clock differences corresponding to the current time nodes and approximate position coordinates of the receiver are obtained through calculation, and then corresponding receiver elevation and time precision attenuation factors corresponding to the current time nodes are obtained through calculation according to the approximate position coordinates of the receiver.
2. After static satellite navigation information and observation information received by a base station receiver and dynamic satellite navigation information and observation information received by a motion carrier receiver are obtained, standard single point positioning (Standard Point Positioning, SPP) calculation is carried out on each satellite navigation information and observation information, a receiver clock error, an elevation and a time precision attenuation factor (TDOP) corresponding to a current time node are obtained through calculation, and the calculation steps of the receiver clock error, the elevation and the TDOP are calculated by adopting the SPP:
(1) The signal transmission time length is obtained according to the transmitting time and the receiving time of the satellite signal, and the time length is multiplied by the speed of light to obtain a signal transmission distance measurement value, which is called pseudo range. The pseudoranges are not equal to the actual range due to the asynchronism of the satellite clock and the receiver clock, orbit errors, tropospheric and ionospheric delays, multipath effects, hardware noise, etc. The orbit error and the satellite clock error are corrected by using navigation information, and the effects of the troposphere delay and the ionosphere delay are eliminated by modeling, so that the pseudo range is expressed as:
ρi＝di+ctR+vi;
Where ρ i is the pseudo-range between the ith satellite and the receiver, d i is the actual range, c is the speed of light, t R is the receiver clock difference, and v i is the error due to multipath effects, hardware noise, etc.
(2) The position coordinates of the ith satellite and the receiver are respectively expressed asAnd (x u,yu,zu), then
(3) Satellite coordinates can be obtained from the broadcast ephemeris and only four satellites need to be observed to solve for four unknown parameters (x u,yu,zu,tR).
From approximate position coordinates of the receiverAnd taylor series expansion, can be obtained:
wherein, the If n satellites are observed, Δρ can be expressed as:
Where (dx, dy, dz) is the difference between the actual position coordinates of the receiver and the approximate position coordinates. Thus, when the number of visible satellites is equal to or greater than four satellites, x= (dx, dy, dz, t R) can be solved. Wherein, the covariance matrix of the calculated value and the actual value of x is
The TDOP is:
preferably, the method further comprises preprocessing the receiver clock error, the elevation and the time precision attenuation factors before inputting the receiver clock error, the elevation and the time precision attenuation factors into a preset receiver clock error prediction model, wherein the preprocessing comprises data discontinuous processing, coarse error detection and correction and sampling time conversion.
3. After the SPP solution obtains the clock error, the elevation and the TDOP of the receiver, preprocessing the data calculated by the SPP solution, wherein the preprocessing steps are as follows:
(1) For data discontinuity, the data is first divided into a series of continuous subsequences, when the time interval between the two subsequences is less than or equal to 10s, the two subsequences are connected into one subsequence by using quadratic polynomial fitting to supplement missing data points, and when the time interval is greater than 10s, the two subsequences are considered to be possibly obtained under different environmental conditions and cannot be supplemented any more.
(2) For the coarse, the coarse is detected using the 3σ criterion and corrected using a quadratic polynomial fit.
(3) The sampling time of the dynamic data used in this experiment was 1s, the sampling time of the static data was 5s, and in order to maintain consistency, the dynamic data was extracted so that the sampling time became 5s.
S3, inputting the receiver clock difference, the elevation and the time precision attenuation factors into a preset receiver clock difference prediction model, predicting the receiver clock difference of the future time node, and generating the receiver clock difference corresponding to the future time node.
Preferably, the receiver comprises a static base station receiver and a dynamic motion carrier receiver, the receiver clock error prediction model comprises a static receiver clock error prediction model and a dynamic receiver clock error prediction model, the receiver clock error, the elevation and the time precision attenuation factors are input into the preset receiver clock error prediction model, the receiver clock error, the elevation and the time precision attenuation factors are input into the static receiver clock error prediction model when the receiver is a base station receiver, and the receiver clock error, the elevation and the time precision attenuation factors are input into the dynamic receiver clock error prediction model when the receiver is a motion carrier receiver.
4. After the SPP solution is preprocessed, the receiver clock error, elevation and TDOP of the base station receiver are input into a corresponding static receiver clock error prediction model, the receiver clock error, elevation and time precision attenuation factors of the carrier receiver are input into a corresponding dynamic static receiver clock error prediction model, so that the static receiver clock error prediction model and the dynamic receiver clock error prediction model predict the receiver clock error of a future time node according to the input receiver clock error, elevation and time precision attenuation factors respectively, and the receiver clock error of the future time node is generated.
Preferably, the receiver clock error prediction model comprises an LSTM model, wherein the LSTM model comprises a plurality of LSTM units, and each LSTM unit comprises:
ft＝σ(Wf[xt,ht-1]+bf);
it＝σ(Wi[xt,ht-1]+bi);
ot＝σ(Wo[xt,ht-1]+bo);
ht＝ot⊙tanh(ct);
wherein f t represents a forgetting gate indicating a proportion of memory information to be retained in memory cells at a current time, i t represents an input gate indicating a proportion of input information at a current time in memory cells at a current time, c t represents memory cells at a current time t to selectively store past information and current input information, o t represents an output gate indicating that current memory information selectively flows into current output information, h t represents an output at a current time, sigma represents a sigmoid activation function, tan h represents a hyperbolic tangent activation function, W * represents a weight matrix, b * represents a bias vector, and c represents a matrix point product.
The method comprises the steps of obtaining satellite navigation information and observation information of a past time node received by a receiver, carrying out standard single-point positioning calculation on the satellite navigation information and the observation information to obtain receiver clock differences, elevations and time precision attenuation factors corresponding to the past time node, preprocessing the receiver clock differences, elevations and time precision attenuation factors, carrying out data discontinuous processing, coarse difference detection and correction and sampling time conversion, carrying out normalization processing on each subsequence of the preprocessed receiver clock differences, elevations and time precision attenuation factors respectively, dividing the subsequence into a plurality of samples, dividing the samples into a training set, a verification set and a test set, and then training the LSTM model according to preset input time steps, output time steps and preset super parameters in the training set, verification set and test set, and obtaining the receiver clock difference prediction model.
Preferably, after the receiver clock differences, the elevation and the time precision attenuation factors are input into a preset receiver clock difference prediction model to predict the receiver clock differences of future time nodes and generate the receiver clock differences corresponding to the future time nodes, the method further comprises the steps of calculating average absolute errors and root mean square errors of the receiver clock differences, comparing the average absolute errors and the root mean square errors of the receiver clock differences with the average absolute errors and the root mean square errors of the receiver clock differences based on a preset quadratic polynomial model and a gray theoretical model respectively, and then evaluating the prediction performance of the receiver clock difference prediction model according to comparison results.
The training process of the receiver clock error prediction model is as follows:
1. Satellite navigation information and observation information received by a base station receiver (static) and a motion carrier receiver (dynamic) in a past period of time are obtained, SPP (specific point) calculation is carried out on the satellite navigation information and the observation information, and corresponding receiver clock difference, elevation and TDOP are obtained.
2. The SPP calculated data is preprocessed, namely, data discontinuous processing, coarse difference detection and correction and sampling time conversion are carried out.
3. Constructing a receiver clock error prediction model based on LSTM, wherein the principle of the LSTM is as follows:
Referring to fig. 2, a unit structure diagram of an LSTM with a gating mechanism is shown, which can solve the problem of gradient disappearance or explosion of a recurrent neural network (Recurrent Neural Network, RNN), capture long-term dependency of a time sequence, and is often used in a time sequence data processing task. The method has the characteristic of cyclic connection, so that information can be transmitted among a plurality of time steps, the output of each unit can become the input of the next time step, and the relation among elements of the sequence can be effectively learned. The LSTM is composed of a plurality of units, each unit comprises a forgetting gate, an input gate and an output gate, and can effectively control the flow of information and the retention of memory, and the structure of the LSTM unit is shown in figure 2:
ft＝σ(Wf[xt,ht-1]+bf);
it＝σ(Wi[xt,ht-1]+bi);
ot＝σ(Wo[xt,ht-1]+bo);
ht＝ot⊙tanh(ct);
wherein f t represents a forgetting gate indicating a proportion of memory information to be retained in memory cells at a current time, i t represents an input gate indicating a proportion of input information at a current time in memory cells at a current time, c t represents memory cells at a current time t to selectively store past information and current input information, o t represents an output gate indicating that current memory information selectively flows into current output information, h t represents an output at a current time, sigma represents a sigmoid activation function, tan h represents a hyperbolic tangent activation function, W * represents a weight matrix, b * represents a bias vector, and c represents a matrix point product.
4. Integrating the preprocessed data, wherein the preprocessed data set is receiver clock difference, elevation and TDOP, each sub-sequence divided in the data set is respectively normalized and divided into a plurality of samples in a sliding window mode (sliding one epoch at a time), the receiver clock difference, elevation and TDOP normalized by the first L in epochs in each sample are taken as model input, the receiver clock difference after inverse normalization of the last L out epochs is taken as model label (label), namely the characteristic dimension of the model input is 3, the time step is L in, the output characteristic dimension is 1, the time step is L out, the plurality of samples are divided into training, verifying and testing subsets in a 6:2:2 mode, and the subsets are combined to form a training set, a verifying set and a testing set. The receiver clock error prediction model is shown in fig. 3;
it should be noted that both static and dynamic situations are separate training models, which should be split into two data sets, and models are also split into static and dynamic models.
5. The invention sets a plurality of input time steps and output time steps, namely L in＝36(3min),48(4min),60(5min),Lout =24 (2 min), 30 (2.5 min) and 36 (3 min) respectively. For each case, the structure and super parameters of the static model and the dynamic model are kept consistent, training and testing are respectively carried out, and specific super parameter settings are shown in the following table 1.
TABLE 1LSTM super-parameter set table
6. And calculating the prediction precision (average absolute error MAE and root mean square error RMSE) of the constructed receiver clock error prediction model, comparing the result with the prediction precision of a quadratic polynomial model and the prediction precision of a gray theoretical model respectively, and evaluating the prediction performance of the receiver clock error prediction model. The average absolute error MAE and the root mean square error RMSE are calculated as follows:
7. and using receiver clock errors predicted by the LSTM model, the quadratic polynomial model and the gray theoretical model for positioning experiments, calculating the root mean square error of the position coordinates in the North, east, up direction, and evaluating the performance of the receiver clock error predicted value for assisting GNSS positioning. Referring to FIG. 4, a flow chart of LSTM receiver clock bias prediction and assisted GNSS positioning is shown.
Therefore, the invention provides a receiver clock difference prediction method, which is used for normalizing the receiver clock difference, the elevation and the TDOP in the current period of time and taking the normalized receiver clock difference, the elevation and the TDOP as model inputs according to a pre-constructed receiver clock difference prediction model, and predicting a receiver clock difference sequence in the future period of time as output. The model can automatically learn the correlation between the receiver clock error and the elevation, acquire the uncertainty of the receiver clock error from the TDOP, model the complex nonlinear relation and improve the prediction precision. In addition, the model considers two situations of static state and dynamic state, trains and tests the subsequences in different time periods, ensures the usability of the model under different dynamics and different environmental conditions, and improves the robustness and generalization capability of the prediction model. In addition, the model can reduce interference of noise, elevation error and the like on the receiver clock error, so that the predicted receiver clock error can assist the GNSS to realize positioning in a complex urban environment, and the positioning accuracy is improved.
Example two
Referring to fig. 5, a schematic structural diagram of a receiver clock error prediction apparatus according to an embodiment of the present invention includes a satellite navigation information and observation information acquisition module, a standard single-point positioning calculation module, and a receiver clock error prediction module;
the satellite navigation information and observation information acquisition module is used for acquiring satellite navigation information and observation information of the current time node received by the receiver;
The standard single-point positioning resolving module is used for carrying out standard single-point positioning resolving on the satellite navigation information and the observation information, and calculating to obtain receiver clock difference, elevation and time precision attenuation factors corresponding to the current time node;
The receiver clock difference prediction module is used for inputting the receiver clock difference, the elevation and the time precision attenuation factors into a preset receiver clock difference prediction model, predicting the receiver clock difference of the future time node and generating the receiver clock difference corresponding to the future time node.
It should be noted that the above-described apparatus embodiments are merely illustrative, and the units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the invention, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
It will be clearly understood by those skilled in the art that, for convenience and brevity, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Example III
Accordingly, an embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes the computer program to implement the receiver clock error prediction method described in the embodiment of the present invention.
The electronic equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The device may include, but is not limited to, a processor, a memory.
The Processor may be a central processing unit (Central Processing Unit, CPU), other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is a control center of the device, connecting the various parts of the overall device using various interfaces and lines.
Example IV
Accordingly, an embodiment of the present invention provides a storage medium, where the storage medium includes a stored computer program, where when the computer program runs, a device where the storage medium is controlled to execute the receiver clock error prediction method described in the embodiment of the present invention.
The memory may be used to store the computer program, and the processor may implement various functions of the device by running or executing the computer program stored in the memory, and invoking data stored in the memory. The memory may mainly include a storage program area which may store an operating system, an application program required for at least one function, etc., and a storage data area which may store data created according to the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The storage medium is a computer readable storage medium, and the computer program is stored in the computer readable storage medium, and when executed by a processor, the computer program can implement the steps of the above-mentioned method embodiments. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.

Claims (8)

1.一种接收机钟差预测方法，其特征在于，包括：1. A receiver clock bias prediction method, characterized in that it includes: 获取接收机接收到的当前时间节点的卫星导航信息和观测信息；Acquire satellite navigation and observation information received by the receiver at the current time point; 对所述卫星导航信息和观测信息进行标准单点定位解算，计算得到当前时间节点对应的接收机钟差、高程和时间精度衰减因子；The satellite navigation information and observation information are subjected to standard single-point positioning calculation to obtain the receiver clock error, elevation and time accuracy attenuation factor corresponding to the current time node; 将所述接收机钟差、高程和时间精度衰减因子输入预设的接收机钟差预测模型，对未来时间节点的接收机钟差进行预测，生成未来时间节点对应的接收机钟差；The receiver clock bias, elevation, and time accuracy attenuation factor are input into a preset receiver clock bias prediction model to predict the receiver clock bias at future time points and generate the receiver clock bias corresponding to the future time points. 其中，所述接收机钟差预测模型包括：LSTM模型；The receiver clock bias prediction model includes: an LSTM model; 所述LSTM模型包括若干个LSTM单元，每一LSTM单元包括：The LSTM model comprises several LSTM units, each LSTM unit including: ； ; ； ; ； ; ； ; ； ; ； ; 其中，表示遗忘门，表示过去记忆信息需要保留到当前时刻的记忆细胞中所占的比例；表示输入门，表示当前时刻的输入信息在当前时刻的记忆细胞中所占的比例；表示当前时刻的记忆细胞，有选择地记忆过去的信息和当前的输入信息；表示输出门，表示当前的记忆信息有选择地流入到当前的输出信息中；表示当前时刻的输出；表示sigmoid激活函数，表示双曲正切激活函数；表示权重矩阵；表示偏置矢量；表示矩阵点乘；in, The forgetting gate indicates the proportion of past memories that need to be retained in the current memory cells; The input gate represents the proportion of the input information at the current moment in the memory cells at the current moment; Indicates the current time The memory cells selectively remember past information and current input information; This indicates an output gate, meaning that currently stored information selectively flows into the current output information; This indicates the output at the current moment; This represents the sigmoid activation function. Represents the hyperbolic tangent activation function; Represents the weight matrix; Indicates the bias vector; Represents matrix dot product; 所述接收机钟差预测模型的生成，包括：The generation of the receiver clock bias prediction model includes: 获取接收机接收到的过去时间节点的卫星导航信息和观测信息；Acquire satellite navigation and observation information received by the receiver at past time points; 对所述卫星导航信息和观测信息进行标准单点定位解算，得到过去时间节点对应的接收机钟差、高程和时间精度衰减因子；The satellite navigation information and observation information are used to perform standard single-point positioning calculations to obtain the receiver clock error, elevation and time accuracy attenuation factor corresponding to past time nodes; 对所述接收机钟差、高程和时间精度衰减因子进行预处理；其中，所述预处理包括：数据不连续处理、粗差检测和修正，以及采样时间转换；The receiver clock error, elevation, and time accuracy attenuation factor are preprocessed; wherein the preprocessing includes: data discontinuity processing, gross error detection and correction, and sampling time conversion; 将预处理后的接收机钟差、高程和时间精度衰减因子中的每一子序列分别进行归一化处理，并划分为若干个样本；Each subsequence in the preprocessed receiver clock error, elevation, and time accuracy attenuation factor is normalized and divided into several samples. 将所述样本划分为训练集、验证集和测试集，继而根据所述训练集、验证集、测试集、每个样本中预设的输入时间步、输出时间步以及预设的超参数，对所述LSTM模型进行训练，得到接收机钟差预测模型。The samples are divided into training set, validation set and test set. Then, the LSTM model is trained according to the training set, validation set, test set, preset input time step, output time step and preset hyperparameters in each sample to obtain the receiver clock error prediction model. 2.如权利要求1所述的接收机钟差预测方法，其特征在于，所述卫星导航信息包括：卫星的轨道位置和钟差；2. The receiver clock bias prediction method as described in claim 1, wherein the satellite navigation information includes: the satellite's orbital position and clock bias; 对所述卫星导航信息和观测信息进行标准单点定位解算，计算得到当前时间节点对应的接收机钟差、高程和时间精度衰减因子，包括：The satellite navigation information and observation information are subjected to standard single-point positioning calculation to obtain the receiver clock error, elevation, and time accuracy attenuation factor corresponding to the current time node, including: 根据所述观测信息计算得到卫星观测伪距；The satellite observation pseudorange is calculated based on the observation information. 根据所述卫星观测伪距、至少四颗卫星的轨道位置和钟差、预设的对流层误差模型以及预设的电离层误差模型，计算得到当前时间节点对应的接收机钟差和接收机的近似位置坐标，进而根据所述接收机的近似位置坐标计算得到对应的接收机高程和当前时间节点对应的时间精度衰减因子。Based on the satellite observation pseudorange, the orbital positions and clock biases of at least four satellites, the preset tropospheric error model, and the preset ionospheric error model, the receiver clock bias and the approximate position coordinates of the receiver corresponding to the current time node are calculated. Then, based on the approximate position coordinates of the receiver, the corresponding receiver elevation and the time accuracy attenuation factor corresponding to the current time node are calculated. 3.如权利要求1所述的接收机钟差预测方法，其特征在于，在将所述接收机钟差、高程和时间精度衰减因子输入预设的接收机钟差预测模型之前，还包括：3. The receiver clock bias prediction method as described in claim 1, characterized in that, before inputting the receiver clock bias, elevation, and time accuracy attenuation factor into a preset receiver clock bias prediction model, it further includes: 对所述接收机钟差、高程和时间精度衰减因子进行预处理；其中，所述预处理包括：数据不连续处理、粗差检测和修正，以及采样时间转换。The receiver clock error, elevation, and time accuracy attenuation factor are preprocessed; wherein the preprocessing includes: data discontinuity processing, gross error detection and correction, and sampling time conversion. 4.如权利要求1所述的接收机钟差预测方法，其特征在于，所述接收机包括：静态的基站接收机和动态的运动载体接收机；4. The receiver clock bias prediction method as described in claim 1, wherein the receiver comprises: a static base station receiver and a dynamic moving carrier receiver; 所述接收机钟差预测模型包括：静态接收机钟差预测模型和动态接收机钟差预测模型；The receiver clock bias prediction model includes: a static receiver clock bias prediction model and a dynamic receiver clock bias prediction model; 将所述接收机钟差、高程和时间精度衰减因子输入预设的接收机钟差预测模型，包括：The receiver clock bias, elevation, and time accuracy attenuation factor are input into a preset receiver clock bias prediction model, including: 当所述接收机为基站接收机时，将所述接收机钟差、高程和时间精度衰减因子输入所述静态接收机钟差预测模型；当所述接收机为运动载体接收机时，将所述接收机钟差、高程和时间精度衰减因子输入所述动态接收机钟差预测模型。When the receiver is a base station receiver, the receiver clock bias, elevation, and time accuracy attenuation factor are input into the static receiver clock bias prediction model; when the receiver is a moving vehicle receiver, the receiver clock bias, elevation, and time accuracy attenuation factor are input into the dynamic receiver clock bias prediction model. 5.如权利要求4所述的接收机钟差预测方法，其特征在于，在将所述接收机钟差、高程和时间精度衰减因子输入预设的接收机钟差预测模型，对未来时间节点的接收机钟差进行预测，生成未来时间节点对应的接收机钟差之后，还包括：5. The receiver clock bias prediction method as described in claim 4, characterized in that, after inputting the receiver clock bias, elevation, and time accuracy attenuation factor into a preset receiver clock bias prediction model to predict the receiver clock bias at future time nodes and generate the receiver clock bias corresponding to the future time nodes, it further includes: 计算所述接收机钟差的平均绝对误差和均方根误差；Calculate the mean absolute error and root mean square error of the receiver clock error; 将所述接收机钟差的平均绝对误差和均方根误差，分别与基于预设的二次多项式模型以及灰色理论模型的接收机钟差的平均绝对误差和均方根误差进行对比，继而根据比对结果对所述接收机钟差预测模型的预测性能进行评估。The mean absolute error and root mean square error of the receiver clock bias are compared with the mean absolute error and root mean square error of the receiver clock bias based on a preset quadratic polynomial model and a grey theory model, respectively. Then, the prediction performance of the receiver clock bias prediction model is evaluated based on the comparison results. 6.一种接收机钟差预测装置，其特征在于，适用于如权利要求1-5任意一项所述的接收机钟差预测方法，包括：卫星导航信息和观测信息获取模块、标准单点定位解算模块以及接收机钟差预测模块；6. A receiver clock bias prediction device, characterized in that it is applicable to the receiver clock bias prediction method as described in any one of claims 1-5, comprising: a satellite navigation information and observation information acquisition module, a standard single-point positioning calculation module, and a receiver clock bias prediction module; 所述卫星导航信息和观测信息获取模块，用于获取接收机接收到的当前时间节点的卫星导航信息和观测信息；The satellite navigation information and observation information acquisition module is used to acquire the satellite navigation information and observation information received by the receiver at the current time node; 所述标准单点定位解算模块，用于对所述卫星导航信息和观测信息进行标准单点定位解算，计算得到当前时间节点对应的接收机钟差、高程和时间精度衰减因子；The standard point positioning solution module is used to perform standard point positioning solution on the satellite navigation information and observation information, and calculate the receiver clock error, elevation and time accuracy attenuation factor corresponding to the current time node. 所述接收机钟差预测模块，用于将所述接收机钟差、高程和时间精度衰减因子输入预设的接收机钟差预测模型，对未来时间节点的接收机钟差进行预测，生成未来时间节点对应的接收机钟差。The receiver clock bias prediction module is used to input the receiver clock bias, elevation and time accuracy attenuation factor into a preset receiver clock bias prediction model, predict the receiver clock bias at future time nodes, and generate the receiver clock bias corresponding to the future time nodes. 7.一种电子设备，其特征在于，包括处理器、存储器以及存储在所述存储器中且被配置为由所述处理器执行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1至5中任意一项所述的接收机钟差预测方法。7. An electronic device, characterized in that it comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the receiver clock bias prediction method as described in any one of claims 1 to 5. 8.一种存储介质，其特征在于，所述存储介质包括存储的计算机程序，其中，在所述计算机程序运行时控制所述存储介质所在设备执行如权利要求1至5中任意一项所述的接收机钟差预测方法。8. A storage medium, characterized in that the storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the storage medium is located to perform the receiver clock bias prediction method as described in any one of claims 1 to 5.
CN202410842927.3A 2024-06-27 2024-06-27 A receiver clock bias prediction method, apparatus, device, and storage medium Active CN118818540B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410842927.3A CN118818540B (en) 2024-06-27 2024-06-27 A receiver clock bias prediction method, apparatus, device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410842927.3A CN118818540B (en) 2024-06-27 2024-06-27 A receiver clock bias prediction method, apparatus, device, and storage medium

Publications (2)

Publication Number Publication Date
CN118818540A CN118818540A (en) 2024-10-22
CN118818540B true CN118818540B (en) 2025-11-04

Family

ID=93073583

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410842927.3A Active CN118818540B (en) 2024-06-27 2024-06-27 A receiver clock bias prediction method, apparatus, device, and storage medium

Country Status (1)

Country Link
CN (1) CN118818540B (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108415050B (en) * 2018-06-04 2020-05-26 北京未来导航科技有限公司 PPP-RTK positioning method based on low-orbit constellation navigation enhancement system
CN114791613B (en) * 2021-01-25 2025-08-08 华为技术有限公司 Ephemeris prediction method and device
CN116224399A (en) * 2023-02-17 2023-06-06 武汉大学 Beidou navigation satellite orbit prediction method based on long-short-term memory neural network
CN117406253A (en) * 2023-10-17 2024-01-16 辽宁工程技术大学 Multi-GNSS satellite clock error modeling and forecasting method based on LSTM and quadratic polynomial combined model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"LSTM-based receiver clock modeling and prediction for GNSS urban positioning";Zhiqiang Dai etc.;《GPS Solutions》;20250725;第29卷;第176页 *

Also Published As

Publication number Publication date
CN118818540A (en) 2024-10-22

Similar Documents

Publication Publication Date Title
US11237276B2 (en) System and method for gaussian process enhanced GNSS corrections generation
US20240142637A1 (en) System and method for gaussian process enhanced gnss corrections generation
US12130366B2 (en) Error model calibration method and apparatus, electronic device, error model-based positioning method and apparatus, terminal, computer-readable storage medium, and program product
US11474263B2 (en) System and method for GNSS ambiguity resolution
Chen et al. Calculation of weighted geometric dilution of precision
EP4103972B1 (en) System and method for integer-less gnss positioning
CN110320536B (en) Satellite positioning parameter calibration method, device, terminal equipment and storage medium
CN119024393B (en) A GNSS model adaptive optimization method for enhanced navigation scene perception in high-precision positioning
Xu et al. A framework for graphical gnss multipath and nlos mitigation
CN116106953B (en) A Time Difference Carrier Phase Enhancement Method for Semi-parametric Estimation of GNSS Relative Positioning
CN118339480A (en) A data preprocessing method, a data preprocessing device and a chip
Zhang et al. MPARELAM: A robust approach for ambiguity resolution in complex RTK positioning scenarios
CN118818540B (en) A receiver clock bias prediction method, apparatus, device, and storage medium
CN115453583A (en) A positioning method, terminal and storage medium
Yoo et al. A coarse-time positioning method for improved availability
CN111487659B (en) State recognition method and device, computer equipment and storage medium
CN116381737B (en) A GNSS positioning solution method and device based on factor graph optimization
Bogatin et al. Evaluation of linear Kalman filter processing geodetic kinematic measurements
McClusky et al. Precise Point Positioning with Ginan: Geoscience Australia’s Open-Source GNSS Analysis Centre Software
Zhang et al. A novel method for improving LEO kinematic Real-Time precise orbit determination with neural networks
Bong et al. GNSS performance enhancement using measurement estimation in harsh environment
Zhilinskiy GLONASS Satellite Pseudorange Errors Mitigation Using Gradient Boosting Machine
CN119986733B (en) Three-dimensional positioning method and device for double-star stationary radiation source based on passive synthetic aperture
CN111538045A (en) On-orbit precision pre-evaluation method for satellite-borne navigation receiver
CN111352135A (en) Pseudo-range gross error detection method, device and readable storage medium

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