High-precision time-frequency synchronization method based on time reference station

Abstract

The invention relates to the technical field of time-frequency synchronization based on a time base station, in particular to a high-precision time-frequency synchronization method based on the time base station, which comprises the following steps of: screening out standard time-frequency synchronization data by combining historical time-frequency surveying and mapping data with a surveying and mapping time-frequency influence model and a clustering algorithm; analyzing abnormal features in the standard time-frequency synchronization data and the first time-frequency synchronization features as second time-frequency synchronization features according to a surveying and mapping time-frequency influence model, further screening out abnormal time-frequency synchronization interference targets causing a multipath effect based on the second time-frequency synchronization features, and calculating out third time-frequency synchronization features for storage; through the method, abnormal data can be screened out and other interference factors can be reduced on the basis of historical data of the same region under the condition of ensuring consistent data environment interference; and meanwhile, the environmental characteristics of the interference target are determined according to the abnormal data, so that the same environmental characteristics can be avoided subsequently, and the influence of the multipath effect on surveying and mapping is further reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of time-frequency synchronization based on a time reference station, and in particular to a high-precision time-frequency synchronization method based on a time reference station. Background Art

[0002] In the process of surveying and mapping, high-precision, high-quality real-time terrain data has always been the key to surveying and mapping work; due to the large scope of terrain surveying and mapping, in order to achieve high-precision and high-accuracy terrain data, it is necessary to enable the installed surveying and mapping equipment to achieve accurate time synchronization of multiple devices. In this process, the Beidou CORS station (Continuously Operating Reference Station) plays an auxiliary role in time synchronization, enabling surveying and mapping equipment to achieve high-precision time synchronization based on the Beidou CORS station, so as to achieve temporal consistency of surveying and mapping data.

[0003] However, there are still some problems in the synchronization process of Beidou CORS stations. During the surveying process, there will inevitably be some buildings or trees, and these plants and artificial facilities will reflect the signal when the surveying equipment receives the time synchronization signal, causing a multipath effect. As a result, some surveying equipment will be interfered with, which will affect the final surveying results and reduce the quality of surveying data.

[0004] In the prior art, some algorithms are used to reduce the multipath effect error, but the impact of the multipath effect cannot be completely eliminated; in order to further reduce the impact of the multipath effect on surveying and mapping, a high-precision time and frequency synchronization method based on a time reference station is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a high-precision time-frequency synchronization method based on a time reference station, which selects standard time-frequency synchronization data through historical time-frequency surveying and mapping data combined with a surveying and mapping time-frequency influence model and a clustering algorithm as a reference standard for subsequent abnormality analysis; then, the abnormal features in the standard time-frequency synchronization data and the first time-frequency synchronization features are analyzed according to the surveying and mapping time-frequency influence model as the second time-frequency synchronization features, and based on the second time-frequency synchronization features, the abnormal time-frequency synchronization interference targets that cause multipath effects are further screened out and the third time-frequency synchronization features are calculated and stored; this method can screen out abnormal data and reduce other interference factors based on historical data in the same area while ensuring that the data environment interference is consistent; at the same time, the environmental characteristics of the interference targets are determined based on the abnormal data, so that they can be avoided when the same environmental characteristics are encountered later, so as to further reduce the impact of the multipath effect on surveying and mapping.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A high-precision time and frequency synchronization method based on a time reference station, comprising:

[0008] Acquire a target surveying and mapping area, and acquire historical time-frequency surveying and mapping data according to the target surveying and mapping area;

[0009] Establish a surveying and mapping time-frequency impact model, preliminarily analyze the time-frequency synchronization interference targets based on historical time-frequency surveying and mapping data, and set standard time-frequency synchronization data based on the time-frequency synchronization interference targets combined with clustering algorithms;

[0010] Determine the multipath interference target range according to the DBSCAN clustering algorithm, and determine the standard time-frequency synchronization data through the historical time-frequency mapping data of the minimum range of the multipath interference target range;

[0011] According to the remaining historical time-frequency surveying and mapping data, the first time-frequency synchronization data is obtained; the time-frequency synchronization interference targets include artificial time-frequency synchronization interference targets and natural time-frequency synchronization interference targets; the data quantity, data type and data type quantity of the standard time-frequency synchronization data and the first time-frequency synchronization data are consistent, and the data types of the standard time-frequency synchronization data and the first time-frequency synchronization data include time synchronization signals, GNSS observation data and differential data;

[0012] Further, the surveying and mapping time-frequency impact model includes a multi-path surveying and mapping time-frequency interference analysis sub-model;

[0013] The time-frequency synchronization interference target is obtained according to the multipath mapping time-frequency interference analysis sub-model;

[0014] The multipath mapping time-frequency interference analysis submodel includes a multipath time-frequency interference processing unit, a multipath time-frequency interference feature analysis unit, a multipath time-frequency interference feature synthesis unit and a multipath time-frequency interference output unit;

[0015] The multipath time-frequency interference processing unit performs image preprocessing on the historical time-frequency surveying and mapping data;

[0016] The multipath time-frequency interference feature analysis unit uses a multi-model to extract interference features from the historical time-frequency mapping data after the image preprocessing, and marks the multipath interference target; the multi-model includes a Yolov5 model, a Faster RCNN model and an SSD model;

[0017] The multipath time-frequency interference feature synthesis unit performs comprehensive calculation based on the marked multipath interference target to further screen the multipath interference target; specifically:

[0018] ;

[0019] in, Score the multipath interference target, is the detection probability of multipath interference target, yolov is the Yolov5 model, FRCNN is the Faster RCNN model, SSD is the SSD model, , and is the score weight, ;

[0020] The multipath time-frequency interference output unit outputs and stores the multipath interference target;

[0021] Based on the surveying and mapping time-frequency influence model, the standard time-frequency synchronization data is analyzed to obtain a reference time-frequency synchronization feature, the first time-frequency synchronization data is analyzed to obtain the first time-frequency synchronization feature, the surveying and mapping time-frequency influence model compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, obtains an abnormal time-frequency synchronization feature of the first time-frequency synchronization feature, and generates a second time-frequency synchronization feature;

[0022] Furthermore, the surveying and mapping time-frequency impact model also includes an abnormal time-frequency analysis sub-model;

[0023] The second time-frequency synchronization feature is obtained according to the abnormal time-frequency analysis sub-model; the abnormal time-frequency analysis sub-model includes a time-frequency data segmentation processing unit, a time-frequency data abnormal feature analysis unit and a time-frequency data abnormal mapping data acquisition unit;

[0024] The time-frequency data segmentation processing unit performs data preprocessing on the standard time-frequency synchronization data and the first time-frequency synchronization data, and after preprocessing, performs time window segmentation of the same length on the standard time-frequency synchronization data and the first time-frequency synchronization data; and obtains pre-input abnormal time-frequency analysis data;

[0025] The time-frequency data abnormal feature analysis unit learns the reference time-frequency synchronization feature through the standard time-frequency synchronization data and stores it; learns the first time-frequency synchronization feature through the first time-frequency synchronization data, compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, and obtains the second time-frequency synchronization feature; the time-frequency data abnormal feature includes 1 layer of Attention mechanism, 8 layers of LSTM layers, 2 layers of residual convolution layers and 2 layers of time convolution layers to extract the reference time-frequency synchronization feature and the first time-frequency synchronization feature; compares the reference time-frequency synchronization feature and the first time-frequency synchronization feature based on the cosine similarity algorithm;

[0026] The time-frequency data anomaly mapping data acquisition unit outputs the historical time-frequency mapping data according to the second time-frequency synchronization feature;

[0027] Acquire abnormal historical time-frequency mapping data corresponding to the historical time-frequency mapping data according to the second time-frequency synchronization feature;

[0028] Inputting the abnormal historical time-frequency surveying and mapping data into the surveying and mapping time-frequency influence model to obtain the abnormal time-frequency synchronization interference target of the abnormal historical time-frequency surveying and mapping data;

[0029] The abnormal time-frequency synchronization interference target is combined with a clustering algorithm to determine the third time-frequency synchronization feature of the same abnormal time-frequency synchronization interference target to calculate the multipath effect and store it; specifically:

[0030] ;

[0031] in, is the third time-frequency synchronization feature of the i-th abnormal time-frequency interference target, , n is the total number of types of abnormal time-frequency interference targets; min is the minimum value; is the distance between the i-th type j-th abnormal time-frequency interference target and the surveying and mapping instrument, , is the total number of synchronous interference coverage of the i-th abnormal time-frequency interference target, It is the synchronous interference coverage range of the i-th and j-th abnormal time-frequency interference target.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The present invention determines the surveying area, determines the interference targets that are prone to multipath effects in the historical time-frequency surveying data based on multiple models, and further confirms the multipath interference targets through multiple models; this method can more accurately determine the position information of the multipath interference targets in the current surveying area based on the existing historical time-frequency surveying data, and confirm based on multiple models to reduce the problem of single model recognition error; it is helpful to subsequently screen out the historical time-frequency surveying data with the least multipath interference targets in the surveying area, and provide a data foundation and data basis for the subsequent abnormal time-frequency data analysis, so as to further reduce the interference of the multipath effect on the surveying data.

[0034] 2. The present invention analyzes the reference time-frequency synchronization features of the current surveying and mapping area based on the surveying and mapping time-frequency influence model by screening out the reference time-frequency synchronization features and the first time-frequency synchronization features, and determines the abnormal features in the first time-frequency synchronization features; this method can screen out the data that is affected by multipath interference in the current data; at the same time, based on the data in the same area, the environmental interference factors of the data can be unified to avoid the influence of other interference factors on the analysis of abnormal data, improve the accuracy of abnormal time-frequency data analysis, and provide an abnormal time-frequency synchronization interference target data basis for the subsequent screening of abnormal time-frequency data, so as to further reduce the interference of multipath effects on surveying and mapping data.

[0035] 3. The present invention identifies abnormal time-frequency synchronization interference targets based on the surveying and mapping time-frequency influence model, combines the clustering algorithm to determine the interference target coverage under the same abnormal time-frequency synchronization interference target, and simultaneously determines the third time-frequency synchronization feature in combination with the distance between the surveying and mapping instrument and the synchronization interference target. This method can be used to analyze the environmental characteristics of interference caused by each interference target based on the data of the surveying and mapping area affected by multipath interference, identify these characteristics and store them, so that when encountering the same environmental characteristics during subsequent surveying and mapping, the surveying and mapping instrument can be avoided to the greatest extent for detection under the environmental characteristics, thereby reducing the occurrence of multipath interference and further reducing the interference of the multipath effect on the surveying and mapping data. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of the method of the present invention;

[0037] Figure 2 It is a structural diagram of the surveying and mapping time-frequency influence model of the present invention;

[0038] Figure 3 A network structure diagram for feature extraction of a time-frequency data segmentation processing unit of the present invention;

[0039] Figure 4 This is a network structure diagram of the residual convolution of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of 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.

[0041] In the actual surveying and mapping process, in order to ensure the time synchronization of real-time surveying and mapping data, it is necessary to synchronize the time of each surveying and mapping instrument. The current high-precision synchronization method is to use the Beidou CORS station based on the Beidou satellite for time synchronization assistance. However, in this process, due to the buildings or trees around the surveying and mapping instrument, multipath effects are likely to occur, reducing the quality of surveying and mapping data. Although there are some algorithms in the prior art that can reduce the multipath effect error, the effects of these algorithms are still limited. Therefore, the present invention provides a high-precision time-frequency synchronization method based on a time reference station, referring to Figure 1 As shown, the technical solution is as follows:

[0042] Acquire a target surveying and mapping area, and acquire historical time-frequency surveying and mapping data according to the target surveying and mapping area;

[0043] Establish a surveying and mapping time-frequency impact model, preliminarily analyze the time-frequency synchronization interference target based on the historical time-frequency surveying and mapping data, set the standard time-frequency synchronization data according to the time-frequency synchronization interference target combined with the clustering algorithm; obtain the first time-frequency synchronization data according to the remaining historical time-frequency surveying and mapping data;

[0044] Based on the surveying and mapping time-frequency influence model, the standard time-frequency synchronization data is analyzed to obtain a reference time-frequency synchronization feature, the first time-frequency synchronization data is analyzed to obtain the first time-frequency synchronization feature, the surveying and mapping time-frequency influence model compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, obtains an abnormal time-frequency synchronization feature of the first time-frequency synchronization feature, and generates a second time-frequency synchronization feature;

[0045] Acquire abnormal historical time-frequency mapping data corresponding to the historical time-frequency mapping data according to the second time-frequency synchronization feature;

[0046] Inputting the abnormal historical time-frequency surveying and mapping data into the surveying and mapping time-frequency influence model to obtain the abnormal time-frequency synchronization interference target of the abnormal historical time-frequency surveying and mapping data;

[0047] The abnormal time-frequency synchronization interference target is combined with a clustering algorithm to determine a third time-frequency synchronization feature for calculating the multipath effect of the same abnormal time-frequency synchronization interference target and store it.

[0048] In order to avoid the interference of multipath effect on surveying and mapping data to the greatest extent, based on the historical time-frequency surveying and mapping data of the same surveying and mapping area, the targets causing multipath interference are identified through the surveying and mapping time-frequency impact model, and the standard time-frequency synchronization data as the benchmark data are screened out based on these targets. Based on this method, the environmental data interference options can be minimized, and the interference data characteristics of all data can be unified, which is also convenient for subsequent processing; at the same time, based on the existing multipath interference algorithm results, the standard time-frequency data with the least impact can be screened out, providing data support for subsequent abnormal analysis and processing, so as to further reduce the interference of multipath effect on surveying and mapping data.

[0049] Based on the reference time-frequency synchronization features and the first time-frequency synchronization features of the screened standard time-frequency synchronization data, the abnormal data are analyzed according to the surveying and mapping time-frequency impact model, and the abnormal time-frequency synchronization interference targets that cause these abnormal data are screened out through the analyzed abnormal data. The environmental characteristics are analyzed and stored in combination with the clustering algorithm and the minimum distance between the surveying and mapping instrument and the abnormal time-frequency synchronization interference target; the environmental characteristics of the same abnormal time-frequency synchronization interference target are screened out in the historical data through this method, and the environmental characteristics are stored in a digitized manner at the same time, so as to facilitate the subsequent encounter of the same environmental characteristics in the surveying and mapping process, and to avoid the surveying and mapping instruments from being placed under the same environmental characteristics to the greatest extent, so as to further reduce the impact of the multipath effect on the surveying and mapping work.

[0050] Embodiment 1

[0051] For the purpose of specific explanation, the following contents are combined to explain the multipath effect interference target identification:

[0052] Acquire a target surveying and mapping area, and acquire historical time-frequency surveying and mapping data according to the target surveying and mapping area; the historical time-frequency surveying and mapping data includes surveying and mapping data and time synchronization data;

[0053] Establish a surveying and mapping time-frequency impact model, preliminarily analyze the time-frequency synchronization interference targets based on historical time-frequency surveying and mapping data, and set standard time-frequency synchronization data based on the time-frequency synchronization interference targets combined with clustering algorithms;

[0054] Determine the multipath interference target range based on the DBSCAN clustering algorithm, and determine the standard time-frequency synchronization data through the historical time-frequency surveying and mapping data of the minimum range of the multipath interference target range; cluster based on the density identification results of the interference targets of the multipath effect, and determine the surveying and mapping instrument data with the least multipath effect among the surveying and mapping instruments through the minimum range as the standard data for analysis. At the same time, this method takes into account and combines the existing multipath effect elimination algorithm to improve the surveying and mapping data results screened out after clustering, so as to minimize the impact of the multipath effect on them, so as to improve the data quality as the reference data, and provide an accurate regional reference data basis for further reducing the interference of the multipath effect in the future;

[0055] According to the remaining historical time-frequency surveying and mapping data, first time-frequency synchronization data is obtained; the time synchronization data includes standard time-frequency synchronization data and first time-frequency synchronization data;

[0056] The time-frequency synchronization interference targets include artificial time-frequency synchronization interference targets (for example, but not limited to buildings, factories, etc.) and natural time-frequency synchronization interference targets (for example, but not limited to trees, etc.); the data quantity, data type and data type quantity of the standard time-frequency synchronization data and the first time-frequency synchronization data are consistent, and the data types of the standard time-frequency synchronization data and the first time-frequency synchronization data include time synchronization signals, GNSS observation data and differential data; in order to ensure the comprehensiveness of data analysis, combined with the multipath effect interference caused by vegetation and artificial buildings in real scenes, all possible interference targets are considered for marking and identification. At the same time, the standard time-frequency synchronization data is determined according to the target surveying and mapping area, which also takes into account the different interferences of noise and multipath effects generated in different areas, and can perform unified data processing, reduce workload, and conduct personalized regional analysis of multipath effects in the current area, so as to provide more accurate data for subsequent analysis, so as to further reduce the impact of multipath effects on surveying and mapping data;

[0057] Furthermore, the surveying and mapping time-frequency impact model includes a multi-path surveying and mapping time-frequency interference analysis sub-model; the time-frequency synchronization interference target is acquired based on the multi-path surveying and mapping time-frequency interference analysis sub-model;

[0058] Reference Figure 2 As shown in the multipath mapping time-frequency interference analysis submodel, the multipath mapping time-frequency interference analysis submodel includes a multipath time-frequency interference processing unit, a multipath time-frequency interference feature analysis unit, a multipath time-frequency interference feature synthesis unit and a multipath time-frequency interference output unit;

[0059] The multipath time-frequency interference processing unit performs image preprocessing on the historical time-frequency mapping data; the image preprocessing process includes histogram image addition, Gaussian filtering, Sobel operator edge sharpening and image graying;

[0060] The multipath time-frequency interference feature analysis unit uses a multi-model to extract interference features from the historical time-frequency mapping data after the image preprocessing, and marks the multipath interference target; the multi-model includes a Yolov5 model, a Faster RCNN model and an SSD model;

[0061] The target detection algorithm can quickly identify interference targets based on existing surveying and mapping data, and also facilitate the data labeling processing for early data training. At the same time, the output results based on target detection can also further quantify the accuracy of data detection to ensure data recognition accuracy and subsequent analysis work, and provide more accurate image data to further reduce the impact of multipath effects on surveying and mapping data;

[0062] In this embodiment, the experimental results of the process of identifying multipath effect interference targets are shown. In the training stage, experts label the multipath interference targets currently known in the surveying and mapping data to train the model. After training, we selected 5 groups of data that did not participate in the test for simulation testing based on the suggestions of relevant technicians and experts. The 5 groups of data are different data in the same area. We compared 3 target detection algorithms and conducted multiple tests to obtain the highest recognition rate. The results of the recognition accuracy are shown in Table 1.

[0063] From Table 1, we can see that the three models have different recognition accuracy rates in data. Combined with the expert suggestions, different models have their own advantages in different scenarios. Therefore, it is decided to use three models for joint recognition of multipath interference targets through experiments. Based on the above experimental results, the recognition results of multiple models are compared and demonstrated. While ensuring the accuracy of multipath interference target recognition, the recognition results of each model can also be combined for comprehensive analysis to ensure high-precision recognition of multipath interference targets, and provide high-precision multipath interference target recognition results to further reduce the impact of multipath effects on surveying and mapping data.

[0064] Table 1 Multiple recognition accuracy of 5 groups of data with multiple models

[0065]

[0066] The multipath time-frequency interference feature synthesis unit performs comprehensive calculation based on the marked multipath interference target to further screen the multipath interference target; specifically:

[0067] ;

[0068] in, Score the multipath interference target, is the detection probability of multipath interference target, yolov is the Yolov5 model, FRCNN is the Faster RCNN model, SSD is the SSD model, , and is the score weight, ;

[0069] The multipath time-frequency interference output unit outputs and stores the multipath interference target;

[0070] Based on the target detection algorithm, it is possible to quickly learn and train known targets. At the same time, it is also possible to analyze and quantify these surveying and mapping data through existing historical surveying and mapping data to enhance the robustness of these surveying and mapping data. At the same time, it can also reduce the work of data analysis related to multipath effects, and provide a more efficient data basis for subsequent abnormal time-frequency synchronization data analysis, and provide a fast and stable data basis for further reducing the impact of multipath effects on surveying and mapping data.

[0071] Embodiment 2

[0072] The following content explains how to identify abnormal time-frequency synchronization data and abnormal multi-effect interference targets:

[0073] Based on the surveying and mapping time-frequency influence model, the standard time-frequency synchronization data is analyzed to obtain a reference time-frequency synchronization feature, the first time-frequency synchronization data is analyzed to obtain the first time-frequency synchronization feature, the surveying and mapping time-frequency influence model compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, obtains an abnormal time-frequency synchronization feature of the first time-frequency synchronization feature, and generates a second time-frequency synchronization feature;

[0074] Furthermore, the surveying and mapping time-frequency impact model also includes an abnormal time-frequency analysis sub-model; the second time-frequency synchronization feature is obtained according to the abnormal time-frequency analysis sub-model; Figure 2As shown in the abnormal time-frequency analysis sub-model, the abnormal time-frequency analysis sub-model includes a time-frequency data segmentation processing unit, a time-frequency data abnormal feature analysis unit and a time-frequency data abnormal mapping data acquisition unit;

[0075] The time-frequency data segmentation processing unit performs data preprocessing on the standard time-frequency synchronization data and the first time-frequency synchronization data, and after preprocessing, performs time window segmentation of the same length on the standard time-frequency synchronization data and the first time-frequency synchronization data; obtains pre-input abnormal time-frequency analysis data; the preprocessing method includes Fourier transform denoising and Z-score normalization;

[0076] The time-frequency data abnormal feature analysis unit learns the reference time-frequency synchronization feature through the standard time-frequency synchronization data and stores it; learns the first time-frequency synchronization feature through the first time-frequency synchronization data, compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, and obtains the second time-frequency synchronization feature; the time-frequency data abnormal feature includes 1 layer of Attention mechanism, 8 layers of LSTM layers, 2 layers of residual convolution layers and 2 layers of time convolution layers to extract the reference time-frequency synchronization feature and the first time-frequency synchronization feature; compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature based on the cosine similarity algorithm; reference Figure 3 As shown, the Attention mechanism corresponds to Figure 3 The attention mechanism of the LSTM layer corresponds to Figure 3 The long short-term memory layer in the residual convolution layer uses one-dimensional convolution, refer to Figure 4 As shown, the temporal convolution layer also uses a one-dimensional convolution layer, which is 2 layers of 1*3 temporal convolution layers;

[0077] In this embodiment, a group of untrained abnormal data is selected in combination with expert experience to compare the recognition accuracy with the existing model. The recognition accuracy results of other abnormal synchronization data are shown in Table 2:

[0078] Table 2 Comparison of the accuracy of abnormal synchronization data recognition of each model

[0079]

[0080] From Table 2, we can see that the recognition accuracy of the proposed model is higher than that of several conventional abnormal time series detection models;

[0081] Based on the Attention mechanism, the abnormal features can be marked more clearly and the abnormal data features can be increased. The LSTM layer can capture the time series features in the data to further improve the recognition accuracy. The residual convolution layer and the time convolution layer can capture the abnormal form of the time series data. The data anomaly recognition from three angles can further improve the recognition accuracy of abnormal synchronization data, so as to achieve the purpose of confirming the multipath effect interference target through abnormal synchronization data, and provide a data basis for subsequent environmental feature analysis and further avoiding multipath effect interference.

[0082] The time-frequency data anomaly mapping data acquisition unit outputs the historical time-frequency mapping data according to the second time-frequency synchronization feature; the time-frequency data anomaly mapping data acquisition unit includes a fully connected layer and a Softmax classification layer;

[0083] By comparing the time-frequency synchronization data of the standard reference data with other time-frequency synchronization data, the characteristics of each data are extracted based on the time series analysis method, and the abnormal data are marked differently based on the standard reference data and other time-frequency synchronization data. This method can minimize the remaining interference factors based on the current regional characteristics and the time characteristics of the collected data, so as to achieve the purpose of enhancing the multipath interference effect abnormal data, improve the recognition accuracy of abnormal synchronization data, provide an abnormal data basis for further avoiding multipath effect interference, and ensure the accuracy of interference target data;

[0084] According to the second time-frequency synchronization feature, corresponding to the historical time-frequency mapping data, abnormal historical time-frequency mapping data is obtained; specifically, based on expert experience and combined with the second time-frequency synchronization feature, abnormal environmental features in the historical time-frequency mapping data are determined and data segmentation is performed to obtain abnormal historical time-frequency mapping data;

[0085] Inputting the abnormal historical time-frequency surveying and mapping data into the surveying and mapping time-frequency influence model to obtain the abnormal time-frequency synchronization interference target of the abnormal historical time-frequency surveying and mapping data;

[0086] The abnormal time-frequency synchronization interference target is combined with a clustering algorithm to determine the third time-frequency synchronization feature of the same abnormal time-frequency synchronization interference target to calculate the multipath effect and store it; specifically:

[0087] ;

[0088] in, is the third time-frequency synchronization feature of the i-th abnormal time-frequency interference target, , n is the total number of types of abnormal time-frequency interference targets; min is the minimum value; is the distance between the i-th type j-th abnormal time-frequency interference target and the surveying and mapping instrument, , is the total number of synchronous interference coverage of the i-th abnormal time-frequency interference target, The synchronous interference coverage range of the i-th type and j-th abnormal time-frequency interference target;

[0089] Based on the environmental features in the surveying and mapping data confirmed by the abnormal synchronization data, the coverage of these multipath interference targets is determined in combination with the density clustering algorithm, and the data is quantified based on the distance and coverage between the surveying and mapping instrument and the multi-target interference. This method can be used to index the actual environmental interference data, so that the quantitative indicators can be calculated and compared through formulas in the subsequent surveying and mapping process to avoid being placed in the same environment and minimize the interference of the multipath effect.

[0090] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A high-precision time and frequency synchronization method based on a time reference station, characterized in that: include: Acquire a target surveying and mapping area, and acquire historical time-frequency surveying and mapping data according to the target surveying and mapping area; Establish a surveying and mapping time-frequency impact model, preliminarily analyze the time-frequency synchronization interference target based on the historical time-frequency surveying and mapping data, set the standard time-frequency synchronization data according to the time-frequency synchronization interference target combined with the clustering algorithm; obtain the first time-frequency synchronization data according to the remaining historical time-frequency surveying and mapping data; Based on the surveying and mapping time-frequency influence model, the standard time-frequency synchronization data is analyzed to obtain a reference time-frequency synchronization feature, the first time-frequency synchronization data is analyzed to obtain a first time-frequency synchronization feature, the surveying and mapping time-frequency influence model compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, obtains an abnormal time-frequency synchronization feature of the first time-frequency synchronization feature, and generates a second time-frequency synchronization feature; Acquire abnormal historical time-frequency mapping data corresponding to the historical time-frequency mapping data according to the second time-frequency synchronization feature; Inputting the abnormal historical time-frequency surveying and mapping data into the surveying and mapping time-frequency influence model to obtain the abnormal time-frequency synchronization interference target of the abnormal historical time-frequency surveying and mapping data; The abnormal time-frequency synchronization interference target is combined with a clustering algorithm to determine a third time-frequency synchronization feature for calculating the multipath effect of the same abnormal time-frequency synchronization interference target and store it.

2. A high-precision time and frequency synchronization method based on a time reference station according to claim 1, characterized in that: The time-frequency synchronization interference targets include artificial time-frequency synchronization interference targets and natural time-frequency synchronization interference targets; the data quantity, data type and data type quantity of the standard time-frequency synchronization data and the first time-frequency synchronization data are consistent, and the data types of the standard time-frequency synchronization data and the first time-frequency synchronization data include time synchronization signals, GNSS observation data and differential data.

3. The high-precision time and frequency synchronization method based on a time reference station according to claim 1, characterized in that: Establishing a surveying and mapping time-frequency impact model, preliminarily analyzing the time-frequency synchronization interference target based on the historical time-frequency surveying and mapping data; inputting the abnormal historical time-frequency surveying and mapping data into the surveying and mapping time-frequency impact model, and obtaining the abnormal time-frequency synchronization interference target of the abnormal historical time-frequency surveying and mapping data includes: The surveying and mapping time-frequency impact model includes a multi-path surveying and mapping time-frequency interference analysis sub-model; The time-frequency synchronization interference target is obtained according to the multipath mapping time-frequency interference analysis submodel; the multipath mapping time-frequency interference analysis submodel includes a multipath time-frequency interference processing unit, a multipath time-frequency interference feature analysis unit, a multipath time-frequency interference feature synthesis unit and a multipath time-frequency interference output unit; The multipath time-frequency interference processing unit performs image preprocessing on the historical time-frequency surveying and mapping data; The multipath time-frequency interference feature analysis unit uses multiple models to extract interference features from the historical time-frequency mapping data after the image preprocessing, and marks the multipath interference targets; the multipath time-frequency interference feature synthesis unit performs comprehensive calculation based on the marked multipath interference targets, and further screens the multipath interference targets; The multipath time-frequency interference output unit outputs and stores the multipath interference target.

4. The high-precision time and frequency synchronization method based on a time reference station according to claim 3, characterized in that: The multipath time-frequency interference feature analysis unit uses multiple models to extract interference features from the historical time-frequency mapping data after the image preprocessing, including: the multiple models include Yolov5 model, Faster RCNN model and SSD model.

5. The high-precision time and frequency synchronization method based on a time reference station according to claim 3, characterized in that: The multipath time-frequency interference feature synthesis unit performs comprehensive calculation based on the marked multipath interference target, and further screening the multipath interference target includes: ； in, Score the multipath interference target, is the detection probability of multipath interference target, yolov is the Yolov5 model, FRCNN is the Faster RCNN model, SSD is the SSD model, , and is the score weight, .

6. The high-precision time and frequency synchronization method based on a time reference station according to claim 1, characterized in that: Setting standard time-frequency synchronization data according to the time-frequency synchronization interference target in combination with a clustering algorithm includes: determining a multipath interference target range according to a DBSCAN clustering algorithm, and determining the standard time-frequency synchronization data through historical time-frequency mapping data of a minimum range of the multipath interference target range.

7. The high-precision time and frequency synchronization method based on a time reference station according to claim 1, characterized in that: Based on the surveying and mapping time-frequency influence model, the standard time-frequency synchronization data is analyzed to obtain a reference time-frequency synchronization feature, the first time-frequency synchronization data is analyzed to obtain the first time-frequency synchronization feature, the surveying and mapping time-frequency influence model compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, and obtains an abnormal time-frequency synchronization feature of the first time-frequency synchronization feature, and generating a second time-frequency synchronization feature includes: The surveying and mapping time-frequency impact model also includes an abnormal time-frequency analysis sub-model; The second time-frequency synchronization feature is obtained according to the abnormal time-frequency analysis sub-model; the abnormal time-frequency analysis sub-model includes a time-frequency data segmentation processing unit, a time-frequency data abnormal feature analysis unit and a time-frequency data abnormal mapping data acquisition unit; The time-frequency data segmentation processing unit performs data preprocessing on the standard time-frequency synchronization data and the first time-frequency synchronization data, and after preprocessing, performs time window segmentation of the same length on the standard time-frequency synchronization data and the first time-frequency synchronization data; and obtains pre-input abnormal time-frequency analysis data; The time-frequency data abnormal feature analysis unit learns a reference time-frequency synchronization feature through the standard time-frequency synchronization data and stores it; learns the first time-frequency synchronization feature through the first time-frequency synchronization data, compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, and obtains the second time-frequency synchronization feature; The time-frequency data anomaly mapping data acquisition unit outputs the historical time-frequency mapping data according to the second time-frequency synchronization feature.

8. A high-precision time and frequency synchronization method based on a time reference station according to claim 7, characterized in that: The time-frequency data abnormal feature analysis unit learns a reference time-frequency synchronization feature through the standard time-frequency synchronization data and stores it; learns the first time-frequency synchronization feature through the first time-frequency synchronization data, compares the reference time-frequency synchronization feature with the first time-frequency synchronization feature, and obtains the second time-frequency synchronization feature, including: the time-frequency data abnormal feature includes 1 layer of Attention mechanism, 8 layers of LSTM layers, 2 layers of residual convolution layers and 2 layers of temporal convolution layers to extract the reference time-frequency synchronization feature and the first time-frequency synchronization feature; compares the reference time-frequency synchronization feature and the first time-frequency synchronization feature based on the cosine similarity algorithm.

9. The high-precision time and frequency synchronization method based on a time reference station according to claim 1, characterized in that: Combining the abnormal time-frequency synchronization interference target with a clustering algorithm, determining the third time-frequency synchronization feature for calculating the multipath effect of the same abnormal time-frequency synchronization interference target for storage includes: obtaining the synchronization interference coverage range of the abnormal time-frequency synchronization interference target corresponding to the second time-frequency synchronization feature according to the DBSCAN clustering algorithm, and calculating the third time-frequency synchronization feature based on the synchronization interference coverage range: ； in, is the third time-frequency synchronization feature of the i-th abnormal time-frequency interference target, , n is the total number of types of abnormal time-frequency interference targets; min is the minimum value; is the distance between the i-th type j-th abnormal time-frequency interference target and the surveying and mapping instrument, , is the total number of synchronous interference coverage of the i-th abnormal time-frequency interference target, It is the synchronous interference coverage range of the i-th and j-th abnormal time-frequency interference target.

Images