FNN-based improved tracking loop and operation method of anti-interference 5G opportunity signal positioning receiver

Abstract

The invention belongs to the technical field of 5G NAVSOP receiving, and particularly relates to the technical field of 5G NAVSOP receiving, both a synchronous adjustment module and a signal preprocessing module receive 5GNR signals, the synchronous adjustment module transmits the signals to a tracking unit, the signal preprocessing module transmits the signals to a pseudo-distance acquisition module, and the pseudo-distance acquisition module acquires the pseudo-distance. The pseudo-distance acquisition module transmits a signal to the linear converter, and the linear converter and the tracking unit transmit the signal to each other; the tracking unit comprises a phase rotation module, an EML discriminator and a pre-training network, the phase rotation module receives a signal of the synchronous adjustment module and transmits the signal to the EML discriminator, the EML discriminator transmits the signal to the pre-training network, the pre-training network transmits the signal to a linear converter, and the linear converter transmits the signal to the synchronous adjustment module. The phase rotation module and the linear converter transmit signals to each other. The method is used for solving the problems of low positioning precision and unstable pseudo-range acquisition caused by the traditional EML technology.

Description

Technical Field

[0001] The present invention belongs to the technical field of 5G NAVSOP receiving, and in particular relates to an operation method of an FNN-based improved tracking loop and an anti-interference 5G opportunity signal positioning receiver. Background Art

[0002] With the development of the information age, location services have become increasingly important. Accurate location information is indispensable in emergency rescue, urban planning, logistics and transportation, and personal navigation. However, in urban environments, high-rise buildings, busy traffic, and interference from electronic signals make accurate positioning extremely difficult. In order to find an alternative to the global satellite navigation system, researchers began to study an innovative navigation technology for opportunity signal navigation, using commercial communication signals as opportunity signals to achieve positioning instead of using traditional navigation signals. Although research on opportunity signal positioning has made progress, it is still challenging to achieve widespread and accurate positioning in urban environments. Currently, Wi-Fi, Bluetooth, and UltraWide Band (UWB) signals used for opportunity signal navigation have defects. Their signals are unevenly distributed and have low coverage. These limitations hinder the widespread application of opportunity signals. However, the development of the fifth generation of wireless technology has brought new possibilities for opportunity signal navigation. The high bandwidth and ultra-dense network deployment characteristics of 5G signals can provide wide and continuous signal coverage for specific areas, thereby providing high-quality opportunity positioning signal sources.

[0003] With the completion of the 5G NAVSOP research framework, specific challenges such as mitigating multipath effects have received increasing attention. Here, the application of various GNSS multipath mitigation strategies such as antenna techniques and high-resolution correlators (HRC) have been considered for navigation receivers based on cellular signals. However, it is difficult to filter out low-altitude signals because multipath mitigation methods using antenna techniques are not fully feasible as signals from ground-based 5G stations usually exhibit low elevation angles. To address this challenge, Ali A. Abdallah and his team adopted a reinforcement learning-based ground vehicle positioning method that showed significant results in reducing multipath effects, thus affirming the great potential of machine learning in this field. However, in complex environments, the challenges of multipath propagation become increasingly important, especially when the signal-to-noise ratio varies greatly and the multipath conditions fluctuate. There is a clear gap in lightweight machine learning algorithms that can effectively track pseudoranges without pre-training. Developing such algorithms is essential to maintain signal integrity and accurately extract positioning data in multipath scenarios, which is crucial in high-precision applications such as autonomous driving. Summary of the invention

[0004] The present invention provides an operation method of an improved tracking loop based on FNN and an anti-interference 5G opportunity signal positioning receiver, so as to solve the problems of low positioning accuracy and unstable pseudo-range acquisition brought about by traditional EML technology.

[0005] The present invention is achieved through the following technical solutions:

[0006] An improved tracking loop based on FNN, the improved tracking loop comprising a synchronization adjustment module, a signal preprocessing module, a tracking unit, a pseudo-range acquisition module and a linear converter;

[0007] The synchronization adjustment module and the signal preprocessing module both receive 5GNR signals, the synchronization adjustment module transmits the signals to the tracking unit, the signal preprocessing module transmits the signals to the pseudo-range acquisition module, the pseudo-range acquisition module transmits the signals to the linear converter, and the linear converter and the tracking unit transmit signals to each other;

[0008] The tracking unit includes a phase rotation module, an EML discriminator and a pre-trained network. The phase rotation module receives a signal from a synchronization adjustment module and transmits it to the EML discriminator. The EML discriminator transmits the signal to the pre-trained network. The pre-trained network transmits the signal to a linear converter. The phase rotation module and the linear converter transmit signals to each other.

[0009] Furthermore, the improved tracking loop includes a discriminant function based on early and late power, the TOA estimation value of the discriminant function based on early and late power normalized by the sampling time T is divided into an integer part and a decimal part, and the zero point and TOA estimation data of the discriminator function are obtained by using the TDL channel loop. The zero point and TOA estimation data of the discriminator function are used as the reference information of the phase detector in the tracking loop, and are converted into empirical parameters through fitting processing;

[0010] The integer part is used to adjust the position of the FFT window, and the decimal part controls the amplitude of the phase rotation;

[0011] The pre-trained network processes the original EML output, generates a new delay tracking result, and uses it as the input of the next tracking cycle.

[0012] Furthermore, the EML discriminator evaluates the time alignment of the signal by comparing the power difference between the early and late signals; it is generated by phase rotation in the frequency domain, and its mathematical expression is shown in formula (1):

[0013]

[0014] Among them, S k represents the DMRS value on the frequency domain subcarrier k, ε represents the preset time offset, and N represents the total number of subcarriers;

[0015] The output of the EML discriminator is the power difference between the early and late signals, which is used to indicate the time deviation of the signal. The deviation metric can be expressed as formula (2):

[0016]

[0017] Where N represents the total number of subcarriers, C represents the received signal strength, The representative normalized S-curve is expressed as formula (3),

[0018]

[0019] in, Represents the normalized timing error.

[0020] Normalization factor k dll The value of is obtained by the derivative value of the discriminator's S curve at 0, as shown in formula (4),

[0021]

[0022] Further normalizing the discriminator can be expressed as formula (5),

[0023]

[0024] The delay estimate η is adjusted according to the output of the discriminator, and the update rule is defined as shown in formula (6),

[0025]

[0026] Furthermore, a linear transformation is used to correct the output of the EML discriminator. The relevant transformation formula is shown in formula (7):

[0027]

[0028] Here, η represents the estimated value of the time delay.

[0029] Furthermore, the pre-trained network uses the feature data of the discriminator function as a training set, and the training set preparation process specifically includes the following steps:

[0030] Step S1: According to the 5G protocol, a basic transmission signal s(k) is generated;

[0031] Step S2: Delay τ to s(k) by applying different normalized symbol delays;

[0032] Step S3: Adjust Nb from -50 to 50 and set γ = 0.01 to simulate signals with different fractional delays, where (Nb max -Nbmin )·γ=1, which is used to ensure that the trained delay tracking network can identify fractional delays within a sampling point.

[0033] Furthermore, in step S2, noise with different signal-to-noise ratios is added to each delayed signal to generate signals s(τ) with different SNR levels, where the SNR values ​​are set to an arithmetic sequence from 5dB to 50dB with a step size of 5dB, covering {5, 10, 15,, 50}dB.

[0034] Furthermore, after the 5G simulation signal is generated, the signal is sent to a preset SDR for data preprocessing and pseudorange acquisition; then the data is sent to a tracking loop; the output value of the tracking loop is used as a feature of the training set, and the relative relationship between the estimated TOA value and the true TOA value is used as a label;

[0035] Each data point (x i ,y i ) all conform to the following formula (8),

[0036]

[0037] in, is the feature value of the i-th sample obtained by the normalized discriminator function, and the label y i It is a binary value indicating the status of the current TOA estimate relative to the true TOA; if the current estimated TOA lags behind the true TOA, the label is 0; if the current estimated TOA is ahead of the true TOA, the label is 1.

[0038] Furthermore, a feedforward neural network is used to construct an improved tracking loop, specifically,

[0039] The network structure includes an input layer, two fully connected layers, and a ReLU activation layer, and finally a softmax layer is used to achieve binary classification;

[0040] Each fully connected layer contains 50 neurons, designed to capture complex data features and patterns;

[0041] The Adam optimizer was used, 100 training cycles were set, the mini-batch size was 64, and the initial learning rate was 0.01.

[0042] An operation method of an anti-interference 5G opportunity signal positioning receiver based on an FNN improved tracking loop, the operation method of the anti-interference 5G opportunity signal positioning receiver uses the above-mentioned FNN-based improved tracking loop, and the operation method of the anti-interference 5G opportunity signal positioning receiver includes the following steps:

[0043] Step 1: Use USRP to receive 5G signals and perform data preprocessing; in which positioning information elements are expanded during data preprocessing;

[0044] Step 2: Based on the data preprocessing in step 1, perform preliminary estimation of the delay;

[0045] Step 3: Based on the relevant preliminary estimated delay in step 2, perform single base station pseudorange measurement;

[0046] Step 4: Based on the single base station pseudorange measurement in step 3, a base station pseudorange data set is constructed, where the base station pseudorange data set includes the pseudorange result obtained in step 3 and the cell ID set obtained in step 1;

[0047] Step 5: Based on the base station pseudorange data set in step 4, the navigation result is obtained by using the improved tracking loop based on FNN as claimed in claim 1.

[0048] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned loop is realized.

[0049] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the circuit described above is implemented.

[0050] The beneficial effects of the present invention are:

[0051] The stability and precision of the invention are significantly improved.

[0052] The present invention ensures that the data for network training has high authenticity and diversity.

[0053] This invention not only demonstrates the potential of ML technology in improving the accuracy and robustness of 5G positioning technology, but also provides a practical approach to address the challenges of positioning in complex environments.

[0054] The present invention can effectively balance computing efficiency and performance.

[0055] The present invention proposes a linear transformation strategy, which optimizes the tracking loop through parameters determined by simulation experiments to reduce the inconsistency between the zero point of the discriminator function and the TOA estimation value in theory and practice.

[0056] The present invention enhances the performance of the tracking loop, and experiments have shown that the most accurate improvement effect is achieved by using a feedforward neural network to improve the tracking loop.

[0057] The present invention realizes signal acquisition of 5G opportunity signals by utilizing the high-performance USRP-B210 device.

[0058] Through field tests, the present invention proves that the designed 5G NAVSOP receiver can achieve meter-level ranging accuracy in urban environments, demonstrating the feasibility and reliability of the ranging algorithm in actual environments.

[0059] The ability of the present invention to maintain stable positioning performance in a high-interference environment demonstrates its significant advantage in anti-interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a structural schematic diagram of the present invention.

[0061] Figure 2 It is a schematic diagram of the data preparation process of the present invention.

[0062] Figure 3 It is a schematic diagram of the algorithm performance under different SNRs, where (a) is a schematic diagram of the algorithm performance when the RMSE is 0.66m, (b) is a schematic diagram of the algorithm performance when the RMSE is 0.64m, and (c) is a schematic diagram of the algorithm performance when the RMSE is 0.62m.

[0063] Figure 4 It is a bar chart of the root mean square error accuracy analysis of each algorithm at 95% probability under different signal-to-noise ratio conditions of the present invention.

[0064] Figure 5 It is a schematic diagram of building a simulation scene of the present invention.

[0065] Figure 6 It is a comparison diagram of the tracking loop improved by ML and the traditional EML tracking loop in scenario 2 of the present invention, as well as the trajectory using only the tracking loop and the real trajectory.

[0066] Figure 7 It is a bar chart comparing the average positioning errors of various algorithms in scenario 2 of the present invention.

[0067] Figure 8 It is a comparison diagram of the tracking loop improved by ML and the traditional EML tracking loop in scenario three of the present invention, as well as the trajectory using only the tracking loop and the real trajectory.

[0068] Fig. 9 It is a bar chart comparing the average positioning errors of various algorithms in scenario three of the present invention.

[0069] Fig.10 It is a schematic diagram of the experimental path of the present invention.

[0070] Fig.11 It is the experimental route map of the present invention.

[0071] Fig.12It is a line graph of the path-distance measurement result of the present invention.

[0072] Fig.13 It is a line graph of the path two ranging results of the present invention.

[0073] Fig.14 It is a line graph of the measured positioning coverage rate of the present invention.

[0074] Fig.15 2 are pseudorange measurement value diagrams, where (a) is a pseudorange measurement value diagram of the SIC algorithm, and (b) is a pseudorange measurement value diagram of the ICSP algorithm. DETAILED DESCRIPTION

[0075] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0076] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0077] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0078] The following is attached to this application specification Figure 1-9 , the technical solutions in the embodiments of the present application are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0079] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0080] Implementation Method 1

[0081] This embodiment proposes an improved tracking loop based on FNN, the improved tracking loop includes a synchronization adjustment module, a signal preprocessing module, a tracking unit, a pseudo-range acquisition module and a linear converter;

[0082] The synchronization adjustment module and the signal preprocessing module both receive 5GNR signals, the synchronization adjustment module transmits the signals to the tracking unit, the signal preprocessing module transmits the signals to the pseudo-range acquisition module, the pseudo-range acquisition module transmits the signals to the linear converter, and the linear converter and the tracking unit transmit signals to each other;

[0083] The tracking unit includes a phase rotation module, an EML discriminator and a pre-trained network. The phase rotation module receives a signal from a synchronization adjustment module and transmits it to the EML discriminator. The EML discriminator transmits the signal to the pre-trained network. The pre-trained network transmits the signal to a linear converter. The phase rotation module and the linear converter transmit signals to each other.

[0084] Furthermore, the improved tracking loop includes a discriminant function based on early and late power, the TOA estimation value of the discriminant function based on early and late power normalized by the sampling time T is divided into an integer part and a decimal part, and the zero point and TOA estimation data of the discriminator function are obtained by using the TDL channel loop. The zero point and TOA estimation data of the discriminator function are used as the reference information of the phase detector in the tracking loop, and are converted into empirical parameters through fitting processing;

[0085] The integer part is used to adjust the position of the FFT window, and the decimal part controls the amplitude of the phase rotation;

[0086] The pre-trained network obtained by offline training can process the original EML output to generate a new delay tracking result, which is used as the input of the next tracking cycle.

[0087] Furthermore, the EML discriminator evaluates the time alignment of the signal by comparing the power difference between the early and late signals; the early and late signals are generated by applying a slight time offset to the reference signal to simulate the signal advance or delay that may occur in a multipath environment; these signals are generated in the frequency domain by phase rotation, and their mathematical expression is shown in formula (1):

[0088]

[0089] Among them, S k represents the DMRS value on subcarrier k in the frequency domain, ε represents the preset time offset, and N represents the total number of subcarriers; these calculations help the EML discriminator determine whether the signal is consistent with the estimated arrival time.

[0090] The output of the EML discriminator is the power difference between the early and late signals, which is used to indicate the time deviation of the signal. The deviation metric can be expressed as formula (2):

[0091]

[0092] Where N represents the total number of subcarriers, C represents the received signal strength, The representative normalized S-curve can be expressed as formula (3),

[0093]

[0094] in, represents the normalized timing error, ε represents the preset time offset, and the best effect is achieved when ε is 0.5.

[0095] Normalization factor k dll The value of is obtained by the derivative value of the discriminator's S curve at 0, as shown in formula (4),

[0096]

[0097] Further normalizing the discriminator can be expressed as formula (5),

[0098]

[0099] The delay estimate η is adjusted according to the output of the discriminator, and the update rule is defined as shown in formula (6),

[0100]

[0101] The working principle of the tracking loop has been analyzed in the previous section. However, in multipath and noise environments, the zero point of the discriminator function often does not match the actual TOA. In order to solve the deviation between the zero point of the discriminator function and the TOA estimate in theory and practical applications, this section uses simulation experiments in the TDL channel environment to preliminarily obtain a series of zero point and TOA estimate data of the discriminator function. These data are used as the benchmark information of the phase detector in the tracking loop and are converted into empirical parameters through fitting. These empirical parameters are used to adjust the normalized delay ratio in simulation and field test data, and are used in the design of tracking loops enhanced by linear transformation technology.

[0102] By iteratively updating the tracking loop cycle, the signal delay can be effectively estimated and tracked to achieve time alignment correction. Although this method is quite accurate in multipath delay estimation, it faces many challenges in complex urban environments with high dynamics and significant multipath effects. In such an environment, the output of the discriminator may be affected by noise interference or path changes in the actual delay value. Therefore, it is necessary to further optimize the correction strategy for delay estimation. The present invention adopts a linear transformation strategy to adjust the discriminator output by applying a linear correction factor to reduce the deviation between the discriminator zero point and the actual arrival time.

[0103] Furthermore, for this purpose, a linear transformation is used to correct the output of the EML discriminator. The relevant transformation formula is shown in formula (7):

[0104]

[0105] Here, η represents the estimated value of the time delay; the linear transformation is defined by parameters α and β and is optimized through extensive simulations under different signal-to-noise ratios and multipath delay conditions. Linear regression analysis using these simulation data can accurately determine the values ​​of α and β, so that the time delay estimate provided by the EML discriminator is closer to the actual value. The application of this method can more accurately perform time alignment correction in complex signal environments. With this improvement, the tracking loop can more effectively handle multipath propagation and noise interference, thereby enhancing the stability and accuracy of the entire system.

[0106] Furthermore, the pre-trained network uses the feature data of the discriminator function as a training set, that is, the output of the discriminator function is used as the input of the pre-trained network, and the output of the pre-trained network is used as the output of the tracking loop. The goal of the tracking loop is to fine-tune the current TOA estimate so as to better align the true TOA value. Therefore, the present invention constructs this problem as a classification task, in which the goal of the network is to predict whether the current TOA lags behind or leads the true TOA; Figure 2 As shown,

[0107] The training set preparation process specifically includes the following steps:

[0108] Step S1: According to the 5G protocol, a basic transmission signal s(k) is generated;

[0109] Step S2: Delay τ to s(k) by applying different normalized symbol delays;

[0110] Step S3: Adjust Nb from -50 to 50 and set γ = 0.01 to simulate signals with different fractional delays, where (Nb max -Nb min)·γ=1, which is used to ensure that the trained delay tracking network can identify fractional delays within a sampling point.

[0111] In order to make the simulated signal closer to the real environment, this paper adds simulated multipath effects into the tapped delay TDL channel model to enhance the authenticity of the simulation. The signal processed by the TDL channel more accurately reflects the propagation characteristics of the real signal.

[0112] Furthermore, in order to further improve the network stability and interference resistance, in step S2, noise with different signal-to-noise ratios is added to each delayed signal to generate signals s(τ) with different SNR levels, where the SNR value is set to an arithmetic sequence from 5dB to 50dB, with a step size of 5dB, covering {5, 10, 15,, 50}dB;

[0113] This setting provides a rich and realistic data basis for network training by simulating a variety of signal-noise environments, ensuring the recognition accuracy and robustness of the time-delay tracking network in various environments.

[0114] Furthermore, after the 5G simulation signal is generated, the signal is sent to a preset SDR for data preprocessing and pseudorange acquisition; then the data is sent to a tracking loop; the output value of the tracking loop is used as a feature of the training set, and the relative relationship between the estimated TOA value and the true TOA value is used as a label;

[0115] Each data point (x i ,y i ) all conform to the following formula (8),

[0116]

[0117] in, is the feature value of the i-th sample obtained by the normalized discriminator function, and the label y i It is a binary value indicating the status of the current TOA estimate relative to the true TOA; if the current estimated TOA lags behind the true TOA, the label is 0; if the current estimated TOA is ahead of the true TOA, the label is 1.

[0118] The adjustment amplitude Δt of the tracking loop will be determined based on the output of the pre-trained network to minimize the classification error and optimize the TOA estimate; the dataset will be split into training and test sets to evaluate the performance of the model during training and verify its generalization ability after training is completed. In this way, the pre-trained network will learn to recognize the complex relationship between input features and TOA states, thereby improving the accuracy of TOA estimation.

[0119] Furthermore, in order to ensure that the improved tracking loop developed based on the ML algorithm can meet the high real-time requirements of positioning and navigation, the present invention pays special attention to its lightweight characteristics when selecting the ML algorithm; the lightweight algorithm can reduce the model's demand for computing resources while ensuring computing efficiency, thereby adapting to the system's requirements for rapid decision-making and processing capabilities. Based on this consideration, the present invention selects three representative lightweight ML algorithms to construct the improved tracking loop, namely: support vector machine

[0120] (Support Vector Machine, SVM), Random Average Decision Trees (Random Average Decision Trees, RADT) and FNN. These algorithms are considered to be ideal for fast and accurate binary classification tasks due to their efficient learning ability and small model size. Through in-depth analysis and comparison of these lightweight algorithms, the aim is to find an improved tracking loop that best meets the real-time requirements of the system.

[0121] Support Vector Machine

[0122] The linear kernel function is used to utilize the linear distribution characteristics of the data, and the kernel function scale is automatically adjusted to adapt to different data characteristics and optimize the classification effect.

[0123] The box constraint parameter is set to 1 by default and can be adjusted according to experimental requirements to balance the complexity of the model and the training effect.

[0124] Choose not to perform data standardization to maintain the original distribution characteristics of the data.

[0125] Randomized Average Decision Tree

[0126] Build 100 decision trees and use the majority voting mechanism to improve the accuracy and stability of classification.

[0127] This method makes full use of the advantages of ensemble learning to improve the model's generalization ability for new data.

[0128] A feedforward neural network is used to construct an improved tracking loop, specifically,

[0129] The network structure includes an input layer, two fully connected layers, and a ReLU activation layer, and finally a softmax layer is used to achieve binary classification;

[0130] Each fully connected layer contains 50 neurons, designed to capture complex data features and patterns;

[0131] The Adam optimizer was used, 100 training cycles were set, the small batch size was 64, and the initial learning rate was 0.01. In this way, the training process was optimized and the model performance was improved.

[0132] Table 1 Accuracy evaluation

[0133]

[0134] The three trained tracking networks with different time delays are verified by using the independently generated validation set data. Taking the classification accuracy as the evaluation criterion, the experimental results shown in Table 1 can be obtained. The results show that the tracking loop improved by FNN achieves the highest accuracy.

[0135] Scene 1

[0136] Improved tracking loop combining ML techniques with linear transformers Based on the theory, this section evaluates in detail the performance of the improved tracking loop by ML in a multipath propagation environment, especially in the context of the TDL channel model. By using EML and linear transformers as standard inputs, the signal is introduced into multiple pre-trained networks, including SVM, RADT and FNN. This experiment aims to evaluate the tracking loop performance under different signal-to-noise ratios and various delay conditions.

[0137] The simulation parameter configuration is shown in Table 2 (the simulation parameters are set with reference to the actual receiving environment)

[0138] By simulating the generation of 5G signals, passing through multipath channels, receiving, and solving, the TOA value is tracked and estimated through the tracking loop structure designed in the previous chapter. After adjusting the SNR conditions and performing 150 independent random repetitions of each network, the following can be obtained: Figure 3 The experimental results.

[0139] Table 2 Simulation parameter configuration

[0140]

[0141] The experimental results show that in this scenario, the use of ML algorithm to improve the tracking loop can achieve low-error ranging effect. The use of SVM to improve the tracking loop makes the ranging accuracy reach 0.66m RMS error, and the use of RADT to improve the tracking loop makes the ranging accuracy reach 0.64m RMS error. In comparison, the FNN network has achieved the highest accuracy and has the strongest anti-noise and anti-multipath capabilities, reaching a ranging accuracy of 0.62m RMS error.

[0142] Scene 2

[0143] In order to further verify the effectiveness of the FNN improved tracking loop, this paper chooses to simulate the second scenario in a complex urban environment. The environment has many obstructions, the 5G base station environment is densely distributed, the signal power is high, and the 5G opportunity signal data of multiple base stations can be received at the same point at the same time. Therefore, under this environmental condition, it is possible to locate through the 5G opportunity signal. For the authenticity of the experiment, this paper selects a 3D building and road model composed of some buildings in a certain urban area of ​​Hong Kong. The boundary range of the map is [114.14596, 114.14815; 22.28350, 22.28614].

[0144] By reading the OSM data, the key building complexes were modeled and the building heights that were consistent with the actual situation were set. A total of 20 5G base stations were deployed on some building roofs, and their latitude (°), longitude (°) and height (m) coordinates are shown in Table 3.

[0145] Table 3 Base station location distribution configuration

[0146]

[0147] They were marked on the map with 20 numbers. According to the road information of the selected area map, two appropriate points were selected as the starting point and the end point. During the trajectory from the starting point to the end point, 5 intermediate points were selected as the connection points to form the motion trajectory. From the starting point, each point was connected along the road in sequence. During this period, all the connecting lines were straight lines along the road. The coordinates of the starting point, the end point and the 5 connection points are shown in Table 4.

[0148] By connecting these seven points at once, we can get the real trajectory of the simulation in this environment.

[0149] Table 4 Path planning

[0150]

[0151] The experimental scene is set up as follows Figure 5 As shown. Using the same method as in Section 3.4, the FSPL model is used to simulate the generation of 5G opportunity signal sources and their propagation. The actual trajectory speed in the simulation experiment is 1m / s, the total length of the path from the starting point to the end point is 272m, the running time is 272s, and the direction is always along the road in the forward direction. During the movement, one point is sampled every second, and this point is judged by 20 5G base stations for signal reception in turn. The base station number and coordinates of the base station that can receive the 5G opportunity signal at this point are recorded for subsequent calculations. When the 5G opportunity signal is subsequently resolved, the coordinates of each point are settled by the triangulation positioning method based on least squares estimation.

[0152] Table 5 Channel parameter configuration

[0153]

[0154] The comparison between the tracking loop improved by ML and the traditional EML tracking loop, as well as the trajectory using only the tracking loop and the real trajectory is shown in Figure 2. Figure 6 shown.

[0155] Depend on Figure 7 The experimental results show that the FNN-based tracking loop improves the positioning accuracy by 13% compared to the traditional EML tracking loop. The simulation results prove that the enhancement method proposed in the present invention significantly enhances the positioning capability.

[0156] Scene 3

[0157] In order to further verify the effectiveness of the FNN improved tracking loop, the present invention simulates another scenario of a complex city, in which the propagation channels of the signals sent by all base stations are adjusted to TDL-A channels, and the channel parameter configuration is shown in Table 6.

[0158] The comparison between the tracking loop improved by ML and the traditional EML tracking loop, as well as the trajectory using only the tracking loop and the real trajectory is shown in Figure 2. Figure 8 shown.

[0159] Depend on Fig. 9 The experimental results show that the performance of the OMP algorithm decreases in the TDL-A scenario, while the performance of the FNN-improved EML is still the best, with an accuracy improvement of 18% compared to the EML algorithm.

[0160] Table 6 Channel parameter configuration

[0161]

[0162] The present invention aims to improve the accuracy and robustness of 5G positioning technology in complex environments.

[0163] Implementation Method 2

[0164] This embodiment provides a method for transporting an anti-interference 5G opportunity signal positioning receiver based on an FNN improved tracking loop, and a series of field experiments were completed using commercial 5G signals at the South Stadium of Harbin Engineering University.

[0165] (1) High-gain omnidirectional custom antenna: The device operates in the frequency range of 3.4GHz to 3.6GHz with a gain of 10dBi.

[0166] (2) Portable inverter power supply: This device provides power for experimental equipment.

[0167] (3) Host computer terminal: This device is used for real-time processing of test data.

[0168] (4) USRP-B210: This device is mainly used for signal acquisition and has a built-in GPS Disciplined Oscillator (GPSDO) module to achieve precise time synchronization. Its hardware clock is controlled by GPSDO and can down-convert and sample 5G signals at a rate of 15.36MSps.

[0169] (5) GPS receiver and antenna: A DOVE482 high-precision navigation terminal is used to accurately estimate the position of pedestrians on the ground. This receiver can achieve centimeter-level positioning accuracy through differential positioning technology. This chapter will use the measurement results of this device as the absolute reference standard for the true distance.

[0170] Table 7 Experimental parameter configuration

[0171]

[0172] Among them, USRP-B210 is a software-defined radio device developed by Ettus Research. It is based on the AD9361 RF front end of Analog Devices and the Zynq-7020 FPGA of Xilinx. It supports a wide frequency range from 70MHz to 6GHz, covering the frequency band of current 5G cellular signals. The device can achieve high-precision time synchronization through the built-in GPSDO module.

[0173] The software receiving platform application is developed based on C++ language, and interacts with USRP devices with the help of UHD library to receive wireless signals. The key parts of the program include initializing and configuring USRP devices, main function design, receiving data flow control, time synchronization and compensation. The following content will explain each part in detail.

[0174] Initialization and configuration: This program first imports the necessary header files, including the UHD library interface (for communicating with the USRP device), the standard input and output library (for console interaction), the string processing and file operation libraries, etc., to provide support for the basic operation of the program. The program also defines several namespaces (for example, namespace po = boost::program_options;) to simplify code writing and enhance code readability and maintainability.

[0175] Main function design: The main function uses the UHD_SAFE_MAIN(int argc, char*argv[]) macro definition to enhance cross-platform compatibility, which is the recommended practice of the UHD library. Inside this function, the program parses the command line parameters to allow the user to customize the configuration of the USRP device, such as sampling rate, frequency, gain, and antenna selection. This provides users with flexibility to configure the USRP device according to specific application requirements.

[0176] Receive data flow control: The program defines the recv_to_file template function, which is the core of data reception and processing. This function configures the USRP device to start continuous or limited number of sample reception and write the received samples to a file. This step is key to the data acquisition process and ensures effective storage and subsequent processing of the data. The key logic of GPSDO time synchronization is implemented in the recv_to_file function.

[0177] Time synchronization and compensation design: First, the program obtains the current GPS time by calling the sensor interface of the USRP device management board. Then, the internal clock of the USRP device is set to align with the GPS time when the next pulse per second (PPS) signal arrives. This alignment process is completed by setting the USRP time at the exact moment before the next PPS arrives, ensuring the time accuracy of data acquisition, which is crucial for the application scenario that relies on time synchronization. In order to further improve the accuracy of time synchronization, the program implements a time compensation mechanism. This mechanism first calculates the time difference (time_difference) between the last PPS signal (time_last_pps) of the USRP device and the current GPS time (gps_current_time). Based on this time difference, the program determines whether time compensation is required and the specific method of compensation. If the calculated time difference is greater than 0.5 seconds, it indicates that there is a significant error in time synchronization and compensation is required. At this time, the program adjusts the time difference to subtract 1 second to reflect the actual offset of time. If the time difference is less than -1 second, the program will enter a loop compensation process. In each loop, the program pauses for a period of time (100 milliseconds), calculates the time difference again, and tries to reduce the time error by adding 1 second. This loop is executed at most 10 times to avoid the risk of infinite loops. With the above compensation logic, the program can dynamically adjust the time setting of the USRP device to ensure that it is highly consistent with the actual GPS time. The compensated time (compensated_time) will be used to set the start time of the receiving task, thereby ensuring that the time stamp of data collection is accurate.

[0178] like Fig.10As shown, an operation method of an anti-interference 5G opportunity signal positioning receiver based on an FNN improved tracking loop is provided. The operation method of the anti-interference 5G opportunity signal positioning receiver uses the FNN improved tracking loop as described in Implementation Example 1. The operation method of the anti-interference 5G opportunity signal positioning receiver includes the following steps:

[0179] Step 1: Use USRP to receive 5G signals and perform data preprocessing; in which positioning information elements are expanded during data preprocessing;

[0180] Step 2: Based on the data preprocessing in step 1, perform preliminary estimation of the delay;

[0181] Step 3: Based on the relevant preliminary estimated delay in step 2, perform single base station pseudorange measurement;

[0182] Step 4: Based on the single base station pseudorange measurement in step 3, a base station pseudorange data set is constructed, where the base station pseudorange data set includes the pseudorange result obtained in step 3 and the cell ID set obtained in step 1;

[0183] Step 5: Based on the base station pseudorange data set in step 4, the navigation result is obtained by using the improved tracking loop based on FNN as claimed in claim 1.

[0184] 5GNAVSOP ranging experiment and result analysis

[0185] In order to preliminarily verify the effectiveness and ranging performance of the designed 5GNAVSOP receiver, a series of field tests were carried out using commercial 5G signals at the South Stadium of Harbin Engineering University.

[0186] The carrier frequencies and of the 5G base stations have been pre-measured and used as prior information in the ranging phase. The selected base station parameters are listed in Table 8. The experimental path is as follows Fig.11 As shown,

[0187] Table 8 Experimental base station parameters

[0188]

[0189] In the experiment, 5GNAVSOP receiver is used to collect signals from the commercial receiver, and a centimeter-level GNSS receiver is used in this experiment to obtain the precise location information of pedestrians and 5G base stations.

[0190] Two pedestrians walked along two predetermined paths at a fixed speed for 70 seconds. To enhance the comparability of the data, the participants paused for about 5 seconds before each experiment and stayed at an absolute position point pre-calibrated by a high-precision positioning device for 8 seconds. This was to ensure the accuracy and contrast of data collection, so as to better analyze the experimental results.

[0191] The off-line data collected by the receiver is used to perform super-resolution pseudo-range calculation using the designed software receiver, and the following can be obtained: Fig.12 and Fig.13 The experimental results.

[0192] Through data analysis, it can be found that the average distance measurement error of path two is 3.17m, while the average distance measurement error of path one is 2.68m.

[0193] The experimental results show that in an urban environment, for a simple scenario with a single macro base station, the 5GNAVSOP receiver designed by the present invention can achieve meter-level ranging accuracy. The field test results also confirm the feasibility and reliability of the ranging algorithm proposed in this study in practical applications.

[0194] ICSP anti-interference test and result analysis

[0195] In the test, commercial 5G signals were used as signal sources.

[0196] Interference robustness was verified using a virtual base station-based verification method. In the study, a virtual base station signal source was generated through software simulation, and parameters such as transmission power, frequency, and location can be customized to simulate the transmission signal characteristics of a real base station, thereby accurately controlling the intensity of interference. The experiment simulated the attenuation of 5G signals in space, which not only simulated the propagation characteristics of base station signals in the natural environment, but also facilitated the evaluation of the robustness of the algorithm under different interference intensities.

[0197] The basic parameters of the base station used in the experiment are listed in Table 9.

[0198] Table 9 Experimental base station parameters

[0199]

[0200] Positioning coverage test

[0201] The purpose of this experiment is to evaluate the performance of various interference cancellation algorithms in the face of the added influence of virtual interference sources. The experimental configuration includes three real base stations and one virtual interference source. The signal strength of the virtual interference source is manually adjusted to test and compare the robustness of each algorithm. The entire test process was repeated 100 times independently. The test results are shown in Fig.14 The figure shows the relationship between interference signal strength and effective base station recovery rate. The effective base station recovery rate refers to the proportion of base stations that successfully extract positioning observation data from all tested base stations. As the interference strength increases, the performance of the ICSP algorithm significantly exceeds that of traditional algorithms such as the cross-correlation method, the SIC method, and the SCP method.

[0202] Especially under high interference conditions, the ICSP algorithm can also maintain a nearly constant recovery rate, demonstrating its excellent ability to cope with strong interference in positioning systems.

[0203] Positioning accuracy test

[0204] The specific experimental plan is set as follows: collect positioning samples every 4 seconds at a fixed point, the total duration is 120 seconds, and the interference intensity is set to 28dBm. Fig.14 It can be seen that under this interference level, the SCP and cross-correlation algorithms cannot achieve 75% effective base station recovery rate (ie, recover the effective positioning information of three base stations), so they cannot perform effective positioning. Therefore, the experiment mainly compares the performance of the SIC and ICSP algorithms.

[0205] The pseudorange measurement results are displayed in Fig.15 In the simulation, the ICSP algorithm can solve the pseudorange relative to four base stations, while the SIC algorithm can only solve the pseudorange relative to three base stations. After converting the base station and receiver coordinates from the LLH coordinate system to the ECEF coordinate system, the least squares (LS) positioning algorithm is used for solution. The average positioning error of the SIC algorithm is 13.82 meters, while the average positioning error of the ICSP algorithm is 11.66 meters. These results show the significant advantages of the ICSP algorithm in terms of the number of base station information recovered and the positioning accuracy.

[0206] Implementation Method 3

[0207] An embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the memory is used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory and the processor are connected via a bus. Specifically, the processor implements any step in the first embodiment above by running the computer program stored in the memory.

[0208] It should be understood that in the embodiments of the present invention, the processor referred to may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0209] The memory may include a read-only memory, a flash memory, and a random access memory, and provides instructions and data to the processor. A part or all of the memory may also include a nonvolatile random access memory.

[0210] It should be understood that if the above-mentioned integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method implementations when executed by the processor. Among them, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code can be in source code form, object code form, executable file or some intermediate form. The above-mentioned computer-readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the above-mentioned computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0211] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest range consistent with the principles and novel features disclosed herein.

[0212] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0213] It should be noted that the methods and detailed examples provided in the above embodiments can be combined with the devices and equipment provided in the embodiments, and references can be made to each other, and no further details will be given.

[0214] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0215] The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above-mentioned embodiments, or replace some of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An improved tracking loop based on FNN, characterized in that: The improved tracking loop includes a synchronization adjustment module, a signal preprocessing module, a tracking unit, a pseudo-range acquisition module and a linear converter; The synchronization adjustment module and the signal preprocessing module both receive 5GNR signals, the synchronization adjustment module transmits the signals to the tracking unit, the signal preprocessing module transmits the signals to the pseudo-range acquisition module, the pseudo-range acquisition module transmits the signals to the linear converter, and the linear converter and the tracking unit transmit signals to each other; The tracking unit includes a phase rotation module, an EML discriminator and a pre-trained network. The phase rotation module receives a signal from a synchronization adjustment module and transmits it to the EML discriminator. The EML discriminator transmits the signal to the pre-trained network. The pre-trained network transmits the signal to a linear converter. The phase rotation module and the linear converter transmit signals to each other.

2. The improved tracking loop according to claim 1, characterized in that The improved tracking loop includes a discriminant function based on early and late power, wherein the TOA estimation value of the discriminant function based on early and late power normalized by the sampling time T is divided into an integer part and a decimal part, and the zero point and TOA estimation data of the discriminator function are obtained by using the TDL channel loop, and the zero point and TOA estimation data of the discriminator function are used as the reference information of the phase detector in the tracking loop, and are converted into empirical parameters through fitting processing; The integer part is used to adjust the position of the FFT window, and the decimal part controls the amplitude of the phase rotation; The pre-trained network processes the original EML output, generates a new delay tracking result, and uses it as the input of the next tracking cycle.

3. The improved tracking loop according to claim 2, characterized in that The EML discriminator evaluates the time alignment of the signal by comparing the power difference between the early and late signals; it is generated by phase rotation in the frequency domain, and its mathematical expression is shown in formula (1): Among them, S k represents the DMRS value on the frequency domain subcarrier k, ε represents the preset time offset, and N represents the total number of subcarriers; The output of the EML discriminator is the power difference between the early and late signals, which is used to indicate the time deviation of the signal. The deviation metric can be expressed as formula (2): Where N represents the total number of subcarriers, C represents the received signal strength, and Λ DLL (e~,ε) represents the normalized S-curve expressed as formula (3), in, represents the normalized timing error; Normalization factor k dll The value of is obtained by the derivative value of the discriminator's S curve at 0, as shown in formula (4), Further normalizing the discriminator can be expressed as formula (5), The delay estimate η is adjusted according to the output of the discriminator, and the update rule is defined as shown in formula (6), The output of the EML discriminator is corrected by linear transformation. The relevant transformation formula is shown in formula (7): Here, η represents the estimated value of the time delay.

4. The improved tracking loop according to claim 1 or 2, characterized in that: The pre-trained network uses the feature data of the discriminator function as a training set, and the training set preparation process specifically includes the following steps: Step S1: According to the 5G protocol, a basic transmission signal s(k) is generated; Step S2: Delay τ to s(k) by applying different normalized symbol delays; Step S3: Adjust Nb from -50 to 50 and set γ = 0.01 to simulate signals with different fractional delays, where (Nb max -Nb min )·γ=1, which is used to ensure that the trained delay tracking network can identify fractional delays within a sampling point.

5. The improved tracking loop according to claim 4, characterized in that In step S2, adding noise with different signal-to-noise ratios to each delayed signal generates signals s(τ) with different SNR levels, where the SNR value is set to an arithmetic sequence of 5dB to 50dB with a step size of 5dB, covering {5, 10, 15,, 50}dB.

6. The improved tracking loop according to claim 5, characterized in that After the 5G simulation signal is generated, it is sent to the preset SDR for data preprocessing and pseudorange acquisition; then the data is sent to the tracking loop; the output value of the tracking loop is used as the feature of the training set, and the relative relationship between the estimated TOA value and the true TOA value is used as the label; Each data point (x i ,y i ) all conform to the following formula (8), in, is the feature value of the i-th sample obtained by the normalized discriminator function, and the label y i It is a binary value indicating the status of the current TOA estimate relative to the true TOA; if the current estimated TOA lags behind the true TOA, the label is 0; if the current estimated TOA is ahead of the true TOA, the label is 1.

7. The improved tracking loop according to claim 6, characterized in that A feedforward neural network is used to construct an improved tracking loop, specifically, The network structure includes an input layer, two fully connected layers, and a ReLU activation layer, and finally a softmax layer is used to achieve binary classification; Each fully connected layer contains 50 neurons, designed to capture complex data features and patterns; The Adam optimizer was used, 100 training cycles were set, the mini-batch size was 64, and the initial learning rate was 0.

01.

8. A method for operating an anti-interference 5G opportunity signal positioning receiver based on an improved tracking loop of FNN, characterized in that: The operation method of the anti-interference 5G opportunity signal positioning receiver uses the FNN-based improved tracking loop as described in any one of claims 1-7, and the operation method of the anti-interference 5G opportunity signal positioning receiver includes the following steps: Step 1: Use USRP to receive 5G signals and perform data preprocessing; in which positioning information elements are expanded during data preprocessing; Step 2: Based on the data preprocessing in step 1, perform preliminary estimation of the delay; Step 3: Based on the relevant preliminary estimated delay in step 2, perform single base station pseudorange measurement; Step 4: Based on the single base station pseudorange measurement in step 3, a base station pseudorange data set is constructed, where the base station pseudorange data set includes the pseudorange result obtained in step 3 and the cell ID set obtained in step 1; Step 5: Based on the base station pseudorange data set in step 4, the navigation result is obtained by using the improved tracking loop based on FNN as claimed in claim 1.

9. A computer device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the improved tracking loop as claimed in any one of claims 1 to 7 when executing the computer program, or implements the steps of the method as claimed in claim 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the improved tracking loop according to any one of claims 1 to 7, or implements the steps of the method according to claim 8.

Images