Communication data transmission method and device of train approach early warning interphone

Abstract

The invention relates to the technical field of communication data transmission, and discloses a communication data transmission method and device for a train approach early warning interphone, and the method comprises the steps: collecting real-time signals and historical state data of the surrounding environment of a train; performing signal attenuation and noise analysis to obtain initial position data; when the signal intensity is too low, a random forest algorithm is adopted to analyze and compensate noise, and an adjustment data set is obtained; a position track is obtained through three-dimensional coordinate calculation and attenuation correction; if the state is not matched with the historical state, the position information is optimized through a noise gain matrix; fusing the multi-source communication correction signals to form a stable transmission data set; and the time delay and the signal-to-noise ratio are monitored in real time, the solution is optimized again when the time exceeds the limit, and finally accurate communication data are generated through fusion. According to the invention, the stability and precision of train positioning and communication in a complex environment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of communication and data transmission, and in particular to a method and device for communication and data transmission of a train approach warning intercom. Background Art

[0002] The train approach warning system is of vital importance in the field of railway safety. It ensures driving safety and dispatching efficiency by monitoring the train's position and movement status in real time, and is an indispensable technical pillar of modern railway transportation.

[0003] The most traditional and widely used method is voice notification via walkie-talkie. Dispatching centers, station attendants, or locomotive drivers use high-power base stations or locomotive radios to broadcast train approach warning information, such as train number, direction, and estimated time of arrival, in the form of voice broadcasts on specific operating frequency bands. Portable walkie-talkies carried by on-site workers receive these voice broadcasts and are informed of the approaching train. However, external factors such as terrain or electromagnetic interference can cause signal fluctuations. For example, when a high-speed train passes through a tunnel, the signal may be temporarily lost due to obstruction, resulting in data distortion or interruption.

[0004] In summary, the existing technology has the problem that in complex environments, such as tunnels, mountainous areas or areas with strong electromagnetic interference, signals are easily interfered with, resulting in data transmission distortion or signal transmission interruption. Summary of the Invention

[0005] The present invention provides a communication data transmission method and device for a train approach warning intercom, so as to achieve communication stability of trains in environments such as tunnels, mountainous areas or areas with strong electromagnetic interference.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a communication data transmission method for a train approach warning intercom, comprising: Collect real-time signals including speed, direction, and distance parameters from the train's surrounding environment, and obtain the train's historical motion status and multi-dimensional communication data streams; performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; When the signal strength in the preliminary location data set is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed based on the compensation coefficient and the preliminary location data set to obtain an adjusted data set; Performing iterative three-dimensional coordinate calculations based on the adjusted data set to obtain a preliminary position estimate; performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; When the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized based on the noise gain matrix to obtain optimized position information; Acquiring an initial signal from the multi-dimensional communication data stream and performing correction to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set; The delay data and signal-to-noise ratio data of the stable transmission data set are obtained in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is fused with the historical motion state of the train to obtain the final accurate communication data.

[0007] In an optional embodiment, performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results includes: Performing analog-to-digital conversion on the speed direction and distance parameters in the real-time signal to obtain a first signal data set; Converting the time domain signal in the first signal data set into a frequency domain signal to obtain a frequency-converted signal, and extracting a signal attenuation feature based on the frequency-converted signal to obtain an attenuation feature data set; Separating noise sources according to the attenuation feature data set to obtain a noise separation data set, and determining the type of noise source to obtain a noise source identification result; A Kalman filter fusion operation is performed on the noise separation data set to obtain a preliminary position data set.

[0008] In an optional embodiment, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset, including: When the signal strength is lower than a preset signal strength threshold, it is determined that an interference factor exists, and the interference type is determined according to the noise source identification result; Extracting noise source characteristics corresponding to the interference type from a pre-established noise source database to obtain environmental noise characteristics; Using a random forest algorithm to analyze and calculate the environmental noise characteristics to obtain a compensation coefficient; The preliminary position data set is weightedly adjusted according to the compensation coefficient to obtain an adjusted data set.

[0009] In an optional embodiment, performing iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate includes: Obtaining base station delay, signal strength, and arrival angle data from the adjusted data set, and performing smoothing on the base station delay, signal strength, and arrival angle data to obtain optimized multi-source data; Iteratively solving the three-dimensional coordinates of the train according to the optimized multi-source data to obtain preliminary three-dimensional coordinates; Extracting characteristic parameters of temperature, humidity, and electromagnetic interference from a pre-established environmental database, and performing multipath fading model correction on the preliminary three-dimensional coordinates to obtain corrected three-dimensional coordinates; When the corrected three-dimensional coordinates meet a preset coordinate convergence threshold, temperature compensation, humidity compensation, and multipath fading correction parameters are integrated to obtain a preliminary position estimate.

[0010] In an optional embodiment, performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data includes: Obtaining time delay data and environmental parameters in the preliminary position estimate, and smoothing the time delay data and the environmental parameters to obtain a smoothed state vector; Performing iterative calculation based on the smoothed state vector to obtain a preliminary position trajectory; When the preliminary position trajectory does not reach a preset convergence threshold, integrating the time delay data and the environmental parameters to obtain a corrected state vector; The corrected state vector is optimized in combination with a signal attenuation model to obtain corrected position trajectory data.

[0011] In an optional embodiment, when the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized based on the noise gain matrix to obtain optimized position information, including: Obtaining an initial state vector from sensor data and environmental parameters in the corrected position trajectory data, and performing smoothing processing on the initial state vector to obtain a smoothed state vector; When the smoothed state vector does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source; Correcting the smoothed state vector according to the noise gain matrix and in combination with environmental parameters to obtain a corrected state vector; An error minimization process is performed on the corrected state vector to obtain optimized position information.

[0012] In an optional embodiment, obtaining an initial signal from the multi-dimensional communication data stream and correcting it to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set includes: Acquire an initial signal from a multi-dimensional communication data stream, and perform adaptive processing on the initial signal to obtain a preprocessed signal; When the preprocessed signal is inconsistent with the signal output by the preset prediction equation, calibration is performed according to the preprocessed signal to obtain a calibration signal; Integrating the calibration signal with the optimized position information in combination with current channel parameters to obtain fused data; Channel optimization processing is performed based on the fused data to obtain a stable transmission data set.

[0013] In an optional embodiment, the real-time acquisition of delay data and signal-to-noise ratio data of the stable transmission data set, and when the delay data or the signal-to-noise ratio data exceeds a preset range threshold, optimizing the three-dimensional coordinate solution of the train to obtain optimized position data, includes: acquiring delay data and signal-to-noise ratio data of the stable transmission data set in real time, and when the delay data or the signal-to-noise ratio data exceeds a preset data threshold, performing deviation detection on the stable transmission data set to obtain an abnormal data point; Perform triangulation positioning based on the signal strength and arrival time difference of the abnormal data point to obtain optimized position data; In an optional embodiment, the fusing of the optimized position data and the historical motion state of the train to obtain final accurate communication data includes: Identifying the characteristics of multipath effects and external noise based on the optimized position data, and combining the historical motion state of the train to obtain classified interference data; The time delay data and signal-to-noise ratio data of the optimized location data are optimized, and the classified interference data and the optimized location data are fused to obtain final accurate communication data.

[0014] In a second aspect, the present invention provides a communication data transmission device for a train approach warning intercom, comprising: The data acquisition module is used to collect real-time signals including speed, direction and distance parameters from the train's surrounding environment and obtain the train's historical motion status; A signal analysis module, configured to perform signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; a signal compensation module configured to, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, analyze the noise source identification result using a random forest algorithm to obtain a compensation coefficient, and make adjustments based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset; A coordinate calculation module, configured to perform iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate; A coordinate correction module, configured to perform signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; a coordinate optimization module, configured to calculate a noise gain matrix based on noise sources when the corrected position trajectory data does not match the historical motion state of the train, and optimize the corrected position trajectory data based on the noise gain matrix to obtain optimized position information; a data fusion module, configured to obtain initial signal data from a multi-dimensional communication data stream and perform correction to obtain calibration signal data, and fuse the optimized position information with the calibration signal data to obtain a stable transmission data set; The data output module is used to obtain the delay data and signal-to-noise ratio data of the stable transmission data set in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is then integrated with the historical motion status of the train to obtain the final accurate communication data.

[0015] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the communication data transmission method of the train approach warning intercom described in any one of the above items is implemented.

[0016] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned communication data transmission methods of the train approach warning intercom.

[0017] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention obtains preliminary position data through signal attenuation analysis and noise identification. When the signal strength is insufficient, the random forest algorithm is used to generate a noise compensation coefficient optimization data set. The position trajectory is obtained through three-dimensional coordinate solution and attenuation correction. The trajectory is further optimized through the noise gain matrix, and a stable transmission data set is generated by combining the calibrated multi-dimensional communication signal. The system monitors the transmission quality (delay, signal-to-noise ratio) in real time, re-optimizes the coordinate solution when the limit is exceeded, and finally integrates the historical motion data to output high-precision communication results. This method effectively solves the problem of signal interference in complex environments such as tunnels, mountainous areas or areas with strong electromagnetic interference, resulting in data transmission distortion or signal transmission interruption.

[0018] (2) This invention is based on multi-source signal fusion and intelligent compensation. It uses random forests to handle noise interference, combines iterative three-dimensional coordinate calculation with dynamic noise gain adjustment, and effectively suppresses errors caused by environmental factors. Multiple verifications of historical motion states and real-time data ensure trajectory consistency, and adaptive channel parameter calibration further guarantees data transmission quality. This technically improves the feasibility and reliability of high-speed rail positioning and communication under complex conditions.

[0019] (3) This invention significantly improves the communication stability of trains in strong interference and multi-attenuation environments, effectively overcoming the error accumulation problem caused by weak signals and high noise in traditional methods. Through intelligent noise compensation, multi-source data fusion, and real-time optimization mechanisms, the system can achieve continuous high-precision positioning and reliable data transmission, providing key technical support for train operation safety, dispatching efficiency, and early warning response, and has important engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 1. It is a flow chart of a communication data transmission method of a train approach warning intercom provided by a first embodiment of the present invention; Figure 2 It is a structural diagram of a communication data transmission device of a train approach warning intercom provided by a second embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] Reference Figure 1 The first embodiment of the present invention provides a method for transmitting communication data of a train approach warning intercom, comprising the following steps: S11, collects real-time signals including speed, direction, and distance parameters from the train's surrounding environment, and obtains the train's historical motion status and multi-dimensional communication data stream; S12, performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; S13, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, analyzing the noise source identification result using a random forest algorithm to obtain a compensation coefficient, and performing an adjustment based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset; S14, performing iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate; S15, performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; S16, when the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized based on the noise gain matrix to obtain optimized position information; S17, obtaining an initial signal from the multi-dimensional communication data stream and performing correction to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set; S18, obtaining the delay data and signal-to-noise ratio data of the stable transmission data set in real time. When the delay data or signal-to-noise ratio data exceeds the preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain the optimized position data, and the optimized position data is integrated with the historical motion state of the train to obtain the final accurate communication data.

[0023] In step S11, real-time signals including speed direction and distance parameters need to be collected from the train's surrounding environment, and the train's historical motion status and multi-dimensional communication data stream need to be obtained.

[0024] It's important to note that in a running train scenario, a sensor network collects real-time data about the train's surroundings, including real-time signals of parameters such as speed, direction, and distance. The sensor network consists of a variety of sensors installed on the train body and along the tracks, such as lidar, accelerometers, and gyroscopes, which measure distance, speed, and direction, respectively.

[0025] The train's historical motion state is the train's historical trajectory and its vector velocity at that point, for example, 21 m / s in the easterly direction. The multi-dimensional communication data stream captures multi-dimensional information about wireless signals from the train's communication module, including signal latency, bandwidth usage, and signal-to-noise ratio.

[0026] In step S12, performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results includes: Performing analog-to-digital conversion on the speed direction and distance parameters in the real-time signal to obtain a first signal data set; Converting the time domain signal in the first signal data set into a frequency domain signal to obtain a frequency-converted signal, and extracting a signal attenuation feature based on the frequency-converted signal to obtain an attenuation feature data set; Separating noise sources according to the attenuation feature data set to obtain a noise separation data set, and determining the type of noise source to obtain a noise source identification result; A Kalman filter fusion operation is performed on the noise separation data set to obtain a preliminary position data set.

[0027] First, the collected real-time signals are digitized using an analog-to-digital converter to generate the first signal data set. Assuming a train is traveling at 80 km / h, the sensor collects data 1000 times per second, generating a digital signal sequence containing speed, azimuth, and obstacle distance. This digital processing ensures high accuracy in subsequent signal analysis, providing a reliable data foundation for train positioning and environmental perception.

[0028] Subsequently, a Fast Fourier Transform (FFT) is used to convert the time-domain signal into a frequency-domain signal to extract signal attenuation characteristics. The time-domain signal may contain complex signals such as train vibration and wind noise. The FFT can identify attenuation characteristics within a specific frequency range, generating an attenuation signature dataset. For example, when a train passes through a tunnel, the signal may experience attenuation in a specific frequency band due to reflection, manifesting as a decrease in signal strength in the 0.5-2 kHz frequency range. This attenuation signature dataset reflects the environmental impact on the signal, such as external factors like tunnel walls and rain or snow. This frequency-domain analysis helps identify patterns of environmental interference, providing a basis for subsequent noise reduction.

[0029] Next, the attenuation feature dataset is subjected to dimensionality reduction to separate the noise signal and determine the noise source category, resulting in noise source identification results. Principal component analysis (PCA) extracts the main components of variation in the data, reducing the high-dimensional signal to a low-dimensional space. The original data may contain 100 feature dimensions. PCA retains the top five principal components, explaining 90% of the signal variation. The noise source may be identified as wind noise, mechanical vibration, or electromagnetic interference. For example, wind noise is characterized by high-frequency random fluctuations, while mechanical vibration is mostly a low-frequency periodic signal. This dimensionality reduction and classification improves data processing efficiency and reduces the impact of noise on positioning accuracy.

[0030] Finally, based on the noise-separated dataset, the Kalman filter algorithm is used to fuse multi-source data, combining speed, direction, and distance parameters to produce a preliminary position dataset. Kalman filtering is then used for prediction and update steps, fusing sensor data to optimize the train's position estimate. Assuming the train's speed at time t is 80 km / h, its heading is 30°, and it is 100 meters away from the obstacle ahead, the Kalman filter integrates historical data with current measurements, correcting for noise-induced deviations and outputting more accurate train position coordinates. This fusion method significantly improves positioning accuracy, especially in complex environments such as tunnels or in strong winds.

[0031] In step S13, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset, including: When the signal strength is lower than a preset signal strength threshold, it is determined that an interference factor exists, and the interference type is determined according to the noise source identification result; Extracting noise source characteristics corresponding to the interference type from a pre-established noise source database to obtain environmental noise characteristics; Using a random forest algorithm to analyze and calculate the environmental noise characteristics to obtain a compensation coefficient; The preliminary position data set is weightedly adjusted according to the compensation coefficient to obtain an adjusted data set.

[0032] First, the signal strength is extracted from the preliminary location data set acquired by the sensor network. Signal strength reflects the communication quality between the sensor and the target object and is typically measured in decibel milliwatts. For example, a train operating in complex terrain might capture a signal strength of -75dBm. Historical data analysis suggests a similar threshold strength of -70dBm. If the signal strength falls below the threshold, interference may be present. This could be electromagnetic interference or physical obstruction. Interference factors are identified by real-time monitoring of signal strength fluctuations and combining them with environmental parameters to determine the type of interference.

[0033] It is worth noting that the preset strength threshold is an empirical value based on a large amount of statistical analysis of historical operating data, and can be dynamically adjusted according to the actual environment and operating conditions; by collecting communication success rate and positioning accuracy data between trains and base stations under different signal-to-noise ratio conditions in typical operating environments (such as plains, tunnels, and mountainous areas), the average minimum signal strength corresponding to the communication success rate being higher than 95% and the positioning error being lower than 1 meter is set as the threshold.

[0034] Subsequently, the database is queried according to the interference type, and the corresponding noise source features are extracted from the pre-established noise source database to obtain the environmental noise features. The pre-established noise source database is a relational database, and its structure includes but is not limited to the interference type (such as electromagnetic interference, wind noise, mechanical vibration), center frequency (Hz), bandwidth (Hz), typical amplitude (mV), typical duration (s) and environmental feature identifiers (such as "inside the tunnel" and "strong wind area"); by deploying test equipment in various typical environments, collecting original noise signals, and extracting feature parameters through Fourier transform, wavelet analysis and other methods, and then labeling and storing them in the database. Assuming that the judgment result points to electromagnetic interference, the extracted feature parameters may include the frequency, amplitude and duration of the interference signal, such as a frequency of 55Hz, an amplitude of 0.2mV, and a duration of 0.1 seconds. These feature parameters serve as input features of the random forest algorithm.

[0035] Next, a random forest algorithm is used to analyze and calculate the characteristic parameters of ambient noise to obtain compensation coefficients. The random forest algorithm constructs a decision tree to perform classification and regression analysis on noise characteristics, outputting compensation coefficients to compensate for the impact of noise on the signal. For example, noise samples from historical train operation data are used as training data. Model hyperparameters, such as the number and depth of trees, are determined through cross-validation and other methods. (For example, the number of decision trees is set to 100, the maximum depth is 10, and the mean squared error (MSE) is used as the splitting criterion.) Historical train motion data of similar types and a training set of pre-built models are collected, preprocessed, and feature-labeled. These data are then sampled to form a training subset for each tree model. At each node split, a subset of noise characteristic parameters, such as frequency, amplitude, and signal-to-noise ratio, are randomly selected as candidate split attributes. The optimal split point is determined by calculating the Gini coefficient or information gain. The complete decision tree is recursively generated until a pre-defined termination condition is met, such as when the number of node samples falls below the tree depth limit. Real-time noise characteristic parameters, with a frequency of 55Hz and an amplitude of 0.2mV, are fed into all constructed decision trees. Each tree outputs a predicted compensation coefficient. For example, if a decision tree, based on different training processes, produces a similar compensation coefficient of 1.1, the outputs of all trees are aggregated and the mean is regressed to obtain a comprehensive compensation coefficient of 1.2. This coefficient reflects the overall attenuation effect of noise on the signal; larger values ​​indicate greater required compensation. The algorithm's advantage lies in its ability to process high-dimensional data and model nonlinear relationships in noise characteristics.

[0036] Finally, the initial position data set is corrected by weighting the input data based on the calculated compensation coefficient, resulting in an adjusted data set. Assume that the original position data is the train coordinates (x=100m, y=200m), and that the signal strength is attenuated by noise, resulting in position deviation. A compensation coefficient of 1.2 is used to weight the coordinates, resulting in the adjusted coordinates (x=120m, y=240m). This adjustment improves the accuracy of the position data by correcting for noise, ensuring the reliability of subsequent navigation or positioning systems.

[0037] In step S14, performing iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate includes: Obtaining base station delay, signal strength, and arrival angle data from the adjusted data set, and performing smoothing on the base station delay, signal strength, and arrival angle data to obtain optimized multi-source data; Iteratively solving the three-dimensional coordinates of the train according to the optimized multi-source data to obtain preliminary three-dimensional coordinates; Extracting characteristic parameters of temperature, humidity, and electromagnetic interference from a pre-established environmental database, and performing multipath fading model correction on the preliminary three-dimensional coordinates to obtain corrected three-dimensional coordinates; When the corrected three-dimensional coordinates meet a preset coordinate convergence threshold, temperature compensation, humidity compensation, and multipath fading correction parameters are integrated to obtain a preliminary position estimate.

[0038] First, the base station latency, signal strength, and angle of arrival data from the adjusted dataset are collected and used for high-precision positioning. Base station latency, signal strength, and angle of arrival are core multi-source data, reflecting signal propagation time, communication quality, and signal direction, respectively. For example, base station latency is measured in nanoseconds (ns) by measuring the signal propagation time from the train to the base station, with a typical value of 200 ns. Signal strength is measured in decibel milliwatts, assuming a value of -65 dBm. Angle of arrival is determined by analyzing the base station antenna array, with a typical value of 30°. This data is collected in real time by a sensor network and provides the foundation for subsequent positioning.

[0039] Subsequently, a Kalman filter is used to smooth the base station delay, signal strength, and angle of arrival data to reduce the impact of noise and generate optimized multi-source data. This process works by fusing historical data with current measurements through prediction and update steps to generate more stable data output. For example, if the signal strength fluctuates significantly during a measurement, the Kalman filter combines the previous measurements and outputs a smoothed signal strength of -66dBm and a delay of 198ns. This smoothing process improves data stability and provides reliable input for subsequent positioning calculations.

[0040] Next, high-precision triangulation is performed based on the optimized multi-source data to calculate the train's three-dimensional coordinates, yielding preliminary 3D coordinates. Initial distance values ​​are calculated using base station delay data (e.g., 200ns, 210ns, and 205ns) through light speed conversion. Signal strength data and angle of arrival measurements are combined. Signal strength data is corrected for non-line-of-sight errors using a path loss model, and angle of arrival measurements provide directional constraints. This geometric positioning equation system is then established, and the least squares method is used to estimate the initial coordinates, resulting in x = 150m, y = 250m, and z = 10m. The theoretical delays / angles between the current coordinates and each base station are calculated and compared with the actual observed values ​​to generate residuals. The coordinates are then adjusted using the Gauss-Newton algorithm to minimize these residuals. Signal strength weighting and angle of arrival confidence factors are simultaneously introduced with each iteration, with weak signal base stations receiving lower weights and narrow beams receiving higher weights. Multiple iterations are performed until the coordinate change converges to a value less than the residuals, ultimately resulting in the optimized 3D coordinates. This method improves initial positioning accuracy through multi-source data fusion.

[0041] The path loss model is built based on multi-source heterogeneous data fusion and machine learning optimization. Data sources include a historical environmental parameter database (temperature, humidity, air pressure, and electromagnetic interference spectrum), multi-base station channel measurement reports (signal strength, delay spread, and multipath amplitude and phase characteristics), and GIS terrain data. The training method uses supervised learning, taking environmental parameters and distance information as input and signal attenuation as a label. A nonlinear mapping relationship is fitted using Gaussian process regression or a neural network. When the input parameters include real-time environmental data (e.g., temperature 25°C, humidity 70%, interference strength 0.2mV / m), distance estimates, and signal frequency, the output is a path loss value or a calibration coefficient (e.g., 1.02). The calculation model integrates physical models (e.g., free-space propagation equations) with data-driven corrections. Dynamically weighting environmental factors (e.g., humidity weighting 0.3, interference weighting 0.5) generates adaptive attenuation, ultimately achieving high-precision calibration (e.g., correcting delay from 2.05ms to 2.09ms).

[0042] Offline pre-training is performed using large-scale historical data (covering actual signal propagation measurements under different seasons, weather, and terrain conditions) to establish a basic attenuation model. Real-time collected environmental parameters are then introduced for online fine-tuning, and a sliding window mechanism is used to update model parameters (such as weighted training using the last 30 minutes of data) to ensure that the model adapts to dynamic environmental changes.

[0043] To mitigate bias in the preliminary coordinates caused by environmental factors such as temperature, humidity, and electromagnetic interference, relevant characteristic parameters are extracted from the environmental database. The preliminary three-dimensional coordinates are then corrected using a multipath fading model to obtain the corrected three-dimensional coordinates. After obtaining the preliminary coordinates, the system collects environmental data in real time (e.g., temperature 25°C, humidity 80%, and 55Hz electromagnetic interference). The system then matches the closest environmental record from the database and extracts the associated parameters. The signal propagation velocity is calibrated using a 0.1% velocity offset corresponding to temperature. A humidity attenuation factor of 1.05 is used to correct path loss in the base station distance calculation. Furthermore, the interference suppression algorithm in the multipath fading model is activated using an electromagnetic interference frequency range of 50-60Hz. Finally, these corrections are substituted into the coordinate solution equations, and the preliminary coordinates are adjusted using weighted least squares. For example, the original coordinates (x = 150m, y = 250m, z = 10m) are corrected to (x = 152m, y = 252m, z = 10.5m), thereby eliminating systematic bias caused by environmental factors.

[0044] The environmental database collects environmental factors for at least one full year and fits the impact of each environmental factor on signal propagation, creating a multidimensional environmental parameter mapping table stored in a structured table format. Each record contains temperature, humidity, electromagnetic interference characteristics (such as center frequency, bandwidth, and intensity threshold), and their corresponding signal propagation correction parameters (such as velocity offset percentage, attenuation coefficient, multipath error weight, and compensation coefficient). For example, at 71% humidity, the speed is 0.99 times the standard speed of light. It should be noted that this mapping relationship is based on industry standard models for atmospheric gas attenuation and refractive index, indicating that under standard atmospheric conditions of 20°C, 71% humidity, and 1013hPa atmospheric pressure, the propagation speed of 2.4GHz radio waves in air is approximately 0.990 to 0.995 times the speed of light. The present invention uses a conservative value of 0.99 for calculations and fine-tunes it using field test data to ensure accuracy.

[0045] Furthermore, the multipath fading model describes the random variations in signal amplitude, phase, and delay that occur as wireless signals propagate through multiple paths (such as reflection, diffraction, and scattering) before reaching the receiver. Its core characteristic is that the superposition of signals caused by multipath propagation can generate constructive or destructive interference, leading to rapid fluctuations in received signal strength (small-scale fading). This model quantifies the environmental impact of signals through parameterization, including delay spread (describing the degree of multipath delay dispersion), coherence bandwidth (the threshold for determining frequency-selective fading), Doppler spread (reflecting the time-varying characteristics of the channel), and the Ricean factor or Rayleigh distribution parameter (distinguishing the presence of a dominant path). A prediction model is established by learning the nonlinear mapping between environmental characteristics and multipath parameters (such as delay spread and Ricean factor) using maximum likelihood estimation or deep learning networks (such as CNN-LSTM hybrid networks). In train positioning correction, the model uses real-time parameters provided by the environmental database (such as humidity attenuation coefficient and interference spectrum) to calculate the power distribution and phase offset of the multipath component, and then estimates the degree of signal distortion. The compensation algorithm is used to reversely correct the measured values ​​of the arrival time (toa) and arrival angle (aoa), ultimately reducing the error impact of the multipath effect on the positioning coordinates.

[0046] Finally, when the corrected coordinates meet the convergence threshold, such as if the deviation from the true position is less than 0.5m, the environmental parameters are integrated using a Bayesian weighted fusion algorithm. A preliminary position estimate is calculated based on the weights for temperature, humidity, and multipath fading. For example, confidence weights are first calculated for each correction source based on the uncertainty of the environmental parameters, such as a weight of 0.4 for temperature, 0.3 for humidity, and 0.3 for multipath fading. The initial weights are assigned based on the inverse of the variance of each environmental factor in historical data and dynamically updated using the real-time error covariance matrix. The temperature-compensated, humidity-corrected, and multipath-corrected coordinates are then multiplied by their corresponding weights and summed to obtain a weighted average coordinate. That is, (x=152, y=252, z=10.5)×0.4+(x=151.5, y=251.8, z=10.2)×0.3+(x=151.7, y=251.2, z=10.1)×0.3=(x=151.8, y=251.5, z=10.3). The covariance matrix is ​​also used to evaluate the correlation between the errors of each correction source, and the weight distribution is dynamically adjusted. For example, because the multipath effect is more pronounced in confined environments such as tunnels, the multipath weight is increased to 0.5, and the other weights are reduced accordingly. The calculation is iterated until the coordinate change is less than the threshold of 0.5m, ensuring that the orbit information is basically consistent. This process continuously integrates scene feature parameters from the environmental database, such as the tunnel reflection delay of 0.02 seconds, and updates the weights using Bayesian probabilistic methods, ultimately achieving high-precision adaptive positioning. This extended solution improves positioning reliability in complex environments and adapts to the needs of diverse scenarios.

[0047] In step S15, performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data includes: Obtaining time delay data and environmental parameters in the preliminary position estimate, and smoothing the time delay data and the environmental parameters to obtain a smoothed state vector; Performing iterative calculation based on the smoothed state vector to obtain a preliminary position trajectory; When the preliminary position trajectory does not reach a preset convergence threshold, integrating the time delay data and the environmental parameters to obtain a corrected state vector; The corrected state vector is optimized in combination with a signal attenuation model to obtain corrected position trajectory data.

[0048] First, multi-source sensors are used to collect delay data and environmental parameters for the preliminary position estimate. Delay data typically refers to the signal propagation time from the train to the base station, measured in nanoseconds, with a typical value of 180 nanoseconds. Environmental parameters include temperature and humidity, such as 20°C and 70% humidity. This data is acquired in real time via the sensor network and provides input for subsequent processing. A Kalman filter is used to smooth the delay data and environmental parameters to reduce noise interference. This method combines historical data with current measurements through prediction and updating to produce a smoothed state vector. Specifically, assuming that the delay data fluctuates between 175 and 185 nanoseconds in a particular measurement, the Kalman filter integrates the previous measurements and outputs a smoothed delay of 182 nanoseconds. Environmental parameters, such as humidity, are adjusted to 71%. This smoothing process improves data reliability.

[0049] Subsequently, the smoothed state vector was combined with an iterative calculation of the signal attenuation model to obtain a preliminary position trajectory. Based on the smoothed delay data of 182ns and the environmental parameter humidity of 71%, using the environmentally calibrated propagation velocity (0.99 times the standard speed of light at 71% humidity), the initial distance value was calculated to be approximately 120m. The model then calculated the free-space path loss and added the additional environmental attenuation, which increased the loss by approximately 3dB at 71% humidity. By comparing the transmit power and receive power with the total loss value, a more accurate actual distance was derived. Finally, combining the corrected distance and signal arrival angle data from multiple base stations, an iterative least squares algorithm was used to solve the train's three-dimensional coordinates (x=140m, y=230m, z=9m) until the residual converged to less than 0.5m.

[0050] The signal attenuation model is constructed based on the fusion analysis of multiple heterogeneous databases. Data sources primarily include an environmental database (continuously collected temperature, humidity, atmospheric pressure, and electromagnetic interference intensity and frequency band data recorded by a spectrometer); multi-base station channel measurement reports (including measured values ​​of signal strength, delay spread, and multipath component amplitude and phase characteristics in different geographical environments); and topographic and building distribution data provided by a high-precision geographic information system (GIS). Model training utilizes machine learning methods such as Gaussian process regression or neural networks. By minimizing a prediction error loss function through an optimization algorithm, the model maps environmental parameters to signal propagation characteristics. Training is terminated by setting a maximum number of iterations (e.g., 1000 rounds) or an early stopping mechanism based on the validation set error (e.g., no decrease after 10 consecutive rounds). The resulting signal attenuation model outputs parameters such as a humidity-signal attenuation coefficient lookup table (e.g., 71% humidity corresponds to an additional attenuation of 3dB), a temperature-propagation velocity correction (e.g., a velocity offset of 0.1% at 25°C), and an integrated electromagnetic interference masking algorithm to suppress noise in specific frequency bands, providing environmental compensation for precise train positioning.

[0051] Next, if the initial position trajectory fails to meet the convergence threshold, for example, if the deviation exceeds 0.6m, further correction is required. The convergence threshold is based on historical trajectory analysis; deviations greater than 0.6m result in coordinate misalignment. The propagation time characteristics of the delay data and the humidity attenuation factor from the environmental parameters are extracted. A humidity of 71% corresponds to an attenuation factor of 1.05. A weighted fusion is used to generate a corrected state vector. The initial distance value of 120m calculated from the delay data is multiplied by the humidity attenuation factor to obtain a corrected distance of 126m. This is combined with the signal arrival angle data to construct a geometric constraint equation system, which is solved iteratively using gradient descent. Each iteration introduces a correction factor for the signal propagation speed caused by environmental parameters. At 71% humidity, the speed is corrected to 0.99 times the speed of light. The coordinate offset is gradually adjusted until the residual converges to less than 0.5m. The final corrected position trajectory (x=142m, y=231m, z=9.2m) is output. This process dynamically compensates for signal propagation errors caused by environmental factors, ensuring that positioning accuracy meets system requirements. The environmental parameter humidity attenuation factor here is derived from the data recorded in the structured table in the environmental database in S14, so it will not be described in detail.

[0052] Finally, the measurement update step combines the signal attenuation model with the corrected state vector to further optimize the position trajectory, resulting in the corrected position trajectory data. During the measurement update phase, the system uses this model in real time to calculate the dynamic attenuation under the current environment (e.g., a sudden change in humidity to 75%). The predicted trajectory is weighted by the Kalman gain and fused with the measured signal strength / delay data to produce the corrected position trajectory (x=141.5m, y=230.8m, z=9.1m), achieving environmentally adaptive high-precision positioning. This approach ensures trajectory continuity and accuracy. The signal attenuation model used here is consistent with the signal attenuation model used in the iteratively smoothed state vector above and is therefore not further described.

[0053] In step S16, when the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized based on the noise gain matrix to obtain optimized position information, including: Obtaining an initial state vector from sensor data and environmental parameters in the corrected position trajectory data, and performing smoothing processing on the initial state vector to obtain a smoothed state vector; When the smoothed state vector does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source; Correcting the smoothed state vector according to the noise gain matrix and in combination with environmental parameters to obtain a corrected state vector; An error minimization process is performed on the corrected state vector to obtain optimized position information.

[0054] First, an initial state vector is obtained from the sensor data and environmental parameters in the corrected position trajectory data. Sensor data typically includes Doppler frequency shift and signal strength, for example, a Doppler frequency shift of 50 Hz and a signal strength of -80 dBm. Environmental parameters may include air pressure and wind speed, for example, an air pressure of 101 kPa and a wind speed of 5 m / s. These data are collected in real time by multi-source sensors on the train to provide input for subsequent processing. The generation of the initial state vector is based on these data, combined with the historical motion trajectory of the train, to preliminarily estimate the position and speed. For example, based on the frequency shift and signal strength, the initial state vector may infer that the train position is x=150 m, y=200 m, and the speed is 20 m / s.

[0055] Data smoothing is then performed based on the initial state vector. Sensor data is preprocessed using weighted averaging or low-pass filtering to produce a smoothed state vector. For example, if the sensor data's signal strength fluctuates between -82dBm and -78dBm, smoothing might produce a stable output of -80.5dBm, and the smoothed speed data would be 19.8m / s. This smoothed state vector improves data stability and lays the foundation for subsequent processing.

[0056] Next, if the smoothed state vector does not match the train's historical state data—for example, if the historical trajectory indicates a speed of 21 m / s but the smoothed value is 19.8 m / s—further correction is required. The Kalman gain matrix, also known as the noise gain matrix, is obtained by multiplying the inverse of the noise source's covariance matrix with the observed noise covariance matrix.

[0057] The noise gain matrix is ​​then used to smooth the state vector correction. For example, if the noise variance is 0.5 m / s², the Kalman gain coefficient is calculated based on this variance. This coefficient determines the weighting of the measured and predicted values. For example, based on historical data analysis, similar measurements are weighted 0.7 and predicted values ​​are weighted 0.3. The smoothed state vector is then integrated with real-time environmental parameters, such as signal strength deviation caused by air pressure changes. The measured value is corrected using a pressure-signal strength mapping, for example, a 0.2 dB signal strength attenuation for every 5 hPa drop in air pressure. The weighted measured value is then superimposed with the weighted predicted value. This is the product of the original measured value, the measured value weight, and the pressure compensation coefficient, and the original predicted value and the predicted value weight, to obtain the corrected state vector. Finally, the coordinate conversion module converts the corrected physical quantities into position coordinates (x = 151 m, y = 201 m) and a velocity value of 20.2 m / s. This process dynamically adjusts for the coupling effects of environmental factors and sensor noise, ensuring that the output more closely reflects the actual train motion.

[0058] Finally, a Kalman filter performs error minimization on the corrected state vector, obtaining the optimized position through recursive prediction and measurement updates. Specifically, based on the corrected state vector (position x=151m, y=201m) and the real-time signal strength measurement of -80.3dBm, the Kalman filter first predicts the current position through state transitions (assuming the system dynamic model is uniform motion, the predicted values ​​remain at x=151m, y=201m) and simultaneously calculates the prediction error covariance. The measurement update phase then converts the signal strength into a distance observation. The path loss is used to convert -80.3dBm into the actual distance (for example, assuming a transmit power of 20dBm corresponds to a distance of 125.2m). The difference is then compared with the predicted position. The predicted position and the observed value are then fused through Kalman gain calculation, ultimately obtaining the optimized state vector (x=150.8m, y=200.9m). The error covariance is then updated. This entire process dynamically balances the reliability of the prediction model with the accuracy of real-time measurements to achieve continuous minimization of position error.

[0059] In one possible implementation, if a train enters a high-noise environment, such as electromagnetic interference in an urban area, the adaptive Kalman filter can incorporate additional environmental parameters, such as an electromagnetic interference intensity of 0.2mV / m, to adjust the gain matrix weights and further optimize the position information. This extended solution improves positioning adaptability in complex environments and ensures trajectory reliability.

[0060] In step S17, obtaining an initial signal from the multi-dimensional communication data stream and performing correction to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set, including: Acquire an initial signal from a multi-dimensional communication data stream, and perform adaptive processing on the initial signal to obtain a preprocessed signal; When the preprocessed signal is inconsistent with the signal output by the preset prediction equation, calibration is performed according to the preprocessed signal to obtain a calibration signal; Integrating the calibration signal with the optimized position information in combination with current channel parameters to obtain fused data; Channel optimization processing is performed based on the fused data to obtain a stable transmission data set.

[0061] First, initial signals are acquired from multi-dimensional communication data streams, using multi-source sensor data collection. For example, the communication module on a train captures multi-dimensional information about wireless signals, including signal latency, bandwidth utilization, and signal-to-noise ratio (SNR). The initial signal might have a latency of 2ms, a bandwidth of 10MHz, and a SNR of 15dB. This data is collected in real time via the communication link between the base station and the train, providing the foundation for subsequent processing. The acquisition process must account for the dynamic changes caused by the high-speed movement of the train to ensure data integrity.

[0062] Subsequently, the initial signal is adaptively preprocessed to obtain a preprocessed signal. Adaptive processing adjusts processing parameters based on the dynamic characteristics of the signal to smooth data fluctuations. Specifically, if the delay data fluctuates between 1.8ms and 2.2ms, a stable 2.05ms output can be achieved through dynamic weighted averaging. If the bandwidth data varies between 9.8MHz and 10.2MHz, it may stabilize at 10MHz after preprocessing. Due to the inconsistent volatility of various types of data, the traditional arithmetic average is not rigorous enough. Therefore, a sliding window variance calculation is used to dynamically smooth the signal strength. This method effectively reduces signal noise, improves data reliability, and lays the foundation for subsequent calibration.

[0063] Next, when the preprocessed signal is inconsistent with the signal output by the preset prediction equation, a calibration is performed based on the path loss calculation to obtain a calibrated signal. The path loss model recalculates compensation based on attenuation factors in signal propagation, such as distance and environmental interference. For example, the prediction equation assumes a delay of 2.1ms, while the preprocessed data is 2.05ms. The deviation may be due to the change in the distance between the train and the base station. The path loss estimation calibration coefficient is 1.02, and the calibrated delay is 2.09ms after adjustment. This calibration ensures that the signal data is more consistent with the actual scenario. The path loss model here is consistent with that in S14, so it will not be repeated.

[0064] The calibration signal and optimized location information are then integrated through data fusion, combined with channel parameters to generate fused data. The data fusion step first calculates a signal compensation factor based on channel parameters, such as a fading coefficient of 0.8 and a multipath delay spread of 0.1ms. This factor compensates for multipath errors in the calibration signal's delay (2.09ms) and performs fading-adaptive adjustments on the bandwidth (10MHz), achieving weighted corrections to the communication parameters. These corrected communication parameters are then spatially aligned and correlated with the optimized location information (x=150.8m, y=200.9m). This ultimately generates fused data that combines precise location coordinates with anti-interference communication characteristics (such as the calibrated delay, bandwidth, and channel compensation coefficient). This fused data improves the correlation between the signal and location information.

[0065] Finally, a Kalman filter is used to optimize latency, bandwidth, and signal-to-noise ratio (SNR) for the fused data, resulting in a stable transmission data set. For example, based on the fused data's latency of 2.09ms and the real-time measurement value of 2.08ms, the Kalman filter optimizes it to 2.085ms through prediction and updates. The SNR is also optimized from 15dB to 15.2dB. This optimization reduces data fluctuations and ensures the stability of the transmitted data set. For example, in high-interference environments such as urban areas, the Kalman filter can introduce additional channel parameters, such as an interference power of 0.1mW, and dynamically adjust the calibration coefficient to further optimize the data. This extended solution improves data processing capabilities in complex scenarios and ensures the reliability of the communication link.

[0066] In step S18, the delay data and signal-to-noise ratio data of the stable transmission data set are acquired in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is then fused with the historical motion state of the train to obtain final accurate communication data, including: acquiring delay data and signal-to-noise ratio data of the stable transmission data set in real time, and when the delay data or the signal-to-noise ratio data exceeds a preset data threshold, performing deviation detection on the stable transmission data set to obtain an abnormal data point; Perform triangulation positioning based on the signal strength and arrival time difference of the abnormal data point to obtain optimized position data; Identifying the characteristics of multipath effects and external noise based on the optimized position data, and combining the historical motion state of the train to obtain classified interference data; The time delay data and signal-to-noise ratio data of the optimized location data are optimized, and the classified interference data and the optimized location data are fused to obtain final accurate communication data.

[0067] First, latency and signal-to-noise ratio data are obtained from a stable transmission dataset. For example, consider a communication system operating on a high-speed train. The dataset contains a latency of 2.1ms and a signal-to-noise ratio of 14.8dB. Preset data thresholds might be set at 2.5ms for latency and 12dB for signal-to-noise ratio. Large errors in latency data, such as those caused by errors in calculated coordinates, often result in deviations. Therefore, these thresholds are often set below these thresholds. For example, if a comparison reveals that the latency data does not exceed the threshold, but the signal-to-noise ratio is lower than expected, deviation detection is triggered. By analyzing historical train status data, signal-to-noise ratio anomalies are identified and anomalous data points are obtained. For example, if the signal-to-noise ratio drops sharply from 15dB to 14.8dB over the past 10 seconds, this is marked as an anomaly. This may be due to signal attenuation caused by the train entering a tunnel. This analysis ensures the precise location of anomalies and provides a basis for subsequent processing.

[0068] Subsequently, triangulation positioning was performed on the anomalous data points, using the signal strength and arrival time difference of the three base stations to calculate the device's position, resulting in optimized location data. The arrival time difference data (0.1μs and 0.15μs) was converted to distance difference using the speed of light, and a set of hyperbolic positioning equations was constructed. Signal strength measurements (-70dBm, -75dBm, and -72dBm) were also incorporated to correct for nonlinear errors. Finally, the least squares method was used to solve the equations to obtain the optimized train position coordinates (x=152.3m, y=198.7m). This optimized location data reflects the train's real-time position in a dynamic environment, improving the accuracy of subsequent data processing.

[0069] Next, the optimized location data and current channel data are used to identify multipath effects and external noise characteristics. The channel data may show a fading coefficient of 0.85 and a multipath-induced delay spread of 0.12ms. Analysis of historical train status data reveals that multipath effects stem from reflections from tall buildings near the train, while external noise may originate from co-channel interference from nearby base stations. Classified interference data is then generated, such as multipath accounting for 60% and noise accounting for 40%. This classification helps accurately identify interference sources and supports optimizing communication quality.

[0070] Finally, data integration is performed to categorize the interference data and optimize the location data. The integration process combines the location coordinates x=152.3m, y=198.7m with the interference data to produce a comprehensive data set. The Kalman filter algorithm further optimizes latency and signal-to-noise ratio, for example, from 2.1ms to 2.08ms and improving the signal-to-noise ratio from 14.8dB to 15.1dB. The optimized, precise communication data ensures the stability of the train communication link, especially in high-interference scenarios such as urban areas. Data integration and filtering effectively improve signal reliability. This approach ensures the efficient operation of the communication system through multi-dimensional data fusion and optimization.

[0071] In summary, the present invention discloses a communication data transmission method for a train approach warning intercom, comprising collecting real-time signals including speed direction and distance parameters from the surrounding environment of the train, and obtaining the historical motion state of the train and a multi-dimensional communication data stream; performing signal attenuation analysis and noise source identification on the real-time signals to obtain a preliminary position data set and a noise source identification result; when the signal strength in the preliminary position data set is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed according to the compensation coefficient and the preliminary position data set to obtain an adjusted data set; performing three-dimensional coordinate iterative solution according to the adjusted data set to obtain a preliminary position estimate; performing signal attenuation correction on the preliminary position estimate, Corrected position trajectory data is obtained; when the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized according to the noise gain matrix to obtain optimized position information; an initial signal is obtained from the multi-dimensional communication data stream and corrected to obtain a calibration signal, and the optimized position information is fused with the calibration signal to obtain a stable transmission data set; delay data and signal-to-noise ratio data of the stable transmission data set are obtained in real time, and when the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data, which is fused according to the optimized position data and the historical motion state of the train to obtain final accurate communication data.

[0072] The present invention uses adaptive data fusion to calibrate channel parameters and path loss models in real time, generating a stable transmission data set including delay, bandwidth and signal-to-noise ratio, ensuring real-time and reliable communication, achieving train positioning accuracy and communication stability in complex environments, and providing key technical support for the safety and efficiency of high-speed rail operations.

[0073] Reference Figure 2 The second embodiment of the present invention provides a communication data transmission device for a train approach warning intercom, comprising: The data acquisition module is used to collect real-time signals including speed, direction and distance parameters from the train's surrounding environment and obtain the train's historical motion status; A signal analysis module, configured to perform signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; a signal compensation module configured to, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, analyze the noise source identification result using a random forest algorithm to obtain a compensation coefficient, and make adjustments based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset; A coordinate calculation module, configured to perform iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate; A coordinate correction module, configured to perform signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; a coordinate optimization module, configured to calculate a noise gain matrix based on noise sources when the corrected position trajectory data does not match the historical motion state of the train, and optimize the corrected position trajectory data based on the noise gain matrix to obtain optimized position information; a data fusion module, configured to obtain initial signal data from a multi-dimensional communication data stream and perform correction to obtain calibration signal data, and fuse the optimized position information with the calibration signal data to obtain a stable transmission data set; The data output module is used to obtain the delay data and signal-to-noise ratio data of the stable transmission data set in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is then integrated with the historical motion status of the train to obtain the final accurate communication data.

[0074] It should be noted that the communication data transmission device for a train approach warning intercom provided in an embodiment of the present invention is used to execute all the process steps of the communication data transmission method for a train approach warning intercom in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0075] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a signal attenuation analysis program. When the processor executes the computer program, the steps of the communication data transmission method of each train approach warning intercom described above are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0076] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0077] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0078] The processor may be a central processing unit (CPU), 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 any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0079] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0080] If the module / unit integrated into the electronic device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic 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 of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0081] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0082] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for transmitting communication data of a train approach warning intercom, characterized in that: include: Collect real-time signals including speed, direction, and distance parameters from the train's surrounding environment, and obtain the train's historical motion status and multi-dimensional communication data streams; performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; When the signal strength in the preliminary location data set is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed based on the compensation coefficient and the preliminary location data set to obtain an adjusted data set; Performing iterative three-dimensional coordinate calculations based on the adjusted data set to obtain a preliminary position estimate; performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; When the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source, and the corrected position trajectory data is optimized based on the noise gain matrix to obtain optimized position information; Acquiring an initial signal from the multi-dimensional communication data stream and performing correction to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set; The delay data and signal-to-noise ratio data of the stable transmission data set are obtained in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is fused with the historical motion state of the train to obtain the final accurate communication data.

2. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: The performing signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results includes: Performing analog-to-digital conversion on the speed direction and distance parameters in the real-time signal to obtain a first signal data set; Converting the time domain signal in the first signal data set into a frequency domain signal to obtain a frequency-converted signal, and extracting a signal attenuation feature based on the frequency-converted signal to obtain an attenuation feature data set; Separating noise sources according to the attenuation feature data set to obtain a noise separation data set, and determining the type of noise source to obtain a noise source identification result; A Kalman filter fusion operation is performed on the noise separation data set to obtain a preliminary position data set.

3. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: When the signal strength in the preliminary location data set is lower than a preset strength threshold, a random forest algorithm is used to analyze the noise source identification result to obtain a compensation coefficient, and an adjustment is performed based on the compensation coefficient and the preliminary location data set to obtain an adjusted data set, including: When the signal strength is lower than a preset signal strength threshold, it is determined that an interference factor exists, and the interference type is determined according to the noise source identification result; Extracting noise source characteristics corresponding to the interference type from a pre-established noise source database to obtain environmental noise characteristics; Using a random forest algorithm to analyze and calculate the environmental noise characteristics to obtain a compensation coefficient; The preliminary position data set is weightedly adjusted according to the compensation coefficient to obtain an adjusted data set.

4. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: The iterative calculation of three-dimensional coordinates based on the adjusted data set to obtain a preliminary position estimate includes: Obtaining base station delay, signal strength, and arrival angle data from the adjusted data set, and performing smoothing on the base station delay, signal strength, and arrival angle data to obtain optimized multi-source data; Iteratively solving the three-dimensional coordinates of the train according to the optimized multi-source data to obtain preliminary three-dimensional coordinates; Extracting characteristic parameters of temperature, humidity, and electromagnetic interference from a pre-established environmental database, and performing multipath fading model correction on the preliminary three-dimensional coordinates to obtain corrected three-dimensional coordinates; When the corrected three-dimensional coordinates meet a preset coordinate convergence threshold, temperature compensation, humidity compensation, and multipath fading correction parameters are integrated to obtain a preliminary position estimate.

5. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: The performing signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data includes: Obtaining time delay data and environmental parameters in the preliminary position estimate, and smoothing the time delay data and the environmental parameters to obtain a smoothed state vector; Performing iterative calculation based on the smoothed state vector to obtain a preliminary position trajectory; When the preliminary position trajectory does not reach a preset convergence threshold, integrating the time delay data and the environmental parameters to obtain a corrected state vector; The corrected state vector is optimized in combination with a signal attenuation model to obtain corrected position trajectory data.

6. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: When the corrected position trajectory data does not match the historical motion state of the train, a noise gain matrix is ​​calculated according to the noise source, and the corrected position trajectory data is optimized according to the noise gain matrix to obtain optimized position information, including: Obtaining an initial state vector from sensor data and environmental parameters in the corrected position trajectory data, and performing smoothing processing on the initial state vector to obtain a smoothed state vector; When the smoothed state vector does not match the historical motion state of the train, a noise gain matrix is ​​calculated based on the noise source; Correcting the smoothed state vector according to the noise gain matrix and in combination with environmental parameters to obtain a corrected state vector; An error minimization process is performed on the corrected state vector to obtain optimized position information.

7. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: The obtaining of an initial signal from the multi-dimensional communication data stream and performing correction to obtain a calibration signal, and fusing the optimized position information with the calibration signal to obtain a stable transmission data set, includes: Acquire an initial signal from a multi-dimensional communication data stream, and perform adaptive processing on the initial signal to obtain a preprocessed signal; When the preprocessed signal is inconsistent with the signal output by the preset prediction equation, calibration is performed according to the preprocessed signal to obtain a calibration signal; Integrating the calibration signal with the optimized position information in combination with current channel parameters to obtain fused data; Channel optimization processing is performed based on the fused data to obtain a stable transmission data set.

8. The communication data transmission method of the train approach warning intercom according to claim 1 is characterized in that: The real-time acquisition of the time delay data and signal-to-noise ratio data of the stable transmission data set, and when the time delay data or the signal-to-noise ratio data exceeds a preset range threshold, optimizing the three-dimensional coordinate solution of the train to obtain optimized position data, includes: acquiring delay data and signal-to-noise ratio data of the stable transmission data set in real time, and when the delay data or the signal-to-noise ratio data exceeds a preset data threshold, performing deviation detection on the stable transmission data set to obtain an abnormal data point; Triangulation positioning is performed based on the signal strength and arrival time difference of the abnormal data points to obtain optimized position data.

9. The communication data transmission method of the train approach warning intercom according to claim 8 is characterized in that: The method of fusing the optimized position data with the historical motion state of the train to obtain final accurate communication data includes: Identifying the characteristics of multipath effects and external noise based on the optimized position data, and combining the historical motion state of the train to obtain classified interference data; The time delay data and signal-to-noise ratio data of the optimized location data are optimized, and the classified interference data and the optimized location data are fused to obtain final accurate communication data.

10. A communication data transmission device for a train approach warning intercom, characterized in that: include: The data acquisition module is used to collect real-time signals including speed, direction and distance parameters from the train's surrounding environment and obtain the train's historical motion status; A signal analysis module, configured to perform signal attenuation analysis and noise source identification on the real-time signal to obtain a preliminary position data set and noise source identification results; a signal compensation module configured to, when the signal strength in the preliminary location dataset is lower than a preset strength threshold, analyze the noise source identification result using a random forest algorithm to obtain a compensation coefficient, and make adjustments based on the compensation coefficient and the preliminary location dataset to obtain an adjusted dataset; A coordinate calculation module, configured to perform iterative three-dimensional coordinate calculation based on the adjusted data set to obtain a preliminary position estimate; A coordinate correction module, configured to perform signal attenuation correction on the preliminary position estimate to obtain corrected position trajectory data; a coordinate optimization module, configured to calculate a noise gain matrix based on noise sources when the corrected position trajectory data does not match the historical motion state of the train, and optimize the corrected position trajectory data based on the noise gain matrix to obtain optimized position information; a data fusion module, configured to obtain initial signal data from a multi-dimensional communication data stream and perform correction to obtain calibration signal data, and fuse the optimized position information with the calibration signal data to obtain a stable transmission data set; The data output module is used to obtain the delay data and signal-to-noise ratio data of the stable transmission data set in real time. When the delay data or the signal-to-noise ratio data exceeds a preset range threshold, the three-dimensional coordinate solution of the train is optimized to obtain optimized position data. The optimized position data is then integrated with the historical motion status of the train to obtain the final accurate communication data.

Images