Rail transit operation and maintenance status data processing method and system based on artificial intelligence

Abstract

The present invention discloses a method and system for processing rail transit operation and maintenance status data based on artificial intelligence, which specifically relates to the field of rail operation and maintenance management technology, and is used to solve the problem that the existing tunnel area of ​​rail transit cannot be discovered in advance. The tunnel area is divided into a complex area and an ordinary area. When the train is in the ordinary area, the delay spread caused by the complex reflection path and the spectrum expansion caused by the dynamic Doppler shift are evaluated by analyzing the high-precision channel impulse response estimation results and the signal time-varying spectrum characteristics, and it is judged whether the signal transmission is normal; in the complex area, it is first judged whether the tunnel curvature and the cross structure cause signal shielding and sudden fading. If there is no shielding, the signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics. Finally, the signal delay diffusion degree and the electromagnetic resonance distortion degree are comprehensively analyzed to evaluate the potential risk of signal transmission.

Description

Technical Field

[0001] The present invention relates to the field of rail operation and maintenance management technology, and more specifically, to a rail transit operation and maintenance status data processing method and system based on artificial intelligence. Background Art

[0002] With the rapid development of rail transit, the speed of trains is constantly increasing, and the safety and reliability of rail transit have become key concerns. In order to ensure the safe operation of trains, real-time operation and maintenance status data transmission and monitoring are essential. However, in underground tunnel environments, due to the closedness and complex structural features of underground tunnels, such as curves and forks, wireless signals are affected by various factors such as reflection and scattering during propagation. These effects will produce multipath effects, that is, signals reach the receiving end through different paths, causing signal superposition and interference. This phenomenon can cause unstable data transmission, increase bit error rate, and affect communication quality.

[0003] At present, the research on wireless signal transmission in underground tunnels is mainly focused on improving the anti-interference ability of communication equipment and optimizing signal modulation methods. However, these methods are often passive responses and cannot detect the potential degree of multipath effects in advance, so it is impossible to take effective preventive and adjustment measures in time.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a rail transit operation and maintenance status data processing method and system based on artificial intelligence to solve the problems raised in the above-mentioned background technology.

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

[0007] The rail transit operation and maintenance status data processing method based on artificial intelligence includes the following steps:

[0008] Divide the tunnel area corresponding to the rail transit route into a complex tunnel area and a common tunnel area;

[0009] When the train is in the ordinary area of ​​the tunnel, the signal delay spread caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the spectrum expansion caused by the dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal;

[0010] Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it is determined whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel;

[0011] When the train is in a complex tunnel area, determine whether the tunnel curvature and cross structure cause signal shielding and sudden fading; if so, issue an alarm signal; otherwise, evaluate the degree of signal distortion caused by electromagnetic resonance by analyzing the high-order statistical characteristics of the signal;

[0012] A comprehensive analysis is conducted on the signal delay diffusion degree caused by complex reflection paths and the signal distortion degree caused by electromagnetic resonance to evaluate the potential risk of signal transmission when the train is in complex areas of the tunnel.

[0013] In a preferred embodiment, the tunnel area corresponding to the rail transit route is divided into a complex tunnel area and a common tunnel area, specifically:

[0014] Collect the train's travel path information, including the curvature and inclination of the track, the location of the crossover switches in the tunnel, and the length and structural shape of the tunnel;

[0015] Use geometric analysis algorithms to analyze the collected route data and extract the geometric information of the track;

[0016] Based on the differences in track geometry and signal transmission characteristics, the tunnel is divided into a complex tunnel area and a common tunnel area; the complex tunnel area includes the curves and branches of the tunnel.

[0017] In a preferred embodiment, by analyzing the high-precision channel impulse response estimation result, the signal delay spread caused by the complex reflection path is evaluated, specifically including:

[0018] Obtain channel impulse response data to capture the transient characteristics of signal propagation;

[0019] The collected impulse response data is preprocessed using an adaptive filtering algorithm to remove environmental noise and random interference;

[0020] The high-resolution delay estimation algorithm is used to extract the delay parameters of the multipath signal from the preprocessed impulse response data:

[0021] Use high-resolution delay estimation algorithms to analyze the multipath components in the signal;

[0022] According to the extracted delay parameters, the delay spread of the channel is calculated to quantify the degree of signal delay spread caused by the complex reflection path:

[0023] The delay spread value is calculated as: Among them, T spread is the delay spread value, P i is the power weight of the ith path, τ i is the delay of the ith path, is the expected value of delay, and N is the number of multipaths.

[0024] In a preferred embodiment, the spectrum expansion degree caused by the dynamic Doppler shift is evaluated by analyzing the time-varying spectrum characteristics of the signal, which specifically includes:

[0025] When the train enters the general area of ​​the tunnel, the raw data of the wireless signal is acquired in real time to capture the time-varying spectrum characteristics of the signal;

[0026] Use short-time Fourier transform to perform time-frequency analysis on the collected original signal to obtain the time-varying spectrum of the signal;

[0027] A high-precision frequency estimation algorithm is used to extract the frequency offset from the time-varying spectrum to obtain the information of dynamic Doppler frequency shift;

[0028] According to the extracted frequency offset, the spectrum expansion value is calculated to quantify the spectrum expansion degree caused by dynamic Doppler frequency shift:

[0029] According to the extracted frequency offset, the spectrum expansion value is calculated using the following formula: Among them, X spread is the spectrum extension value, is the average value of frequency offset, T is the analysis time, Represents the frequency offset at time t.

[0030] In a preferred embodiment, based on the degree of signal delay diffusion caused by the complex reflection path and the degree of spectrum expansion caused by the dynamic Doppler frequency shift, it is judged whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel, specifically:

[0031] The delay extension value T spread With threshold T threshold Compare; the spectrum expansion value X spread With threshold X threshold Make comparisons;

[0032] When T spread ≤T threshold , and X spread ≤X threshold When , it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is normal; otherwise, it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is abnormal.

[0033] In a preferred embodiment, when the train is in a complex tunnel area, determining whether the tunnel curvature and the cross structure cause signal shielding and sudden fading specifically includes:

[0034] When the train enters a complex area in a tunnel, real-time signal strength data is collected to capture changes in the signal in a complex environment:

[0035] The curvature radius and intersection structure position of the tunnel are obtained by using geometric analysis algorithms, and the geometric characteristics of the area where the train is located are determined by combining them with the real-time position data of the train.

[0036] Compare the collected signal strength data with the normal signal range preset by the system to determine whether the signal is blocked or attenuated;

[0037] When a signal strength drop exceeding a preset threshold is detected, the geometric characteristics of the location are recorded to analyze whether the tunnel curvature or cross structure causes signal obstruction.

[0038] In a preferred embodiment, when the tunnel curvature and the cross structure do not cause signal shielding and sudden fading, the degree of signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal, specifically including:

[0039] The cross-spectral density function is used to analyze the original signal and its delayed version, calculate the cross-spectral density of the signal, and extract high-order statistical characteristics;

[0040] Apply high-order statistical analysis algorithms to extract characteristic parameters of signals from the cross-spectral density results and capture the nonlinear distortion characteristics caused by electromagnetic resonance;

[0041] According to the extracted characteristic parameters, the electromagnetic resonance signal distortion index is calculated to evaluate the degree of signal distortion caused by electromagnetic resonance:

[0042] According to the third-order cumulants and fourth-order cumulants extracted from the high-order statistical characteristics, the electromagnetic resonance signal distortion index is calculated, and its expression is: Among them, M EM is the electromagnetic resonance signal distortion index, V is the number of signal frequency components, B 3 (h q ) is the qth frequency component h q The third-order cumulant under 4 (h q ) is the qth frequency component h q The fourth-order cumulant under .

[0043] In a preferred embodiment, the degree of signal delay diffusion caused by the complex reflection path and the degree of signal distortion caused by electromagnetic resonance are comprehensively analyzed to evaluate the potential risk of signal transmission when the train is in a complex area of ​​the tunnel, specifically:

[0044] Normalizing the delay spread value and the electromagnetic resonance signal distortion index, assigning weighting coefficients to the normalized delay spread value and the electromagnetic resonance signal distortion index, respectively, and calculating a complex area signal risk index;

[0045] The signal risk index of complex area is calculated by the preset threshold R corresponding to it. thresh Compare and evaluate the potential risk level of signal transmission when the train is in a complex area of ​​a tunnel:

[0046] If R total >R thresh , it is determined that the potential risk of signal transmission when the train is in a complex area of ​​the tunnel is high; if R total ≤R thresh , it is determined that the potential risk level of signal transmission when the train is in the complex area of ​​the tunnel is normal.

[0047] On the other hand, the present invention provides a rail transit operation and maintenance status data processing system based on artificial intelligence, including a tunnel area division module, a delay spread assessment module, a general area assessment module, a signal shielding judgment module, a signal distortion analysis module and a complex area assessment module;

[0048] Tunnel area division module: divides the tunnel area corresponding to the rail transit route into a complex tunnel area and a common tunnel area. The complex tunnel area includes the curves and branches of the tunnel.

[0049] Delay spread assessment module: When the train is in the ordinary area of ​​the tunnel, the signal delay spread caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the spectrum expansion caused by the dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal;

[0050] Ordinary area assessment module: Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it determines whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel;

[0051] Signal shielding judgment module: When the train is in a complex tunnel area, it determines whether the tunnel curvature and cross structure cause signal shielding and sudden fading;

[0052] Signal distortion analysis module: When the tunnel curvature and cross structure do not cause signal shielding and sudden fading, the signal distortion degree caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal;

[0053] Complex area assessment module: Comprehensively analyzes the degree of signal delay diffusion caused by complex reflection paths and the degree of signal distortion caused by electromagnetic resonance, and assesses the potential risk of signal transmission when the train is in complex areas of the tunnel.

[0054] The technical effects and advantages of the rail transit operation and maintenance status data processing method and system based on artificial intelligence of the present invention are as follows:

[0055] 1. By dividing the tunnel area into complex areas and ordinary areas, and using special analysis methods for different areas, we can accurately evaluate the delay spread caused by complex reflection paths, the spectrum expansion caused by dynamic Doppler frequency shift, and the degree of signal distortion caused by electromagnetic resonance. This will enable us to promptly discover potential problems in signal transmission, take effective measures to reduce the bit error rate, and improve the reliability and stability of data transmission.

[0056] 2. Differentiated analysis strategies are designed for the different characteristics of complex areas (such as bends and forks) and ordinary areas of the tunnel. In ordinary areas, the focus is on evaluating delay spread and spectrum spread; in complex areas, first determine whether there is signal shielding and sudden fading, and then evaluate the signal distortion caused by electromagnetic resonance. This design improves the system's adaptability to different environments and enhances the robustness of signal transmission. By predicting and evaluating the potential risks of signal transmission in advance, operation and maintenance personnel can arrange maintenance and inspection work in a targeted manner to avoid unnecessary waste of resources. Especially in complex areas of tunnels, it is possible to focus on monitoring and maintaining areas where problems may exist, thereby improving the efficiency and effectiveness of operation and maintenance work. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of a rail transit operation and maintenance status data processing method based on artificial intelligence of the present invention;

[0058] Figure 2 It is a structural schematic diagram of the rail transit operation and maintenance status data processing system based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Example 1

[0061] Figure 1 The present invention provides a rail transit operation and maintenance status data processing method based on artificial intelligence, which includes the following steps:

[0062] The tunnel area corresponding to the rail transit route is divided into a complex tunnel area and an ordinary tunnel area. The complex tunnel area includes the curves and branches of the tunnel.

[0063] When the train is in the ordinary area of ​​the tunnel, the degree of signal delay diffusion caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the degree of spectrum expansion caused by dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal.

[0064] Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it is judged whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel.

[0065] When the train is in a complex area of ​​a tunnel, it is determined whether the curvature of the tunnel and the cross structure cause signal shielding and sudden fading; if so, an alarm signal is issued; otherwise, the degree of signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal.

[0066] A comprehensive analysis is conducted on the signal delay diffusion degree caused by complex reflection paths and the signal distortion degree caused by electromagnetic resonance to evaluate the potential risk of signal transmission when the train is in complex areas of the tunnel.

[0067] The tunnel area corresponding to the rail transit route is divided into a complex tunnel area and a common tunnel area, specifically:

[0068] The track detection system installed on the train collects the train's travel path information, which includes the curvature and inclination of the track, the location of the cross switches in the tunnel, the length of the tunnel, and the structural shape of the tunnel.

[0069] The collected route data is analyzed using a geometric analysis algorithm to extract track geometry information, such as track curvature, curve radius, and the distribution of crossing switches.

[0070] The curvature information of the tunnel can be calculated by the change in speed of the train when it is traveling on the curve and the change in the track geometry parameters. Generally speaking, when the curvature radius of the tunnel is lower than a preset threshold (such as 500 meters), the section of track can be classified as a complex area because in this case, the multipath effect is more obvious.

[0071] For the branch track, the branch track location in the tunnel is located through sensor data or based on the Geographic Information System (GIS). When a section of track in the tunnel intersects with other tracks, the location is marked as a complex area of ​​the tunnel.

[0072] Based on the differences in track geometry and signal transmission characteristics, tunnels are divided into complex tunnel areas and ordinary tunnel areas. Complex tunnel areas include the following two types:

[0073] Curve: When the curvature of the track reaches or exceeds the set curvature threshold, this part of the track is divided into a complex tunnel area. Usually, signal reflection, interference and shielding are prone to occur in the curve area.

[0074] Switch: At track intersections or switch locations, these areas are also complex areas due to the multipath propagation of signals and the complexity of the track structure.

[0075] It is worth noting that the complex areas of the tunnel are not limited to the curves and branches of the tunnel. According to the actual situation of the rail transit tunnel, the definition of the complex areas of the tunnel can be increased, which will not be repeated here.

[0076] The parts of the tunnel without curves and turnout structures are defined as normal areas. In these areas, the signal propagation path is relatively stable, with less reflection and interference.

[0077] Among them, for the division of complex areas in the tunnel, a segmentation algorithm based on track geometry data (such as curvature analysis based on Bezier curve fitting) can be used for automatic identification. This algorithm can automatically identify curves based on the actual curvature data of the track and mark their starting and ending points.

[0078] By analyzing the high-precision channel impulse response estimation results, the signal delay spread caused by complex reflection paths is evaluated, including:

[0079] When the train enters the general area of ​​the tunnel, the high-precision channel impulse response real-time acquisition device is started to obtain the channel impulse response data to capture the transient characteristics of signal propagation:

[0080] The high-precision channel impulse response real-time acquisition device collects data based on multiple antennas installed around the train and track. Impulse response refers to the response signal received by the receiving end after the signal propagates through multiple paths in the channel.

[0081] The impulse response data is defined as:

[0082] Suppose the transmitter sends a unit impulse signal, and the signal received by the receiver is the convolution y(t)=H(t)*x(t) after the channel, where H(t) represents the channel impulse response; x(t) is the input signal of the transmitter, usually a unit pulse signal, that is, a short pulse transmitted at t=0; y(t) is the signal received by the receiver after multipath propagation, usually manifested as the superposition of several delayed signals; by analyzing y(t), the multipath effect of the channel is estimated, and the multipath delay information is extracted.

[0083] By collecting the impulse response data of the channel in real time, the transient characteristics of the signal propagation can be captured, including the multipath characteristics of the signal reaching the receiving end.

[0084] The collected impulse response data is preprocessed using an adaptive filtering algorithm to remove environmental noise and random interference:

[0085] The collected channel impulse response data may contain random interference caused by environmental noise, equipment errors, etc. In order to improve the accuracy of the data, the collected data needs to be preprocessed.

[0086] Adaptive filtering is used to reduce the noise of data. The adaptive filter automatically adjusts its coefficients according to the changes in the input signal to remove noise while retaining useful signal components.

[0087] The high-resolution delay estimation algorithm is used to extract the delay parameters of the multipath signal from the preprocessed impulse response data:

[0088] Use high-resolution delay estimation algorithms, such as the MUSIC algorithm (Multiple Signal Classification) or the ESPRlT algorithm (Estimation of Signal Parameters via Rotational Invariance Techniques), to analyze the multipath components in the signal.

[0089] Among them, the MUSIC algorithm can separate the delay components of different path signals from the noise by constructing the covariance matrix of the signal and using eigenvalue decomposition. The specific formula is as follows: Among them, R is the covariance matrix of the impulse response data signal after filtering, y filtered (t) is the impulse response data signal after filtering, E[·] represents the expected value, is the conjugate transpose of the impulse response data signal after filtering, and t is the time variable.

[0090] Perform eigenvalue decomposition on R, extract the signal subspace and noise subspace, and further obtain the multipath delay parameter τ i , where τ i It represents the delay of the path, and i is the number of the path.

[0091] Delay parameter τ i It represents the time difference of the signal from the transmitter to the receiver through different reflection paths. i It corresponds to a reflection path and reflects the propagation characteristics of the path.

[0092] According to the extracted delay parameters, the delay spread of the channel is calculated to quantify the degree of signal delay spread caused by the complex reflection path:

[0093] The delay spread value is a statistical characteristic of the channel multipath delay, which is used to describe the delay difference of the signal between different paths. Its calculation formula is: Among them, T spread is the delay spread value; P i is the power weight of the i-th path, indicating the relative strength of the signal on this path; τ i is the delay of the ith path; is the expected value of delay, that is, the weighted average of all path delays; N is the number of multipaths.

[0094] The larger the delay spread value, the greater the delay difference between different paths, the more serious the delay spread of the signal at the receiving end, and the higher the possibility of inter-symbol interference; when the delay spread value exceeds a certain threshold, inter-symbol interference (ISI) will seriously affect the quality of data transmission.

[0095] By analyzing the time-varying spectrum characteristics of the signal, the degree of spectrum expansion caused by dynamic Doppler frequency shift is evaluated, including:

[0096] When the train enters the general area of ​​the tunnel, the raw data of the wireless signal is acquired in real time to capture the time-varying spectrum characteristics of the signal:

[0097] When the train enters the general area of ​​the tunnel, the wireless signal near the train is acquired in real time. The collected signal is expressed in time u(t). Due to the high-speed movement of the train, the signal v(t) at the receiving end is affected by the Doppler effect and is expressed as: Among them, u(t) is the original signal sent by the transmitter, v(t) is the signal from the receiver, and d f It represents the frequency offset caused by the Doppler effect, and j is an imaginary unit.

[0098] The received signal v(t) is recorded through the signal acquisition device.

[0099] Use short-time Fourier transform to perform time-frequency analysis on the collected original signal to obtain the time-varying spectrum of the signal:

[0100] In order to evaluate the impact of dynamic Doppler frequency shift, it is necessary to perform time-frequency analysis on the acquired signal v(t). Short-Time Fourier Transform (STFT) is used to analyze the spectral changes of the signal at different time points.

[0101] The formula for short-time Fourier transform is: Among them, STFT {v(t)}(t, f) represents the spectral distribution of the signal at time t and frequency f; v(λ) is the received signal; z(λ-t) is the window function used to segment the signal; f represents the frequency, and λ is the integral variable.

[0102] Through STFT, the time-varying spectrum of the signal is obtained, showing the frequency distribution of the signal at different times.

[0103] A high-precision frequency estimation algorithm is used to extract the frequency offset from the time-varying spectrum to obtain the dynamic Doppler frequency shift information:

[0104] The frequency offset caused by the dynamic Doppler shift is extracted from the time-varying spectrum. To this end, a high-precision frequency estimation algorithm is used, such as the X-Peak algorithm, which accurately estimates the frequency offset by extracting peaks on the time-frequency plane.

[0105] The frequency offset estimation formula is as follows: in, Represents the frequency offset at time t; through the frequency offset estimation formula, the frequency offset at different times is extracted The frequency offset is used in subsequent spectrum expansion calculations.

[0106] According to the extracted frequency offset, the spectrum expansion value is calculated to quantify the spectrum expansion degree caused by dynamic Doppler frequency shift:

[0107] According to the extracted frequency offset The spectral spread value is calculated to quantify the extent of the spectrum spread caused by the Doppler effect.

[0108] The calculation formula of the spectrum extension value is: Among them, X spread is the spectrum extension value, is the average value of frequency offset, and T is the analysis time.

[0109] The spectrum expansion value reflects the influence range of dynamic Doppler frequency shift on the signal spectrum. The larger the spectrum expansion value, the greater the spectrum expansion caused by dynamic Doppler frequency shift, the larger the range of frequency offset change, and the lower the signal transmission stability.

[0110] Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it is judged whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel. Specifically:

[0111] The delay spread value T calculated by spread The threshold T threshold For comparison:

[0112] If T spread >T threshold, it indicates that the delay spread caused by the complex reflection path is serious and the degree of inter-symbol interference is high, and the system issues a warning signal; at this time, the interference can be reduced by adjusting the transmission power, changing the signal modulation method, etc. At the same time, the operation and maintenance system will record the analysis results and notify the operation and maintenance personnel so that further safety measures can be taken.

[0113] If T spread ≤T threshold , the signal delay spread is within an acceptable range and data transmission can maintain high reliability.

[0114] T threshold The setting is based on the physical characteristics of the channel and the system's bit error rate tolerance. It is usually determined by analyzing historical data and measuring the multipath propagation characteristics of different areas in the rail transit system to determine the maximum acceptable value of signal delay spread. In the specific setting process, the train speed, the complexity of the tunnel environment, and the modulation method of the communication system must also be considered. For scenarios where the impact of inter-symbol interference is significant, the threshold can be set lower to ensure that the signal quality remains within a controllable range.

[0115] The calculated spectrum extension value X spread With the preset threshold X threshold For comparison:

[0116] If X spread >X threshold , it indicates that the dynamic Doppler effect has a significant impact on signal transmission and the spectrum is severely expanded, which may lead to unstable signal transmission. The operation and maintenance system will issue a warning and take necessary measures, such as adjusting the signal modulation method or transmission power.

[0117] If X spread ≤X threshold , the spectrum expansion is within a controllable range and the quality of signal transmission is relatively stable.

[0118] X threshold The setting depends on the model of train speed and dynamic Doppler shift, combined with the frequency tolerance range of the communication system. By simulating and analyzing the frequency offset caused by Doppler shift, the maximum allowable range of spectrum expansion is determined to ensure that the signal will not cause excessive spectrum expansion due to frequency shift. At the same time, the threshold should match the modulation mode and signal bandwidth of the communication system to ensure that the system can maintain stable data transmission at different train speeds.

[0119] When T spread ≤T threshold , and X spread ≤X threshold When , it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is normal; otherwise, it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is abnormal.

[0120] Based on two key parameters, delay spread caused by complex reflection paths and spectrum spread caused by dynamic Doppler frequency shift, the rationality lies in that it evaluates the time domain and frequency domain effects during signal transmission respectively. Delay spread reflects the impact of multipath propagation on inter-symbol interference, while spectrum spread evaluates the interference of the Doppler effect on signal frequency stability when the train moves at high speed. By combining two independent but related factors to judge the stability of signal transmission, this dual evaluation mechanism not only improves the accuracy of judgment, but also enhances the flexibility of the system to cope with complex environmental changes, enabling the system to adaptively optimize signal quality instead of passively responding to interference.

[0121] When the train is in a complex tunnel area, determine whether the tunnel curvature and cross structure cause signal shielding and sudden fading, including:

[0122] When the train enters a complex area in a tunnel, real-time signal strength data is collected to capture changes in the signal in a complex environment:

[0123] When the train enters a complex area in a tunnel, the signal strength monitoring device on the train is activated to collect real-time data on the strength of the wireless signal. The monitoring device consists of multiple antennas and can capture changes in the strength of the wireless signal at different times and locations.

[0124] In order to ensure sensitive capture of signal changes, the system sets the acquisition frequency to multiple times per second (for example, 10 times per second) to ensure that the train can capture rapidly changing signal strength during high-speed movement.

[0125] The curvature radius and intersection structure position of the tunnel are obtained by using the geometric analysis algorithm. By combining it with the real-time position data of the train, the geometric characteristics of the area where the train is located are determined:

[0126] The real-time position data of the train in the tunnel is obtained through the location information collection system installed on the train (such as GPS or track sensors). At the same time, the system uses the geometric information of the track infrastructure to obtain the curvature radius and the location of the cross structure of the tunnel.

[0127] The curvature of the tunnel is calculated using a geometric analysis algorithm, and the radius of curvature is defined as the radius of the tunnel curve; generally, the sharper the curve of the tunnel, the smaller the radius of curvature.

[0128] The location of crossing structures (such as switches and junctions) is based on the pre-set track geometry data and the real-time position of the train. By combining the current position of the train with the track geometry information, it can be determined whether the train is near the crossing structure.

[0129] Compare the collected signal strength data with the normal signal range preset by the system to determine whether the signal is blocked or attenuated:

[0130] Compare the collected real-time signal strength data with the normal signal range preset in the system to determine whether the signal is blocked or suddenly faded. The normal signal range is obtained based on the historical data of signal strength during normal operation of rail transit, and is usually set according to the normal operation of trains in different tunnel areas.

[0131] If the real-time signal strength is less than the preset minimum threshold of the signal strength, it is considered that the signal strength has dropped beyond the normal range, and signal shielding or fading has occurred;

[0132] The preset minimum threshold of the signal strength represents the lowest acceptable value of the signal under normal circumstances.

[0133] For example, a normal signal strength may be between -70dBm and -40dBm. When the signal strength is lower than -70dBm, the system will determine that the signal is in a shielding or fading state.

[0134] When the signal strength drops beyond the preset threshold, the geometric characteristics of the location are recorded to analyze whether the tunnel curvature or cross structure causes signal obstruction:

[0135] When the real-time signal strength is less than the preset minimum threshold of signal strength, the specific position of the train and the corresponding tunnel geometry are recorded, including the tunnel curvature radius and the intersection structure location data at that location. Subsequently, the system analyzes whether the drop in signal strength is related to the geometry of the tunnel.

[0136] If the curvature radius of the tunnel the train is currently in is small (i.e. the tunnel curve is sharp), the multipath reflection effect is enhanced and the signal may experience significant attenuation. The size of the curvature radius is used to determine whether the signal attenuation is caused by the curve.

[0137] If the train is near a crossing structure, signal degradation may also increase significantly as the signal may be reflected or blocked by surrounding metal structures. The system will analyze whether the drop in signal strength is correlated with the location of the crossing structure.

[0138] If the signal strength decreases while the train is in an area with a small curvature radius or dense cross structures, it is determined that the signal shielding or fading is caused by the tunnel curvature or cross structures, that is, the tunnel curvature and cross structures cause signal shielding and sudden fading. Based on the analysis results, if it is confirmed that the signal shielding is caused by the tunnel curvature or cross structures, the system will issue a warning signal and notify the operation and maintenance personnel to take corresponding measures.

[0139] When the tunnel curvature and cross structure do not cause signal shielding and sudden fading, the degree of signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal, including:

[0140] The cross-spectral density function is used to analyze the original signal and its delayed version, calculate the cross-spectral density of the signal, and extract high-order statistical characteristics:

[0141] The wireless signal P(t) around the train is acquired in real time. The wireless signal around the train contains all signal characteristics that may be affected by electromagnetic resonance during high-speed movement of the train.

[0142] In order to ensure the accuracy of signal analysis, the collected P(t) needs to be preprocessed. An adaptive filtering algorithm is used to remove environmental noise and interference to extract effective signal components and obtain the processed signal Q(t).

[0143] Cross-spectral density analysis is a tool used to reveal frequency-domain correlations between two signals (or different versions of the same signal) and is able to capture higher-order nonlinear features induced by electromagnetic resonances.

[0144] Based on the preprocessed signal, the cross-spectral density function (CSD) is applied to analyze the original signal Q(t) and its delayed version Q(t+δ) to calculate the cross-spectral density of the signal.

[0145] Among them, Q(t+δ) is the signal after Q(t) is delayed by δ time, which is used to capture the changes of the signal at different times. This delay is used to analyze the correlation between the signals at different time points through the cross-spectral density, thereby identifying the impact of electromagnetic resonance on the signal.

[0146] The calculation formula of cross-spectral density is as follows: C PQ (h) = E{Q(t)·R * (t+δ)}; where C PQ (h) is the cross-spectral density of the original signal Q(t) and the delayed signal R(t) at frequency h; R * (t+δ) is the complex conjugate form of the delayed signal R(t), and δ is the time delay; h is the frequency variable, representing each frequency component in the spectrum.

[0147] It is possible to obtain the cross-spectral density diagram of the signal at different frequencies, revealing the nonlinear characteristics in the signal spectrum, especially the signal distortion characteristics under the influence of electromagnetic resonance.

[0148] Apply high-order statistical analysis algorithms to extract characteristic parameters of the signal from the cross-spectral density results and capture the nonlinear distortion characteristics caused by electromagnetic resonance:

[0149] The cross-spectral density C is calculated using the Higher-Order Statistics (HOS) algorithm. PQ(h) Further processing is performed to extract the high-order nonlinear characteristics caused by electromagnetic resonance. Conventional linear analysis methods are difficult to capture the complex signal characteristics caused by electromagnetic resonance, so high-order statistics such as third-order cumulants and fourth-order cumulants are needed to identify nonlinear distortion in the signal.

[0150] The calculation formula of the third-order cumulant is: 3 (h 1 ,h 2 )=E{Q(h 1 )·Q(h 2 )·Q * (h 1 +h 2 )}; Among them, B 3 (h 1 ,h 2 ) is the signal at frequency h 1 and h 2 The third-order cumulant under 1 ) is the signal at frequency h 1 The spectrum below shows that Q(h 2 ) is the signal at frequency h 2 The spectrum below shows that Q * (h 1 +h 2 ) is the signal at frequency h 1 +h 2 The complex conjugate spectrum of .

[0151] The calculation formula of the fourth-order cumulant is: 4 (h 1 ,h 2 ,h 3 )=E{Q(h 1 )·Q(h 2 )·Q * (h 3 )·Q * (h 1 +h 2 -h 3 )}; Among them, B 4 (h 1 ,h 2 ,h 3 ) is the signal at frequency h 1 、h 2 and h 3 The fourth-order cumulant under .

[0152] High-order cumulants are used to detect nonlinear distortion of signals caused by electromagnetic resonance. Usually, electromagnetic resonance causes the third-order and fourth-order cumulants of the signal to deviate significantly from the normal distribution, showing significant nonlinear characteristics.

[0153] According to the extracted characteristic parameters, the electromagnetic resonance signal distortion index is calculated to evaluate the degree of signal distortion caused by electromagnetic resonance:

[0154] According to the third-order cumulants and fourth-order cumulants extracted from the high-order statistical characteristics, the electromagnetic resonance signal distortion index is further calculated to quantify the degree of signal distortion. The electromagnetic resonance signal distortion index is calculated to represent the overall impact of electromagnetic resonance on the signal, and its expression is: Among them, M EM is the electromagnetic resonance signal distortion index, V is the number of signal frequency components, B 3 (h q ) is the qth frequency component h q The third-order cumulant under 4 (h q ) is the qth frequency component h q The fourth-order cumulant under .

[0155] The larger the electromagnetic resonance signal distortion index is, the more significant the impact of electromagnetic resonance on the signal is, and the higher the degree of signal distortion caused by electromagnetic resonance is.

[0156] The signal delay diffusion degree caused by the complex reflection path and the signal distortion degree caused by the electromagnetic resonance are comprehensively analyzed to evaluate the potential risk of signal transmission when the train is in the complex area of ​​the tunnel. Specifically:

[0157] In order to accurately assess the potential risk of signal transmission when the train is in a complex area of ​​the tunnel, the signal delay spread caused by the complex reflection path and the signal distortion caused by the electromagnetic resonance are comprehensively analyzed. The specific method is to perform a weighted summation of the delay spread value and the electromagnetic resonance signal distortion index, specifically:

[0158] The delay spread value and the electromagnetic resonance signal distortion index are normalized, and the normalized delay spread value and the electromagnetic resonance signal distortion index are respectively assigned weighting coefficients to calculate the complex area signal risk index, which is expressed as: R total =α·T spread +β·M EM ; Among them, R total is the signal risk index of complex areas, α and β are the weight coefficients of the delay spread value and the electromagnetic resonance signal distortion index, respectively, and both α and β are greater than 0.

[0159] The weighting coefficients α and β are set based on the system's sensitivity to delay spread and electromagnetic resonance. Specifically:

[0160] If the system is more sensitive to the impact of delay spread, the value of α should be appropriately increased to increase the weight of delay spread in the comprehensive risk assessment.

[0161] If the system operates in an environment with severe electromagnetic resonance effects, β should be higher to ensure that the proportion of distortion effects is appropriately reflected in the comprehensive evaluation.

[0162] The specific value of the weighting coefficient can be determined by statistical analysis and simulation of historical data. For example, based on the results of actual tests, if the inter-symbol interference has a more significant effect than the electromagnetic resonance in the system, α=0.7 and β=0.3 can be set.

[0163] The greater the complex area signal risk index, the greater the potential risk of signal transmission when the train is in the complex area of ​​the tunnel.

[0164] The signal risk index of complex area is calculated by the preset threshold R corresponding to it. thresh A comparison was made to assess the potential risk level of signal transmission when the train is in complex areas of the tunnel.

[0165] If R total >R thresh , it is determined that the potential risk of signal transmission when the train is in a complex area of ​​the tunnel is high, indicating that there is a high potential risk of signal transmission. The system will issue an early warning and recommend intervention measures, such as adjusting the transmission power and signal modulation method, etc. Specifically:

[0166] First, the system automatically adjusts the transmission power and increases the signal strength to offset the signal attenuation caused by complex reflection paths or electromagnetic resonance. At the same time, the signal modulation method is adjusted, such as switching to a more interference-resistant modulation technology to reduce the impact of inter-symbol interference. Secondly, the operation and maintenance system will trigger an alarm to notify the relevant operation and maintenance personnel to conduct on-site inspections and maintenance in a timely manner to ensure the normal operation of the equipment. In addition, the current environmental parameters and signal quality data are recorded for subsequent analysis and formulation of optimization strategies to ensure the stability and reliability of signal transmission in complex environments.

[0167] If R total ≤R thresh , it is determined that the potential risk level of signal transmission when the train is in the complex area of ​​the tunnel is normal, the signal transmission quality is normal, and no additional intervention is required.

[0168] R thresh The setting is based on historical data analysis and experimental results, taking into account the signal transmission stability and reliability of the system under actual operating conditions. By statistically analyzing the signal transmission performance under different environmental conditions, the maximum acceptable risk level is determined. At the same time, in combination with industry standards and safety regulations, a reasonable threshold is set to ensure timely response when signal quality deteriorates, thereby ensuring the safety and stability of train operation.

[0169] Example 2

[0170] The difference between Example 2 of the present invention and Example 1 is that this example introduces a rail transit operation and maintenance status data processing system based on artificial intelligence.

[0171] Figure 2 A structural schematic diagram of the rail transit operation and maintenance status data processing system based on artificial intelligence of the present invention is given. The rail transit operation and maintenance status data processing system based on artificial intelligence includes a tunnel area division module, a delay spread evaluation module, a common area evaluation module, a signal shielding judgment module, a signal distortion analysis module and a complex area evaluation module.

[0172] Tunnel area division module: The tunnel area corresponding to the rail transit route is divided into a complex tunnel area and a common tunnel area. The complex tunnel area includes the curves and branches of the tunnel.

[0173] Delay spread assessment module: When the train is in the ordinary area of ​​the tunnel, the signal delay spread caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the spectrum expansion caused by the dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal.

[0174] Ordinary area assessment module: Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it determines whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel.

[0175] Signal shielding judgment module: When the train is in a complex area of ​​a tunnel, it determines whether the curvature of the tunnel and the cross structure cause signal shielding and sudden fading.

[0176] Signal distortion analysis module: When the tunnel curvature and cross structure do not cause signal shielding and sudden fading, the degree of signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal.

[0177] Complex area assessment module: Comprehensively analyzes the degree of signal delay diffusion caused by complex reflection paths and the degree of signal distortion caused by electromagnetic resonance, and assesses the potential risk of signal transmission when the train is in complex areas of the tunnel.

[0178] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0179] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0180] Those of ordinary skill in the art will appreciate that the modules 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 this application.

[0181] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0182] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0183] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0185] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0187] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rail transit operation and maintenance status data processing method based on artificial intelligence, characterized in that: The steps include: Divide the tunnel area corresponding to the rail transit route into a complex tunnel area and a common tunnel area; When the train is in the ordinary area of ​​the tunnel, the signal delay spread caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the spectrum expansion caused by the dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal; Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it is determined whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel; When the train is in a complex tunnel area, determine whether the tunnel curvature and cross structures cause signal shielding and sudden fading; If so, an alarm signal is issued; Otherwise, the degree of signal distortion caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal, including: The cross-spectral density function is used to analyze the original signal and its delayed version, calculate the cross-spectral density of the signal, and extract high-order statistical characteristics; Apply high-order statistical analysis algorithms to extract characteristic parameters of signals from the cross-spectral density results and capture the nonlinear distortion characteristics caused by electromagnetic resonance; According to the extracted characteristic parameters, the electromagnetic resonance signal distortion index is calculated to evaluate the degree of signal distortion caused by electromagnetic resonance: According to the third-order cumulants and fourth-order cumulants extracted from the high-order statistical characteristics, the electromagnetic resonance signal distortion index is calculated, and its expression is: Among them, M EM is the electromagnetic resonance signal distortion index, V is the number of signal frequency components, B3(h q ) is the qth frequency component h q The third-order cumulant under q ) is the qth frequency component h q The fourth-order cumulants under ; The signal delay diffusion degree caused by the complex reflection path and the signal distortion degree caused by the electromagnetic resonance are comprehensively analyzed to evaluate the potential risk of signal transmission when the train is in the complex area of ​​the tunnel. Specifically: Normalizing the delay spread value and the electromagnetic resonance signal distortion index, assigning weighting coefficients to the normalized delay spread value and the electromagnetic resonance signal distortion index, respectively, and calculating a complex area signal risk index; The signal risk index of complex area is calculated by the preset threshold R corresponding to it. thresh Compare and evaluate the potential risk level of signal transmission when the train is in a complex area of ​​a tunnel: If R total >R thresh , it is determined that the potential risk of signal transmission when the train is in a complex area of ​​the tunnel is high; if R total ≤R thresh , then it is determined that the potential risk level of signal transmission when the train is in the complex area of ​​the tunnel is normal; Among them, R total It is the signal risk index of complex areas.

2. The method for processing rail transit operation and maintenance status data based on artificial intelligence according to claim 1 is characterized in that: The tunnel area corresponding to the rail transit route is divided into a complex tunnel area and a common tunnel area, specifically: Collect the train's travel path information, including the curvature and inclination of the track, the location of the crossover switches in the tunnel, and the length and structural shape of the tunnel; Use geometric analysis algorithms to analyze the collected route data and extract the geometric information of the track; Based on the differences in track geometry and signal transmission characteristics, the tunnel is divided into a complex tunnel area and a common tunnel area. Complex areas of tunnels include curves and branches in tunnels.

3. The method for processing rail transit operation and maintenance status data based on artificial intelligence according to claim 2 is characterized in that: By analyzing the high-precision channel impulse response estimation results, the signal delay spread caused by complex reflection paths is evaluated, including: Obtain channel impulse response data to capture the transient characteristics of signal propagation; The collected impulse response data is preprocessed using an adaptive filtering algorithm to remove environmental noise and random interference; The high-resolution delay estimation algorithm is used to extract the delay parameters of the multipath signal from the preprocessed impulse response data: Use high-resolution delay estimation algorithms to analyze the multipath components in the signal; According to the extracted delay parameters, the delay spread of the channel is calculated to quantify the degree of signal delay spread caused by the complex reflection path: The delay spread value is calculated as: Among them, T spread is the delay spread value, P i is the power weight of the ith path, τ i is the delay of the ith path, is the expected value of delay, and N is the number of multipaths.

4. The method for processing rail transit operation and maintenance status data based on artificial intelligence according to claim 3 is characterized in that: By analyzing the time-varying spectrum characteristics of the signal, the degree of spectrum expansion caused by dynamic Doppler frequency shift is evaluated, including: When the train enters the general area of ​​the tunnel, the raw data of the wireless signal is acquired in real time to capture the time-varying spectrum characteristics of the signal; Use short-time Fourier transform to perform time-frequency analysis on the collected original signal to obtain the time-varying spectrum of the signal; A high-precision frequency estimation algorithm is used to extract the frequency offset from the time-varying spectrum to obtain the information of dynamic Doppler frequency shift; According to the extracted frequency offset, the spectrum expansion value is calculated to quantify the spectrum expansion degree caused by dynamic Doppler frequency shift: According to the extracted frequency offset, the spectrum expansion value is calculated using the following formula: Among them, X spread is the spectrum extension value, is the average value of frequency offset, T is the analysis time, Represents the frequency offset at time t.

5. The method for processing rail transit operation and maintenance status data based on artificial intelligence according to claim 4 is characterized in that: Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it is judged whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel. Specifically: The delay extension value T spread With threshold T threshold Compare; the spectrum expansion value X spread With threshold X threshold Make comparisons; When T spread ≤T threshold , and X spread ≤X threshold When , it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is normal; Otherwise, it is determined that the signal transmission when the train is in the ordinary area of ​​the tunnel is abnormal.

6. The method for processing rail transit operation and maintenance status data based on artificial intelligence according to claim 5 is characterized in that: When the train is in a complex tunnel area, determine whether the tunnel curvature and cross structure cause signal shielding and sudden fading, including: When the train enters a complex area in a tunnel, it collects signal strength data in real time to capture changes in the signal in a complex environment; The curvature radius and intersection structure position of the tunnel are obtained by using geometric analysis algorithms, and the geometric characteristics of the area where the train is located are determined by combining them with the real-time position data of the train. Compare the collected signal strength data with the normal signal range preset by the system to determine whether the signal is blocked or attenuated; When a signal strength drop exceeding a preset threshold is detected, the geometric characteristics of the location are recorded to analyze whether the tunnel curvature or cross structure causes signal obstruction.

7. A rail transit operation and maintenance status data processing system based on artificial intelligence, used to implement the rail transit operation and maintenance status data processing method based on artificial intelligence according to any one of claims 1 to 6, characterized in that: It includes tunnel area division module, delay spread assessment module, common area assessment module, signal shielding judgment module, signal distortion analysis module and complex area assessment module; Tunnel area division module: divides the tunnel area corresponding to the rail transit route into a complex tunnel area and a common tunnel area. The complex tunnel area includes the curves and branches of the tunnel. Delay spread assessment module: When the train is in the ordinary area of ​​the tunnel, the signal delay spread caused by the complex reflection path is evaluated by analyzing the high-precision channel impulse response estimation results; the spectrum expansion caused by the dynamic Doppler frequency shift is evaluated by analyzing the time-varying spectrum characteristics of the signal; Ordinary area assessment module: Based on the degree of signal delay diffusion caused by complex reflection paths and the degree of spectrum expansion caused by dynamic Doppler frequency shift, it determines whether the signal transmission is normal when the train is in the ordinary area of ​​the tunnel; Signal shielding judgment module: When the train is in a complex tunnel area, it determines whether the tunnel curvature and cross structure cause signal shielding and sudden fading; Signal distortion analysis module: When the tunnel curvature and cross structure do not cause signal shielding and sudden fading, the signal distortion degree caused by electromagnetic resonance is evaluated by analyzing the high-order statistical characteristics of the signal; Complex area assessment module: Comprehensively analyzes the degree of signal delay diffusion caused by complex reflection paths and the degree of signal distortion caused by electromagnetic resonance, and assesses the potential risk of signal transmission when the train is in complex areas of the tunnel.

Images