A method and device for identifying abnormal carrier-to-interference ratio in GSM-R repeaters

Abstract

This invention proposes a method and apparatus for identifying anomalies in the carrier-to-interference ratio (CTR) of GSM-R repeaters, relating to the field of dynamic detection technology for railway wireless communication. The method includes: acquiring handover information data in real time based on dynamic detection of the GSM-R network; extracting the effective service range of the current cell and acquiring repeater distribution information data within the effective service range; extracting the CTR waveform data of the cell; analyzing the local concave features of the CTR waveform to determine the set of concave locations; filtering the set of concave locations to obtain the repeater coverage area; when a repeater exists within the repeater coverage area, smoothing the CTR waveform within the coverage area and extracting the baseline; extracting repeater waveform data with a slope less than a preset slope threshold based on the slope of the baseline to obtain repeater feature data; analyzing statistical distribution characteristics and determining the degree of degradation corresponding to the statistical distribution characteristics according to a preset degradation evaluation standard.

Description

Technical Field

[0001] This invention relates to the field of dynamic detection technology for railway wireless communication, and more particularly to a method and device for identifying abnormal carrier-to-interference ratios in GSM-R repeaters. Background Technology

[0002] This section is intended to provide background or context for embodiments of the present invention. The description herein is not intended to imply that it is prior art simply because it is included in this section.

[0003] As a dedicated channel for wireless data transmission between railway vehicles and the ground, the GSM-R network undertakes services such as train number verification, wireless transmission of dispatching commands, and transmission of train operation control information, playing an irreplaceable role in organizing railway transportation, directing train operations, and facilitating railway business communication. To ensure the normal operation of the GSM-R network, high-speed comprehensive inspection trains and electrical inspection vehicles are currently used to conduct GSM-R tests on high-speed and conventional railways. The tests include wireless signal strength coverage, quality of service, and electromagnetic environment. Based on current communication testing, some GSM-R networks have been found to have problems such as substandard signal strength coverage, handover failures, dropped calls, abnormal handovers, and poor call quality. However, the current GSM-R communication testing system does not yet have the ability to automatically identify abnormal carrier-to-interference ratios in GSM-R repeaters.

[0004] Analysis based on historical testing data shows that as the service life of GSM-R repeaters extends, the number of GSM-R repeaters with deteriorated carrier-to-interference ratios gradually increases. Abnormal carrier-to-interference ratios of GSM-R repeaters will directly lead to a deterioration in the communication quality between high-speed trains and ground command and control centers, greatly increasing the risk of wireless link communication interruption and endangering train operation control, dispatching command, and operational safety.

[0005] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects, detect abnormalities in the carrier-to-interference ratio of GSM-R repeaters as early as possible, and eliminate the impact of abnormalities in the carrier-to-interference ratio of GSM-R repeaters on network operation quality. Summary of the Invention

[0006] To address the problems existing in the prior art, this invention proposes a method and device for identifying abnormal carrier-to-interference ratios in GSM-R repeaters, which can detect and eliminate the impact of abnormal carrier-to-interference ratios in GSM-R repeaters on network operation quality as early as possible.

[0007] In a first aspect of the present invention, a method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater is proposed, the method comprising:

[0008] Based on dynamic detection of the GSM-R network, handover information data is obtained in real time.

[0009] Based on the handover information data and ledger information data, the effective service range of the current cell is extracted, and the distribution information of repeaters within the effective service range of the current cell is obtained;

[0010] Based on the repeater distribution information data, extract the cell carrier-to-interference ratio waveform data;

[0011] Based on the carrier-to-interference ratio waveform data of the cell, analyze the local concave characteristics of the carrier-to-interference ratio waveform to determine the set of concave locations;

[0012] The set of recessed locations is filtered to obtain the coverage area of ​​the repeater.

[0013] When a repeater exists within the coverage area of ​​the repeater, the carrier-to-interference ratio waveform within the coverage area is smoothed and the baseline is extracted;

[0014] The baseline slope curve is determined based on the slope of the baseline, and repeater waveform data with slopes less than a preset slope threshold are extracted based on the baseline slope curve to obtain repeater feature data.

[0015] Based on the statistical distribution characteristics of the repeater feature data, and according to the preset degradation degree evaluation criteria, the degradation degree corresponding to the statistical distribution characteristics is determined.

[0016] In a second aspect of the present invention, a device for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater is provided, the device comprising:

[0017] The dynamic monitoring module is used to dynamically detect and acquire handover information data in real time based on the GSM-R network.

[0018] The effective service range extraction module is used to extract the effective service range of the current cell based on the handover information data and ledger information data, and obtain the repeater distribution information data within the effective service range of the current cell;

[0019] The carrier-to-interference ratio waveform data extraction module is used to extract cell carrier-to-interference ratio waveform data based on the repeater distribution information data.

[0020] The indentation feature analysis module is used to analyze the local indentation features of the carrier-to-interference ratio waveform based on the carrier-to-interference ratio waveform data of the cell, and to determine the set of indentation locations.

[0021] The repeater coverage area determination module is used to filter the set of recessed locations to obtain the repeater coverage area.

[0022] The baseline extraction module is used to perform data smoothing processing on the carrier-to-interference ratio waveform within the coverage area of ​​the repeater and extract the baseline when there is a repeater within the coverage area of ​​the repeater.

[0023] The baseline analysis module is used to determine the baseline slope curve based on the slope of the baseline, and extract repeater waveform data with a slope less than a preset slope threshold based on the baseline slope curve to obtain repeater feature data.

[0024] The degradation judgment module is used to analyze the statistical distribution characteristics of the repeater feature data and determine the degree of degradation corresponding to the statistical distribution characteristics according to the preset degradation degree evaluation standard.

[0025] In a third aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater.

[0026] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for identifying anomalies in the carrier-to-interference ratio of GSM-R repeaters.

[0027] In a fifth aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements a method for identifying anomalies in the carrier-to-interference ratio of GSM-R repeaters.

[0028] This invention proposes a method and device for identifying abnormal carrier-to-interference ratios (CTR) in GSM-R repeaters. Based on GSM-R dynamic detection data, it extracts CTR detection waveform data and extracts key waveform feature parameters according to data characteristics, enabling automatic identification of CTR anomalies in repeaters. This invention significantly improves the efficiency of CTR anomaly identification, laying the foundation for intelligent detection and data analysis. Simultaneously, it effectively distinguishes between early and significant CTR degradation in GSM-R repeaters, providing technical support for GSM-R wireless network maintenance units and facilitating preventative and condition-based maintenance. The overall solution exhibits strong robustness, adaptively eliminating the impact of CTR degradation caused by non-GSM-R equipment performance deterioration on identification accuracy, providing strong technical support for dynamic detection of railway wireless communication. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic flowchart of a method for identifying abnormal carrier-to-interference ratio in GSM-R repeaters according to an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of the GSM-R repeater carrier-to-interference ratio anomaly identification method according to another embodiment of the present invention.

[0032] Figure 3 This is a schematic diagram of the GSM-R repeater carrier-to-interference ratio anomaly identification process according to a specific embodiment of the present invention.

[0033] Figure 4 This is a schematic diagram of the algorithm for extracting concave features based on gray value morphology according to a specific embodiment of the present invention.

[0034] Figure 5 This is a schematic diagram of the baseline extraction process based on the adaptive smoothing asymmetric least squares algorithm according to a specific embodiment of the present invention.

[0035] Figure 6 This is a schematic diagram of the architecture of a GSM-R repeater carrier-to-interference ratio anomaly identification device according to an embodiment of the present invention.

[0036] Figure 7 This is a schematic diagram of the architecture of a GSM-R repeater carrier-to-interference ratio anomaly identification device according to another embodiment of the present invention.

[0037] Figure 8 This is a schematic diagram of a computer device structure according to an embodiment of the present invention. Detailed Implementation

[0038] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0039] Those skilled in the art will recognize that embodiments of the present invention can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0040] According to an embodiment of the present invention, a method and device for identifying abnormal carrier-to-interference ratio of GSM-R repeaters are proposed, which relates to the field of dynamic detection technology for railway wireless communication.

[0041] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0042] Figure 1This is a schematic flowchart of a method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0043] S101, based on dynamic detection of the GSM-R network, acquires handover information data in real time;

[0044] S102, Based on the handover information data and ledger information data, extract the effective service range of the current cell and obtain the repeater distribution information data within the effective service range of the current cell;

[0045] S103, extract the cell carrier-to-interference ratio waveform data based on the repeater distribution information data;

[0046] S104, Based on the carrier-to-interference ratio waveform data of the cell, analyze the local concave features of the carrier-to-interference ratio waveform and determine the set of concave locations;

[0047] S105, Filter the set of recessed locations to obtain the repeater coverage area;

[0048] S106, when there is a repeater within the coverage area of ​​the repeater, perform data smoothing on the carrier-to-interference ratio waveform within the coverage area of ​​the repeater and extract the baseline;

[0049] S107, Determine the baseline slope curve based on the slope of the baseline, and extract repeater waveform data with a slope less than a preset slope threshold based on the baseline slope curve to obtain repeater feature data;

[0050] S108, Analyze the statistical distribution characteristics based on the repeater characteristic data, and determine the degree of degradation corresponding to the statistical distribution characteristics according to the preset degradation degree evaluation standard.

[0051] While the carrier-to-interference ratio (CIR) parameter of a GSM-R cell can be obtained during dynamic detection of GSM-R wireless networks, existing GSM-R communication detection systems lack the ability to automatically identify CIR anomalies in GSM-R repeaters. Anomaly identification relies on manual experience, resulting in low efficiency, inconsistent standards, and numerous false positives and false negatives. Furthermore, GSM-R communication detection systems evaluate CIR based on received wireless signals, providing CIR waveforms that represent measurements at different kilometer markers across the entire GSM-R cell. Since GSM-R repeaters are integral parts of a GSM-R cell, their CIR waveforms do not differentiate between specific repeater regions. Accurately extracting the waveform of a specific GSM-R repeater from the overall GSM-R cell CIR waveform is a key challenge in anomaly identification and forms the basis for successful CIR anomaly identification. Simultaneously, under conditions where CIR is affected by external factors such as interference, accurately extracting regions that directly characterize the equipment based on the GSM-R repeater waveform is also a crucial step in the identification process. Furthermore, the varying service times of different GSM-R repeaters lead to significant differences in the abnormal carrier-to-interference ratio (CRI) waveforms. Specifically, these can be categorized into early degradation and significant degradation, and identifying these two degradation phenomena based on the detected waveforms is a challenge. To address these issues, this invention proposes a method for identifying abnormal CRI in GSM-R repeaters. Based on GSM-R dynamic detection data, the method extracts CRI detection waveform data and extracts key waveform feature parameters according to data characteristics, enabling automatic identification of abnormal CRI in repeaters. This significantly improves the efficiency of CRI anomaly identification, laying the foundation for intelligent detection and data analysis. This invention effectively distinguishes between early and significant CRI degradation in GSM-R repeaters, providing technical support for GSM-R wireless network maintenance units and facilitating preventative and condition-based maintenance. The overall solution exhibits strong robustness, adaptively eliminating the impact of CRI degradation caused by non-GSM-R equipment performance degradation on identification accuracy, providing strong technical support for dynamic detection of railway wireless communication.

[0052] To provide a clearer explanation of the above-mentioned method for identifying anomalies in the carrier-to-interference ratio of GSM-R repeaters, each step will be explained in detail below.

[0053] In one embodiment, S101, based on dynamic detection of the GSM-R network, handover information data is obtained in real time.

[0054] Among them, dynamic detection based on GSM-R network includes: using railway-dedicated inspection vehicles to collect status parameters of railway facilities, including GSM-R network, during train operation. These status parameters are used to assess the service status of the facilities.

[0055] In one embodiment, S102, based on the handover information data and ledger information data, the effective service range of the current cell is extracted, and the distribution information data of repeaters within the effective service range of the current cell is obtained.

[0056] The handover information data includes: the location information from when the test terminal occupies the current cell to when it releases the current cell, and the cell ID information of the current cell.

[0057] The ledger information data consists of GSM-R base station information for railway lines, including: base station name, base station location (mileage, latitude and longitude), base station frequency, and the cell ID information corresponding to the base station.

[0058] The effective service range of the current cell is the mileage range occupied by the test terminal in the current cell where no handover anomaly has occurred. When a handover anomaly occurs, the effective service range of the cell is further determined by combining the base station location information. The main function of S102 is to eliminate the impact of abnormal carrier-to-interference ratio caused by factors other than the repeater equipment itself on the algorithm recognition results, thereby improving the robustness of the recognition algorithm.

[0059] In one embodiment, S103, the cell carrier-to-interference ratio waveform data is extracted based on the repeater distribution information data.

[0060] Specifically, based on the repeater distribution information data, it is determined whether there are repeaters within the effective service range of the current cell;

[0061] If it exists, extract the cell carrier-to-interference ratio waveform data;

[0062] If it does not exist, continue with dynamic detection of the GSM-R network.

[0063] In one embodiment, S104, the local concave features of the carrier-to-interference ratio waveform are analyzed based on the cell carrier-to-interference ratio waveform data to determine the set of concave locations.

[0064] Based on the cell carrier-to-interference ratio waveform data, a gray-value morphological method is used to extract local concave features of the carrier-to-interference ratio waveform and determine the set of concave locations. The processing steps of the gray-value morphological method are as follows: peaks are eliminated and concaves are preserved through opening operations; concaves are filled and peaks are preserved through closing operations; top-hat transformation is performed to extract concaves, and bottom-hat transformation is performed to enhance concave regions in the signal; threshold processing is performed to achieve concave detection, and the concave locations are marked and returned.

[0065] In one embodiment, S105, the set of recessed locations is filtered to obtain the repeater coverage area.

[0066] The set of depression locations is filtered using a binary morphological filtering method to eliminate the interference of carrier-to-interference ratio waveform noise on depression detection, thereby obtaining the repeater coverage area.

[0067] In one embodiment, S106, when there is a repeater within the coverage area of ​​the repeater, the carrier-to-interference ratio waveform within the coverage area of ​​the repeater is subjected to data smoothing processing and the baseline is extracted.

[0068] Based on the coverage area of ​​the repeater, determine whether a repeater exists;

[0069] If present, the carrier-to-interference ratio waveform within the repeater's coverage area is processed using an adaptive smoothing asymmetric least squares algorithm to extract the baseline. The adaptive smoothing asymmetric least squares algorithm is used to process signal data with asymmetric noise, performing data smoothing and baseline extraction. The process involves: initializing the weight matrix as an identity matrix, setting smoothing parameters and a convergence threshold; solving the least squares problem of the smoothed signal through iterative processing, updating the weights based on the residuals, and checking the convergence condition; stopping when the change in the smoothed signal is less than a preset threshold or the maximum number of iterations is reached.

[0070] If it does not exist, continue with dynamic detection of the GSM-R network.

[0071] In one embodiment, S107, a baseline slope curve is determined based on the slope of the baseline, and repeater waveform data with a slope less than a preset slope threshold is extracted based on the baseline slope curve to obtain repeater feature data.

[0072] Specifically, repeater waveform data corresponding to slopes within a preset range (less than a preset slope threshold) are extracted to obtain repeater feature data.

[0073] In one embodiment, S108, the statistical distribution characteristics are analyzed based on the repeater characteristic data, and the degree of degradation corresponding to the statistical distribution characteristics is determined according to a preset degradation degree evaluation standard.

[0074] Based on the analysis and statistical distribution characteristics of the repeater feature data, the first mode, the second mode and their corresponding proportions are extracted in sequence.

[0075] Based on the first mode, the second mode, and their corresponding proportions, the degree of degradation corresponding to the statistical distribution characteristics is determined according to a preset degradation degree evaluation standard. If the first mode is less than a first set value, it is determined to be significant degradation; if the first mode is the first set value and the proportion of the second mode is greater than a preset proportion value, it is determined to be early degradation.

[0076] Further reference Figure 2 The method also includes:

[0077] S109 displays the significant degradation and early degradation corresponding to the repeater's carrier-to-interference ratio at the repeater's location in the visualization interface.

[0078] It should be noted that although the operation of the method of the present invention has been described in a specific order in the above embodiments and figures, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0079] The method for identifying abnormal carrier-to-interference ratio of GSM-R repeaters according to the present invention will be described below with reference to a specific embodiment.

[0080] refer to Figure 3 This is a schematic diagram illustrating the abnormal carrier-to-interference ratio identification process of a GSM-R repeater according to a specific embodiment of the present invention. (Reference) Figure 3 Specific methods include:

[0081] S301 extracts the effective coverage area data of the cell based on handover and ledger information.

[0082] The effective coverage area data of the cell is extracted based on handover (a technology that ensures uninterrupted call quality when a mobile station moves from one base station's coverage area to another during a call) and ledger information (detailed records of repeaters and cells). This step is to determine the scope of subsequent analysis.

[0083] Specifically, handover information data is acquired in real time during the dynamic detection process of the GSM-R network.

[0084] Dynamic inspection refers to the use of dedicated railway inspection vehicles to collect status parameters of railway infrastructure such as GSM-R networks during train operation, thereby assessing the service status of the infrastructure.

[0085] The handover information data includes: the location information from when the test terminal occupies the current cell to when it releases the current cell, and the cell ID information of the current cell.

[0086] Based on the ledger information, extract the effective service area of ​​the current community. Obtain the distribution information of repeaters within the effective service area of ​​the current community.

[0087] The effective service range refers to the mileage range occupied by the test terminal within the cell under conditions where no handover anomalies occur. When a handover anomaly occurs, the effective service range of the cell needs to be further determined by combining base station location information. The purpose of this step is to eliminate the impact of abnormal carrier-to-interference ratio caused by factors other than the repeater equipment itself on the algorithm's recognition results, thereby improving the robustness of the recognition algorithm.

[0088] S302, it is determined that there is a repeater station within the cell coverage area.

[0089] Check if a repeater exists within the effective coverage area of ​​the extracted cell. If no repeater exists, return to S301 and continue with GSM-R network dynamic detection. If a repeater exists, proceed to the next step.

[0090] S303, extract the carrier-to-interference ratio waveform data.

[0091] If a repeater is present within the service area, further extract the cell carrier-to-interference ratio waveform data.

[0092] The carrier-to-interference ratio (C / I) is the ratio of the received useful signal level to the total number of non-useful signal levels, and it is an important indicator of communication quality. The C / I waveform data is extracted from relevant communication data, reflecting how signal quality changes over time or due to other factors.

[0093] S304 uses gray value morphology to extract concave features.

[0094] Specifically, based on the carrier-to-interference ratio waveform data of the cell, the gray value morphology method is used to extract the local concave features of the carrier-to-interference ratio waveform to obtain the set of concave locations.

[0095] The main steps of extracting local concave features of the carrier-to-interference ratio waveform using gray value morphological filtering include: performing an opening operation to eliminate peaks and retain concave features; then, performing a closing operation to fill concave features and retain peaks; next, performing a top-hat transform to extract concave features; then, performing a bottom-hat transform to enhance concave regions in the signal; and finally, performing thresholding to detect concave features, marking and returning the concave location.

[0096] Gray-value morphology is an image processing technique used to process grayscale images. Here, it is used to extract concave features from carrier-to-interference ratio waveform data. Concave features may indicate areas of signal quality degradation, and this step is to preliminarily identify areas that may have problems.

[0097] S305 uses binary morphology to extract the concave region.

[0098] Specifically, binary morphology is used to process the set of depression locations to obtain the coverage area of ​​the repeater.

[0099] Among them, processing the set of depression locations using binary morphological filtering means processing the set using binary morphological dilation operation to eliminate the interference of carrier-to-interference ratio waveform noise on depression detection and obtain the repeater coverage area.

[0100] S306, It is determined that a repeater station exists in the recessed area.

[0101] If no repeater is found, return to S301 and continue with the GSM-R network dynamic detection.

[0102] If a repeater is present, proceed to the next step.

[0103] S307 uses an adaptive smoothing asymmetric least squares algorithm to extract the baseline.

[0104] Specifically, the adaptive smoothing asymmetric least squares algorithm is used to process the carrier-to-interference ratio waveform within the repeater coverage area to extract the baseline L. Rep .

[0105] The adaptive smoothing asymmetric least squares algorithm is used for data smoothing and baseline extraction, and is particularly suitable for processing signal data with asymmetric noise. The main steps include initializing the weight matrix as an identity matrix, setting the smoothing parameters and convergence threshold; then, performing an iterative process to solve the least squares problem of the smoothed signal, updating the weights according to the residuals, and checking the convergence condition; finally, stopping when the change in the smoothed signal is less than the preset threshold or the maximum number of iterations is reached.

[0106] The baseline is the fundamental part of a signal, reflecting its overall trend. The adaptive smoothing asymmetric least squares algorithm can automatically adjust the smoothing level according to the characteristics of the data, improving the accuracy of baseline extraction.

[0107] S308, extract baseline slope features.

[0108] Calculate baseline L Rep The slope of the baseline slope curve L is obtained. S According to the baseline slope curve L S The repeater waveform data with a slope less than a preset slope threshold is extracted to obtain repeater feature data W. F .

[0109] S309, determine whether the slope is greater than the preset slope threshold.

[0110] If the slope is greater than the threshold, return to S301 and continue with the dynamic detection of the GSM-R network.

[0111] If a repeater is present, proceed to the next step.

[0112] S310, reconstructing characteristic waveforms of repeater station carrier-to-interference ratio.

[0113] If the slope is not greater than the threshold, it means that the change in signal quality is within a certain range. This step will reconstruct the carrier-to-interference ratio characteristic waveform of the repeater for subsequent analysis.

[0114] S311, Statistical analysis of load-to-dry ratio.

[0115] Statistical analysis was performed on the reconstructed carrier-to-interference ratio characteristic waveform, and the mode was calculated to understand the distribution of signal quality.

[0116] Specifically, analyze W F Based on the statistical distribution characteristics, the primary mode, secondary mode, and their corresponding proportions are extracted sequentially. Early degradation and significant degradation are distinguished according to the following judgment logic: if the primary mode is less than a first preset value, it is judged as significant degradation; if the primary mode is the first preset value and the proportion of the secondary mode is greater than a preset proportion value, it is judged as early degradation.

[0117] S312, Degradation level determination.

[0118] The early degradation and significant degradation judgment results corresponding to the repeater's carrier-to-interference ratio are displayed at the corresponding repeater location on the interface.

[0119] Specifically, the degree of degradation of the repeater is determined based on the statistical analysis of the carrier-to-interference ratio. The degree of degradation can be divided into different levels to assess the working condition of the repeater.

[0120] The specific method for extracting local concave features of the carrier-to-interference ratio waveform using gray value morphology in S304 is explained in detail below. (Reference) Figure 4 This is a schematic diagram of the algorithm for extracting concave features based on gray value morphology according to a specific embodiment of the present invention. Figure 4 As shown, the specific methods include:

[0121] S401, Opening operation:

[0122] First, an opening operation is performed on the carrier-to-interference ratio (CIR) waveform data. This operation processes the signal using structuring elements (which can be understood as filters with specific shapes and sizes), effectively eliminating peaks in the waveform while preserving the dips. In actual CIR waveforms, there may be spikes caused by noise or other interference factors. These spikes are not characteristics related to the repeater's CIR anomaly. The opening operation can remove these interferences, making the subsequent extraction of dip features more accurate.

[0123] S402, Closing Operation:

[0124] Next, a closing operation is performed, which is the opposite of an opening operation. It uses structuring elements to fill the recessed areas while preserving the peak values. After the opening operation, although some interfering peak values ​​are removed, some originally continuous recessed areas may become incomplete. The closing operation can repair these incomplete recessed areas, making the recessed features clearer and more complete, which facilitates subsequent processing.

[0125] S403, Top Cap Transformation:

[0126] After the closing operation is completed, a top-hat transform is performed. The top-hat transform subtracts the opening operation result from the original image, and its purpose is to extract the concave features in the signal. At this point, after the previous opening and closing operations, noise and unnecessary peaks in the signal have been effectively suppressed, and the top-hat transform can accurately highlight those concave parts that represent possible anomalies in the repeater.

[0127] S404, bottom cap transformation:

[0128] The following step involves a bottom-hat transform, which subtracts the original image from the closed image. This step primarily enhances the concave regions in the signal. Through the bottom-hat transform, previously less noticeable concave regions become more prominent, further improving the recognizability of concave features and aiding in more accurate detection and analysis of these features in subsequent steps.

[0129] S405, Depression Enhancement:

[0130] The previously processed signal is then enhanced by a depression feature. This step may involve using a specific algorithm or processing method to further highlight the depression feature, making the difference between the depression and other parts more significant, so that the depression location can be more accurately identified during subsequent thresholding.

[0131] S406, Threshold processing:

[0132] The enhanced signal is processed using a set threshold. If the value of a point or region in the signal meets the threshold condition, the location is determined to be a depression and marked. Through threshold processing, the depression features in the signal are transformed into specific location information and recorded in the form of a binary set. This set of marked depression locations is an important basis for subsequent operations such as determining the coverage area of ​​repeaters.

[0133] S407, output recessed position:

[0134] After a series of processing steps, a binary set of depression locations is finally output. This set contains location information for all locations in the carrier-to-interference ratio waveform that meet the depression characteristic conditions, providing crucial data support for subsequent determination of repeater coverage and analysis of repeater carrier-to-interference ratio anomalies.

[0135] The specific method for processing the carrier-to-interference ratio waveform within the repeater coverage area using the adaptive smoothing asymmetric least squares algorithm in S306 is explained in detail below. (Reference) Figure 5 This is a schematic diagram illustrating the baseline extraction process based on an adaptive smoothing asymmetric least squares algorithm according to a specific embodiment of the present invention. Figure 5 As shown, the specific methods include:

[0136] S501, set the smoothing parameters and convergence threshold, and initialize the weight matrix as the identity matrix:

[0137] The smoothing parameter controls the smoothness of the baseline; the larger the parameter, the smoother the baseline.

[0138] The convergence threshold is used to determine whether the iteration has stopped. When the baseline change is less than the threshold, the iteration is considered to have converged.

[0139] The weight matrix is ​​initialized as an identity matrix. The weight matrix is ​​used to assign different weights to different data points during the iteration process to adapt to changes in the data.

[0140] S502, Initial Baseline Estimation.

[0141] Based on the input data and the initialized weight matrix, the first baseline estimation is performed.

[0142] S503, the baseline change is less than the threshold or the maximum number of iterations has been reached;

[0143] Check if the change in the baseline is less than the convergence threshold, or if the preset maximum number of iterations has been reached.

[0144] If not, proceed to S504; if yes, proceed to S507.

[0145] S504 calculates the residual signal.

[0146] The residual signal is the difference between the actual data and the current baseline estimate. By calculating the residual signal, we can understand the difference between the current baseline estimate and the actual data.

[0147] S505, dynamically adjusts weights.

[0148] The elements in the weight matrix are dynamically adjusted based on the magnitude and distribution of the residual signal. Weights are increased for regions with smaller residuals and decreased for regions with larger residuals. This allows the algorithm to focus more on the main trends in the data, improving the accuracy of baseline estimation.

[0149] S506, Smoothing constraint, update baseline estimate.

[0150] After dynamically adjusting the weights, a smoothing constraint is applied to update the baseline estimate. The smoothing constraint ensures the smoothness of the baseline and avoids excessive fluctuations.

[0151] S507, Output baseline estimate.

[0152] When the iteration converges or the maximum number of iterations is reached, the final baseline estimation result is output.

[0153] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 6An exemplary embodiment of the GSM-R repeater carrier-to-interference ratio anomaly identification device of the present invention will be described.

[0154] The implementation of the GSM-R repeater carrier-to-interference ratio anomaly identification device can refer to the implementation of the above method, and repeated details will not be elaborated further. The term "module" or "unit" used below can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0155] Based on the same inventive concept, this invention also proposes a GSM-R repeater carrier-to-interference ratio anomaly identification device, such as... Figure 6 As shown, the device includes:

[0156] The dynamic monitoring module 610 is used for dynamic detection based on the GSM-R network to obtain handover information data in real time.

[0157] The effective service range extraction module 620 is used to extract the effective service range of the current cell based on the handover information data and ledger information data, and obtain the repeater distribution information data within the effective service range of the current cell;

[0158] The carrier-to-interference ratio waveform data extraction module 630 is used to extract cell carrier-to-interference ratio waveform data based on the repeater distribution information data.

[0159] The indentation feature analysis module 640 is used to analyze the local indentation features of the carrier-to-interference ratio waveform based on the carrier-to-interference ratio waveform data of the cell, and to determine the set of indentation locations.

[0160] The repeater coverage range determination module 650 is used to filter the set of recessed locations to obtain the repeater coverage range.

[0161] The baseline extraction module 660 is used to perform data smoothing processing on the carrier-to-interference ratio waveform within the coverage area of ​​the repeater and extract the baseline when there is a repeater within the coverage area of ​​the repeater.

[0162] The baseline analysis module 670 is used to determine the baseline slope curve based on the slope of the baseline, and extract repeater waveform data with a slope less than a preset slope threshold based on the baseline slope curve to obtain repeater feature data.

[0163] The degradation judgment module 680 is used to analyze the statistical distribution characteristics of the repeater feature data and determine the degree of degradation corresponding to the statistical distribution characteristics according to the preset degradation degree evaluation standard.

[0164] In one embodiment, the dynamic monitoring module is specifically used for:

[0165] During train operation, railway-dedicated inspection vehicles are used to collect status parameters of railway facilities, including the GSM-R network, which are used to assess the service status of the facilities.

[0166] In one embodiment, the handover information data includes: location information from when the test terminal occupies the current cell to when it releases the current cell, and the cell ID information of the current cell.

[0167] In one embodiment, the ledger information data is data on GSM-R base station information for railway lines, including: base station name, base station location, base station frequency, and the cell ID information corresponding to the base station.

[0168] In one embodiment, the effective service range of the current cell is the mileage range of the current cell occupied by a test terminal that has not experienced a handover anomaly; when a handover anomaly occurs, the effective service range of the cell is further determined by combining the base station location information.

[0169] In one embodiment, the carrier-to-interference ratio waveform data extraction module 630 is specifically used for:

[0170] Based on the repeater distribution information data, determine whether there are repeaters within the effective service range of the current cell;

[0171] If it exists, extract the cell carrier-to-interference ratio waveform data;

[0172] If it does not exist, continue with dynamic detection of the GSM-R network.

[0173] In one embodiment, the indentation feature analysis module 640 is specifically used for:

[0174] Based on the cell carrier-to-interference ratio waveform data, a gray-value morphological method is used to extract local concave features of the carrier-to-interference ratio waveform and determine the set of concave locations. The processing steps of the gray-value morphological method are as follows: peaks are eliminated and concaves are preserved through opening operations; concaves are filled and peaks are preserved through closing operations; top-hat transformation is performed to extract concaves, and bottom-hat transformation is performed to enhance concave regions in the signal; threshold processing is performed to achieve concave detection, and the concave locations are marked and returned.

[0175] In one embodiment, the repeater coverage range determination module 650 is specifically used for:

[0176] The set of depression locations is filtered using a binary morphological filtering method to eliminate the interference of carrier-to-interference ratio waveform noise on depression detection, thereby obtaining the repeater coverage area.

[0177] In one embodiment, the baseline extraction module 660 is specifically used for:

[0178] Based on the coverage area of ​​the repeater, determine whether a repeater exists;

[0179] If present, the carrier-to-interference ratio waveform within the repeater's coverage area is processed using an adaptive smoothing asymmetric least squares algorithm to extract the baseline. The adaptive smoothing asymmetric least squares algorithm is used to process signal data with asymmetric noise, performing data smoothing and baseline extraction. The process involves: initializing the weight matrix as an identity matrix, setting smoothing parameters and a convergence threshold; solving the least squares problem of the smoothed signal through iterative processing, updating the weights based on the residuals, and checking the convergence condition; stopping when the change in the smoothed signal is less than a preset threshold or the maximum number of iterations is reached.

[0180] If it does not exist, continue with dynamic detection of the GSM-R network.

[0181] In one embodiment, the degradation judgment module 680 is specifically used for:

[0182] Based on the analysis and statistical distribution characteristics of the repeater feature data, the first mode, the second mode and their corresponding proportions are extracted in sequence.

[0183] Based on the first mode, the second mode, and their corresponding proportions, the degree of degradation corresponding to the statistical distribution characteristics is determined according to a preset degradation degree evaluation standard. If the first mode is less than a first set value, it is determined to be significant degradation; if the first mode is the first set value and the proportion of the second mode is greater than a preset proportion value, it is determined to be early degradation.

[0184] In another embodiment, reference Figure 7 The device also includes: a display module 710;

[0185] Display module 710 is specifically used for:

[0186] Significant degradation and early degradation corresponding to the repeater's carrier-to-interference ratio are displayed at the repeater's location in the visualization interface.

[0187] It should be noted that although several modules of the GSM-R repeater carrier-to-interference ratio anomaly identification device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules described above can be embodied in a single module. Conversely, the features and functions of a single module described above can be further divided and embodied by multiple modules.

[0188] Based on the aforementioned inventive concept, such as Figure 8As shown, the present invention also proposes a computer device 800, including a memory 810, a processor 820, and a computer program 830 stored in the memory 810 and executable on the processor 820. When the processor 820 executes the computer program 830, it implements the aforementioned GSM-R repeater carrier-to-interference ratio anomaly identification method.

[0189] Based on the aforementioned inventive concept, this invention proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for identifying abnormal carrier-to-interference ratios in GSM-R repeaters.

[0190] Based on the aforementioned inventive concept, this invention proposes a computer program product, which includes a computer program that, when executed by a processor, implements a method for identifying abnormal carrier-to-interference ratios in GSM-R repeaters.

[0191] This invention proposes a method and device for identifying abnormal carrier-to-interference ratios (CTR) in GSM-R repeaters. Based on GSM-R dynamic detection data, it extracts CTR detection waveform data and extracts key waveform feature parameters according to data characteristics, enabling automatic identification of CTR anomalies in repeaters. This invention significantly improves the efficiency of CTR anomaly identification, laying the foundation for intelligent detection and data analysis. Simultaneously, it effectively distinguishes between early and significant CTR degradation in GSM-R repeaters, providing technical support for GSM-R wireless network maintenance units and facilitating preventative and condition-based maintenance. The overall solution exhibits strong robustness, adaptively eliminating the impact of CTR degradation caused by non-GSM-R equipment performance deterioration on identification accuracy, providing strong technical support for dynamic detection of railway wireless communication.

[0192] The acquisition, storage, use, and processing of data in this application comply with relevant laws and regulations.

[0193] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0194] This invention is described with reference to flowchart illustrations and / or block diagrams of methods and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0195] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0196] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0197] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater, characterized in that, The method includes: Based on dynamic detection of the GSM-R network, handover information data is obtained in real time. Based on the handover information data and ledger information data, the effective service range of the current cell is extracted, and the distribution information of repeaters within the effective service range of the current cell is obtained; Based on the repeater distribution information data, extract the cell carrier-to-interference ratio waveform data; Based on the carrier-to-interference ratio waveform data of the cell, analyze the local concave characteristics of the carrier-to-interference ratio waveform to determine the set of concave locations; The set of recessed locations is filtered to obtain the coverage area of ​​the repeater. When a repeater exists within the coverage area of ​​a repeater, the carrier-to-interference ratio waveform within the coverage area of ​​the repeater is smoothed and the baseline is extracted. The baseline slope curve is determined based on the slope of the baseline, and repeater waveform data with slopes less than a preset slope threshold are extracted based on the baseline slope curve to obtain repeater feature data. Based on the statistical distribution characteristics of the repeater feature data, and according to the preset degradation degree evaluation criteria, the degradation degree corresponding to the statistical distribution characteristics is determined.

2. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 1, characterized in that, Dynamic detection based on GSM-R network includes: Using dedicated railway inspection vehicles, status parameters of railway facilities, including the GSM-R network, are collected during train operation. These status parameters are used to assess the service status of the facilities.

3. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 1, characterized in that, The handover information data includes: the location information from when the test terminal occupies the current cell to when it releases the current cell, and the cell ID information of the current cell.

4. The method for identifying abnormal carrier-to-interference ratio in GSM-R repeaters according to claim 1, characterized in that, The ledger information data is data on GSM-R base stations along railway lines, including: base station name, base station location, base station frequency, and the cell ID information corresponding to the base station.

5. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 1, characterized in that, The effective service range of the current cell is the mileage range occupied by the test terminal in the current cell when no handover anomaly occurs; when a handover anomaly occurs, the effective service range of the cell is further determined by combining the base station location information.

6. The method for identifying abnormal carrier-to-interference ratio in GSM-R repeaters according to claim 1, characterized in that, Based on the repeater distribution information data, extract the cell carrier-to-interference ratio waveform data, including: Based on the repeater distribution information data, determine whether there are repeaters within the effective service range of the current cell; If it exists, extract the cell carrier-to-interference ratio waveform data; If it does not exist, continue with dynamic detection of the GSM-R network.

7. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 1, characterized in that, Based on the analysis of the cell's carrier-to-interference ratio waveform data, the local concave characteristics of the carrier-to-interference ratio waveform are determined, and a set of concave location locations is identified, including: Based on the cell carrier-to-interference ratio waveform data, a gray-value morphological method is used to extract local concave features of the carrier-to-interference ratio waveform and determine the set of concave locations. The processing steps of the gray-value morphological method are as follows: peaks are eliminated and concaves are preserved through opening operations; concaves are filled and peaks are preserved through closing operations; top-hat transformation is performed to extract concaves, and bottom-hat transformation is performed to enhance concave regions in the signal; threshold processing is performed to achieve concave detection, and the concave locations are marked and returned.

8. The method for identifying abnormal carrier-to-interference ratio in GSM-R repeaters according to claim 1, characterized in that, The set of recessed locations is filtered to obtain the repeater coverage area, including: The set of depression locations is filtered using a binary morphological filtering method to eliminate the interference of carrier-to-interference ratio waveform noise on depression detection, thereby obtaining the repeater coverage area.

9. The method for identifying abnormal carrier-to-interference ratio in GSM-R repeaters according to claim 1, characterized in that, When a repeater exists within the repeater's coverage area, the carrier-to-interference ratio waveform within the repeater's coverage area is smoothed and a baseline is extracted, including: Based on the coverage area of ​​the repeater, determine whether a repeater exists; If present, the carrier-to-interference ratio waveform within the repeater's coverage area is processed using an adaptive smoothing asymmetric least squares algorithm to extract the baseline. The adaptive smoothing asymmetric least squares algorithm is used to process signal data with asymmetric noise, performing data smoothing and baseline extraction. The process involves: initializing the weight matrix as an identity matrix, setting smoothing parameters and a convergence threshold; solving the least squares problem of the smoothed signal through iterative processing, updating the weights based on the residuals, and checking the convergence condition; stopping when the change in the smoothed signal is less than a preset threshold or the maximum number of iterations is reached. If it does not exist, continue with dynamic detection of the GSM-R network.

10. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 1, characterized in that, Based on the statistical distribution characteristics analyzed from the repeater feature data, and according to the preset degradation degree evaluation criteria, the degradation degree corresponding to the statistical distribution characteristics is determined, including: Based on the analysis and statistical distribution characteristics of the repeater feature data, the first mode, the second mode and their corresponding proportions are extracted in sequence. Based on the first mode, the second mode, and their corresponding proportions, the degree of degradation corresponding to the statistical distribution characteristics is determined according to a preset degradation degree evaluation standard. If the first mode is less than a first set value, it is determined to be significant degradation; if the first mode is the first set value and the proportion of the second mode is greater than a preset proportion value, it is determined to be early degradation.

11. The method for identifying anomalies in the carrier-to-interference ratio of a GSM-R repeater according to claim 10, characterized in that, The method also includes: Significant degradation and early degradation corresponding to the repeater's carrier-to-interference ratio are displayed at the repeater's location in the visualization interface.

12. A device for identifying abnormal carrier-to-interference ratio in a GSM-R repeater, characterized in that, The device includes: The dynamic monitoring module is used to dynamically detect and acquire handover information data in real time based on the GSM-R network. The effective service range extraction module is used to extract the effective service range of the current cell based on the handover information data and ledger information data, and obtain the repeater distribution information data within the effective service range of the current cell; The carrier-to-interference ratio waveform data extraction module is used to extract cell carrier-to-interference ratio waveform data based on the repeater distribution information data. The indentation feature analysis module is used to analyze the local indentation features of the carrier-to-interference ratio waveform based on the carrier-to-interference ratio waveform data of the cell, and to determine the set of indentation locations. The repeater coverage area determination module is used to filter the set of recessed locations to obtain the repeater coverage area. The baseline extraction module is used to perform data smoothing processing on the carrier-to-interference ratio waveform within the coverage area of ​​a repeater and extract the baseline when a repeater exists within the coverage area of ​​the repeater. The baseline analysis module is used to determine the baseline slope curve based on the slope of the baseline, and extract repeater waveform data with a slope less than a preset slope threshold based on the baseline slope curve to obtain repeater feature data. The degradation judgment module is used to analyze the statistical distribution characteristics of the repeater feature data and determine the degree of degradation corresponding to the statistical distribution characteristics according to the preset degradation degree evaluation standard.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 11.

15. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 11.

Images