Method and device for monitoring braking performance of heavy-load freight train

Abstract

The invention provides a heavy-load freight train braking performance monitoring method and device, and the method comprises the steps: synchronously collecting the braking pressure signals of a first locomotive, a second locomotive and a plurality of trucks in a heavy-load freight train based on GNSS time, and obtaining the train pipe pressure data of each section of the heavy-load freight train and the corresponding time label; if the brake pressure signal meets the preset stability condition, the time difference between the first locomotive and the second locomotive and the time difference between the first locomotive and each truck are calculated on the basis of the time labels; and judging whether the braking performance of the heavy-load freight train is normal or not based on the maximum value of the time difference and the distribution dispersion. By analyzing the time difference of the brake pressure signals of all the sections, the brake performance of the whole train can be accurately evaluated, potential fault risks can be found in time, and powerful support is provided for guaranteeing safe operation of the heavy-load train.

Description

Technical Field

[0001] This application relates to the field of rail transit safety monitoring technology, and in particular to a method and device for monitoring the braking performance of heavy-duty freight trains. Background Technology

[0002] Heavy-haul rail transport plays a vital role in the economy, and the safe operation of heavy-haul freight trains is crucial for ensuring transport efficiency. Braking performance is one of the important factors affecting the safe operation of heavy-haul trains. Traditional methods for monitoring the braking performance of heavy-haul freight trains mainly rely on manual inspection and periodic maintenance, which have the following shortcomings: manual inspection requires a lot of manpower and time, and it is difficult to achieve real-time monitoring of train braking performance; manual inspection mainly relies on experience judgment, making it difficult to accurately assess the differences in braking performance across different sections of the train; traditional periodic maintenance cannot promptly detect potential faults and performance degradation in the train's braking system.

[0003] To address the aforementioned issues, some sensor- and data analysis-based train braking performance monitoring systems have emerged in the existing technology. For example, some systems use wired networks to connect sensors at various cross-sections to achieve synchronous data acquisition and transmission. However, this approach has the following drawbacks: wired networks are susceptible to interference from the external environment and have high maintenance costs. For long-formation trains such as heavy-haul freight trains, the wiring and maintenance of wired networks are extremely difficult.

[0004] In addition, existing wireless monitoring solutions typically only focus on the braking pressure signals at the head or tail of the train, making it difficult to comprehensively assess the braking performance of the entire train. Summary of the Invention

[0005] In view of this, this application provides a method and apparatus for monitoring the braking performance of heavy-duty freight trains to solve at least one of the aforementioned problems.

[0006] To achieve the above objectives, this application adopts the following approach:

[0007] According to a first aspect of this application, a method for monitoring the braking performance of heavy-haul freight trains is provided, the method comprising:

[0008] Based on the Global Navigation Satellite System (GNSS), the braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in the heavy-haul freight train are collected synchronously in time to obtain the train pipe pressure data and their corresponding time tags at each section of the heavy-haul freight train. The first locomotive is located at the head of the heavy-haul freight train, the second locomotive is located in the middle of the heavy-haul freight train, and the multiple freight cars are located at different sections of the heavy-haul freight train at equal intervals.

[0009] If the braking pressure signal meets the preset stability condition, then the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car are calculated based on the time tag.

[0010] Based on the maximum value and distribution dispersion of the time difference, it is determined whether the braking performance of the heavy-load freight train is normal.

[0011] In one embodiment of this application, the preset stability condition in the above method includes: the standard deviation of all braking pressure signals is less than a set threshold. If it is less than the threshold, the stability condition is met; otherwise, the stability condition is not met.

[0012] In one embodiment of this application, determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference includes:

[0013] Determine whether the maximum value is less than a preset maximum value threshold, and whether the distribution dispersion is less than a preset dispersion threshold;

[0014] If the maximum value is less than a preset maximum value threshold and the distribution dispersion is less than a preset dispersion threshold, then the braking performance of the heavy-load freight train is determined to be normal; otherwise, it is determined to be abnormal.

[0015] In one embodiment of this application, the method further includes: dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data of the heavy-haul freight train, line conditions, vehicle type and load information.

[0016] In one embodiment of this application, the method described above for dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data of the heavy-haul freight train, track conditions, and vehicle type includes:

[0017] Collect historical operational data of heavy-haul freight trains;

[0018] Historical operation data are classified and grouped according to route conditions, vehicle type, and load information;

[0019] For each set of data, calculate the maximum value and distribution dispersion of the time difference under different operating conditions;

[0020] Analyze the relationship between different factors and the maximum value threshold and the dispersion threshold, and establish a mapping model;

[0021] Based on the mapping model, the maximum value threshold and the dispersion threshold are dynamically calibrated according to the current line conditions, vehicle type and load information.

[0022] In one embodiment of this application, the method further includes: adjusting the dynamic calibrated maximum value threshold and dispersion threshold with a safety margin according to weather conditions and specific transportation task requirements, so as to improve the safety of braking performance monitoring.

[0023] In one embodiment of this application, the method further includes:

[0024] Extract the pressure waveform characteristics of the train pipe pressure data at each cross-section. The waveform characteristics include rise or fall time, peak value, stabilization time, fluctuation amplitude, and noise power.

[0025] Based on the extracted pressure waveform features, a multivariate health index is constructed, which is used to characterize the health status of the braking system at each cross section.

[0026] The step of determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference further includes:

[0027] Based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, it is determined whether the braking performance of the heavy-haul freight train is normal.

[0028] In one embodiment of this application, determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index includes:

[0029] Normal threshold ranges are set for the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, respectively;

[0030] If the maximum value and the dispersion of the time difference are both within their normal threshold range, and the multivariate health index is also within its normal threshold range, then the braking performance of the heavy-duty freight train is determined to be normal.

[0031] If the maximum value or distribution dispersion of the time difference exceeds its normal threshold range, but the multivariate health index is within its normal threshold range, it is determined that the braking performance is slightly abnormal and a corresponding warning message is generated.

[0032] If the multivariate health index exceeds its normal threshold range, it is determined that the braking performance is seriously abnormal and an alarm message is generated.

[0033] In one embodiment of this application, the method further includes:

[0034] When the GNSS clock is unstable or the signal is lost, the local high-precision clock is switched as the main time reference for synchronous acquisition, and the drift of the local high-precision clock is compensated by using the free timestamp correction.

[0035] In one embodiment of this application, the method described above for compensating for the drift of a local high-precision clock using detached timestamp correction includes:

[0036] Select two or more adjacent brake pressure sensor sections in a heavy-haul freight train;

[0037] After the braking command is issued, the propagation time of the braking pressure wave between adjacent sections is calculated.

[0038] Based on the theoretical speed of pressure wave propagation and the actual measured propagation time, a time deviation model between adjacent sections is established.

[0039] The time deviation model is used to correct the timestamp of the local high-precision clock to compensate for the error caused by clock drift.

[0040] According to a second aspect of this application, a braking performance monitoring device for heavy-duty freight trains is provided, the device comprising:

[0041] The signal acquisition module is used to synchronously acquire the braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in the heavy-duty freight train based on GNSS time, and obtain the train pipe pressure data and their corresponding time tags at each section of the heavy-duty freight train. The first locomotive is located at the head of the heavy-duty freight train, the second locomotive is located in the middle of the heavy-duty freight train, and the multiple freight cars are located at different sections of the heavy-duty freight train at equal intervals.

[0042] The time difference calculation module is used to calculate the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car, based on the time tag, when the braking pressure signal meets the preset stability conditions.

[0043] The braking performance judgment module is used to determine whether the braking performance of the heavy-duty freight train is normal based on the maximum value and distribution dispersion of the time difference.

[0044] In one embodiment of this application, the aforementioned preset stability condition includes: the standard deviation of all braking pressure signals is less than a set threshold. If it is less than the threshold, the stability condition is met; otherwise, the stability condition is not met.

[0045] In one embodiment of this application, the braking performance determination module is specifically used for:

[0046] Determine whether the maximum value is less than a preset maximum value threshold, and whether the distribution dispersion is less than a preset dispersion threshold;

[0047] If the maximum value is less than a preset maximum value threshold and the distribution dispersion is less than a preset dispersion threshold, then the braking performance of the heavy-load freight train is determined to be normal; otherwise, it is determined to be abnormal.

[0048] In one embodiment of this application, the above-mentioned device includes: a threshold dynamic calibration module, used to dynamically calibrate the maximum value threshold and the dispersion threshold based on the historical operating data, line conditions, vehicle type and load information of the heavy-haul freight train.

[0049] In one embodiment of this application, the above-mentioned threshold dynamic calibration module includes:

[0050] The historical data acquisition unit is used to collect historical operating data of heavy-haul freight trains;

[0051] The data grouping unit is used to classify and group historical operation data according to line conditions, vehicle type, and load information;

[0052] The group calculation unit is used to calculate the maximum value and distribution dispersion of the time difference under different operating conditions for each group of data.

[0053] The mapping model building unit is used to analyze the relationship between different factors and the maximum value threshold and the dispersion threshold, and to establish a mapping model.

[0054] The dynamic calibration unit is used to dynamically calibrate the maximum value threshold and the dispersion threshold based on the mapping model and according to the current line conditions, vehicle type and load information.

[0055] In one embodiment of this application, the above-mentioned device further includes: a threshold adjustment module, used to adjust the dynamically calibrated maximum value threshold and dispersion threshold with a safety margin according to weather conditions and specific requirements of transportation tasks, so as to improve the safety of braking performance monitoring.

[0056] In one embodiment of this application, the above-described apparatus further includes:

[0057] The waveform feature extraction module is used to extract the pressure waveform features of the train pipe pressure data at each cross section. The waveform features include rise or fall time, peak value, stabilization time, fluctuation amplitude, and noise power.

[0058] The health index construction module is used to construct a multivariate health index based on the extracted pressure waveform features. The health index is used to characterize the health status of the braking system at each cross-section.

[0059] The braking performance judgment module is specifically used for:

[0060] Based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, it is determined whether the braking performance of the heavy-haul freight train is normal.

[0061] In one embodiment of this application, the braking performance determination module is specifically used for:

[0062] Normal threshold ranges are set for the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, respectively;

[0063] If the maximum value and the dispersion of the time difference are both within their normal threshold range, and the multivariate health index is also within its normal threshold range, then the braking performance of the heavy-duty freight train is determined to be normal.

[0064] If the maximum value or distribution dispersion of the time difference exceeds its normal threshold range, but the multivariate health index is within its normal threshold range, it is determined that the braking performance is slightly abnormal and a corresponding warning message is generated.

[0065] If the multivariate health index exceeds its normal threshold range, it is determined that the braking performance is seriously abnormal and an alarm message is generated.

[0066] In one embodiment of this application, the above-described apparatus further includes:

[0067] The clock compensation module is used to switch to the local high-precision clock as the main time reference for synchronous acquisition when the GNSS clock is unstable or the signal is lost, and to compensate for the drift of the local high-precision clock by using the free timestamp correction.

[0068] In one embodiment of this application, the clock compensation module includes:

[0069] The section selection unit is used to select two or more adjacent brake pressure sensor sections in a heavy-duty freight train.

[0070] The propagation time calculation unit is used to calculate the propagation time of the braking pressure wave between adjacent sections after the braking command is issued.

[0071] The deviation model construction unit is used to establish a time deviation model between adjacent sections based on the theoretical speed of pressure wave propagation and the actual measured propagation time.

[0072] The clock drift compensation unit is used to correct the timestamp of the local high-precision clock using the time deviation model to compensate for the error caused by clock drift.

[0073] According to a third aspect of this application, an electronic 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 the steps of the method described above.

[0074] According to a fourth aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0075] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0076] As can be seen from the above technical solution, the on-board safety monitoring method and device for heavy-haul freight trains provided in this application can realize the synchronous acquisition of braking pressure signals from multiple sections of heavy-haul freight trains without relying on wired networks, thus reducing maintenance costs and difficulties. Furthermore, by analyzing the time difference of braking pressure signals from each section, this application can accurately assess the braking performance of the entire train, promptly identify potential fault risks, and provide strong support for ensuring the safe operation of heavy-haul trains. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0078] Figure 1 This is a flowchart illustrating a method for monitoring the braking performance of a heavy-duty freight train, as provided in an embodiment of this application.

[0079] Figure 2 This is a schematic diagram of the process for calibrating the maximum value threshold and the dispersion threshold provided in the embodiments of this application;

[0080] Figure 3 This is a schematic diagram of the process for adjusting the safety margin provided in an embodiment of this application;

[0081] Figure 4 This is a schematic diagram of the process for compensating for the drift of a local high-precision clock provided in an embodiment of this application;

[0082] Figure 5 This is a schematic flowchart of a braking performance monitoring device for heavy-duty freight trains provided in an embodiment of this application;

[0083] Figure 6This is a schematic block diagram of the system configuration of the electronic device provided in the embodiments of the invention. Detailed Implementation

[0084] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of this application are used to explain this application, but are not intended to limit this application.

[0085] like Figure 1 The diagram shown is a flowchart illustrating a method for monitoring the braking performance of heavy-haul freight trains according to an embodiment of this application. The implementation entity of this method is a ground data analysis server, and the method includes the following steps:

[0086] Step S101: Based on GNSS time synchronization, the braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in the heavy-haul freight train are collected to obtain the train pipe pressure data and their corresponding time tags at each section of the heavy-haul freight train. The first locomotive is located at the head of the heavy-haul freight train, the second locomotive is located in the middle of the heavy-haul freight train, and the multiple freight cars are located at different sections of the heavy-haul freight train at equal intervals.

[0087] Brake pressure sensors are installed on multiple sections of the heavy-haul freight train (including the first locomotive, the second locomotive, and multiple freight cars at equidistant intervals at different section positions). These brake pressure sensors are used to monitor the train pipe pressure at each section in real time, and they are connected to signal acquisition equipment to form a heavy-haul freight train braking performance monitoring system.

[0088] The aforementioned signal acquisition equipment is connected to a GNSS satellite receiver to obtain a unified time reference, achieving time synchronization of braking pressure monitoring data across various sections. The signal acquisition equipment has a built-in battery, ensuring minimal time deviation and enabling it to correct its own time by obtaining a time synchronization signal within the GNSS satellite connection segment, resulting in a time deviation of less than 10ms.

[0089] The signal acquisition equipment collects signals from various sensors, performs voltage-to-physical quantity conversion, and calculates the train pipe pressure data P at each cross-section using the following formula:

[0090] P = k × V + b;

[0091] Where V represents the voltage of each channel acquired by the signal acquisition device; k represents the proportionality coefficient, used to convert the voltage value into the corresponding pressure value unit; and b represents the intercept or offset, used to correct zero-point drift caused by factors such as sensors or circuits.

[0092] Simultaneously, based on GNSS satellite time, a time tag T is added to each train pipe pressure data P. For example, the first locomotive braking pressure data is (Pj1, Tj1), the second locomotive braking pressure data is (Pj2, Tj2), and the multi-section braking pressure data of freight cars is (Ph1, Th1), (Ph2, Th2)...(Phn, Thn), where n is the number of freight cars.

[0093] The signal acquisition equipment can transmit the collected braking pressure data to a ground data analysis server via 4G / 5G mobile internet.

[0094] Step S102: If the braking pressure signal meets the preset stability condition, then calculate the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car, based on the time tag.

[0095] Before calculating the time difference, this step requires determining whether the braking pressure signals at each cross-section meet a preset stability condition. In one embodiment of this application, the stability condition can be defined as the standard deviation of all braking pressure signals being less than a set threshold. If the stability condition is met, the subsequent time difference calculation is performed; otherwise, it is necessary to wait for the pressure to stabilize or perform other processing. This is because if the pressure levels at different cross-sections differ too much, directly comparing the time difference will confuse causality and make it difficult to reflect braking synchronicity from the time difference, which may be masked by static differences. However, when the pressure fluctuates but the overall trend is similar, the time difference can reveal whether the responses of each cross-section are consistent at the same event (such as braking start, braking completion); if the pressure difference is huge, even if the time difference is small, it does not necessarily indicate good synchronization.

[0096] If the braking pressure signal of each section meets the stability condition, then the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car, is calculated based on the time tag corresponding to each section.

[0097] For example, to calculate the time difference between Tj1 and Tj2, Th1, Th2...Thn:

[0098] Tjc1 = Tj2 - Tj1;

[0099] Thc1 = Th1 - Tj1;

[0100] Thc2 = Th2 - Tj1; ...

[0102] THcn = Thn - Tj1;

[0103] Where Tj1 and Tj2 represent the braking pressure signal time stamps of the first and second locomotives, respectively, and Th1, Th2...Thn represent the braking pressure signal time stamps of each freight car. The calculated time differences Tjc1, Thc1, Thc2...Thcn reflect the transmission speed of the braking signal in the train.

[0104] Step S103: Based on the maximum value and distribution dispersion of the time difference, determine whether the braking performance of the heavy-load freight train is normal.

[0105] After calculating the time difference between each section, it is necessary to calculate the maximum value of the time difference (Max(Tjc1, Thc1, Thc2...Thcn)) and its distribution dispersion (e.g., standard deviation, variance, etc.), as well as the distribution dispersion of the time difference. This distribution dispersion includes, but is not limited to, standard deviation, variance, and four-way position distance. The maximum value of the time difference reflects the maximum delay in the transmission of the braking signal within the train, while the distribution dispersion reflects the uniformity of the braking signal transmission.

[0106] The braking process is essentially the transmission of braking pressure from the front to the rear of the train. Ideally, braking pressure should arrive at all sections simultaneously, and the rate of pressure drop should be uniform. However, in reality, due to factors such as train length, pipeline resistance, and gaps between vehicles, the transmission of braking signals will be delayed and attenuated.

[0107] The maximum time difference reflects the maximum delay in the transmission of the braking signal within the train. If the maximum value is too large, it indicates that the braking signal transmission speed is too slow, which may indicate the following problems: pipe blockage or leakage, leading to obstructed pressure transmission; brake cylinder malfunction, resulting in sluggish braking response; or poor vehicle connection, causing signal transmission delay. These problems will directly affect braking performance, leading to increased braking distance and even causing safety accidents.

[0108] The dispersion of the braking signal reflects the uniformity of the braking signal transmission. If the dispersion is too large, it indicates that there are significant differences in the braking signal transmission between different sections, which may lead to the following problems: inconsistent performance of the vehicle braking system, resulting in some vehicles braking too strongly or too weakly; uneven distribution of pipeline pressure, resulting in significant differences in braking effect between different sections. These problems can cause longitudinal impulses during train braking, affecting passenger comfort, and in severe cases, may lead to vehicle derailment.

[0109] Relying solely on the maximum value or dispersion of the time difference is insufficient to accurately determine braking performance. For example, if the braking signals at all sections exhibit the same delay, the maximum value of the time difference may be small, but the overall braking performance will still be poor. Therefore, this application aims to comprehensively evaluate braking performance by considering both the maximum value and dispersion of the time difference.

[0110] As can be seen, this application indirectly reflects the transmission speed and uniformity of the braking signal in the train by analyzing the maximum value and distribution dispersion of the time difference, thereby evaluating the braking performance of the train. While the method in this application does not directly measure braking distance or braking force, it has advantages such as real-time monitoring and ease of implementation, and can play an important role in the safety monitoring of heavy-haul trains.

[0111] As can be seen from the above technical solution, the on-board safety monitoring method for heavy-haul freight trains provided in this application can achieve synchronous acquisition of braking pressure signals from multiple sections of heavy-haul freight trains without relying on wired networks, thus reducing maintenance costs and difficulties. Furthermore, by analyzing the time difference of braking pressure signals from each section, this application can accurately assess the braking performance of the entire train, promptly identify potential fault risks, and provide strong support for ensuring the safe operation of heavy-haul trains.

[0112] In one embodiment of this application, determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference in step S103 above includes:

[0113] Determine whether the maximum value is less than a preset maximum value threshold, and whether the distribution dispersion is less than a preset dispersion threshold;

[0114] If the maximum value is less than a preset maximum value threshold and the distribution dispersion is less than a preset dispersion threshold, then the braking performance of the heavy-load freight train is determined to be normal; otherwise, it is determined to be abnormal.

[0115] As mentioned earlier, if the maximum value of the time difference is less than the preset maximum value threshold, and the distribution dispersion is less than the preset dispersion threshold, then the braking performance of the heavy-haul freight train is determined to be normal. This indicates that the braking signal is transmitted quickly enough in the train, and the braking response between different sections is relatively consistent, resulting in good overall braking performance.

[0116] If the maximum value of the time difference is greater than or equal to a preset maximum value threshold, or the distribution dispersion is greater than or equal to a preset dispersion threshold, the braking performance of the heavy-haul freight train is determined to be abnormal. This indicates that there is a delay or unevenness in the transmission of the braking signal in the train, which may indicate problems such as braking system failure, pipeline blockage or leakage, requiring further inspection and maintenance.

[0117] In another embodiment of this application, the above method further includes: dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data of heavy-haul freight trains, line conditions, vehicle type and load information.

[0118] If preset maximum and dispersion thresholds remain fixed, they may not be suitable for evaluating the braking performance of heavy-haul freight trains under different operating conditions. For example, the braking performance of a train will differ significantly between empty and fully loaded conditions; using the same threshold may lead to misjudgments. By dynamically calibrating the thresholds based on factors such as historical operating data of heavy-haul freight trains, track conditions, vehicle type, and load information, the thresholds can better reflect actual operating conditions, improving the accuracy and reliability of braking performance assessments.

[0119] In another embodiment of this application, such as Figure 2 As shown, the step of dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data of heavy-haul freight trains, track conditions, vehicle type, and load information may further include:

[0120] Step S201: Collect historical operation data of heavy-haul freight trains.

[0121] This step involves collecting raw data for subsequent analysis and mapping model building. This step ensures the comprehensiveness and accuracy of the data by collecting various data from heavy-haul freight trains during actual operation. Data collection should be of a certain scale, with the time span as long as possible, covering various operating conditions. The operational data includes, but is not limited to: train pipe pressure data at each cross-section and their corresponding time stamps, operating speed, track data (track gradient, curvature, tunnel, bridge information, etc.), vehicle data (vehicle type, vehicle formation, vehicle status, etc.), load information, and environmental information (temperature, humidity, weather conditions, etc.).

[0122] Step S202: Classify and group the historical operation data according to the route conditions, vehicle type and load information.

[0123] The historical operational data collected may contain various problems, such as missing data, anomalies, duplication, and inconsistencies. Therefore, before classifying and grouping the data, these historical operational data can be preprocessed. This preprocessing includes data cleaning, data transformation, and data integration. Data cleaning includes handling missing values, outliers, duplicate values, and erroneous values; data transformation includes data standardization and discretization; and data integration includes data merging and transformation.

[0124] Then, based on factors such as line conditions, vehicle type, and load information, the historical operating data is divided into different groups. This embodiment does not limit the specific grouping and classification methods; the purpose of grouping and classification here is to enable more precise analysis and modeling later. Specifically, by classifying and grouping historical operating data according to factors such as line conditions, vehicle type, and load information, the overall, generalized data can be decomposed into smaller, more specific subsets. In this way, in subsequent analysis, the impact of different line conditions, vehicle types, and load conditions on braking performance can be studied separately, resulting in more refined analysis results. The braking performance of trains may vary significantly under different line conditions, vehicle types, and load information. If all data is used directly to build a unified mapping model without classification and grouping, these differences will be ignored, leading to reduced model accuracy. By classifying and grouping the data, mapping models can be built for different situations, thereby improving the accuracy of the model.

[0125] Step S203: For each set of data, calculate the maximum value and distribution dispersion of the time difference under different operating conditions.

[0126] This step involves extracting key indicators reflecting braking performance from each data set. For each data set, the maximum value and dispersion of the time difference under different operating conditions are calculated. Operating conditions can include different speed ranges and different braking conditions.

[0127] Step S204: Analyze the relationship between different factors and the maximum value threshold and the dispersion threshold, and establish a mapping model.

[0128] This section establishes the correlation between factors such as route conditions, vehicle type, and load information and the maximum and dispersion thresholds. By analyzing the degree and direction of the influence of different factors on the maximum and dispersion thresholds, the optimal mapping relationship can be found. Specifically, regression analysis methods can be used to establish the correlation, i.e., establishing regression equations between the maximum or dispersion threshold and each influencing factor, such as linear regression or multinomial regression. Neural network models can also be used to automatically establish mapping relationships by learning from historical data. Alternatively, a rule-based mapping model can be established based on an expert system and the experience of domain experts.

[0129] Step S205: Based on the mapping model, dynamically calibrate the maximum value threshold and the dispersion threshold according to the current line conditions, vehicle type and load information.

[0130] This step adjusts the maximum value threshold and dispersion threshold in real time based on the current operating status to improve the accuracy of braking performance assessment. By inputting parameters such as current track conditions, vehicle type, and load information into the mapping model, the corresponding maximum value threshold and dispersion threshold are calculated.

[0131] In this embodiment, a lookup table method can be used to pre-calculate the thresholds for different operating states, store them in the database, and query them in real time.

[0132] Through the above steps, dynamic calibration of the maximum value threshold and the dispersion threshold can be achieved, improving the accuracy and reliability of braking performance monitoring for heavy-haul freight trains and providing strong support for ensuring safe train operation.

[0133] In another embodiment of this application, the above method may further include: adjusting the dynamic calibrated maximum value threshold and dispersion threshold with a safety margin according to weather conditions and specific requirements of transportation tasks, so as to improve the safety of braking performance monitoring.

[0134] In this embodiment, it is considered that severe weather conditions (such as rain, snow, hail, strong winds, etc.) can affect the braking performance of trains. For example, rain and snow reduce the coefficient of friction between the wheels and the rails, leading to a longer braking distance. Therefore, under severe weather conditions, it is necessary to appropriately adjust the maximum value threshold and the dispersion threshold to improve the sensitivity of braking performance monitoring and ensure safety.

[0135] At the same time, it is also considered that different transportation tasks have different requirements for the braking performance of trains. For example, trains transporting dangerous goods have higher requirements for braking performance. Therefore, for special transportation tasks, it is necessary to appropriately adjust the maximum value threshold and dispersion threshold to meet higher safety standards.

[0136] The safety margin adjustment strategy in this embodiment can be formulated according to weather conditions and transportation task requirements. For example, in rainy or snowy weather, the maximum value threshold can be reduced and the dispersion threshold can be increased; in hail weather, the maximum value threshold can be significantly reduced and the dispersion threshold can be significantly increased; when transporting dangerous goods, the maximum value threshold can be reduced and the dispersion threshold can be increased; when running on long downhill slopes, the maximum value threshold can be reduced and the dispersion threshold can be increased.

[0137] Therefore, this embodiment can acquire weather and transportation task information in real time during train operation, and dynamically adjust the maximum value threshold and dispersion threshold according to the adjustment strategy and adjustment range. Weather information can be acquired in real time through meteorological sensors, weather forecasting systems, etc. Transportation task information can be obtained from the train dispatching system or transportation management system. A safety margin adjustment module can be added to the braking performance monitoring system to achieve automatic threshold adjustment, and when the adjusted threshold is triggered, an alarm message will be issued in a timely manner to remind the driver and dispatcher. Table 1 below is a specific example of safety margin adjustment:

[0138] Table 1

[0139]

[0140] Using the above methods, the maximum value threshold and dispersion threshold of the dynamic calibration can be adjusted with a safety margin according to weather conditions and specific transportation needs, thereby improving the safety of heavy-haul train braking performance monitoring and reducing the risk of accidents.

[0141] In another embodiment of this application, such as Figure 3 As shown, the method described above in this application further includes:

[0142] Step S301: Extract the pressure waveform characteristics of the train pipe pressure data at each cross-section. The waveform characteristics include rise or fall time, peak value, stabilization time, fluctuation amplitude, and noise power.

[0143] This step aims to extract key characteristic parameters reflecting the health status of the braking system from the train pipe pressure waveform. Specifically, the train pipe pressure data collected from each section can be analyzed to extract rise or fall time, peak value, settling time, fluctuation amplitude, and noise power. Rise or fall time refers to the time required for the braking pressure to reach a stable value, reflecting the braking system's response speed; the stable value is the preset pressure value during braking, reflecting the braking capacity of the system; the settling time is the time it takes for the pressure to remain stable after reaching the stable value, reflecting the braking system's pressure-holding capacity; the fluctuation amplitude is the range of pressure fluctuation in a stable state, reflecting the stability of the braking system; and the noise power is the noise intensity in the pressure signal, reflecting the quality of the sensor and data acquisition system.

[0144] The extraction method is as follows: First, the raw pressure data is filtered and denoised to improve signal quality. Then, the continuous pressure data is divided into independent braking waveforms. For each braking waveform, the five characteristic parameters mentioned above are calculated, which can be performed using time-domain analysis, frequency-domain analysis, and other methods.

[0145] Step S302: Based on the extracted pressure waveform features, construct a multivariate health index, which is used to characterize the health status of the braking system at each cross section.

[0146] This step combines multiple pressure waveform characteristics to form an indicator that can comprehensively reflect the health status of the braking system.

[0147] When constructing a multivariate health index, different weights can be assigned based on the importance of each feature parameter. The weighted feature parameters are then combined to form the multivariate health index. A higher health index indicates a better health condition of the braking system. A lower health index indicates a worse health condition of the braking system, suggesting potential malfunctions or risks.

[0148] The step S103 above, which determines whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference, further includes: determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value, distribution dispersion, and the multivariate health index.

[0149] In this embodiment, it is necessary to comprehensively consider the time characteristics of braking signal transmission and the health status of the braking system itself in order to improve the accuracy and reliability of braking performance judgment.

[0150] In another embodiment of this application, this step may further include:

[0151] Normal threshold ranges are set for the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, respectively;

[0152] If the maximum value and the dispersion of the time difference are both within their normal threshold range, and the multivariate health index is also within its normal threshold range, then the braking performance of the heavy-duty freight train is determined to be normal.

[0153] If the maximum value or distribution dispersion of the time difference exceeds its normal threshold range, but the multivariate health index is within its normal threshold range, it is determined that the braking performance is slightly abnormal and a corresponding warning message is generated.

[0154] If the multivariate health index exceeds its normal threshold range, it is determined that the braking performance is seriously abnormal and an alarm message is generated.

[0155] This embodiment comprehensively considers the time characteristics of braking signal transmission and the health status of the braking system itself, enabling a more comprehensive and accurate assessment of the braking performance of heavy-haul freight trains. By setting different threshold ranges and anomaly levels, refined monitoring and early warning of braking performance can be achieved, thereby improving the safe operation level of heavy-haul trains.

[0156] In another embodiment of this application, the above method further includes: when the GNSS clock is unstable or the signal is lost, switching to the local high-precision clock as the main time reference for synchronous acquisition, and using free timestamp correction to compensate for the drift of the local high-precision clock.

[0157] GNSS signals are susceptible to interference from environmental factors, such as obstruction by tall buildings, tunnels, and severe weather, leading to signal instability or loss. Monitoring the braking performance of heavy-haul trains relies on precise time synchronization of multi-section data; deviations in time synchronization can result in inaccurate braking performance assessments. Local high-precision clocks (such as atomic clocks and temperature-controlled crystal oscillators) offer high stability and accuracy, providing a reliable time reference within a short timeframe.

[0158] In this embodiment, when the GNSS signal is unstable or lost, the system automatically switches to the local high-precision clock as the primary time reference for synchronous acquisition. When the GNSS signal returns to normal, the system can switch back to the GNSS clock and calibrate the local high-precision clock.

[0159] In another embodiment of this application, such as Figure 4 As shown, this step of using detached timestamp correction to compensate for the drift of the local high-precision clock may further include:

[0160] Step S401: Select two or more adjacent brake pressure sensor sections in the heavy-haul freight train.

[0161] This step is to determine the sensor sections used to build the time deviation model. Specifically, on a heavy-haul freight train, two or more adjacent sections equipped with brake pressure sensors are selected. Choosing adjacent sections reduces errors caused by excessive distance. In this embodiment, two or more adjacent sections can be selected. Selecting more sections can improve the model's accuracy but also increases computational complexity. The specific number can be adjusted according to actual needs.

[0162] Step S402: After the braking command is issued, calculate the propagation time of the braking pressure wave between adjacent sections.

[0163] After the braking command is issued, the time point when the pressure sensor on the adjacent cross section detects the pressure change is recorded. By calculating the time difference between the pressure change time points of the two cross sections, the actual propagation time of the braking pressure wave is obtained.

[0164] In this step, the moment the braking command is issued can be determined using signals from the locomotive control system or the driver's operation record. Simultaneously, a pressure threshold is set at each cross-section. When the pressure detected by the pressure sensor exceeds this threshold, the current timestamp is recorded as the time point of pressure change. Then, the pressure change time points on adjacent cross-sections are subtracted to obtain the actual propagation time of the braking pressure wave.

[0165] Step S403: Based on the theoretical speed of pressure wave propagation and the actual measured propagation time, establish a time deviation model between adjacent sections.

[0166] The time deviation model here is a mathematical model that reflects the relationship between the time deviation between adjacent sections and the actual propagation time. The theoretical speed can be calculated by consulting relevant materials or conducting experimental measurements to determine the theoretical propagation speed of the braking pressure wave in the train tube. The theoretical speed is affected by factors such as the material, pressure, and temperature of the train tube and can be corrected as needed.

[0167] Based on the theoretical velocity and the distance between the cross-section, the theoretical propagation time of the braking pressure wave is calculated. This theoretical propagation time is then compared with the actual measured propagation time to obtain the time deviation. Next, a mathematical model is established between the time deviation and the actual propagation time; linear models, nonlinear models, etc., can be used. For example, the following linear model can be used:

[0168] Δt = a×t + b;

[0169] Where Δt represents the time deviation, t represents the actual propagation time, a represents the drift coefficient, and b represents the initial deviation.

[0170] Step S404: Using the time deviation model, correct the timestamp of the local high-precision clock to compensate for the error caused by clock drift.

[0171] Using the established time deviation model, the time deviation is calculated based on the actual propagation time, and the timestamp of the local high-precision clock is corrected to compensate for errors caused by clock drift. In practice, the pressure wave propagation time between adjacent sections can be measured in real time during each braking process, and the current time deviation is calculated using the time deviation model. Then, the calculated time deviation is subtracted from the timestamp of the local high-precision clock to obtain the corrected timestamp. Finally, the corrected timestamp is used to update the timestamp of the braking pressure data.

[0172] In this embodiment, updating the timestamp of the braking pressure data using a corrected timestamp improves the time synchronization accuracy of the braking pressure data, thereby enabling a more accurate assessment of the braking performance of heavy-haul freight trains. This helps improve the safe operation of heavy-haul trains and reduce the risk of accidents.

[0173] like Figure 5 The diagram shown is a structural schematic of a heavy-duty freight train braking performance monitoring device provided in an embodiment of this application. The device includes:

[0174] The signal acquisition module 510 is used to synchronously acquire the braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in the heavy-haul freight train based on GNSS time, and obtain the train pipe pressure data and their corresponding time tags of each section of the heavy-haul freight car. The first locomotive is located at the head position of the heavy-haul freight train, the second locomotive is located at the middle position of the heavy-haul freight train, and the multiple freight cars are located at different sections of the heavy-haul freight train at equal intervals.

[0175] The time difference calculation module 520 is used to calculate the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car, based on the time tag, when the braking pressure signal meets the preset stability conditions.

[0176] The braking performance judgment module 530 is used to determine whether the braking performance of the heavy-duty freight train is normal based on the maximum value and distribution dispersion of the time difference.

[0177] In one embodiment of this application, the aforementioned preset stability condition includes: the standard deviation of all braking pressure signals is less than a set threshold. If it is less than the threshold, the stability condition is met; otherwise, the stability condition is not met.

[0178] In one embodiment of this application, the braking performance determination module is specifically used for:

[0179] Determine whether the maximum value is less than a preset maximum value threshold, and whether the distribution dispersion is less than a preset dispersion threshold;

[0180] If the maximum value is less than a preset maximum value threshold and the distribution dispersion is less than a preset dispersion threshold, then the braking performance of the heavy-load freight train is determined to be normal; otherwise, it is determined to be abnormal.

[0181] In one embodiment of this application, the above-mentioned device includes: a threshold dynamic calibration module, used to dynamically calibrate the maximum value threshold and the dispersion threshold based on the historical operating data, line conditions, vehicle type and load information of the heavy-haul freight train.

[0182] In one embodiment of this application, the above-mentioned threshold dynamic calibration module includes:

[0183] The historical data acquisition unit is used to collect historical operating data of heavy-haul freight trains;

[0184] The data grouping unit is used to classify and group historical operation data according to line conditions, vehicle type, and load information;

[0185] The group calculation unit is used to calculate the maximum value and distribution dispersion of the time difference under different operating conditions for each group of data.

[0186] The mapping model building unit is used to analyze the relationship between different factors and the maximum value threshold and the dispersion threshold, and to establish a mapping model.

[0187] The dynamic calibration unit is used to dynamically calibrate the maximum value threshold and the dispersion threshold based on the mapping model and according to the current line conditions, vehicle type and load information.

[0188] In one embodiment of this application, the above-mentioned device further includes: a threshold adjustment module, used to adjust the dynamically calibrated maximum value threshold and dispersion threshold with a safety margin according to weather conditions and specific requirements of transportation tasks, so as to improve the safety of braking performance monitoring.

[0189] In one embodiment of this application, the above-described apparatus further includes:

[0190] The waveform feature extraction module is used to extract the pressure waveform features of the train pipe pressure data at each cross section. The waveform features include rise or fall time, peak value, stabilization time, fluctuation amplitude, and noise power.

[0191] The health index construction module is used to construct a multivariate health index based on the extracted pressure waveform features. The health index is used to characterize the health status of the braking system at each cross-section.

[0192] The braking performance judgment module is specifically used for:

[0193] Based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, it is determined whether the braking performance of the heavy-haul freight train is normal.

[0194] In one embodiment of this application, the braking performance determination module is specifically used for:

[0195] Normal threshold ranges are set for the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, respectively;

[0196] If the maximum value and the dispersion of the time difference are both within their normal threshold range, and the multivariate health index is also within its normal threshold range, then the braking performance of the heavy-duty freight train is determined to be normal.

[0197] If the maximum value or distribution dispersion of the time difference exceeds its normal threshold range, but the multivariate health index is within its normal threshold range, it is determined that the braking performance is slightly abnormal and a corresponding warning message is generated.

[0198] If the multivariate health index exceeds its normal threshold range, it is determined that the braking performance is seriously abnormal and an alarm message is generated.

[0199] In one embodiment of this application, the above-described apparatus further includes:

[0200] The clock compensation module is used to switch to the local high-precision clock as the main time reference for synchronous acquisition when the GNSS clock is unstable or the signal is lost, and to compensate for the drift of the local high-precision clock by using the free timestamp correction.

[0201] In one embodiment of this application, the clock compensation module includes:

[0202] The section selection unit is used to select two or more adjacent brake pressure sensor sections in a heavy-duty freight train.

[0203] The propagation time calculation unit is used to calculate the propagation time of the braking pressure wave between adjacent sections after the braking command is issued.

[0204] The deviation model construction unit is used to establish a time deviation model between adjacent sections based on the theoretical speed of pressure wave propagation and the actual measured propagation time.

[0205] The clock drift compensation unit is used to correct the timestamp of the local high-precision clock using the time deviation model to compensate for the error caused by clock drift.

[0206] As can be seen from the above technical solution, the on-board safety monitoring device for heavy-haul freight trains provided in this application can achieve synchronous acquisition of braking pressure signals from multiple sections of the heavy-haul freight train without relying on wired networks, thus reducing maintenance costs and difficulties. Furthermore, by analyzing the time difference of the braking pressure signals from each section, this application can accurately assess the braking performance of the entire train, promptly identify potential fault risks, and provide strong support for ensuring the safe operation of heavy-haul trains.

[0207] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method.

[0208] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0209] This application also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the above-described method.

[0210] like Figure 6 The electronic device 600 may also include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 6 All components shown; in addition, electronic device 600 may also include Figure 6 The components shown can be referenced in the prior art.

[0211] like Figure 6 The central processing unit 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The central processing unit 100 receives inputs and controls the operation of various components of the electronic device 600.

[0212] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0213] Input unit 120 provides input to central processing unit 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0214] The memory 140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142 for storing application and function programs or processes for executing the operation of the electronic device 600 via the central processing unit 100.

[0215] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various drivers for the electronic device for communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0216] The communication module 110 is a transmitter / receiver that sends and receives signals via the antenna 111. The communication module (transmitter / receiver) is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0217] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication modules (transmitters / receivers) are also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby enabling typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to a central processing unit 100, enabling on-device recording via the microphone 132 and on-device playback of stored audio via the speaker 131.

[0218] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application 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.

[0219] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. 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... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0220] 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.

[0221] 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.

[0222] This application uses specific embodiments to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0223] As can be seen from the above technical solution, the safety monitoring method for braking performance of heavy-haul freight trains provided in this application achieves dynamic adjustment of the safety threshold, improving the accuracy and reliability of safety monitoring. It overcomes the shortcomings of existing technologies that use fixed safety thresholds, enabling dynamic adjustment of the safety threshold according to actual operating conditions, adapting to complex and changing operating environments, and reducing false alarms or missed alarms. At the same time, this application also enhances the capabilities of current status analysis and trend analysis, providing decision support for safety management.

Claims

1. A method for monitoring the braking performance of heavy-haul freight trains, characterized in that, The method includes: Based on GNSS time-synchronous acquisition of braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in a heavy-haul freight train, train pipe pressure data and their corresponding time tags are obtained at each section of the heavy-haul freight train. The first locomotive is located at the head of the heavy-haul freight train, the second locomotive is located in the middle of the heavy-haul freight train, and the multiple freight cars are located at different sections of the heavy-haul freight train at equal intervals. If the braking pressure signal meets the preset stability condition, then the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car are calculated based on the time tag. Based on the maximum value and distribution dispersion of the time difference, it is determined whether the braking performance of the heavy-load freight train is normal.

2. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 1, characterized in that, The preset stability conditions include: the standard deviation of all braking pressure signals is less than a set threshold. If it is less than the threshold, the stability conditions are met; otherwise, the stability conditions are not met.

3. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 1, characterized in that, The determination of whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference includes: Determine whether the maximum value is less than a preset maximum value threshold, and whether the distribution dispersion is less than a preset dispersion threshold; If the maximum value is less than a preset maximum value threshold and the distribution dispersion is less than a preset dispersion threshold, then the braking performance of the heavy-load freight train is determined to be normal; otherwise, it is determined to be abnormal.

4. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 3, characterized in that, The method further includes: dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data, line conditions, vehicle type and load information of the heavy-haul freight train.

5. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 4, characterized in that, The step of dynamically calibrating the maximum value threshold and the dispersion threshold based on the historical operating data of the heavy-haul freight train, track conditions, and vehicle type includes: Collect historical operational data of heavy-haul freight trains; Historical operation data are classified and grouped according to route conditions, vehicle type, and load information; For each set of data, calculate the maximum value and distribution dispersion of the time difference under different operating conditions; Analyze the relationship between different factors and the maximum value threshold and the dispersion threshold, and establish a mapping model; Based on the mapping model, the maximum value threshold and the dispersion threshold are dynamically calibrated according to the current line conditions, vehicle type and load information.

6. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 5, characterized in that, The method further includes: adjusting the maximum value threshold and dispersion threshold of the dynamic calibration with a safety margin according to weather conditions and specific needs of transportation tasks, so as to improve the safety of braking performance monitoring.

7. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 1, characterized in that, The method further includes: Extract the pressure waveform characteristics of the train pipe pressure data at each cross-section. The waveform characteristics include rise or fall time, peak value, stabilization time, fluctuation amplitude, and noise power. Based on the extracted pressure waveform features, a multivariate health index is constructed, which is used to characterize the health status of the braking system at each cross section. The step of determining whether the braking performance of the heavy-haul freight train is normal based on the maximum value and distribution dispersion of the time difference further includes: Based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, it is determined whether the braking performance of the heavy-haul freight train is normal.

8. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 7, characterized in that, The determination of whether the braking performance of the heavy-haul freight train is normal based on the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index includes: Normal threshold ranges are set for the maximum value of the time difference, the dispersion of the distribution, and the multivariate health index, respectively; If the maximum value and the dispersion of the time difference are both within their normal threshold range, and the multivariate health index is also within its normal threshold range, then the braking performance of the heavy-duty freight train is determined to be normal. If the maximum value or distribution dispersion of the time difference exceeds its normal threshold range, but the multivariate health index is within its normal threshold range, it is determined that the braking performance is slightly abnormal and a corresponding warning message is generated. If the multivariate health index exceeds its normal threshold range, it is determined that the braking performance is seriously abnormal and an alarm message is generated.

9. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 1, characterized in that, The method further includes: When the GNSS clock is unstable or the signal is lost, the local high-precision clock is switched as the main time reference for synchronous acquisition, and the drift of the local high-precision clock is compensated by using the free timestamp correction.

10. The method for monitoring the braking performance of heavy-haul freight trains as described in claim 9, characterized in that, The method of compensating for the drift of the local high-precision clock using detached timestamp correction includes: Select two or more adjacent brake pressure sensor sections in a heavy-haul freight train; After the braking command is issued, the propagation time of the braking pressure wave between adjacent sections is calculated. Based on the theoretical speed of pressure wave propagation and the actual measured propagation time, a time deviation model between adjacent sections is established. The time deviation model is used to correct the timestamp of the local high-precision clock to compensate for the error caused by clock drift.

11. A device for monitoring the braking performance of heavy-duty freight trains, characterized in that, The device includes: The signal acquisition module is used to synchronously acquire the braking pressure signals of the first locomotive, the second locomotive, and multiple freight cars in the heavy-duty freight train based on GNSS time, and obtain the train pipe pressure data and their corresponding time tags at each section of the heavy-duty freight train. The first locomotive is located at the head of the heavy-duty freight train, the second locomotive is located in the middle of the heavy-duty freight train, and the multiple freight cars are located at different sections of the heavy-duty freight train at equal intervals. The time difference calculation module is used to calculate the time difference between the first locomotive and the second locomotive, and between the first locomotive and each freight car, based on the time tag, when the braking pressure signal meets the preset stability conditions. The braking performance judgment module is used to determine whether the braking performance of the heavy-duty freight train is normal based on the maximum value and distribution dispersion of the time difference.

12. An electronic 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 steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 10.

Images