Track geometric deterioration early warning method and device based on vehicle-mounted line inspection tester

Abstract

The invention discloses a track geometric deterioration early warning method and device based on a vehicle-mounted line inspection tester, and the method comprises the steps: obtaining the total data detected under a plurality of train numbers at the same mileage point; utilizing a density clustering algorithm to extract invalid data from the total data of each train number; comparing the invalid data proportion with a preset ratio range, and evaluating the data quality grade of each train number according to a comparison result; selecting two groups of data, determining a saliency level between the two groups of data by adopting a rank sum test method, and judging whether saliency difference exists between the two groups of data according to the saliency level; determining that the data quality grade classification meets a rationality requirement according to a significant difference judgment result; and according to the evaluation result of the data quality grade of each train number, carrying out early warning processing on geometric deterioration of the track. According to the method, the quality of detection data can be effectively evaluated, and the accuracy of track geometric deterioration early warning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of railway engineering, and in particular to a method and device for early warning of track geometry degradation based on a vehicle-mounted track inspection instrument. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the field of railway engineering tracks, professional inspection trains equipped with track geometry dynamic detection systems are used to implement periodic track geometry inspections. At the same time, operating trains are equipped with on-board track inspection instruments to monitor the dynamic changes in track geometry quality in real time and issue timely warnings. It can be seen that the on-board track inspection ritual is an important technical means for stabilizing track geometry quality and ensuring railway transportation safety during the inspection cycle. As the number of locomotives equipped with on-board track inspection instruments increases, the detection frequency response increases, and the deviation data generated also increases dramatically; at the same time, the deviation data also faces interference from monitoring devices (sensor noise, drift, and even failures in harsh vibration environments), operating environments (such as local strong winds, high-speed trains on adjacent lines, etc.) and human factors (such as installation and maintenance behaviors that do not comply with regulations), resulting in a large amount of invalid or abnormal data in the deviation data, which seriously affects the data quality and the accuracy of monitoring and early warning. Summary of the invention

[0004] The embodiment of the present invention provides a track geometry degradation early warning method based on a vehicle-mounted track inspection instrument, which is used to effectively evaluate the quality of detection data and improve the accuracy of track geometry degradation early warning. The method includes:

[0005] At the same mileage point, obtain the total data detected by the vehicle-mounted line inspection instrument under multiple train trips;

[0006] Using density clustering algorithm, invalid data is extracted from the total data detected under each train; the proportion of invalid data under each train in the total data of the train is compared with the preset ratio range, and the data quality level of each train is evaluated according to the comparison result;

[0007] Select two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, use the rank sum test method to determine the significance level between the two groups of data, and judge whether there is a significant difference between the two groups of data based on the significance level; and determine that the data quality level classification meets the rationality requirements based on the significant difference judgment results;

[0008] On the basis that the data quality level classification meets the rationality requirements, early warning processing of track geometry degradation is carried out according to the evaluation results of the data quality level of each train.

[0009] The embodiment of the present invention further provides a track geometry degradation early warning device based on a vehicle-mounted track inspection instrument, which is used to effectively evaluate the quality of detection data and improve the accuracy of track geometry degradation early warning. The device includes:

[0010] A data acquisition module is used to acquire the total data detected by the vehicle-mounted line inspection instrument under multiple train trips at the same mileage point;

[0011] The data quality level evaluation module is used to extract invalid data from the total data detected under each train by using a density clustering algorithm; compare the proportion of invalid data under each train in the total data of the train with a preset ratio range, and evaluate the data quality level of each train according to the comparison result;

[0012] The data quality classification rationality judgment module is used to select two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, use the rank sum test method to determine the significance level between the two groups of data, and judge whether there is a significant difference between the two groups of data according to the significance level; according to the significant difference judgment result, determine whether the data quality classification meets the rationality requirements;

[0013] The track geometry degradation early warning module is used to carry out early warning processing of track geometry degradation based on the evaluation results of the data quality level of each train trip, on the basis that the data quality level classification meets the rationality requirements.

[0014] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned track geometry degradation early warning method based on the vehicle-mounted track inspection instrument when executing the computer program.

[0015] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the track geometry degradation early warning method based on the vehicle-mounted track inspection instrument is implemented.

[0016] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the track geometry degradation early warning method based on the vehicle-mounted track inspection instrument is implemented.

[0017] In an embodiment of the present invention, at the same mileage point, total data detected by a vehicle-mounted line inspection instrument under multiple train trips are obtained; invalid data are extracted from the total data detected under each train trip using a density clustering algorithm; the proportion of invalid data under each train trip in the total data of the train trip is compared with a preset ratio range, and the data quality level of each train trip is evaluated according to the comparison result; two groups of data are selected from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, and a rank sum test method is used to determine the significance level between the two groups of data, and whether there is a significant difference between the two groups of data is judged according to the significance level; according to the result of the significant difference judgment, it is determined that the data quality level classification meets the rationality requirements; on the basis that the data quality level classification meets the rationality requirements, early warning processing of track geometry degradation is performed according to the evaluation result of the data quality level of each train trip. In the above process, the embodiment of the present invention uses a density clustering algorithm to extract invalid data from the total data detected under each train trip, which significantly improves the data processing efficiency. The rank sum test method is used to determine the significant difference between the data with the highest data quality level and the data with the lowest data quality level, and verify the rationality of the data quality level classification, thereby effectively evaluating the quality of the detection data and improving the accuracy of track geometry degradation warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0019] Figure 1 It is a flow chart of a track geometry degradation early warning method based on a vehicle-mounted track inspection instrument in an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of identifying invalid data points of horizontal acceleration based on density clustering algorithm in an embodiment of the present invention;

[0021] Figure 3 Schematic diagram of identifying invalid data points of vertical acceleration based on density clustering algorithm in an embodiment of the present invention;

[0022] Figure 4 This is a distribution diagram of the detection data of the level A and level C vehicle-mounted line inspection instruments in the embodiment of the present invention;

[0023] Figure 5 A vertical acceleration trend diagram in an embodiment of the present invention;

[0024] Figure 6It is a horizontal acceleration trend diagram in an embodiment of the present invention;

[0025] Figure 7 Schematic diagram of a track geometry degradation early warning device based on a vehicle-mounted track inspector in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0027] Figure 1 Flow chart of a track geometry degradation early warning method based on a vehicle-mounted track inspection instrument in an embodiment of the present invention, the method comprising:

[0028] Step 101, at the same mileage point, obtaining total data detected by the vehicle-mounted line inspection instrument under multiple train trips;

[0029] Step 102, using a density clustering algorithm, extract invalid data from the total data detected for each train number; compare the proportion of invalid data for each train number in the total data of the train number with a preset ratio range, and evaluate the data quality level of each train number based on the comparison result;

[0030] Step 103, selecting two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, using the rank sum test method to determine the significance level between the two groups of data, and judging whether there is a significant difference between the two groups of data according to the significance level; and judging the result of the significant difference, determining whether the data quality level classification meets the rationality requirement;

[0031] Step 104, on the basis that the data quality level classification meets the rationality requirements, according to the evaluation results of the data quality level of each train trip, early warning processing of track geometry degradation is performed.

[0032] Each step is described in detail below.

[0033] In step 101, at the same mileage point, the total data detected by the vehicle-mounted line inspection instrument under multiple trains is obtained; in step 102, the density clustering algorithm is used to extract invalid data from the total data detected under each train; the proportion of invalid data under each train in the total data of the train is compared with a preset ratio range, and the data quality level of each train is evaluated based on the comparison result.

[0034] In a specific embodiment, the total data detected by all vehicle-mounted line inspectors at the same mileage point of Line A within one day is obtained through a vehicle-mounted line inspector, and the total data includes horizontal acceleration and vertical acceleration deviation data. During the detection period, the vehicle-mounted line inspector serves as a special equipment for dynamically monitoring the geometric smoothness of the line track, and can dynamically monitor the line status in real time and detect adverse changes in time. Combined with weather data and high-speed vehicle meeting data, the lateral and vertical acceleration deviation data monitored by the vehicle-mounted line inspectors at the same mileage point are respectively screened for invalid data using a density clustering algorithm, and the device number of the vehicle-mounted line inspector with abnormal data characteristics (invalid data) at the same mileage point is marked, and the other mileage points of Line A are marked in the same way. Among them, the density clustering algorithm is defined as follows:

[0035] Take the data points detected by the vehicle-mounted line inspection instrument at the same mileage point as the center of the circle, draw a circle with a preset radius, and the number of monitoring data within the circle is the density value of the monitoring data point. Through a large number of data experiments, the optimal density threshold is selected. The points whose number of monitoring data points contained in the circle is less than the optimal density threshold are low-density points, and vice versa. If a high-density monitoring data point is within the circle of another high-density monitoring data point, connect the two monitoring data points. And so on, the monitoring data points are continuously connected. If there is a low-density monitoring data point that is also within the circle of high-density monitoring data points, connect this low-density monitoring data point to the nearest high-density monitoring data point, which is called a boundary point. All the monitoring data points connected together form a cluster, and the low-density monitoring data points that are not at any high-density point are invalid data points. Such as Figure 2 is a schematic diagram of identifying invalid data points of horizontal acceleration based on a density clustering algorithm in an embodiment of the present invention, Figure 3 Schematic diagram of identifying invalid vertical acceleration data points based on a density clustering algorithm in an embodiment of the present invention; Figure 2 The orange mark in the figure is an invalid data point for the horizontal acceleration at 1140 km up a certain line. Figure 3 The orange mark in the figure indicates the invalid data point of the vertical acceleration at 1145 km.

[0036] After using the density clustering algorithm to identify invalid data points, the invalid data points are further correlated with meteorological data and on-road data for in-depth analysis to exclude other invalid data that may be generated by meteorological conditions (such as strong winds, rain, freezing, etc.) or on-road situations (such as airflow disturbances when encountering other vehicles at close range). This can more accurately identify vehicle shaking caused by road problems, thereby improving the accuracy and reliability of data analysis.

[0037] In one embodiment, the track geometry degradation early warning method based on the vehicle-mounted track inspection instrument further includes:

[0038] Use the analytic hierarchy process to determine the weight value corresponding to each preset data quality assessment indicator;

[0039] The data quality assessment result is determined according to the weight value corresponding to each preset data quality assessment indicator.

[0040] In one embodiment, determining the weight value corresponding to each preset data quality assessment indicator includes:

[0041] According to the preset data quality assessment indicators, a data quality assessment matrix is ​​established using the hierarchical analysis method, and the weight values ​​corresponding to the data quality assessment indicators are determined according to the data quality assessment matrix;

[0042] According to the weight values ​​corresponding to the data quality assessment indicators and the empirical weight values ​​pre-acquired by the user, a comprehensive evaluation function is established to determine the data quality assessment results.

[0043] In a specific embodiment, the analytic hierarchy process is used to comprehensively evaluate the quality of the data detected by the vehicle-mounted line inspection instrument. This method can combine qualitative and quantitative analysis, has strong operability, simple principles, and strong rigor, and is widely used in the analysis and decision-making of complex systems. The empirical weight values ​​pre-acquired by the expert scoring method are used, where the empirical weight values ​​include the weight values ​​corresponding to the risk loss index and the weight values ​​corresponding to the risk loss probability index. The analytic hierarchy process is used to judge the data quality of a certain vehicle-mounted line, as follows:

[0044] First, the first data quality evaluation matrix is ​​established. The first type of data quality indicators include: data integrity evaluation indicators, data accuracy evaluation indicators, data consistency evaluation indicators and data timeliness evaluation indicators; among them, the data integrity evaluation indicators are used to ensure that the data collected by the vehicle-mounted line inspection instrument covers the entire mileage of the line, is complete, and has no omissions or losses; the data accuracy evaluation indicators are used to screen invalid data and check whether the data is accurate; the data consistency evaluation indicators are used to evaluate whether the distribution of the monitoring data collected by the vehicle-mounted line inspection instrument at different times and the same line mileage is consistent, so as to judge the reliability and stability of the data; the data timeliness evaluation indicators are used to update the speed and real-time performance of the vehicle-mounted line inspection instrument detection data to ensure that the data can timely reflect the changes in the track status. Secondly, the first data quality evaluation matrix is ​​normalized, and the weight vector corresponding to the first type of data quality indicators is calculated according to the processed first data quality evaluation matrix, and the maximum characteristic root is calculated according to the weight vector, and the data quality is judged according to the maximum characteristic root.

[0045] In a specific embodiment, the proportion of invalid data in the total data of each train is calculated to evaluate the data quality level of each train: Invalid data proportion = number of invalid data items / total number of items) × 100%.

[0046] Low percentage of invalid data: It is generally believed that a data set with a low percentage of invalid data (such as less than 5%) is of high quality and the data grade is A.

[0047] Moderate proportion of invalid data: Invalid data accounts for between 5% and 10% and may require further data cleaning and verification. The data level is B.

[0048] High proportion of invalid data: If the proportion of invalid data exceeds 10%, the quality of the dataset may be low and requires detailed data cleaning and quality control processes. The data level is C.

[0049] When the horizontal acceleration data in the detection data with data quality levels A and B is greater than or equal to the preset horizontal acceleration threshold, or the vertical acceleration data is greater than or equal to the preset vertical acceleration threshold, early warning processing is performed.

[0050] In step 103, two groups of data are selected from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level. The rank sum test method is used to determine the significance level between the two groups of data, and whether there is a significant difference between the two groups of data is determined based on the significance level; based on the result of the significant difference judgment, it is determined that the data quality level classification meets the rationality requirements.

[0051] In one embodiment, a rank sum test is used to determine the significance level between two sets of data, and judging whether there is a significant difference between the two sets of data according to the significance level includes:

[0052] When the two groups of data do not obey the normal distribution, the Wilcoxon rank sum test method is used to calculate the significance level between the two groups of data;

[0053] According to the significance level between the two groups of data, determine whether there is a significant difference in the overall distribution of the two groups of data.

[0054] like Figure 4 As shown, Figure 4 It is a distribution diagram of the detection data of the vehicle-mounted line inspection instrument of level A and level C in the embodiment of the present invention. In a specific embodiment, the Wilcoxon rank sum test (also known as the Mann-Whitney U test) is a non-parametric hypothesis testing method, which is specifically used to compare whether there are significant differences between two independent samples (in this case, the detection data of vehicle-mounted line inspection instruments of levels A and C). It is suitable for vehicle-mounted line inspection instrument monitoring data sets that are difficult to accurately describe by a normal distribution model. By calculating the difference in the rank sums between the monitoring data samples, the Wilcoxon rank sum test can effectively evaluate whether there are statistically significant differences between the two groups of monitoring data samples, thereby providing strong support for our understanding of the distribution characteristics of monitoring data of different levels.

[0055] The calculation formula of the test statistic U is:

[0056]

[0057] Among them: n1 and n2 are data samples of level A and level C respectively, and R1 is the rank sum of data samples corresponding to level A.

[0058] The calculated test statistic U value needs to be compared with the standard U distribution table to determine whether to reject the null hypothesis. At the significance level alpha = 0.05, there is a significant difference in the medians of the two groups of data, thus verifying the rationality of the data quality level classification.

[0059] In step 104, on the basis that the data quality level classification meets the rationality requirements, early warning processing of track geometry degradation is performed according to the evaluation results of the data quality level of each train.

[0060] In one embodiment, after performing corresponding warning processing according to the evaluation result of the data quality level of each train, the method further includes:

[0061] According to the evaluation result of the data quality level of each train, data with the same data quality level under different trains are obtained;

[0062] Perform trend analysis on data with the same quality level at the same mileage point and different train numbers, and identify potential track geometry anomalies based on the analysis results.

[0063] In a specific embodiment, trend analysis is performed on the horizontal acceleration data and vertical acceleration data with the same data quality level at the same mileage point and different train numbers, and trend items within the maintenance cycle are extracted, such as Figure 5 A vertical acceleration trend diagram in an embodiment of the present invention; Figure 6 This is a horizontal acceleration trend graph in an embodiment of the present invention. The trend graph can intuitively show the changing trend of the detection values ​​of different levels of vehicle-mounted track inspection instruments over time, helping to quickly identify potential abnormal fluctuations, periodic changes or stability problems. Through the trend graph, the effectiveness of maintenance measures can be more accurately evaluated, and possible maintenance interventions can be discovered and predicted in a timely manner, thereby optimizing maintenance strategies and ensuring the smooth operation of the rail system.

[0064] The present invention also provides a track geometry degradation early warning device based on a vehicle-mounted track inspection instrument in an embodiment, as described in the following embodiment. Since the principle of solving the problem by the device is similar to that of the track geometry degradation early warning method based on a vehicle-mounted track inspection instrument, the implementation of the device can refer to the implementation of the track geometry degradation early warning method based on a vehicle-mounted track inspection instrument, and the repeated parts will not be repeated.

[0065] Figure 7 Schematic diagram of a track geometry degradation early warning device based on a vehicle-mounted track inspection instrument in an embodiment of the present invention, the device comprises:

[0066] The data acquisition module 701 is used to acquire the total data detected by the vehicle-mounted line inspection instrument under multiple train trips at the same mileage point;

[0067] The data quality level evaluation module 702 is used to extract invalid data from the total data detected under each train number by using a density clustering algorithm; compare the proportion of invalid data under each train number in the total data of the train number with a preset ratio range, and evaluate the data quality level of each train number according to the comparison result;

[0068] The data quality classification rationality judgment module 703 is used to select two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, use the rank sum test method to determine the significance level between the two groups of data, and judge whether there is a significant difference between the two groups of data according to the significance level; and determine whether the data quality classification meets the rationality requirements according to the significant difference judgment result;

[0069] The track geometry degradation early warning module 704 is used to perform early warning processing of track geometry degradation based on the evaluation results of the data quality level of each train trip on the basis that the data quality level classification meets the rationality requirements.

[0070] In one embodiment, a data quality assessment module is further included, which is specifically used to:

[0071] Use the analytic hierarchy process to determine the weight value corresponding to each preset data quality assessment indicator;

[0072] The data quality assessment result is determined according to the weight value corresponding to each preset data quality assessment indicator.

[0073] In one embodiment, the data quality assessment module is specifically used to:

[0074] According to the preset data quality assessment indicators, a data quality assessment matrix is ​​established using the hierarchical analysis method, and the weight values ​​corresponding to the data quality assessment indicators are determined according to the data quality assessment matrix;

[0075] According to the weight values ​​corresponding to the data quality assessment indicators and the empirical weight values ​​pre-acquired by the user, a comprehensive evaluation function is established to determine the data quality assessment results.

[0076] In one embodiment, the data quality classification rationality judgment module 703 is specifically used to:

[0077] When the two groups of data do not obey the normal distribution, the Wilcoxon rank sum test method is used to calculate the significance level between the two groups of data;

[0078] According to the significance level between the two groups of data, determine whether there is a significant difference in the overall distribution of the two groups of data.

[0079] In one embodiment, a trend analysis module is further included, which is specifically used to:

[0080] According to the evaluation result of the data quality level of each train, data with the same data quality level under different trains are obtained;

[0081] Perform trend analysis on data with the same quality level at the same mileage point and different train numbers, and identify potential track geometry anomalies based on the analysis results.

[0082] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned track geometry degradation early warning method based on the vehicle-mounted track inspection instrument when executing the computer program.

[0083] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the track geometry degradation early warning method based on the vehicle-mounted track inspection instrument is implemented.

[0084] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the track geometry degradation early warning method based on the vehicle-mounted track inspection instrument is implemented.

[0085] In an embodiment of the present invention, at the same mileage point, total data detected by a vehicle-mounted line inspection instrument under multiple train trips are obtained; invalid data are extracted from the total data detected under each train trip using a density clustering algorithm; the proportion of invalid data under each train trip in the total data of the train trip is compared with a preset ratio range, and the data quality level of each train trip is evaluated according to the comparison result; two groups of data are selected from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, and a rank sum test method is used to determine the significance level between the two groups of data, and whether there is a significant difference between the two groups of data is judged according to the significance level; according to the result of the significant difference judgment, it is determined that the data quality level classification meets the rationality requirements; on the basis that the data quality level classification meets the rationality requirements, early warning processing of track geometry degradation is performed according to the evaluation result of the data quality level of each train trip. In the above process, the embodiment of the present invention uses a density clustering algorithm to extract invalid data from the total data detected under each train trip, which significantly improves the data processing efficiency. The rank sum test method is used to determine the significant difference between the data with the highest data quality level and the data with the lowest data quality level, and verify the rationality of the data quality level classification, thereby effectively evaluating the quality of the detection data and improving the accuracy of track geometry degradation warning.

[0086] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A track geometry degradation early warning method based on a vehicle-mounted track inspection instrument, characterized in that: include: At the same mileage point, obtain the total data detected by the vehicle-mounted line inspection instrument under multiple train trips; Using density clustering algorithm, invalid data is extracted from the total data detected under each train trip; The proportion of invalid data in the total data of each train is compared with the preset ratio range, and the data quality level of each train is evaluated according to the comparison result; Select two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, use the rank sum test method to determine the significance level between the two groups of data, and judge whether there is a significant difference between the two groups of data based on the significance level; and determine that the data quality level classification meets the rationality requirements based on the significant difference judgment results; On the basis that the data quality level classification meets the rationality requirements, early warning processing of track geometry degradation is carried out according to the evaluation results of the data quality level of each train.

2. The method according to claim 1, characterized in that Also includes: Use the analytic hierarchy process to determine the weight value corresponding to each preset data quality assessment indicator; The data quality assessment result is determined according to the weight value corresponding to each preset data quality assessment indicator.

3. The method according to claim 2, characterized in that The analytic hierarchy process is used to determine the weight value corresponding to each preset data quality assessment indicator, including: According to the preset data quality assessment indicators, a data quality assessment matrix is ​​established using the hierarchical analysis method, and the weight values ​​corresponding to the data quality assessment indicators are determined according to the data quality assessment matrix; According to the weight values ​​corresponding to the data quality assessment indicators and the empirical weight values ​​pre-acquired by the user, a comprehensive evaluation function is established to determine the data quality assessment results.

4. The method according to claim 1, characterized in that The rank sum test method is used to determine the significance level between the two groups of data, and whether there is a significant difference between the two groups of data is judged according to the significance level, including: When the two groups of data do not obey the normal distribution, the Wilcoxon rank sum test method is used to calculate the significance level between the two groups of data; According to the significance level between the two groups of data, determine whether there is a significant difference in the overall distribution of the two groups of data.

5. The method according to claim 1, characterized in that After the corresponding early warning processing is carried out according to the evaluation results of the data quality level of each train, it also includes: According to the evaluation result of the data quality level of each train, data with the same data quality level under different trains are obtained; Perform trend analysis on data with the same quality level at the same mileage point and different train numbers, and identify potential track geometry anomalies based on the analysis results.

6. A track geometry degradation early warning device based on a vehicle-mounted track inspection instrument, characterized in that: include: A data acquisition module is used to acquire the total data detected by the vehicle-mounted line inspection instrument under multiple train trips at the same mileage point; The data quality level evaluation module is used to extract invalid data from the total data detected under each train by using a density clustering algorithm; compare the proportion of invalid data under each train in the total data of the train with a preset ratio range, and evaluate the data quality level of each train according to the comparison result; The data quality classification rationality judgment module is used to select two groups of data from the data quality levels of multiple train trips: data with the highest data quality level and data with the lowest data quality level, use the rank sum test method to determine the significance level between the two groups of data, and judge whether there is a significant difference between the two groups of data based on the significance level; According to the results of significant difference judgment, determine whether the data quality classification meets the rationality requirements; The track geometry degradation early warning module is used to carry out early warning processing of track geometry degradation based on the evaluation results of the data quality level of each train trip, on the basis that the data quality level classification meets the rationality requirements.

7. The device according to claim 6, characterized in that It also includes a data quality assessment module, which is specifically used to: Use the analytic hierarchy process to determine the weight value corresponding to each preset data quality assessment indicator; The data quality assessment result is determined according to the weight value corresponding to each preset data quality assessment indicator.

8. The device according to claim 7, characterized in that Data quality assessment module, specifically used for: According to the preset data quality assessment indicators, a data quality assessment matrix is ​​established using the hierarchical analysis method, and the weight values ​​corresponding to the data quality assessment indicators are determined according to the data quality assessment matrix; According to the weight values ​​corresponding to the data quality assessment indicators and the empirical weight values ​​pre-acquired by the user, a comprehensive evaluation function is established to determine the data quality assessment results.

9. The device according to claim 6, characterized in that The data quality classification rationality judgment module is specifically used for: When the two groups of data do not obey the normal distribution, the Wilcoxon rank sum test method is used to calculate the significance level between the two groups of data; According to the significance level between the two groups of data, determine whether there is a significant difference in the overall distribution of the two groups of data.

10. The device according to claim 6, characterized in that Also includes trend analysis modules, specifically for: According to the evaluation result of the data quality level of each train, data with the same data quality level under different trains are obtained; Perform trend analysis on data with the same quality level at the same mileage point and different train numbers, and identify potential track geometry anomalies based on the analysis results.

11. 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, the method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images