Urban rail comprehensive inspection vehicle multi-source detection data mileage correction method and system

Abstract

The present application relates to a kind of urban rail integrated detection vehicle multi-source detection data mileage correction method and system.The method includes: data feature identification: by analyzing the change feature of pantograph-catenary pullout value, the instantaneous mutation feature point at the joint of anchor section is identified, to obtain a series of feature points corresponding to the joint position in through mileage;Pantograph-catenary pullout value data feature and through mileage alignment: by feature point alignment and resampling, pantograph-catenary pullout value data is matched with through mileage, to correct mileage deviation and enhance data positioning accuracy;Multi-source data "time-mileage" synchronization: by linear interpolation reconstruction time series, ensure that pantograph-catenary pullout value data after resampling is synchronized in time and mileage, and new time information is given to other professional detection data.The system includes detection module, database and processing module, wherein, processing module can extract pantograph-catenary pullout value detection data from database and complete mileage correction using mileage correction method.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban rail detection technology, and particularly relates to a multi-source detection data mileage correction method and system for a comprehensive detection vehicle for urban rail. BACKGROUND

[0002] The comprehensive detection vehicle for urban rail (hereinafter referred to as "comprehensive detection vehicle") is a vehicle specially used for detection and maintenance of urban rail transit lines. It is equipped with various advanced detection equipment and systems, which can realize comprehensive and efficient detection of track, pantograph, communication and other facility states. During operation, the comprehensive detection vehicle receives detection data through various professional sensors, while collecting time and mileage information. These data are used to evaluate the geometric parameters of the track (such as track gauge, level, height, direction), the geometric parameters of the catenary (such as pull-out value, guide height, hard point), and the performance of the signal system (such as signal lights, switches, track circuits). In addition, the comprehensive detection vehicle is also equipped with high-precision devices such as laser scanners, inertial navigation systems, high-definition cameras and data acquisition systems, to ensure the accuracy and reliability of the detection results. Through real-time data transmission and remote monitoring platform, management personnel can timely grasp the detection situation, realize precise maintenance and efficient maintenance, and ensure the safe and stable operation of urban rail transit.

[0003] When a disease is detected, manual re-inspection and repair work are required. This requires the mileage information of each detection point in the detection system to be consistent with the field mileage. However, the mileage positioning system of the comprehensive detection vehicle uses the method of optical encoder pulse counting. Its principle is that the wheel of the comprehensive detection vehicle for urban rail drives the optical encoder to rotate synchronously, the pulse interval is calculated according to the wheel circumference and the number of pulses, and the distance passed is calculated through pulse counting and pulse interval. Therefore, the following factors cause deviation in the mileage positioning during the detection process:

[0004] (1) Wheel eccentricity: there may be a deviation between the actual circumference and the theoretical circumference of the wheel;

[0005] (2) Acceleration or braking: acceleration or braking causes sliding friction between the wheel and the track, resulting in deviation;

[0006] (3) Difference between system mileage calculation and line design drawing: the system mileage calculation is continuous mileage, while the line design drawing has long and short chain information, thus causing a certain deviation.

[0007] Due to the superposition of the above factors, the deviation gradually accumulates with the increase of the detection mileage, eventually causing a large deviation between the mileage corresponding to the detection data in the system and the field mileage, i.e. mileage mispositioning. This seriously affects the positioning accuracy of field re-inspection and maintenance.

[0008] Current methods related to railway detection data mileage correction (alignment) include:

[0009] (1) Correcting the detection section based on data characteristics

[0010] For example, Zhao Zhengyang et al. in the article "Track Dynamic Geometric State and Wheel Rail Force Detection Data Mileage Calibration Method and Application" (Zhao Zhengyang, Wang Bing, Li Yang, et al. Track Dynamic Geometric State and Wheel Rail Force Detection Data Mileage Calibration Method and Application [J]. Railway Construction, 2022, 62(10): 55-59.) proposed a mileage calibration method for track dynamic geometric state and wheel rail force detection data under unified collection and dispersed collection mode. Under unified collection mode, first calibrate the mileage of track dynamic geometric state detection data, then synchronize and align the mileage of wheel rail force detection data. Under dispersed collection mode, use special section, line element and detection waveform correlation analysis method to realize the mileage calibration of wheel rail force detection data. However, the circular curve involved in this article contains four feature points, and its recognition accuracy is greatly limited; and the main point section is used as the reference to correct the mileage error, which only gets accurate correction near the main point, and still has a large error in other areas.

[0011] (2) Hardware assistance

[0012] For example, Yang Chao et al. in the article "Principle and Application of GPS Mileage Automatic Correction System" (Yang Chao, Wang Weidong. Principle and Application of GPS Mileage Automatic Correction System [J]. Railway Computer Application, 2009, 18(5): 33-35.) mentioned installing Global Positioning System (GPS) and Differential Positioning System (DGPS) on the comprehensive inspection car to automatically correct the mileage deviation in real time. For another example, Liu Xiaolei et al. in the article "Application of RFID Technology in Train High-precision Positioning" (Liu Xiaolei, Huang Pu. Application of RFID Technology in Train High-precision Positioning [J]. Urban Rapid Transit, 2017, 30(3): 107-111.) mentioned that Radio Frequency Identification (RFID) technology and near-field wireless communication technology can be used to install transmitters and receivers with mileage codes on the track line and vehicle body to control the mileage deviation from the source. However, the above methods have the following defects: on the one hand, urban rail transit is mostly located in underground tunnels, and wireless signal transmission is difficult without signal transceiver equipment; on the other hand, whether it is to add equipment to enhance wireless signal transmission or to add other types of auxiliary equipment, it will produce high installation costs, and subsequent maintenance costs are also involved. In addition, some special lines also have restrictions on adding external equipment.

[0013] Therefore, the prior art still cannot well solve the problem of mileage deviation (i.e. mileage misplacement) of the comprehensive inspection vehicle in the detection process due to various factors, so that there is an error between the mileage point corresponding to the detection data and the field mileage point, which seriously affects the positioning accuracy of field re-measurement and maintenance. Therefore, a method is needed to align the mileage information in the system with the mileage in reality, realize accurate maintenance, and improve work efficiency.

[0014] In addition, on the one hand, there are differences in the understanding of those skilled in the art; on the other hand, a large number of literatures and patents have been studied by the applicant when making the present application, but due to the limitation of space, all details and contents have not been listed in detail, which does not mean that the present application does not have these characteristics of the prior art. On the contrary, the present application has all the characteristics of the prior art, and the applicant reserves the right to add relevant prior art in the background art. SUMMARY

[0015] In view of the deficiencies of the prior art, the present application provides a metro comprehensive inspection vehicle multi-source detection data mileage correction method and system, especially a metro comprehensive inspection vehicle multi-source detection data mileage correction method and system based on pantograph-catenary pull-out value data characteristics, to solve at least part of the above technical problems.

[0016] The present application discloses a metro comprehensive inspection vehicle multi-source detection data mileage correction method, which comprises:

[0017] S1, data feature recognition: by analyzing the change characteristics of the pantograph-catenary pull-out value, the instantaneous mutation feature points at the joint of the anchor section are identified, to obtain a series of feature points corresponding to the joint position of the through mileage;

[0018] S2, aligning the pull-out value data characteristics with the through mileage: by feature point alignment and resampling, the pantograph-catenary pull-out value data is matched with the through mileage, to correct the mileage deviation and enhance the data positioning accuracy;

[0019] S3, multi-source data "time-mileage" synchronization: by linear interpolation reconstruction of time series, the resampled pantograph-catenary pull-out value data is ensured to be synchronized in time and mileage, and new time information is assigned to other professional detection data.

[0020] The present application utilizes the pantograph-catenary pull-out value data characteristics for multi-source detection data mileage correction. The pantograph-catenary pull-out value data characteristics are obvious and easy to obtain, because these characteristics are caused by on-site hardware (such as anchor section joints), and the mileage information of these hardware has been accurately recorded in the through mileage. By drawing a "mileage (x) - pull-out value (y)" curve, the slope mutation points can be intuitively identified, which are the characteristic points, thereby ensuring high accuracy of data feature identification and reducing the possibility of misjudgment. The operation process mainly includes three steps of data feature identification, characteristic point alignment and multi-source data synchronization. The calculation amount of each step is small, which is suitable for large-scale data processing. The data acquisition difficulty is low, and the pantograph-catenary pull-out value data can be collected in real time through the sensor on the comprehensive inspection vehicle without complex equipment or technology. Through the identification and alignment of the characteristic points, the mileage deviation can be effectively eliminated, and the positioning accuracy of the multi-source detection data is improved, thereby improving the accuracy of the detection results. High-precision data alignment and synchronization not only optimize the maintenance strategy, reduce unnecessary maintenance work and reduce maintenance costs, but also enhance the overall reliability of the system, and provide strong technical support for the detection and maintenance of urban rail transit.

[0021] According to a preferred embodiment, the instantaneous mutation characteristic points at the anchor section joints are obtained by drawing a "mileage - pull-out value" curve, wherein the slope between each data point and its previous data point in the "mileage - pull-out value" curve is calculated, and when the slope corresponding to any data point exceeds the set slope threshold, the point is taken as a characteristic point and the mileage of the data is recorded as the identification of the characteristic point.

[0022] According to a preferred embodiment, the identified characteristic points are extracted to form a data feature set, and the data feature set is calculated with the through mileage anchor section joint mileage set to obtain a phase difference set. The phase difference set is applied to each element of the original data feature set as a translation amount to obtain a translated data feature set, thereby realizing the alignment of the pantograph-catenary pull-out value data characteristic information and the anchor section joints in the through mileage.

[0023] According to a preferred embodiment, in the pantograph-catenary pull-out value data resampling process, any two adjacent original data characteristic points are selected from the original data feature set, and the two original data characteristic points are mapped into the translated data feature set to obtain corresponding two new data characteristic points. The sampling points are obtained in the original interval formed between the two original data characteristic points at a preset sampling frequency to form a pull-out value data set.

[0024] According to a preferred embodiment, the sampling points in the resampling interval formed between two new data feature points are obtained in a manner that keeps the same sampling frequency, wherein when the original interval length is less than the corresponding resampling interval length, the number of sampling points in the resampling interval increases; when the original interval length is greater than the corresponding resampling interval length, the number of sampling points in the resampling interval decreases.

[0025] According to a preferred embodiment, for any new sampling point located in the resampling interval, the corresponding pantograph-catenary pull-out value can be calculated by linear interpolation, and the calculated pantograph-catenary pull-out value can be incorporated into the new pull-out value data set to realize the alignment of the pull-out value data and the through mileage.

[0026] According to a preferred embodiment, for any new sampling point, the two nearest original data feature points are first found, and linear interpolation is used to calculate the new time point, so that the mileage value corresponding to the new sampling point is consistent with the new time point, thereby synchronizing the pantograph-catenary pull-out value data and the mileage data in the time dimension.

[0027] According to a preferred embodiment, the various professional detection data collected by the urban rail comprehensive detection vehicle during operation can be stored in the database as multi-source data with detection mileage and detection time, wherein the multi-source data includes pantograph-catenary pull-out value detection data.

[0028] According to a preferred embodiment, when the field mileage and the detection mileage are inconsistent, the alignment of the field mileage and the through mileage is realized through the database, wherein the correspondence table of the field mileage and the through mileage is maintained in advance in the database to establish a mileage comparison table, and then the field mileage is extracted through the association retrieval method.

[0029] The present application also discloses a kind of urban rail comprehensive detection vehicle multi-source detection data mileage correction system, it includes: detection module, it includes a plurality of detection devices for obtaining different types of detection data;Database, for storing the detection data obtained by each detection device;Processing module, for extracting data from database and processing data, to complete mileage correction. Preferably, the pantograph-catenary pull-out value detection device configured by the detection module can send the pantograph-catenary pull-out value detection data obtained to the database, so that the processing module can extract the pantograph-catenary pull-out value detection data from the database and complete the mileage correction using the aforementioned mileage correction method. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 It is the main step diagram of a kind of preferred embodiment of the present application provides a mileage correction method;

[0031] Figure 2 It is the schematic diagram of the structure plane of pantograph and catenary;

[0032] Figure 3 It is a schematic diagram of the mechanism of sudden change of pull-out value at the joint of anchor segment;

[0033] Figure 4 This is a schematic diagram of data feature identification of a preferred embodiment provided by the present invention;

[0034] Figure 5 This is a schematic diagram of pull-out value resampling according to a preferred embodiment of the present invention;

[0035] Figure 6 This is a schematic diagram of assigning on-site mileage labels according to a preferred embodiment of the present invention;

[0036] Figure 7 This is an operational flow chart of a mileage correction method according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following is a detailed description with reference to the accompanying drawings.

[0038] Example 1

[0039] like Figure 1 As shown, the present invention discloses a method for correcting the mileage of multi-source detection data of an urban rail integrated inspection vehicle (or simply an integrated inspection vehicle), in particular, a method for correcting the mileage of multi-source detection data of an urban rail integrated inspection vehicle based on the characteristics of pantograph-catenary pullout value data, which includes:

[0040] S1, data feature identification;

[0041] S2. Align the extracted data features with the through mileage;

[0042] S3. Multi-source data "time-mileage" synchronization.

[0043] Optimally, comprehensive inspection vehicles can be used to inspect and evaluate various infrastructure of rail transit systems in real time to ensure safety and efficiency. These vehicles integrate a variety of advanced inspection technologies, including laser measurement, photoelectric sensing, high-definition video, and high-speed data acquisition and processing systems. Equipped with multiple sensors and antennas, they ensure real-time monitoring and data recording while in motion. These vehicles regularly operate on track lines, providing continuous monitoring and fault warnings for the rail transit system. This proactive inspection approach not only improves the safety of urban rail transit but also significantly reduces maintenance costs and operational risks.

[0044] Preferably, the mileage correction method of the present invention may further include, before step S1 , the following steps: S0 , multi-source data collection and storage.

[0045] Preferably, the multi-source data is a general term of various professional detection data collected by the comprehensive inspection vehicle during operation, which includes track detection data, pantograph-catenary detection data, communication signal detection data, power system detection data, etc., so as to realize comprehensive detection of the facility state. Different professional detection processes can be completed by different detection devices carried on the comprehensive inspection vehicle. The track detection can include gauge, level and high-low (unevenness) detection, and track wear and cross-section detection to obtain corresponding track detection data, wherein the gauge, level and high-low (unevenness) detection can be performed by using laser ranging sensors, acceleration sensors and gyroscopes, etc.; the real cross-sectional shape of the track can be captured by using laser scanning technology to perform track wear and cross-section detection. The pantograph-catenary detection can include contact wire wear and height detection, pull-out value (contact wire offset) detection and dynamic pantograph-catenary relationship detection to obtain pantograph-catenary detection data, wherein the contact wire wear and height detection can be performed by using laser ranging and visual recognition technology; the pull-out value (contact wire offset) detection can be performed by using a camera and computer vision technology; the dynamic pantograph-catenary relationship detection can be performed by using high-speed photography and sensors in combination to monitor the relative motion of the pantograph and the contact wire. The communication signal detection can include wireless signal strength and quality detection and signal system state detection to obtain communication signal detection data, wherein the wireless signal strength and quality detection can be performed by using a radio spectrum analyzer; the signal system state detection can be performed by using signal monitoring software to analyze the connectivity and quality of the communication signal. The power system detection can include power supply voltage and current detection to obtain power system detection data, wherein the power supply voltage and current detection can be performed by using voltage and current sensors for real-time monitoring.

[0046] Preferably, the original data recorded by the comprehensive inspection vehicle during operation can include detection mileage and detection time, wherein the detection mileage is used to represent the relative spatial position of the detection point, which generally starts from "0"; the detection time is used to record the time information of the data acquisition of a certain point in the detection process.

[0047] Preferably, the multi-source data collected by the comprehensive inspection vehicle can be stored in a database, wherein the data stored in the database can include pantograph-catenary pull-out value detection data (which can be referred to as pantograph-catenary pull-out value or pull-out value) and other professional detection data. Preferably, the pantograph-catenary pull-out value detection data is a type of pantograph-catenary detection data, which is a detection value of the lateral offset of the contact wire from the center line of the pantograph. The detection of the pull-out value is crucial to ensure the stability of power transmission and reduce the wear between the pantograph and the contact wire. Excessive pull-out value can cause the pantograph to separate from the contact wire, thereby interrupting power supply and affecting normal train operation. Preferably, the pantograph-catenary pull-out value detection data can be obtained by installing a high-definition camera on the comprehensive inspection vehicle to capture the relative position between the pantograph and the contact wire in real time, and then calculating the lateral offset between the pantograph and the contact wire through image analysis technology; or by using laser positioning technology to accurately measure the lateral distance between the pantograph and the contact wire, and then processing the laser measurement data. Preferably, the collected image or laser data is analyzed in real time by a vehicle-mounted computer, and the analysis software built-in the vehicle-mounted computer can automatically identify the positions of the pantograph and the contact wire and calculate the pull-out value, wherein the generated pull-out value data can be presented in the form of time series and used for monitoring trends and detecting abnormalities. In the prior art, the pantograph-catenary pull-out value detection data is usually used as an important indicator for evaluating the stability of the power supply system during train operation, so that track maintenance personnel can detect problems in time and perform preventive maintenance by monitoring the pull-out value. For example, if the pull-out value of a certain section of track continuously exceeds the set safety range, the installation of the track or the catenary needs to be checked, and whether the position of the pantograph needs to be adjusted. The present application uses the unique characteristics of the pantograph-catenary pull-out value detection data to segment the alignment of the pantograph-catenary pull-out value detection data and the through mileage by using the feature points in the pantograph-catenary pull-out value detection data as boundaries, and finally realizes the mileage correction of the multi-source detection data of the urban rail comprehensive inspection vehicle.

[0048] In urban rail transit, rigid catenary is a commonly used power supply mode, especially in underground tunnel environment. The rigid catenary is composed of metal poles and crossbars, which has high strength and firmness in structure, and is installed by fixed suspension, so that the contact wire does not have the tension problem in traditional suspension mode. Therefore, in the process of dynamic detection, the "mileage-pull-out value" curve between the pantograph and the contact wire shows uniform regularity and has significant periodicity. However, at the anchor joint, the situation is different. As shown in Figure 2 , the anchor joint is a key structure for smooth transition between the contact wire anchor sections, which connects the front and rear contact wires through parallel overlapping of short sections. As shown in Figure 3As shown, when the pantograph moves to the anchor joint, the power supply line transitions to the next section of the contact wire. The pullout value at this point exhibits a sudden, transient change. This sudden change is caused by a sudden change in the physical connection of the contact wire and is a crucial characteristic that cannot be ignored during the inspection process. This sudden change is a unique characteristic of the pantograph-catenary pullout value test data. By reverse-analyzing the changes in the pantograph-catenary pullout value, the location of the anchor joint can be identified. This identification is based on comparing the detected sudden changes in the pantograph-catenary pullout value with the through-line mileage information, as the mileage information of the anchor joint is queryable and accurate in the through-line mileage. Furthermore, because the comprehensive inspection vehicle is equipped with multiple specialized equipment during the inspection process, the mileage information collected simultaneously from each specialized inspection data is consistent. Therefore, the through-line mileage can be aligned with the on-site mileage through a step-by-step correlation method. This alignment of multi-source inspection data with the on-site mileage not only improves the accuracy of the inspection data but also enhances the reliability and operability of the analysis results. Through mileage refers to the length of the subway line that is physically connected after construction is complete. This includes mileage records for hardware facilities such as anchor joints. On-site mileage refers to the actual mileage markers on site, including information such as the length of the chain and kilometer markers, such as "K20+300." These markers are physically displayed on-site for easy identification by staff.

[0049] Preferably, if Figure 4 As shown, the bow-net pullout value detection data with unique characteristics can be manifested as a transient mutation between two consecutive detection points. This transient mutation can be intuitively seen by plotting the "mileage (x)-pullout value (y)" curve. The absolute value of the slope of the curve at the location where the transient mutation occurs is significantly larger than that at other locations. Furthermore, the data for plotting the "mileage (x)-pullout value (y)" curve is high-precision data obtained by extracting the bow-net pullout value-related data from the original data collected by the comprehensive inspection vehicle and performing pre-processing operations such as smoothing to reduce the impact of noise. The smoothing process can, for example, use a moving average method or a low-pass filter.

[0050] Preferably, in step S1, based on the drawn “mileage (x)-pullout value (y)” curve, the slope between each data point and its previous data point can be calculated, wherein the slope can be calculated by the following formula:

[0051]

[0052] Among them, y i and y i-1 are the extracted values ​​of the i-th and i-1-th data points, respectively, x i and x i-1 are the mileage of the i-th and i-1-th data points respectively.

[0053] Further, a slope threshold θ is set to distinguish normal slope and mutation slope. By traversing all calculated slopes, check whether each slope exceeds the threshold θ. If a certain slope exceeds the threshold θ, consider the position as a feature point and record the data mileage x i as the identification of feature points.

[0054] Preferably, in order to further improve the accuracy of identification, the preliminary identified feature points can be verified. Verification methods include but are not limited to checking the continuity and stability of the data before and after the feature points, and comparing with the known anchor joint positions. If the pull-out value data around the feature points conforms to the expected mutation pattern and is consistent with the known anchor joint positions, the validity of the feature points is confirmed.

[0055] Preferably, the confirmed valid feature points are recorded to form a data feature identification list. Each feature point can include its mileage position and corresponding arch-catenary pull-out value change. These feature points can be used in subsequent mileage alignment steps.

[0056] Preferably, through the identification of arch-catenary pull-out value data features, a series of feature points corresponding to the anchor joint positions in the through mileage can be obtained. Preferably, after obtaining a series of feature points, step S2 can be performed, wherein step S2 can include the following sub-steps: feature data alignment; pull-out value data resampling.

[0057] Preferably, in the coordinate system defined by the “mileage (x) - pull-out value (y)” curve, the identified feature points are extracted from the arch-catenary pull-out value data to form a data feature set B = {b1, b2, …, b n These feature points are represented as slope mutation points on the “mileage (x) - pull-out value (y)” curve, which are identified by calculating the slope between adjacent points and setting a threshold. Each feature point contains its mileage position b i and the corresponding arch-catenary pull-out value change. At the same time, the known anchor joint position information is extracted from the through mileage database to form a through mileage anchor joint mileage set R = {r1, r2, …, r n These information includes the mileage position r i of each anchor joint, where the through mileage data is usually derived from the full length information recorded after the completion of the subway engineering construction, and has high accuracy.

[0058] Preferably, for each pair of data, the difference between the data feature x coordinate and the through mileage anchor joint mileage x coordinate is calculated to obtain a phase difference set Δ. The specific calculation formula is as follows:

[0059] δ i = r i -b i

[0060] Δ={δ1,δ2,…,δ n}

[0061] Among them, δ i is the difference between the i-th data pair, i is an integer and 1≤i≤n; Δ is the phase difference set.

[0062] Optionally, the phase difference value Δ can be found by performing statistical analysis on the phase difference set Δ avg , which is used to reflect the overall offset between the bow-net pull-out value data and the through mileage, wherein the overall offset can be more accurately estimated by calculating the average or median.

[0063] Preferably, the phase difference set Δ is applied as a translation amount to each element of the original data feature set B to obtain the translated data feature set B'. The specific calculation formula is as follows:

[0064] b′ i =b i +δ i

[0065] B′={b′1,b′2,…,b′ n}

[0066] Among them, b' i is the value of the i-th data in the original data feature set B after translation, i is an integer and 1≤i≤n; B' is the data feature set after translation.

[0067] To ensure the accuracy of the alignment results, the resampled data can be verified. Specific methods include: feature point comparison, which compares the translated feature point B' with the anchor segment joint position R in the through-mileage to check for consistency; and data visualization, which plots the translated "mileage (x) - pullout value (y)" curve to observe the smoothness of the curve and the sudden changes in the feature points to ensure that the aligned data meets expectations.

[0068] Through the above steps, the characteristic information (i.e., characteristic points) of the pantograph-catenary pullout data can be aligned with the anchor joints in the through-line mileage. This method is not only simple to operate and requires minimal computation, but also effectively eliminates mileage deviations and improves the positioning accuracy of multi-source inspection data, providing reliable support for urban rail inspection and maintenance.

[0069] Preferably, in the process of aligning the characteristic data, the characteristic points of the pantograph-catenary pullout value data are aligned with the joints of the anchor sections in the through mileage, and a new characteristic point set B'={b'1, b'2, ..., b' n In order to further ensure the accuracy of the pulled value data at the new mileage position, the pulled value data needs to be resampled.

[0070] Preferably, when the pull-out value data is resampled, the pull-out value data set L k,k+1 = {l1, l2, …, ln} is defined first, where m represents the number of sampling points between any two adjacent data feature points (i.e. data points) b m and b k in set B, and 1≤k k+1 <n, k, m, n are positive integers. When set B is aligned with the anchor section mileage set R in the through mileage, data feature points b k and b k+1 are mapped to new positions b' k and b' k+1 respectively. In this process, the original pull-out value data set L k,k+1 also needs to be resampled accordingly to adapt to the new data point distribution.

[0071] Preferably, in the resampling process of the catenary-pantograph pull-out value data, the frequency of the sampler is kept unchanged, so that the elements in the pull-out value data set L k,k+1 are uniformly distributed, the sampling frequency (unit length interval) is f s , i.e. there are f s sampling points per meter or the distance between each point is Δk=1 / f s . When the original interval length is u=b k+1 -b k , the corresponding resampled interval length is u'=b' k+1 -b' k , and the stretching and compression processing method of the data is as follows:

[0072] When u'>u, it means that the aligned data interval is larger than the original data interval, i.e. the original data is stretched. To maintain the same frequency, the data is mapped to a longer interval length based on the up-sampling method, more sampling points are generated in the interval [b' k , b' k+1 , i.e. the number of sampling points in the interval [b' k , b' k+1 is increased;

[0073] When u'<u, it means that the aligned data interval is smaller than the original data interval, i.e. the original data is compressed. To maintain the same frequency, the data is mapped to a shorter interval length based on the down-sampling method, fewer sampling points are generated in the interval [b' k , b' k+1 , i.e. the number of sampling points in the interval [b' k , b' k+1 is reduced.

[0074] Preferably, for any new sampling point d' j , its corresponding pull-out value l' j is calculated by linear interpolation method as follows:

[0075]

[0076] where b' k ≤ d' j < b' k+1 , i.e. the new sampling point is located between the new data feature points.

[0077] Through the above steps, a new pull-out value data set L' k,k+1 = {l'1, l'2, …, l' j} is generated, as shown in Figure 5 . At this point, the pull-out value data is aligned with the through mileage to obtain the associated data of the two.

[0078] Preferably, in order to ensure the accuracy of the resampled data, the resampled data can be verified by feature point comparison and / or data visualization.

[0079] In each professional detection process, in addition to the corresponding detection indicators, the original data also includes time information and mileage information. The same set of time encoders is used by each detection device of the comprehensive inspection vehicle, i.e. the mileage information corresponding to all detection data collected in each professional detection process at the same time is consistent, to ensure the smooth implementation of multi-source data "time-mileage" synchronization. Preferably, step S2 has realized the dimensional alignment of the pull-out value data and the through mileage, and since resampling processing is performed, the number of sampling points has changed, resulting in that the original time sequence is no longer applicable. Therefore, in step S3, the time sequence can be reconstructed by linear interpolation.

[0080] Preferably, in the initial state, the time sequence t i of each detection device corresponds to the mileage value d i at the time of sampling, forming a "time-mileage" correspondence relationship:

[0081]

[0082] where t i represents the i-th time point, and d i represents the mileage value corresponding to the i-th time point. Since the data collection of each detection system is performed synchronously during the operation of the comprehensive inspection vehicle, the mileage value d i corresponding to each time point t i should be consistent.

[0083] After the mileage calibration and resampling processing of the detection data such as the pantograph wire pull-out value, a new mileage value d' j is obtained i . In addition to u' = u, the resampling processing changes the number and distribution of sampling points, so the time sequence also needs to be recalculated according to the new mileage distribution. Preferably, the time synchronization can use linear interpolation to calculate the new time point t' j , and the calculation formula is as follows:

[0084]

[0085] where t k and t k+1 are the original times corresponding to the feature points b k and b k+1 , and b k ≤ d' j < b k+1 .

[0086] Therefore, for each new mileage value d' j , the two nearest original mileage values b k and b k+1 are found, such that b k ≤ d' j < b k+1 , and then the new time point t' j is calculated using linear interpolation. In this way, the new mileage d' j can be consistent with the new time point t' j , so that the pantograph wire pull-out value data and the mileage data are synchronized in the time dimension.

[0087] The present application ensures that each detection system has consistent mileage data at the same time point by assigning new time information to other professional detection data, achieving the effect of "time-mileage" synchronization, and ultimately realizing the alignment of multi-source data and through mileage. Through the time synchronization method, the mileage data of each detection system at the same time point is consistent, eliminating errors caused by different data acquisition times, and improving the consistency of the data. The linear interpolation method is simple and efficient, with low computational complexity, suitable for large-scale data processing, and can quickly complete the reconstruction of the time sequence, improving the computational efficiency. Through the interpolation method, the missing sampling points caused by resampling are filled, ensuring the integrity and continuity of the data. The time synchronization method is based on the unified time encoder of the comprehensive inspection vehicle, ensuring the reliability of data synchronization and improving the positioning accuracy of multi-source detection data.

[0088] Preferably, the mileage correction method of the present application can further comprise S4, field mileage label assignment, after step S3, wherein step S4 is mainly used in the case that the field mileage is inconsistent with the detected mileage. Further, since the field mileage mostly exists in the case of "broken chain", i.e. in the railway or road engineering, due to local re-alignment, segmented measurement and other reasons, the pile number (i.e. the mileage pile number) is discontinuous, while the mileage recorded by the inspection vehicle equipment in the detection process is continuous, thereby causing the inconsistency between the field mileage and the detected mileage, which seriously affects the field re-measurement and maintenance positioning. The present application corrects the mileage difference of the original detection data by calculating the length of the long and short chain, and finally realizes the correlation alignment of "multi-source detection data-field mileage" through the label mapping method.

[0089] Preferably, in step S4, the field mileage information is K={K1, K2, …, K n}Since the field mileage length and the through mileage length remain consistent regardless of whether the field mileage exists in the case of "broken chain", there must exist a mileage point corresponding to the field mileage on the through mileage, which can be mapped to the through mileage as a whole by taking the field mileage as a label, so as to achieve the alignment of the field mileage and the through mileage, and further realize the alignment effect of the multi-source data and the field mileage, and the principle is shown in Figure 6

[0090] Preferably, the present application can realize the alignment of the field mileage and the through mileage through a database, wherein the correspondence table of the field mileage and the through mileage can be maintained in advance in the database to establish a refined mileage comparison table, and then the field mileage can be extracted through the correlation retrieval method. The mileage comparison table can be shown in the following table.

[0091] id Actual mileage Mileage n K n ]]> G n ]]> n+1 K n+1 ]]> G n+1 ]]> n+2 K n+2 ]]> G n+2 ]]> … … …

[0092] Based on this, the present application provides a city rail comprehensive inspection vehicle multi-source detection data mileage correction method based on the data characteristics of the pantograph-catenary pull-out value, which has the advantages of simple operation process, small calculation amount, low data acquisition difficulty, good correction effect and the like, and the specific operation process can be shown in Figure 7

[0093] Embodiment 2

[0094] This embodiment is a further improvement of embodiment 1, and the repeated contents will not be described again.

[0095] The present application also discloses a city rail comprehensive inspection vehicle multi-source detection data mileage correction system, in particular a city rail comprehensive inspection vehicle multi-source detection data mileage correction system based on the data characteristics of the pantograph-catenary pull-out value, which is used to execute the mileage correction method as described in embodiment 1.

[0096] ​​Preferably, the mileage correction system can comprise: a detection module comprising a plurality of detection devices for acquiring different types of detection data; a database for storing the detection data acquired by the detection devices; and a processing module for extracting the data from the database and processing the data to complete the mileage correction.

[0097] Preferably, the detection module can be configured with a pantograph pull-out value detection device for acquiring pantograph pull-out value detection data, wherein the pantograph pull-out value detection device can send the acquired pantograph pull-out value detection data to the database so that the processing module can extract the same from the database and complete the mileage correction using the mileage correction method as described in Embodiment 1.

[0098] It should be noted that the above specific embodiments are exemplary, and those skilled in the art can think of various solutions under the inspiration of the disclosure of the present application, and these solutions also belong to the disclosed range of the present application and fall within the protection scope of the present application. Those skilled in the art should understand that the specification and drawings of the present application are illustrative and not constitute a limitation on the claims. The protection scope of the present application is defined by the claims and their equivalents. The specification of the present application contains a plurality of inventive concepts, such as "preferably" or "according to a preferred embodiment", which means that the corresponding paragraph discloses an independent concept, and the applicant reserves the right to file a divisional application according to each inventive concept. Throughout the text, the features introduced by "preferably" are only optional ways, and should not be understood as necessarily provided, therefore the applicant reserves the right to abandon or delete the relevant preferred features at any time.

Claims

1. A method for correcting the mileage of multi-source detection data of a city rail integrated detection vehicle, characterized in that, It comprises: S1, data feature recognition: by analyzing the change characteristics of the catenary pantograph extraction value, the instantaneous mutation feature points at the joint of the anchor section are identified to obtain a series of feature points corresponding to the anchor section joint position in the through mileage; S2, alignment of extraction value data features and through mileage: through feature point alignment and resampling, the catenary pantograph extraction value data is matched with the through mileage to correct the mileage deviation and enhance the data positioning accuracy; S3, multi-source data "time-mileage" synchronization: through linear interpolation reconstruction of time series, the resampled catenary pantograph extraction value data is ensured to be synchronized in time and mileage, and new time information is assigned to other professional detection data, The identified feature points are extracted to form a data feature set, and the data feature set is calculated with the anchor section joint mileage set of the through mileage to obtain a phase difference set, which is applied to each element of the original data feature set as a translation amount, to obtain a translated data feature set, thereby realizing the alignment of the catenary pantograph extraction value data feature information and the anchor section joint in the through mileage, In the resampling process of the catenary pantograph extraction value data, any two adjacent original data feature points are selected from the original data feature set, and the two original data feature points are mapped into the translated data feature set to obtain corresponding two new data feature points, and sampling points are obtained in the original interval formed between the two original data feature points at a preset sampling frequency to form a extraction value data set.

2. The method of claim 1, wherein, The instantaneous mutation feature points at the joint of the anchor section are obtained by drawing a "mileage-extraction value" curve, wherein the slope between each data point and its previous data point in the "mileage-extraction value" curve is calculated, and when the slope corresponding to any data point exceeds the set slope threshold, the point is taken as a feature point and the mileage of the data is recorded as the identification of the feature point.

3. The method of claim 1, wherein, In the resampling interval formed between the two new data feature points, sampling points are obtained in the same sampling frequency, wherein when the original interval length is less than the corresponding resampling interval length, the number of sampling points in the resampling interval increases; when the original interval length is greater than the corresponding resampling interval length, the number of sampling points in the resampling interval decreases.

4. The method of claim 3, wherein, For any new sampling point located in the resampling interval, the corresponding catenary pantograph extraction value can be calculated by linear interpolation method, and the calculated catenary pantograph extraction value can be incorporated into the new extraction value data set to realize the alignment of the extraction value data and the through mileage.

5. The method of claim 4, wherein, For any new sampling point, find the nearest two original data feature points, and use linear interpolation to calculate the new time point, so that the mileage value corresponding to the new sampling point is consistent with the new time point, thereby synchronizing the catenary pantograph extraction value data and the mileage data in the time dimension.

6. The method of claim 1, wherein, The various professional detection data collected by the urban rail comprehensive detection vehicle during operation can be stored in the database as multi-source data with detection mileage and detection time, wherein the multi-source data includes catenary pantograph extraction value detection data.

7. The method of claim 6, wherein, When the field mileage is inconsistent with the detection mileage, the field mileage is aligned with the through mileage through a database, wherein a field mileage and through mileage correspondence table is maintained in advance in the database to establish a mileage comparison table, and then the field mileage is extracted through a correlation search.

8. A metro integrated inspection vehicle multi-source detection data mileage correction system, characterized in that, It comprises: a detection module comprising a plurality of detection devices for acquiring different types of detection data; a database for storing the detection data acquired by the detection devices; a processing module for extracting data from the database and performing data processing to complete mileage correction, wherein the pantograph-catenary pull-out value detection device configured in the detection module can send the acquired pantograph-catenary pull-out value detection data to the database, so that the processing module can extract the pantograph-catenary pull-out value detection data from the database and complete the mileage correction by using the mileage correction method according to any one of claims 1-7.

Images