Recognition method, system and equipment for reverse positioning point of curved section of flexible contact network

Abstract

The invention discloses a flexible catenary curve segment reverse positioning point identification method, system and device, and particularly relates to the catenary positioning point identification field, and the technical key points are that each pull-out value extreme point is taken as a center, and a second pull-out value area is constructed for each pull-out value extreme point according to a preset mileage range; fitting the data before the extreme point and the data after the extreme point in the second pull-out value region to obtain a first fitting function and a second fitting function, and fitting all the data before the extreme point and the data after the extreme point in the second pull-out value region to obtain a third fitting function; calculating to obtain a first function fitting error based on the data before the extreme point, the data after the extreme point, the first fitting function and the second fitting function, and calculating to obtain a second function fitting error based on the data before the extreme point, the data after the extreme point and the third fitting function; and comparing the first function fitting error with the second function fitting error to obtain a flexible contact net curve segment inverse positioning point identification result.

Description

Technical Field

[0001] The present invention relates to the field of contact network positioning point identification, and in particular to a method, system and equipment for identifying reverse positioning points of a flexible contact network curve segment. Background Art

[0002] In electrified railway design, the catenary is the power supply system installed above the railway line. It consists of contact wires, positioning devices, support devices, pillars, and related infrastructure. The catenary's primary function is to transmit electrical energy from the transmission line to the pantographs of electric locomotives, thereby providing power to the locomotives. There are two types of catenary conductors: flexible conductors, which are suitable for outdoor railway lines and can withstand varying weather conditions; and rigid conductors, which, due to their sturdiness, are primarily used in tunnel environments such as subways.

[0003] Evaluating the performance of the catenary, particularly its current-collecting performance, relies primarily on two key parameters: geometric parameters, which primarily include conductor height and pullout (the horizontal distance between the contact wire and the track centerline). These parameters influence the stability of the catenary and the current-collecting efficiency of the pantograph. Dynamic parameters, which address the catenary's performance under dynamic conditions, such as vibration, are crucial. To accurately evaluate the catenary's geometric parameters, the detection system must be able to precisely identify the catenary's location points to ensure that its design and installation meet technical specifications, thereby ensuring the safe and efficient operation of electric locomotives.

[0004] In the prior art, contact network positioning point detection mainly uses visual recognition or radar scanning as technical means. For example, a Chinese patent with publication number CN111723794A discloses a real-time flexible contact network positioning point recognition method, which performs real-time detection of positioning points in the flexible contact network based on image recognition technology; a Chinese patent with publication number CN116242316A discloses a method and device for real-time detection of rigid contact network positioning points, which performs rigid contact network positioning point detection based on the positioning point contour features of vision and line laser scanning; a Chinese patent with publication number CN205097980U discloses a contact network inspection and maintenance vehicle based on laser radar, which performs point detection based on the point cloud features of laser radar scanning. However, during the operation of the above-mentioned detection system, the vehicle moves at high speed, and technical means such as visual recognition or radar scanning cannot avoid positioning deviation caused by recognition calculation delay.

[0005] For flexible contact networks, the positioning points can be accurately identified based on the geometric inflection point characteristics of the pull-out values ​​continuously measured by the detection system, such as Figure 1 As shown, for straight sections, the extreme value points of the value curve are the corresponding positioning points; see also Figure 2As shown in the figure, the contact line in the curved section is in reverse positioning mode, and there are interference extreme points in the continuously measured pull-out value curve. Moreover, the interference points and the true positioning points have similar features. It is difficult to identify the true and false positions using conventional methods, thus affecting the recognition accuracy.

[0006] Therefore, the present invention aims to provide a method, system and device for identifying reverse positioning points of a curved section of a flexible contact network to solve the above-mentioned related problems. Summary of the Invention

[0007] The technical problem to be solved by the present invention is that the existing technology cannot avoid the positioning deviation caused by the recognition calculation delay, and it is difficult to identify the interference extreme points existing on the contact line of the curved section, and lacks related problems of recognition accuracy. The purpose is to provide a method, system and equipment for identifying the reverse positioning points of the curved section of the flexible contact network. By adopting the Gauss-Newton method in the nonlinear optimization method to fit the pull-out value data near the extreme point with a straight line and a quadratic curve, and based on the comparison of the sum of squares of the fitting errors, the pseudo positioning points caused by the reverse positioning device in the curved section are successfully filtered out, which significantly improves the correct recognition rate of the reverse positioning points and enhances the positioning accuracy of the detection system. At the same time, the positioning point recognition method provided by the present invention is directly based on the pull-out value continuously detected by the detection system, reduces the positioning deviation caused by the recognition calculation delay, and automatically adapts to the positioning point recognition of the curved section and the straight section of the flexible contact network.

[0008] The present invention is achieved through the following technical solutions: A method for identifying reverse positioning points of a flexible contact network curve segment, the method comprising: Acquire multiple pull-out values ​​of the flexible contact network curve segment, and construct a first pull-out value region for each pull-out value according to a preset mileage range; select a pull-out value extreme point in each first pull-out value region to obtain multiple pull-out value extreme points; With each extreme point of the pull-out value as the center, a second pull-out value region is constructed for each extreme point of the pull-out value according to a preset mileage range; the data before and after the extreme point are fitted in the second pull-out value region to obtain a first fitting function and a second fitting function; and all the data before and after the extreme point are fitted in the second pull-out value region to obtain a third fitting function; Based on the data before the extreme point, the data after the extreme point, the first fitting function and the second fitting function, a first function fitting error is calculated; based on the data before the extreme point, the data after the extreme point and the third fitting function, a second function fitting error is calculated; The fitting error of the first function is compared with the fitting error of the second function to obtain the identification result of the reverse positioning point of the flexible contact network curve segment.

[0009] Furthermore, a plurality of pull-out values ​​of the flexible contact network curve segment are obtained, and a first pull-out value region is constructed for each pull-out value according to a preset mileage range; a pull-out value extreme point is selected in each first pull-out value region to obtain a plurality of pull-out value extreme points, specifically: Obtain multiple pull-out values ​​of flexible catenary curve segments based on the catenary detection system; Each pull-out value is used as an initial pull-out value, and a first pull-out value area is constructed with the initial pull-out value as the center according to a preset mileage range. The remaining pull-out values ​​in the first pull-out value area are used to determine whether the initial pull-out value is a pull-out value extreme point, and multiple pull-out value extreme points are obtained based on the determination result.

[0010] Furthermore, the data before the extreme point and the data after the extreme point are fitted in the second pull-out value region to obtain a first fitting function and a second fitting function, specifically: In the second pull-out value area, the pull-out value to the left of the pull-out value extreme point is used as the data before the extreme point, and the pull-out value to the right of the pull-out value extreme point is used as the data after the extreme point; The straight line fitting method of the Gauss-Newton method is used to fit the data before the extreme point and the data after the extreme point respectively to obtain a first fitting function and a second fitting function.

[0011] Furthermore, all the data before and after the extreme point are fitted in the second pull-out value region to obtain a third fitting function, specifically: In the second pull-out value area, the pull-out value to the left of the pull-out value extreme point is used as the data before the extreme point, and the pull-out value to the right of the pull-out value extreme point is used as the data after the extreme point; The quadratic curve fitting method of the Gauss-Newton method is used to fit all the data before and after the extreme point to obtain the third fitting function.

[0012] Furthermore, based on the data before the extreme point, the data after the extreme point, the first fitting function and the second fitting function, the first function fitting error is calculated. Based on the data before the extreme point, the data after the extreme point and the third fitting function, the second function fitting error is calculated, specifically: Calculate the first sum of squares of errors between the first fitting function and the data before the extreme point, and the second sum of squares of errors between the second fitting function and the data after the extreme point, and use the first sum of squares of errors and the second sum of squares of errors to obtain the fitting error of the first function; The third sum of squares of errors between the data before the extreme point, the data after the extreme point, and the third fitting function is calculated, and the fitting error of the second function is obtained using the third sum of squares.

[0013] Furthermore, the fitting error of the first function and the fitting error of the second function are compared to obtain the identification result of the reverse positioning point of the flexible contact network curve segment, which is specifically: For the same extreme point of the pulled-out value, if the fitting error of the first function is smaller than the fitting error of the second function, then the extreme point of the pulled-out value is the anti-positioning point of the true curve segment; if the fitting error of the first function is larger than the fitting error of the second function, then the extreme point of the pulled-out value is the anti-positioning point of the pseudo curve segment.

[0014] The present invention further provides a flexible contact network curve segment reverse positioning point identification system, which is used in any one of the flexible contact network curve segment reverse positioning point identification methods described above, and the system includes: A pull-out value extreme point acquisition module is used to obtain multiple pull-out values ​​of the flexible contact network, construct a first pull-out value area for each pull-out value according to a preset mileage range, select a pull-out value extreme point in each first pull-out value area, and obtain multiple pull-out value extreme points; a pull-out value data fitting module, configured to construct a second pull-out value region for each pull-out value extreme point according to a preset mileage range, with each pull-out value extreme point as the center; fit the data before and after the extreme point within the second pull-out value region to obtain a first fitting function and a second fitting function; and fit all the data before and after the extreme point within the second pull-out value region to obtain a third fitting function; an error calculation module, configured to calculate a first function fitting error based on data before and after the extreme point, the first fitting function, and the second fitting function, and to calculate a second function fitting error based on data before and after the extreme point, the data and the third fitting function; The extreme point identification module is used to compare the first function fitting error and the second function fitting error to obtain the flexible contact network extreme point identification result.

[0015] The present invention also provides a computer device, comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described above are implemented.

[0017] The present invention also provides a computer program product comprising instructions, which, when executed by a computer device cluster, enables the computer device cluster to perform any of the above methods.

[0018] Compared with the prior art, the present invention has the following advantages and beneficial effects: In the present invention, by adopting the Gauss-Newton method in the nonlinear optimization method to fit the pull-out value data near the extreme point with a straight line and a quadratic curve, and based on the comparison of the sum of squares of the fitting errors, the pseudo positioning points caused by the anti-positioning device in the curved section are successfully filtered out, which significantly improves the correct recognition rate of the anti-positioning points and enhances the positioning accuracy of the detection system; at the same time, the positioning point recognition method provided by the present invention is directly based on the pull-out value continuously detected by the detection system, reduces the positioning deviation caused by the recognition calculation delay, and automatically adapts to the positioning point recognition of the curved and straight sections of the flexible contact network. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings: Figure 1 A schematic diagram of the result of pulling out the value curve and positioning point recognition for a straight road section in the prior art; Figure 2 A schematic diagram of the value curve and positioning point recognition results of the curved road section in the prior art; Figure 3 Schematic diagram of a method flow for identifying reverse positioning points of a flexible contact network curve segment in this embodiment; Figure 4 This is a schematic diagram of the curve value curve and positioning point identification results of the curved road section of this technical solution; Figure 5 Schematic diagram of system modules of a flexible contact network curve segment reverse positioning point identification system in this embodiment; Figure 6 A schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] In this disclosure, unless otherwise specified, the use of terms such as "first" and "second" to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases, based on the context of the description, they may also refer to different instances.

[0022] The terms used in the descriptions of various examples in this disclosure are for the purpose of describing specific examples only and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in this disclosure encompasses any one and all possible combinations of the listed items.

[0023] Example 1 See also Figure 3 As shown, this embodiment provides a method for identifying reverse positioning points of a flexible contact network curved segment. This identification method can be used not only for identifying reverse positioning points of a flexible contact network curved segment, but also for identifying positioning points of a flexible contact network straight segment. In this embodiment, the identification of reverse positioning points of a flexible contact network curved segment is taken as an example. The specific method includes: S1: Acquire multiple pull-out values ​​of the flexible contact network curve segment, construct a first pull-out value region for each pull-out value according to a preset mileage range; select a pull-out value extreme point in each first pull-out value region to obtain multiple pull-out value extreme points; Specifically, in this embodiment, multiple pull-out values ​​of the flexible contact network curve segment are obtained based on the contact network detection system; each pull-out value is used as the initial pull-out value, and a first pull-out value area is constructed with the initial pull-out value as the center according to a preset mileage range, and the remaining pull-out values ​​in the first pull-out value area are used to determine whether the initial pull-out value is a pull-out value extreme point, and multiple pull-out value extreme points are obtained based on the judgment result.

[0024] At the same time, the remaining pull-out values ​​in the first pull-out value area are used to determine whether the initial pull-out value is a pull-out value extreme point, and multiple pull-out value extreme points are obtained based on the judgment results. Specifically, if the remaining pull-out values ​​in the first pull-out value area are all less than or greater than the initial pull-out value, then the initial pull-out value is a pull-out value extreme point, and the extreme point position for the flexible contact network is most likely a positioning point. Otherwise, the initial pull-out value is not a pull-out value extreme point, and all pull-out value extreme point indexes are recorded.

[0025] It should be noted that, in this embodiment, the contact network detection system is a conventional contact network detection system in this field. The system can continuously measure the geometric parameters of the contact network, such as the height value, pull-out value, etc. This technical solution is a conventional technical means and will not be elaborated on; the preset mileage range is an empirical value. In order to highlight the data form of the area near the extreme point of the pull-out value, the empirical value can be taken as 1 / 10 to 1 / 3 of the span (generally 50m), which is more appropriate. Compare 8m, 10m, 12m or other distances. In this embodiment, the preset mileage range adopts the mileage range of 8m before and after the pull-out value. Other mileage ranges can also be used in other embodiments, and will not be elaborated on here.

[0026] S2: With each extreme point of the pull-out value as the center, a second pull-out value region is constructed for each extreme point of the pull-out value within a preset mileage range; the data before and after the extreme point are fitted within the second pull-out value region to obtain a first fitting function and a second fitting function; and all the data before and after the extreme point are fitted within the second pull-out value region to obtain a third fitting function; Specifically, in this embodiment, a second pull-out value region is constructed for each pull-out value extreme point based on a preset mileage range and with each pull-out value extreme point as the center. Within the second pull-out value region, the pull-out values ​​to the left of the pull-out value extreme point are used as data before the extreme point, and the pull-out values ​​to the right of the pull-out value extreme point are used as data after the extreme point. The straight line fitting method of the Gauss-Newton method is used to fit the data before the extreme point and the data after the extreme point, respectively, to obtain a first fitting function and a second fitting function. The quadratic curve fitting method of the Gauss-Newton method is used to fit all the data before the extreme point and the data after the extreme point, to obtain a third fitting function. At the same time, in this embodiment, the technical steps of the straight line fitting method of the Gauss-Newton method are as follows: first, assume that the straight line to be fitted is , the least squares problem for the parameters of the straight line to be fitted is: ,in, Represents the variable to be estimated, N represents the total number of observations, and N is a positive integer; then the error is defined as: ,in, Indicates the The mileage value of each observation, Indicates the The Jacobian matrix is: ,make , then the Gauss-Newton method incremental equation for this problem is: , for all observations have: ,in To be solved Iteration increment, Indicates the The model error for each observation, Indicates the The Jacobian matrix of the observation value is obtained; then the incremental equation of the Gauss-Newton method is solved. The solution process is as follows: (1) Given the initial value ; (2) For all observations of the kth iteration , find the current Jacobian matrix and error ; (3) Solve the current increment equation ; (4) If Small enough or error , then stop the iteration, otherwise, let , return to step (2).

[0027] The technical steps of the quadratic curve fitting method of the Gauss-Newton method are as follows: First, assume that the curve to be fitted is: , the least squares problem for the parameters of the curve to be fitted is constructed as: ,in, Represents the variable to be estimated, and then defines the error as: , then its Jacobian matrix is: ,make , then the Gauss-Newton method incremental equation for this problem is: , for all observations: ,in To be solved Iteration increment, Indicates the The model error for each observation, Indicates the The Jacobian matrix of the observation value is obtained; then the Gauss-Newton incremental equation is solved. The solution process is as follows: (1) Given the initial value ; (2) For all observations of the kth iteration , find the current Jacobian matrix and error ; (3) Solve the current increment equation ; (4) If Small enough or error , then stop the iteration, otherwise, let , return to step (2).

[0028] It should be noted that the preset mileage range uses a mileage range of 8m before and after the pull-out value. Other mileage ranges can also be used in other embodiments, which will not be elaborated here. The data before and after the extreme point are both used as pseudo-positioning points for further filtering of curved road sections.

[0029] S3: Calculate the fitting error of the first function based on the data before the extreme point, the data after the extreme point, the first fitting function, and the second fitting function; calculate the fitting error of the second function based on the data before the extreme point, the data after the extreme point, and the third fitting function; Specifically, in this embodiment, the first sum of squares of errors between the first fitting function and the data before the extreme point, and the second sum of squares of errors between the second fitting function and the data after the extreme point are calculated respectively, and the first sum of squares of errors and the second sum of squares of errors are used to obtain the fitting error of the first function; the third sum of squares of errors between the data before the extreme point, the data after the extreme point and the third fitting function are calculated, and the third sum of squares is used to obtain the fitting error of the second function.

[0030] It should be noted that, in this embodiment, the first function fitting error is the sum of the first error square sum and the second error square sum, and the second function fitting error is the third square sum.

[0031] S4: Compare the fitting error of the first function and the fitting error of the second function to obtain the reverse positioning point identification result of the flexible contact network curve segment.

[0032] Specifically, in this embodiment, for the same pull-out value extreme point, if the first function fitting error is smaller than the second function fitting error, then the pull-out value extreme point is the true curve segment anti-positioning point; if the first function fitting error is greater than the second function fitting error, then the pull-out value extreme point is the false curve segment anti-positioning point.

[0033] It should be noted that in this embodiment, since there may be a very small number of cases where the fitting error of the first function is relatively close to the fitting error of the second function, an error tolerance can be appropriately set. In this embodiment, the error tolerance is 200. In other embodiments, it can be determined according to actual conditions, and no excessive restrictions are made here. Through this processing method, the missed recognition rate of the anti-positioning point can be reduced.

[0034] See also Figure 4 , showing a schematic diagram of the pull-out value curve and positioning point identification results of a curved section using this embodiment. The present invention uses the Gauss-Newton method in the nonlinear optimization method to fit the pull-out value data near the extreme point with a straight line and a quadratic curve, and based on the comparison of the sum of squares of the fitting errors, successfully filters out the pseudo positioning points caused by the anti-positioning device in the curved section, significantly improves the correct recognition rate of the anti-positioning points, and enhances the positioning accuracy of the detection system; at the same time, the positioning point identification method provided by the present invention is directly based on the pull-out value continuously detected by the detection system, reduces the positioning deviation caused by the recognition calculation delay, and automatically adapts to the positioning point identification of the curved and straight sections of the flexible contact network.

[0035] Example 2 See also Figure 5As shown, the present invention also provides a flexible contact network curve segment reverse positioning point identification system, which is used in any one of the flexible contact network curve segment reverse positioning point identification methods described above, and the system includes: A pull-out value extreme point acquisition module 100 is used to obtain multiple pull-out values ​​of the flexible contact network, construct a first pull-out value region for each pull-out value according to a preset mileage range, and select a pull-out value extreme point in each first pull-out value region to obtain multiple pull-out value extreme points; The pull-out value data fitting module 200 is configured to construct a second pull-out value region for each pull-out value extreme point based on a preset mileage range and with each pull-out value extreme point as the center; fit the data before and after the extreme point within the second pull-out value region to obtain a first fitting function and a second fitting function; and fit all the data before and after the extreme point within the second pull-out value region to obtain a third fitting function. An error calculation module 300 is configured to calculate a first function fitting error based on the data before the extreme point, the data after the extreme point, the first fitting function, and the second fitting function, and to calculate a second function fitting error based on the data before the extreme point, the data after the extreme point, and the third fitting function; The extreme point identification module 400 is used to compare the first function fitting error and the second function fitting error to obtain the flexible contact network extreme point identification result.

[0036] It should be noted that the modules in the system of Example 2 correspond to the steps in the method of Example 1. The steps in the method of Example 1 have been described in detail in Example 1. The contents of the modules in the system will not be described in detail in this Example 2.

[0037] Example 3 See also Figure 6 As shown, this embodiment further provides a computer device, including a system memory 1005 and a processor 1001, wherein the system memory 1005 stores a computer program, and the processor 1001 implements the steps of any of the above methods when executing the computer program.

[0038] It should be noted that the processor 1001 is configured to execute the steps of the above method embodiments according to the instructions in the program code. Alternatively, the processor 1001 implements the functions of the modules / units in the above system / device embodiments when executing the computer program.

[0039] Specifically, in this embodiment, the computer program may be divided into one or more modules / units, one or more modules / units being stored in the system memory 1005 and executed by the processor 1001 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0040] The terminal device may be a computing device such as a desktop computer, laptop, PDA, or cloud server. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will appreciate that this does not limit the terminal device and may include more or fewer components than shown, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, and the like.

[0041] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0042] The system memory 1005 can be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The system memory 1005 can also be the storage device 1004 of the terminal device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the terminal device. Furthermore, the system memory 1005 can also include both the internal storage unit of the terminal device and the storage device 1004. The system memory 1005 is used to store computer programs and other programs and data required by the terminal device. The system memory 1005 can also be used to temporarily store data that has been output or is about to be output.

[0043] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0044] Example 4 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0045] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art.

[0046] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In an embodiment of the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0047] Example 5 This embodiment further provides a computer program product comprising instructions. When the instructions are executed by a computer device cluster, the computer device cluster executes the method described in Embodiment 1.

[0048] The specific implementation methods 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 implementation method 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 method for identifying reverse positioning points of a flexible contact network curve segment, characterized in that the method include: Acquire multiple pull-out values ​​of the flexible contact network curve segment, and construct a first pull-out value area for each pull-out value according to a preset mileage range; Selecting a pull-out value extreme point in each first pull-out value region to obtain a plurality of pull-out value extreme points; Taking each extreme point of the pull-out value as the center, a second pull-out value area is constructed for each extreme point of the pull-out value according to a preset mileage range; Fitting the data before the extreme point and the data after the extreme point in the second pull-out value region respectively to obtain a first fitting function and a second fitting function, and fitting all the data before the extreme point and the data after the extreme point in the second pull-out value region to obtain a third fitting function; Based on the data before the extreme point, the data after the extreme point, the first fitting function and the second fitting function, the fitting error of the first function is calculated; Based on the data before the extreme point, the data after the extreme point and the third fitting function, the fitting error of the second function is calculated; The fitting error of the first function is compared with the fitting error of the second function to obtain the identification result of the reverse positioning point of the flexible contact network curve segment.

2. A method for identifying reverse positioning points of a flexible contact network curve segment according to claim 1, characterized in that: Obtain multiple pull-out values ​​of the flexible contact network curve segment, and construct a first pull-out value area for each pull-out value according to a preset mileage range; select a pull-out value extreme point in each first pull-out value area to obtain multiple pull-out value extreme points, specifically: Obtain multiple pull-out values ​​of flexible catenary curve segments based on the catenary detection system; Each pull-out value is used as an initial pull-out value, and a first pull-out value area is constructed with the initial pull-out value as the center according to a preset mileage range. The remaining pull-out values ​​in the first pull-out value area are used to determine whether the initial pull-out value is a pull-out value extreme point, and multiple pull-out value extreme points are obtained based on the determination result.

3. The method for identifying reverse positioning points of a flexible contact network curve segment according to claim 1, characterized in that: In the second pull-out value region, the data before the extreme point and the data after the extreme point are fitted respectively to obtain the first fitting function and the second fitting function, which are specifically: In the second pull-out value area, the pull-out value to the left of the pull-out value extreme point is used as the data before the extreme point, and the pull-out value to the right of the pull-out value extreme point is used as the data after the extreme point; The straight line fitting method of the Gauss-Newton method is used to fit the data before the extreme point and the data after the extreme point respectively to obtain a first fitting function and a second fitting function.

4. The method for identifying reverse positioning points of a flexible contact network curve segment according to claim 1, characterized in that: Fit all the data before and after the extreme point in the second pull-out value region to obtain the third fitting function, specifically: In the second pull-out value area, the pull-out value to the left of the pull-out value extreme point is used as the data before the extreme point, and the pull-out value to the right of the pull-out value extreme point is used as the data after the extreme point; The quadratic curve fitting method of the Gauss-Newton method is used to fit all the data before and after the extreme point to obtain the third fitting function.

5. The method for identifying reverse positioning points of a flexible contact network curve segment according to claim 1, characterized in that: Based on the data before the extreme point, the data after the extreme point, the first fitting function and the second fitting function, the fitting error of the first function is calculated. Based on the data before the extreme point, the data after the extreme point and the third fitting function, the fitting error of the second function is calculated. Specifically, Calculate the first sum of squares of errors between the first fitting function and the data before the extreme point, and the second sum of squares of errors between the second fitting function and the data after the extreme point, and use the first sum of squares of errors and the second sum of squares of errors to obtain the fitting error of the first function; The third sum of squares of errors between the data before the extreme point, the data after the extreme point, and the third fitting function is calculated, and the fitting error of the second function is obtained using the third sum of squares.

6. The method for identifying reverse positioning points of a flexible contact network curve segment according to claim 1, characterized in that: Comparing the fitting error of the first function and the fitting error of the second function, the identification result of the reverse positioning point of the flexible contact network curve segment is obtained, which is specifically: For the same extreme point of the pulled-out value, if the fitting error of the first function is smaller than the fitting error of the second function, then the extreme point of the pulled-out value is the anti-positioning point of the true curve segment; if the fitting error of the first function is larger than the fitting error of the second function, then the extreme point of the pulled-out value is the anti-positioning point of the pseudo curve segment.

7. A flexible contact network curve section reverse positioning point identification system, characterized in that: The system is used in a method for identifying reverse positioning points of a flexible contact network curve segment according to any one of claims 1 to 6, and the system comprises: A pull-out value extreme point acquisition module is used to obtain multiple pull-out values ​​of the flexible contact network, construct a first pull-out value area for each pull-out value according to a preset mileage range, select a pull-out value extreme point in each first pull-out value area, and obtain multiple pull-out value extreme points; a pull-out value data fitting module, configured to construct a second pull-out value region for each pull-out value extreme point according to a preset mileage range, with each pull-out value extreme point as the center; fit the data before and after the extreme point within the second pull-out value region to obtain a first fitting function and a second fitting function; and fit all the data before and after the extreme point within the second pull-out value region to obtain a third fitting function; an error calculation module, configured to calculate a first function fitting error based on data before and after the extreme point, the first fitting function, and the second fitting function, and to calculate a second function fitting error based on data before and after the extreme point, the data and the third fitting function; The extreme point identification module is used to compare the first function fitting error and the second function fitting error to obtain the flexible contact network extreme point identification result.

8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device cluster, the computer device cluster is caused to perform the method according to any one of claims 1 to 6.

Images