Automatic point distribution method for 5T equipment

Abstract

The invention relates to the technical field of railway safety detection, and discloses a 5T equipment automatic stationing method, computer equipment, a computer readable storage medium and a computer program product in order to solve the problems of low efficiency and complex check data when 5T equipment is manually arranged. The method comprises the steps that the crown number mileage of each key point of any section of design line is obtained, the key points comprise a bridge, a tunnel, a broken chain and a detour section, and the crown number mileage is expressed in an interval mode; converting the crown mileage into an actual continuous mileage through line interval mapping; on the basis of the arrangement requirement of any 5T equipment, according to the actual continuous mileage of each key point, the distribution position of the 5T equipment is calculated, and a plurality of feasible solutions are obtained; and optimizing the plurality of feasible solutions through a multi-objective evolutionary algorithm for adaptively adjusting weight vectors to obtain an optimal solution. By adopting the method, automatic point distribution of the 5T equipment is realized, and the point distribution efficiency and reliability are improved.

Description

Technical Field

[0001] The present application relates to the field of railway safety detection technology, and more specifically, to a 5T equipment automatic deployment method, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] At a time when my country's high-speed railways are developing rapidly, their safe, stable and efficient operation is of vital importance. As the key monitoring and control unit of the railway system, the rationality of the layout of 5T equipment is directly related to the safe, stable and efficient operation of the railway system.

[0003] The 5T equipment in railways refers to five key categories of equipment used for vehicle safety testing and fault diagnosis in China's railway system. These include THDS (Telescopic Temperature Detection System), TPDS (Trackside Dynamic Monitoring System for Vehicle Running Quality), TADS (Trackside Acoustic Diagnostic System for Rolling Bearing Faults), TFDS (Trackside Image Detection System for Freight Car Faults), and ATIS (Automatic Vehicle Identification System). These devices utilize automated and intelligent technologies to enable real-time monitoring of train operating status and fault warnings, ensuring the safety and efficiency of railway transportation.

[0004] However, the current complex and ever-changing environment along railway lines, with restrictions imposed by natural terrain such as mountains and rivers, as well as interference from human factors such as the layout of different stations, sections, tunnels, and bridges, poses numerous challenges to the deployment of 5T equipment. Improper deployment can lead to blind spots in monitoring, preventing timely acquisition of critical data, and thus impacting the safe operation of trains. It can also lead to wasted equipment resources and increased operating costs.

[0005] Currently, 5T equipment deployment plans are still based on manual design experience. This manual deployment has the following problems: information omissions and the tendency to fall into local optimality instead of achieving global optimality. Therefore, it is particularly urgent to propose an automatic deployment method for 5T equipment. Summary of the Invention

[0006] In order to solve the above problems, the present invention provides a 5T equipment automatic deployment method, computer equipment, computer-readable storage medium and computer program product, which can realize the automatic deployment of 5T equipment and improve the efficiency and reliability of deployment.

[0007] To achieve the above objectives, according to a first aspect of the present invention, a method for automatic point placement of 5T equipment is provided, the method comprising:

[0008] Get the numbered mileage of each key point of any designed route. Key points include bridges, tunnels, broken links, and detours. The numbered mileage is expressed in the form of intervals.

[0009] Through route section mapping, the serial number mileage is converted into actual continuous mileage;

[0010] Based on the layout requirements of any 5T equipment and the actual continuous mileage of each key point, the layout position of the 5T equipment is calculated to obtain multiple feasible solutions;

[0011] Through the multi-objective evolutionary algorithm with adaptive adjustment of weight vectors, multiple feasible solutions are optimized to obtain the optimal solution.

[0012] Furthermore, through line interval mapping, the crown mileage is converted into actual continuous mileage, including compression mapping of the detour section to obtain the actual continuous mileage of each point in the detour section; the crown mileage of each point in each normal interval is converted into the distance from the starting point of the line to obtain the actual continuous mileage of each point in the normal interval. The normal interval is the interval on the line excluding the detour section and the broken link.

[0013] Furthermore, based on the layout requirements of any 5T device, the layout positions of the 5T device are calculated according to the actual continuous mileage of each key point, and multiple feasible solutions are obtained, including initializing an empty location list of detection devices for any 5T device; for each normal section on the line, obtaining the actual continuous mileage of each point in the normal section; initializing the starting position of the layout in the normal section; according to the layout requirements of the 5T device, cyclically calculating the starting position of the layout, and adding the starting position of the layout that meets the layout requirements to the location list of the detection device to obtain multiple feasible solutions.

[0014] Furthermore, according to the layout requirements of the 5T equipment, the starting position of the layout is calculated cyclically, and the starting position of the layout that meets the layout requirements is added to the position list of the detection equipment to obtain multiple feasible solutions, including initializing the starting position of the layout to P for each interval [a, b) on the line. i =a+D max , loop to calculate the starting position of the distribution point until P i ≥ bA, D max and A are the set spacing and set arrangement spacing determined according to the layout requirements of 5T equipment, respectively. max Less than A; calculate the next point position P i+1 =P i +k×TD, k is an integer, TD is the step adjustment value; respectively judge P i and P i+1 Whether the layout requirements are met; if so, P i and P i+1 Add to the location list of the detection device; by adjusting D max Update the starting position of the distribution points and calculate multiple feasible solutions.

[0015] Furthermore, based on the layout requirements of any 5T device, the layout locations of the 5T devices are calculated according to the actual continuous mileage of each key point, and multiple feasible solutions are obtained, including for special stations located on the line. If the special station is located in the current section, any 5T device is arranged at both ends of the station or at the entrance.

[0016] Furthermore, a multi-objective evolutionary algorithm with adaptively adjusted weight vectors is used to optimize multiple feasible solutions to obtain the optimal solution, including step 1, defining the objective function vector F(x) = (f1(x), f2(x), ..., fm(x)) T , where fm(x) is the mth objective function, x is the decision variable, and m is an integer; step 2, use the Latin hypercube sampling method to generate the initial population, set the population size to N, the target dimension to m, and N to be an integer; step 3, use uniform random sampling and weighted transformation to generate a set of weight vectors; step 4, judge the population diversity through the sparsity function, merge the offspring with the external population and eliminate the dominant solution. When the number of individuals is too large, eliminate individuals with low sparsity by comparing the sparsity value; step 5, based on the update rule, periodically update the weight vector adaptively so that the weight vector adapts to the Pareto front of the current problem; step 6, repeat steps 3 to 5 above until the set maximum number of iterations is reached, and output the optimized solution set, which is the individuals in the external population, and the optimal solution in the optimized solution set is used as the recommended solution, and other solutions are used as feasible solutions.

[0017] Furthermore, step 3 uses uniform random sampling and weighted transformation to generate a set of weight vectors, including using uniform random sampling to generate N m-dimensional weight vectors, where the N m-dimensional weight vectors are uniformly distributed in space; and using weighted transformation to adjust the N m-dimensional weight vectors, including:

[0018]

[0019] Among them, λ i，j is the jth component of the i-th weight vector, 1≤i≤N, 1≤j≤m.

[0020] According to a second aspect of the present invention, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of any one of the above methods.

[0021] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0022] According to a fourth aspect of the present invention, there is also provided a computer program product, comprising a computer program, which implements the steps of any one of the above methods when executed by a processor.

[0023] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0024] In the 5T equipment automatic layout method provided by the present invention, after obtaining the crown mileage of each key point of any section of the designed line, the crown mileage is first converted into actual continuous mileage through line interval mapping to solve the discontinuity problem between the detour section and the main line mileage; secondly, points are recursively taken according to the set step size within the entire line section to ensure that the layout position of any 5T equipment meets the layout requirements of the 5T equipment, and multiple feasible solutions are obtained, thereby realizing the automatic layout of the 5T equipment and solving the working mode of the traditional layout scheme that requires manual design based on the design drawing image; then, for the multi-objective optimization problem, a multi-objective evolutionary algorithm with adaptive adjustment of the weight vector is used to obtain the optimal solution set and the optimal solution in the optimal solution set, thereby effectively solving the multi-objective optimization problem in the 5T equipment layout, and being suitable for the reasonable layout of 5T equipment along the railway. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flow chart of a 5T equipment automatic point placement method provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of the line interval mapping steps provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0030] The terms "first," "second," "third," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0031] like Figure 1 As shown, a method for automatic deployment of 5T equipment is provided. The method can be executed by a terminal or by a server that communicates with the terminal through a network. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server can be an independent server or a server cluster composed of multiple servers. The method is described by applying it to a terminal as an example, and includes the following steps:

[0032] Step 101, obtain the prefix mileage of each key point of any designed route, the key points include bridges, tunnels, broken links, and detours, and the prefix mileage is expressed in the form of intervals.

[0033] like Figure 2 As shown, the line (also called the main line) includes multiple intervals such as DK0+000 to DK53+380, DK53+200 to DK104+780, DK103+900 to DK109+600, DK110+230 to DK150+000, etc., which are expressed in the form of serial number mileage.

[0034] Step 102: Convert the serial number mileage into actual continuous mileage through route section mapping.

[0035] The actual continuous mileage is the distance from the starting point of the line. Figure 2 As shown, the serial number mileage mapping obtains multiple actual continuous mileages such as 0 to 53380, 53380 to 104960, 104960 to 110660, and 110660 to 150430.

[0036] Step 103 : Based on the layout requirements of any 5T device and the actual continuous mileage of each key point, the layout positions of the 5T device are calculated to obtain multiple feasible solutions.

[0037] Step 104 , optimizing multiple feasible solutions by using a multi-objective evolutionary algorithm that adaptively adjusts weight vectors to obtain an optimal solution.

[0038] In the above-mentioned automatic layout method of 5T equipment, after obtaining the crown mileage of each key point of any designed line, the crown mileage is first converted into actual continuous mileage through line interval mapping to solve the discontinuity problem between the detour interval and the main line mileage; secondly, points are recursively obtained according to the set step size within the entire line interval to ensure that the layout position of any 5T equipment meets the layout requirements of the 5T equipment, and multiple feasible solutions are obtained, thereby realizing the automatic layout of 5T equipment; then, for the multi-objective optimization problem, the multi-objective evolutionary algorithm with adaptive adjustment of the weight vector is used to obtain the optimal solution set and the optimal solution in the optimal solution set, thereby effectively solving the multi-objective optimization problem in the 5T equipment layout, improving the efficiency and reliability of the layout, and being suitable for the reasonable layout of 5T equipment along the railway.

[0039] In one embodiment, the automatic deployment method for 5T equipment first uses an improved dynamic programming algorithm to map the line intervals and arrange detection stations based on the complexity of the data along the railway, such as broken links and detour sections, to achieve a continuous interval description of the entire line; on this basis, a multi-objective evolutionary algorithm with adaptive adjustment of weight vectors is introduced to optimize the deployment plan.

[0040] In one embodiment, the vehicle axle temperature intelligent detection system (abbreviated as THDS detection station or THDS device) in the 5T device is taken as an example to illustrate the automatic layout method of the 5T device. The layout requirements of other types of 5T equipment are different from the layout requirements of the THDS detection station. The layout requirements of the THDS detection station include but are not limited to not being in special sections such as bridges and tunnels, and the distance from existing facilities is within the allowable range (not less than 30 kilometers and not more than 35 kilometers. In this embodiment, the layout spacing is set to 32 kilometers, that is, 32,000 meters). The 5T device automatic layout method specifically includes the following steps:

[0041] S1.1. Line Interval Mapping. Actual line mileage is abstracted at a three-level level, forming virtual continuous intervals for mathematical calculations and comparisons. Line interval mapping is implemented as follows: First, the mileage data provided by the professional departments for lines, stations, bridges, and tunnels (referred to as stations, bridges, and tunnels) is expressed as intervals. Intervals may intersect, union, cross, or be discontinuous. Each point within an interval is recorded as the design mileage (RealPoint).

[0042] Secondly, the numbered mileage is converted to the distance from the route's starting point (i.e., actual continuous mileage), and each point within the interval is recorded as a numerical mileage (NormalPoint). Since actual routes are always continuous from beginning to end, mapping the numbered mileage to actual continuous mileage ensures numerical continuity and uniqueness of the numbered mileage points.

[0043] Secondly, the detour section (i.e. the section corresponding to the detour segment) is compressed and mapped, and the points in the detour section are mapped with equivalent mileage (EquivalancePoint) to ensure that the position where the detour segment joins the main line and the sequence of the detour segments can be correctly expressed. Due to the existence of the detour segment, the detour segment and the tunnels and bridges arranged in the detour segment are expressed with a different numbering system from the main line, and the detour segment exists on a non-baseline, and the data description between the detour segments is also discontinuous. The position where the detour segment joins the main line and the sequence of the detour segments cannot be expressed with a numbering description. If it is directly mapped to actual continuous mileage, it cannot be guaranteed that the same numerical actual continuous mileage of the two lines refers to the same point, and it is impossible to use data to determine whether they are co-located. For this reason, if Figure 2 As shown, the detour interval is processed using equivalent mileage (EquivalancePoint). At points within the detour interval, actual continuous mileage values ​​are used for mapping, and the spacing is directly expressed based on the addition and subtraction of the numerical length. At points outside the detour interval, continuous value mapping is performed to the baseline, and the starting and ending points of the detour segment are mapped to express the calculated spacing.

[0044] S1.2. After realizing the line interval mapping, the entire line is divided into left and right lines and described as complete continuous intervals. The THDS detection station layout problem is converted into selecting points in any [a, b) interval (a and b both represent mileage) on the entire line. The specific steps are as follows: (1) Initialize an empty THDS device location list P = []; (2) For each interval [a, b) on the line, determine whether it is a detour interval; (3) If so, perform compression mapping processing through EquivalancePoint conversion to obtain the actual continuous mileage of each point in the detour interval; (4) Initialize the starting position P of the point layout in the normal interval (the interval on the line except the detour section and the broken link) i =a+D max , loop to calculate the starting position of the distribution point until P i ≥b-32000, D max D is the set distance determined according to the layout requirements of THDS detection stations. max <32000; (5) Calculate the next possible point location P i+1 =P i +k×TD, where k is an integer and TD is the step size adjustment value; (6) Determine P i Whether the layout requirements are met (not within special sections such as bridges and tunnels, and the distance from existing facilities is within the allowable range, etc.); (7) If the layout requirements are met, then P i Add to the THDS device location list P; (8) by adjusting D max , update the starting position P of the layout i, multiple feasible solutions of THDS detection stations are calculated; (9) Due to the existence of special stations, the train inspection station and the large marshalling station must arrange detection facilities at both ends of the station (in the direction of train entry), that is, for each special station [c, d), if the special station is located in the current section [a, b), THDS equipment is arranged at both ends of the station (or at the entrance), that is, for the station in the [c, d] section, if the direction of travel is from c to d, the detection facility needs to be set at the c mileage, otherwise it needs to be set at the mileage d. For the general full-line section [s, e), if there are multiple special stations A_k=[s_k, e_k), where k=1…n, the section can be equivalently converted to the form of: [s, s_1), [e_1, s_2), [e_2, s_3), …, [e_n, e), where each section is a section without special stations, and when the facilities are finally arranged, the equipment at both ends of the special station can be completed.

[0045] Special stations can be used to divide the entire line into multiple sections containing special stations. Selecting points for each section can reduce the difficulty of processing a single, long section. However, these sections require additional verification of whether the line ends are included. If existing line equipment extends to the line at the starting and ending points, the distance to the equipment is converted and calculated to ensure that the mainline section length requirements are met.

[0046] That is, in the entire line interval [si, ei], according to the step size D∈[D min , D max ] to select points, ensure that points are laid out at both ends of the line, and that the length of the section without detection facilities at both ends of the section is also [D min , D max ]between.

[0047] D min ≤|P i+1 -P i ∣≤D max (1)

[0048] For a special station layout point P, let its interval be [s, e], then:

[0049] s-Δs≤P i ≤s or e≤P i ≤e+Δe (2)

[0050] Among them, s and e represent the starting point and end point of the line section respectively, Δs represents the safe distance at the entrance to meet the layout conditions, Δe represents the safe distance at the exit to meet the layout conditions, P i represents the location of the i-th THDS device, where i = 1…n. Furthermore, Δs and Δe require the use of mileage data provided by the line and station yard, as well as the turnout table data for each station, to calculate the safety distance value through mileage and coordinate conversion.

[0051] S1.3. Multi-objective evolutionary algorithm with adaptive adjustment of weight vectors. On the premise that feasible solutions for n THDS detection stations have been obtained, a multi-objective evolutionary algorithm with adaptive adjustment of weight vectors is used to further optimize these solutions and obtain a set of reasonable recommended solutions. The specific steps are as follows: (1) Problem definition: The detection station layout problem is abstracted into a multi-objective optimization problem, where each objective function represents a different performance indicator (the objective function includes whether the coverage of the detection station is as large as possible, whether the number of detection stations is as large as possible at both ends of the station, whether the number of detection stations is as small as possible, etc.). Objective function vector F(x) = (f1(x), f2(x), ..., fm(x)) T , where fm(x) is the mth objective function, x is the decision variable (representing the layout of the detection station), and m is a positive number; (2) Initialization: Use the Latin hypercube sampling (LHS) method to generate the initial population P, set the population size to N, the target dimension to m, and N to be an integer; (3) Weight vector initialization: Use the uniform random (UR) sampling method and weighted (WS) transformation to generate a set of weight vectors λ; (4) Update the external population: Use the sparsity function to judge the population diversity, avoid falling into the local optimal solution, merge the offspring with the external population PE And eliminate the dominant solution. When the number of individuals is too large, eliminate individuals with low sparsity by comparing the sparsity value; (5) Adaptive update of weight vector: Periodically adaptively update the weight vector to make the weight vector adapt to the Pareto front (PF) of the current problem; (6) Iterative output of optimized solution: Repeat steps (3) to (5) until the set maximum number of iterations or the maximum number of evaluations is reached, and then terminate and output the optimized solution set. The optimized solution set is the individuals in the external population PE. The optimal solution is recommended as the solution, and other solutions are recommended to the user as feasible solutions.

[0052] In one embodiment, in step (2) initialization, the initial population P can be expressed as:

[0053]

[0054] Among them, each dimension variable x i The domain interval [x i,1 ,x i,u ] represents partitioning all feasible solutions into N equal small intervals, generating an N×m matrix, where each column is a random permutation of the sequence 1, 2, ..., N. Then, a small hypercube is selected in each row of the matrix, and a sample is randomly generated in each selected small hypercube. This sample is the initial population P.

[0055] In one embodiment, in step (3) weight vector initialization, the uniform random sampling method is specifically to generate N m-dimensional weight vectors, ensuring that these vectors are uniformly distributed in space. The weighted transformation is used to adjust these weight vectors to make them more suitable for solving the multi-objective optimization problem, specifically:

[0056]

[0057] Among them, λ i，j is the jth component of the i-th weight vector, 1≤i≤N, 1≤j≤m.

[0058] Since the indicator descriptions are of different dimensions, it is necessary to calculate the weight vector of each solution after initialization, that is, to perform correlation calculation on the indicator preference. Here, the common clustering method Chebyshev function is used for calculation:

[0059] (λ i ,P)=argmin{x∈P}g tche (x|λ i ,z * )

[0060] Where z* represents the ideal point, and each individual in the population represents a set of probe station layout plans. Calculate the ideal point z* in the target space, which is the vector consisting of the optimal values ​​of each objective function.

[0061] In one embodiment, step (4) of updating the external population specifically comprises: referring to the cosine similarity calculation method, calculating the sparsity value of individual x:

[0062]

[0063] Where T is the size of the neighborhood set and xi is one of the T most similar individuals to x.

[0064] After obtaining the sparsity, the offspring with different sparsities are transformed and reorganized, and the resulting set F is merged with the external population PE and the dominant solution is eliminated. When the number of individuals in PE is too large, individuals with low sparsity are eliminated by comparing their sparsity values.

[0065] P E =UpdateP E (P E ,F)

[0066] The population is updated by randomly selecting parent individuals and applying binary crossover (SBX) and polynomial mutation (PM) operations to generate new offspring individuals. Each time the population is updated, the fitness of the individuals is re-evaluated using the Chebyshev function and compared with the parent individuals to select the better individuals to form a new population.

[0067] In one embodiment, in step (5) of adaptively updating the weight vector, the updating rule can be based on the individuals in the external population and the ideal point z*, expressed as:

[0068]

[0069] Among them, λ′ x is the updated weight vector, f m (P x ) is about P x The function value of the mth objective, is the ideal point value constant of the mth target, ε is a small positive number used to prevent the denominator from being zero, and m is the dimension of the vector, that is, how many such components there are.

[0070] In this embodiment, a method for automatic layout of 5T equipment has the following beneficial effects: (1) high degree of automation: it solves the problem that the traditional layout scheme requires manual design based on the design drawing image, overcomes the omission of information during manual layout and the problem of falling into local optimality instead of global optimality during manual layout, comprehensively considers the influencing factors and layout indicators such as the monitoring range, coverage density, topography along the line, and station interval distribution of the 5T equipment, and designs a complete set of mathematical abstract methods for digitizing and automatically calculating the pre-professional design content of lines, bridges, tunnels, roadbeds, etc., automatically splices and restores multi-professional data information along the line, and by combining the improved automatic layout algorithm with the multi-objective evolutionary algorithm, it can quickly find a layout scheme that meets the design conditions, greatly reducing the calculation time and the workload of manual intervention, and improving the degree of automation of layout; (2) strong applicability: the present invention is applicable to 5T equipment and different layout requirements for automatic layout and multi-objective optimization; (3) strong practicality: it can effectively improve the safety and reliability of the railway system, minimize the number of detection stations, maximize the number of layouts at both ends of the station, and avoid layout on bridges or tunnels, etc., while reducing construction costs and design costs, and has important practical application value.

[0071] The present application also provides a computer device, the internal structure diagram of which can be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for automatic deployment of 5T equipment is implemented.

[0072] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0073] like Figure 3 As shown, the present application also provides a computer device, which includes a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps in the above-mentioned method embodiments.

[0074] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0075] The present application also provides a computer program product, including a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0076] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0077] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] The above description is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0079] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements 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 5T equipment automatic point distribution method, characterized in that: include: Obtain the numbered mileage of each key point of any designed route, including bridges, tunnels, broken links, and detours. The numbered mileage is expressed in the form of intervals. By mapping the route interval, the serial number mileage is converted into actual continuous mileage; Based on the layout requirements of any 5T device, the layout positions of the 5T device are calculated according to the actual continuous mileage of each key point to obtain multiple feasible solutions; The multiple feasible solutions are optimized by a multi-objective evolutionary algorithm which adaptively adjusts the weight vectors to obtain the optimal solution.

2. The method according to claim 1, wherein The process of converting the serial number mileage into actual continuous mileage through route interval mapping includes: Perform compression mapping on the detour section to obtain the actual continuous mileage of each point in the detour section; Convert the serial number mileage of each point in each normal section into the distance from the starting point of the line to obtain the actual continuous mileage of each point in the normal section. The normal section is the section on the line excluding the detour section and broken link.

3. The method according to claim 1, wherein Based on the layout requirements of any 5T device, the layout positions of the 5T device are calculated according to the actual continuous mileage of each key point to obtain multiple feasible solutions, including: For any 5T device, initialize an empty location list of the detection device; For each normal section on the route, obtain the actual continuous mileage of each point in the normal section; Initialize the starting position of the distribution points in the normal interval; According to the layout requirements of the 5T device, the starting positions of the layout points are calculated cyclically, and the starting positions of the layout points that meet the layout requirements are added to the position list of the detection device to obtain multiple feasible solutions.

4. The method according to claim 3, wherein According to the layout requirements of the 5T device, the starting positions of the layout points are calculated cyclically, and the starting positions of the layout points that meet the layout requirements are added to the position list of the detection device to obtain multiple feasible solutions, including: For each interval [a, b) on the line, the initial starting position of the layout is P i =a+D max , loop to calculate the starting position of the distribution point until P i ≥ bA, D max and A are the set spacing and set arrangement spacing determined according to the layout requirements of 5T equipment, respectively. max Less than A; Calculate the next point position P i+1 =P i +k×TD, k is an integer, TD is the step size adjustment value; Determine P respectively i and P i+1 whether the layout requirements are met; If satisfied, then P i and P i+1 Add to the location list of the detection device; By adjusting D max Update the starting position of the distribution points and calculate multiple feasible solutions.

5. The method according to claim 1, wherein Based on the layout requirements of any 5T device, the layout positions of the 5T device are calculated according to the actual continuous mileage of each key point to obtain multiple feasible solutions, including: For special stations located on the line, if the special station is located within the current section, any 5T equipment shall be arranged at both ends of the station or at the entrance.

6. The method according to claim 1, wherein The multi-objective evolutionary algorithm, which optimizes the multiple feasible solutions by adaptively adjusting the weight vector, to obtain the optimal solution, includes: Step 1: Define the objective function vector F(x) = (f1(x), f2(x), ..., fm(x)) T , where fm(x) is the mth objective function, x is the decision variable, and m is an integer; Step 2: Use the Latin hypercube sampling method to generate the initial population. Let the population size be N, the target dimension be m, and N be an integer. Step 3: Generate a set of weight vectors using uniform random sampling and weighted transformation; Step 4: Determine the population diversity through the sparsity function, merge the offspring with the external population and eliminate the dominant solution. When the number of individuals is too large, eliminate individuals with low sparsity by comparing the sparsity values. Step 5: Based on the update rule, the weight vector is periodically updated adaptively to make the weight vector adapt to the Pareto front of the current problem; Step 6: Repeat steps 3 to 5 above until the maximum number of iterations is reached, and output the optimized solution set, which is the individual in the external population. The best solution in the optimized solution set is used as the recommended solution, and the other solutions are used as feasible solutions.

7. The method according to claim 6, wherein In step 3, uniform random sampling and weighted transformation are used to generate a set of weight vectors, including: Generate N m-dimensional weight vectors using uniform random sampling, where the N m-dimensional weight vectors are uniformly distributed in space; The N m-dimensional weight vectors are adjusted using a weighted transformation, including: Among them, λ i，j is the jth component of the i-th weight vector, 1≤i≤N, 1≤j≤m.

8. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images