A high-precision positioning method and system for high-speed trains

Abstract

The present invention relates to a high-precision positioning method and system for high-speed trains, and belongs to the technical field of high-speed train positioning. A multi-objective optimization model is first established, and the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function, and the constraint conditions include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map. Then, the first positioning data of the Beidou satellite navigation system and the second positioning data of the inertial navigation system are used as inputs of the multi-objective optimization model, and the improved differential evolution algorithm is used to solve the problem, and the optimal positioning data of the high-speed train is obtained. Based on the positioning strategy integrated with the Beidou satellite navigation system, the inertial navigation system and the electronic map, the reliability of the high-speed train positioning is improved, and the high-precision positioning of the high-speed train is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-speed train positioning, and in particular to a high-speed train high-precision positioning method and system based on the integration of a Beidou satellite navigation system, an inertial navigation system and an electronic map. Background Art

[0002] Railway transportation is one of the pillar industries of my country's national economy. With the rapid development of railway transportation, how to improve transportation efficiency, reduce operating and maintenance costs, and ensure the safety of the transportation process has become a new issue of concern for railway transportation. Realizing continuous autonomous positioning of trains and establishing a more advanced and complete intelligent control system for train operation is an effective way to solve this problem. At the same time, continuous autonomous positioning of trains is also a prerequisite for building a safe, convenient, efficient, economical and green railway transportation network.

[0003] In recent years, the main research on train positioning can be divided into four aspects: multi-sensor information fusion, wireless sensor networks, heuristic algorithms and electronic map matching. Multi-sensor information fusion is a method of positioning the position of high-speed trains by reasonably combining the information measured by each sensor according to certain criteria; wireless sensor network is a distributed sensor network, which consists of sensors or mobile base stations distributed along the railway and receiving devices on the train. Its positioning methods are mainly divided into four types: signal strength positioning method, direction measurement positioning method, arrival time positioning method and arrival time difference positioning method; heuristic algorithms are mainly used to solve multi-sensor information fusion and wireless sensor network problems, among which the most representative ones are fuzzy control theory, genetic algorithm and artificial neural network; electronic map matching is an auxiliary positioning method that matches the positioning results of other positioning systems with the electronic track map to eliminate the longitudinal error of the railway track and achieve more accurate positioning.

[0004] At present, the research on the fusion positioning method of high-speed trains mainly focuses on the fusion positioning between various navigation systems and sensor networks, but the positioning accuracy of existing methods is limited and it is impossible to complete the high-precision positioning of trains. Electronic map matching can improve the positioning accuracy, but the information transmission takes a lot of time, so there are few studies that use electronic map matching for the fusion positioning process, and high-precision positioning combined with map information has not been achieved.

[0005] Based on this, there is an urgent need for a high-precision positioning technology for high-speed trains based on electronic maps. Summary of the invention

[0006] The purpose of the present invention is to provide a high-precision positioning method and system for high-speed trains, which integrates the Beidou satellite navigation system, the inertial navigation system and the electronic map, and adopts an improved differential evolution algorithm for solving, thereby improving the reliability of high-speed train positioning and achieving high-precision positioning of high-speed trains.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] A high-precision positioning method for a high-speed train, the positioning method comprising:

[0009] Acquire first positioning data obtained by positioning a high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system;

[0010] The first positioning data and the second positioning data are used as inputs of a multi-objective optimization model, and an improved differential evolution algorithm is used to solve the model to obtain the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map.

[0011] A high-precision positioning system for a high-speed train, the positioning system comprising:

[0012] A positioning data acquisition module, used to acquire first positioning data obtained by positioning the high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system;

[0013] An optimization module is used to use the first positioning data and the second positioning data as inputs of a multi-objective optimization model, and use an improved differential evolution algorithm to solve the problem to obtain the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map.

[0014] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0015] The present invention is used to provide a high-precision positioning method and system for high-speed trains. A multi-objective optimization model is first established, which includes an objective function and a constraint condition. The objective function is a weighted function of a positioning error function of a Beidou satellite navigation system, a distance error function of an inertial navigation system, and a direction error function of an inertial navigation system. The constraint condition includes a positioning error constraint of the Beidou satellite navigation system, a distance error constraint and a direction error constraint of an inertial navigation system, and a positioning error constraint of an electronic map. The electronic map information is added to the high-speed train positioning process in the form of a track constraint. Then, first positioning data obtained by positioning the high-speed train through the Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through the inertial navigation system are obtained. The first positioning data and the second positioning data are used as inputs of the multi-objective optimization model, and an improved differential evolution algorithm is used for solving the problem to obtain the optimal positioning data of the high-speed train. The Beidou satellite navigation system, the inertial navigation system, and the electronic map are integrated, and the improved differential evolution algorithm is used for solving the problem to improve the reliability of the high-speed train positioning and realize the high-precision positioning of the high-speed train. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A method flow chart of the positioning method provided by Embodiment 1 of the present invention;

[0018] Figure 2 This is a principle block diagram of the positioning method provided in Embodiment 1 of the present invention;

[0019] Figure 3 A schematic diagram of the mutation operation of the improved differential evolution algorithm provided in Example 1 of the present invention;

[0020] Figure 4 A flowchart of the solution of the improved differential evolution algorithm provided in Example 1 of the present invention;

[0021] Figure 5 A comparison diagram of the positions before and after positioning in the simulation experiment provided in Example 1 of the present invention;

[0022] Figure 6 This is a comparison diagram of the errors before and after positioning in the simulation experiment provided in Example 1 of the present invention;

[0023] Figure 7 This is a system block diagram of a positioning system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] The purpose of the present invention is to provide a high-precision positioning method and system for high-speed trains, which integrates the Beidou satellite navigation system, the inertial navigation system and the electronic map, and adopts an improved differential evolution algorithm for solving, thereby improving the reliability of high-speed train positioning and achieving high-precision positioning of high-speed trains.

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] Embodiment 1:

[0028] This embodiment is used to provide a high-precision positioning method for high-speed trains. Figure 1 and Figure 2 As shown, the positioning method includes:

[0029] S1: Acquire first positioning data obtained by positioning a high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system;

[0030] S2: Using the first positioning data and the second positioning data as inputs of a multi-objective optimization model, solving the model using an improved differential evolution algorithm, and obtaining the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map.

[0031] In this embodiment, the positioning error, direction error and distance error are weighted to form an objective function, and the positioning error range and the orbit equation of the electronic map are converted into constraint conditions, so as to convert the high-speed train positioning problem integrating the Beidou satellite navigation system, the inertial navigation system and the electronic map into a multi-objective optimization problem, establish a multi-objective optimization model, and use an improved differential evolution algorithm to solve the multi-objective optimization model to obtain the optimal positioning data of the high-speed train.

[0032] Specifically, the multi-objective optimization model of this embodiment includes an objective function and constraints.

[0033] Among them, according to the analysis of the train positioning system, the objective function required for train positioning is designed, and the process of establishing the objective function is:

[0034] (1) The fitness function f is obtained from the positioning error of the Beidou satellite navigation system 1 , f 1 That is, the positioning error function of the Beidou satellite navigation system, which is the distance from the individual coordinates to the reference coordinates of the Beidou satellite navigation system, as follows:

[0035] f 1 =||pp(i,t)-sp(t)||;

[0036] Wherein, pp(i,t) is the i-th individual of the current positioning t (referring to the current positioning as the t-th positioning); sp(t) is the first positioning data of the current positioning t, obtained by the Beidou satellite navigation system; ||pp(i,t)-sp(t)|| represents the modulus length between the i-th individual generated by the current positioning t and the first positioning data obtained by the Beidou satellite navigation system. It should be noted that the positioning data in this embodiment refers to the position coordinates of the high-speed train.

[0037] (2) Obtain the fitness function f from the distance error of the inertial navigation system 2 , f 2 That is the distance error function of the inertial navigation system, which is the distance from the individual coordinates to the reference coordinates of the inertial navigation system, as follows:

[0038] f 2 =||pp(i,t)-s(t)||;

[0039] Wherein, s(t) is the second positioning data of the current position t, which is obtained by the inertial navigation system; ||pp(i,t)-s(t)|| represents the modulus length of the second positioning data of the i-th individual generated by the current position t and the inertial navigation system.

[0040] (3) Obtain the fitness function f from the direction error of the inertial navigation system 3 , f 3 That is, the direction error function of the inertial navigation system is the direction error value corresponding to the individual coordinates, as follows:

[0041]

[0042] Among them, φ pp(i,t)s(t-1) is the azimuth change value between the i-th individual at the current location t and the best location data obtained at the last location t-1; φ tIt is the azimuth change value measured by the inertial navigation system at the current position t.

[0043] It should be noted that X pp(i,t) , Y pp(i,t) , Z pp(i,t) That is, the three-dimensional position coordinates of the i-th individual at the current location t; X s(t-1) , Y s(t-1) , Z s(t-1) That is, the three-dimensional position coordinates of the best positioning data obtained from the last positioning t-1.

[0044] (4) The inverse of the maximum error is used to weight the corresponding fitness function, and the multi-objective optimization problem is converted into a single-objective optimization problem. Since the Beidou satellite navigation system is an absolute positioning system, the error value is independent of time, while the error value of the inertial navigation system is related to time. Therefore, the weighting coefficient of the Beidou satellite navigation system uses the inverse of the maximum error, and the weighting coefficient of the inertial navigation system uses the inverse of the maximum error that occurred before the current positioning. The weighted objective function is:

[0045]

[0046] Among them, F(t) is the objective function of the current location t; is the maximum error range value of the Beidou satellite navigation system (in this embodiment, it can be set to 15m); f 1 is the positioning error function of the Beidou satellite navigation system; max(e 1 ) is the maximum distance error value that the inertial navigation system has experienced before the current positioning t; f 2 is the distance error function of the inertial navigation system; max(e 2 ) is the maximum direction error value of the inertial navigation system before the current positioning t; f 3 is the direction error function of the inertial navigation system;

[0047] This embodiment establishes a constraint equation based on the electronic map and the high-speed train positioning requirements to obtain the constraint conditions of the multi-objective optimization problem of high-speed train positioning, that is, the constraint conditions of the multi-objective optimization model include:

[0048] (1) The constrained inequality obtained from the positioning error of the Beidou satellite navigation system, that is, the positioning error constraint of the Beidou satellite navigation system is:

[0049]

[0050] (2) The constraint inequality obtained from the distance error of the inertial navigation system, that is, the distance error constraint of the inertial navigation system is:

[0051]

[0052] in, It is the maximum distance error allowed by the inertial navigation system.

[0053] (3) The constraint inequality obtained from the direction error of the inertial navigation system, that is, the direction error constraint of the inertial navigation system is:

[0054]

[0055] Among them, |φ pp(i,t)s(t-1) -φ t | represents the absolute value of the direction error, It is the maximum direction error value allowed by the inertial navigation system.

[0056] (4) The constraint inequality obtained from the high-speed railway track equation (obtained based on the electronic map), that is, the positioning error constraint of the electronic map is:

[0057]

[0058] Wherein, y and z are the actual coordinates in the third positioning data obtained by positioning the high-speed train through the electronic map, and the third positioning data is the position of the high-speed train displayed on the electronic map; 1 (x), f 2 (x) are the fitting coordinates of the high-speed train obtained by fitting the y and z curve functions about x in the WGS84 coordinate system based on the point data of the electronic map, so that the electronic map information is added to the high-speed train positioning process in the form of track constraints, thereby saving the time for data transmission required for map matching positioning, and using the electronic map information to accurately determine the positioning result and save data transmission time. y, z, f 1 (x), f 2 (x) refers to the coordinates in the WGS84 coordinate system, x is longitude, y is latitude, and z is elevation. The current high-speed railway line gauge is 1.435m, so the plane error is set to ±0.7m and the elevation error is set to ±0.2m.

[0059] It should be noted that before starting positioning, this embodiment will fit the electronic map point data of the high-speed train track between the two stations into straight lines, circular curves and transition curves to obtain a track equation that can reasonably describe the characteristics of the high-speed train track between the two stations. During the current positioning, the corresponding track equation will be selected according to the first positioning data and the second positioning data, that is, f 1 (x), f 2 (x).

[0060] Preferably, after obtaining the first positioning data of the Beidou satellite navigation system, the second positioning data of the inertial navigation system, and the third positioning data of the electronic map of the high-speed train track, this embodiment will perform data preprocessing, specifically as follows: perform coordinate projection transformation, unify the first positioning data, the second positioning data and the third positioning data into the same map coordinate system, which can be the WGS84 coordinate system in this embodiment; use the density-based spatial clustering of applications with noise (DBSCAN) method to perform data screening to eliminate invalid data, and the specific operations are: for the first positioning data, if it is abnormal, delete the data; for the second positioning data and the third positioning data, if they are abnormal, delete the data and perform fitting interpolation processing.

[0061] In designing the algorithm for solving the high-speed train positioning problem based on the integration of the Beidou satellite navigation system, the inertial navigation system and the electronic map, this embodiment improves the algorithm according to the high-speed train positioning requirements, and specifically refers to the gray wolf algorithm idea to improve the mutation operation of the differential evolution algorithm, that is, the improved differential evolution algorithm of this embodiment is obtained by improving the mutation operation of the differential evolution algorithm, and the mutation operation of the improved differential evolution algorithm is:

[0062] (1) Arrange the individuals in the current generation population in descending order according to the objective function value, and select the first three individuals as the optimal individuals;

[0063] (2) Randomly select three individuals from the individuals other than the best individual in the current generation population, and reconstruct a new individual based on the three individuals;

[0064] Reconstructing a new individual based on three individuals means that a new individual is composed of the difference vectors of one of the individuals and the other two individuals. Specifically, reconstructing a new individual based on three individuals may include: randomly selecting an individual from the three individuals as the original individual; calculating the first difference between the remaining two individuals of the three individuals except the original individual, and calculating the product of the first difference and the first variation factor to obtain a first change; calculating the sum of the original individual and the first change, and reconstructing a new individual.

[0065] (3) Generate an individual in the next generation population based on the new individual and the best individual;

[0066] Generating an individual in the next generation population according to the new individual and the optimal individual is to instruct the new individual to generate an individual in the next generation population after adding the difference vector between the original individual and each optimal individual. Specifically, generating an individual in the next generation population according to the new individual and the optimal individual may include: recording the optimal individuals as the first individual, the second individual, and the third individual respectively; calculating the second difference between the first individual and the original individual, and calculating the product of the second difference and the second variation factor to obtain the second variation; calculating the third difference between the second individual and the original individual, and calculating the product of the third difference and the third variation factor to obtain the third variation; calculating the fourth difference between the third individual and the original individual, and calculating the product of the fourth difference and the fourth variation factor to obtain the fourth variation; calculating the sum of the new individual, the second variation, the third variation, and the fourth variation to obtain an individual in the next generation population.

[0067] (4) Determine whether the number of individuals in the next generation population is equal to the number of individuals in the current generation population; if so, complete the mutation operation; if not, return to the step of "randomly selecting three individuals from the individuals other than the best individual in the current generation population".

[0068] like Figure 3 As shown, the above mutation operation includes the following formula:

[0069]

[0070] in, is the i-th individual in the g-th generation population, which is a d-dimensional vector. In this embodiment, since the positioning data is a 3-dimensional coordinate, d is 3; It is the new individual generated during the mutation operation; are three individuals randomly selected from the g-th generation population, p1≠p2≠p3 and the three individuals are not the best individuals, For the original individual; is the i-th individual in the g+1-th generation population; is the best individual in the g-th generation population; F 1 、F 2 、F 3 、F 4 are the first, second, third and fourth variation factors respectively, and F 1 It can be obtained from rand(0,0.5), F 2 、F 3 、F 4 It can be obtained from rand(0, 0.25).

[0071] This embodiment improves the mutation operation of the differential evolution algorithm, which not only speeds up the algorithm's solution speed, but also prevents the algorithm from falling into a local optimum, thereby improving the algorithm's performance and the real-time nature of high-speed train positioning.

[0072] Combined with the above mutation operations, such as Figure 4 As shown, the improved differential evolution algorithm is used to solve the multi-objective optimization model transformed from the high-speed train positioning problem based on the integration of the Beidou satellite navigation system, the inertial navigation system and the electronic map to obtain the positioning result of the high-speed train. That is, the improved differential evolution algorithm can be used to solve the problem, which includes:

[0073] (1) Screening the point data of the electronic map to eliminate invalid map data, and performing segmented fitting according to the stations after interpolation to establish an orbit equation; obtaining the first positioning data of the Beidou satellite navigation system and the second positioning data of the inertial navigation system, and selecting a suitable orbit equation from the orbit equations obtained by segmented fitting according to the first positioning data and the second positioning data after screening and eliminating invalid data; performing coordinate projection transformation on the first positioning data, and unifying it with the second positioning data and the third positioning data into the same coordinate system; and then substituting the first positioning data, the second positioning data, the third positioning data and the suitable orbit equation into the multi-objective optimization model, in which only the individual is an unknown quantity.

[0074] Set the population size N and the maximum number of iterations g max , crossover factor and mutation factor F 1 、F 2 、F 3 、F 4 .

[0075] (2) randomly generating an initial population according to the second positioning data;

[0076] Specifically, the initial population is generated by adding a random value within an error range to the second positioning data to complete the initialization of the population.

[0077] The formula used for population initialization is:

[0078] pp(i,t)=s(t)+(r-0.5)*max(e 1 );

[0079] Among them, pp(i,t) is a three-dimensional coordinate vector, representing the randomly generated i-th initial individual; s(t) is a three-dimensional coordinate vector, representing the second positioning data of the inertial navigation system; r represents a 1*3 vector randomly generated between (0, 1).

[0080] After randomly generating N individuals using the above formula, the initial population is obtained. In the process of generating individuals, it is necessary to pay attention to that the generated individuals must meet the constraints.

[0081] (3) Calculate the objective function value of each individual in the initial population, and perform mutation, crossover, and selection operations on the initial population in sequence according to the objective function value to obtain a new population;

[0082] In the process of generating a new population, it is necessary to pay attention to the fact that the generated individuals must meet the constraints.

[0083] (4) Determine whether the maximum number of iterations has been reached; if so, the current number of iterations g>g max , the iteration ends, and the individual with the largest objective function value in the new population is selected as the best individual. The best individual is the best positioning data and the final matching positioning result output; if not, the iteration continues, and the new population is used as the initial population in the next iteration, and returns to the step of "calculating the objective function value of each individual in the initial population".

[0084] Preferably, after obtaining the best positioning data of the high-speed train, the positioning method of this embodiment also includes: performing parameter correction on the Beidou satellite navigation system and the inertial navigation system according to the best positioning data, and using the corrected Beidou satellite navigation system and the corrected inertial navigation system for the next positioning. Specifically, the best positioning data obtained by the improved differential evolution algorithm is fed back to the inertial navigation system and the Beidou satellite navigation system, and for the inertial navigation system, the position, speed and acceleration measured by the inertial navigation system are updated and corrected, and the positioning is performed on the basis of the best positioning data at the next positioning; for the satellite positioning system, the longitude and latitude of the best positioning data are used to make a difference with the longitude and latitude of the first positioning data to obtain an offset, and the offset is used to perform a certain offset processing on the positioning result of the Beidou satellite navigation system at the next positioning to reduce the error of the positioning results provided by the two navigation systems at the next positioning.

[0085] This embodiment can preset the time interval between two adjacent positionings to determine the time point of the next positioning, or customize the time point of the next positioning according to needs. Regardless of the method used to determine the time point of the next positioning, this embodiment will continue to perform positioning during the operation of the high-speed train until the high-speed train stops running.

[0086] Here, this embodiment provides a simulation experiment example to further introduce the effect of the positioning method of this embodiment:

[0087] This embodiment uses the motion data measured by a car equipped with a Beidou satellite navigation system provided by the Beidou Open Laboratory website, and designs a high-speed train positioning simulation experiment based on the integration of the Beidou satellite navigation system, inertial navigation system and electronic map based on MATLAB software. Figure 5 Position comparison chart before and after positioning Figure 6 From the comparison of the errors before and after positioning, it can be seen that the positioning method of this embodiment can improve the positioning accuracy and positioning reliability of high-speed trains. Simulation data show that the average time for a single positioning solution is 0.11s, and the average positioning error is 3.649m. The results show that the high-speed train positioning method based on the integration of the Beidou satellite navigation system, the inertial navigation system and the electronic map proposed in this embodiment meets the requirements of high-speed train positioning, can effectively improve the train positioning accuracy, and is conducive to ensuring the safety of high-speed trains and the establishment of intelligent train control systems.

[0088] This embodiment is used to provide a high-precision positioning method for high-speed trains based on the integration of the Beidou satellite navigation system, the inertial navigation system and the electronic map. It adopts a positioning strategy that integrates the Beidou satellite navigation system, the inertial navigation system and the electronic map, improves the reliability of high-speed train positioning, and realizes high-precision positioning of high-speed trains.

[0089] Embodiment 2:

[0090] This embodiment is used to provide a high-precision positioning system for high-speed trains. Figure 7 As shown, the positioning system includes:

[0091] A positioning data acquisition module M1 is used to acquire first positioning data obtained by positioning the high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system;

[0092] The optimization module M2 is used to use the first positioning data and the second positioning data as inputs of a multi-objective optimization model, and use an improved differential evolution algorithm to solve the problem to obtain the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map.

[0093] Compared with the prior art, the significant advantages of this embodiment are: (1) the high-speed train positioning strategy based on the integration of the Beidou satellite navigation system, the inertial navigation system and the electronic map improves the reliability of high-speed train positioning and realizes high-precision positioning of high-speed trains; (2) the improvement of the mutation operation of the differential evolution algorithm not only speeds up the algorithm's solution speed, but also avoids the algorithm from falling into the local optimum, thereby improving the algorithm's performance and the real-time performance of high-speed train positioning.

[0094] Each embodiment in this specification focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0095] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A high-precision positioning method for high-speed trains, characterized in that: The positioning method comprises: Acquire first positioning data obtained by positioning a high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system; The first positioning data and the second positioning data are used as inputs of a multi-objective optimization model, and an improved differential evolution algorithm is used to solve the problem to obtain the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map; The improved differential evolution algorithm is obtained by improving the mutation operation of the differential evolution algorithm; The mutation operation of the improved differential evolution algorithm is: Arrange the individuals in the current generation population in descending order according to the objective function value, and select the first three individuals as the best individuals; Randomly select three individuals from the individuals other than the optimal individual in the current generation population, and reconstruct a new individual based on the three individuals; Generate an individual in the next generation population according to the new individual and the optimal individual; Determine whether the number of individuals in the next generation population is equal to the number of individuals in the current generation population; If yes, the mutation operation is completed; If not, return to the step of "randomly selecting three individuals from the individuals other than the optimal individual in the current generation population"; The step of reconstructing a new individual according to the three individuals specifically includes: Randomly select one individual from the three individuals as the original individual; Calculating a first difference between two individuals of the three individuals except the original individual, and calculating the product of the first difference and a first variation factor to obtain a first variation; Calculate the sum of the original individual and the first variation, and reconstruct a new individual; The step of generating an individual in the next generation population according to the new individual and the optimal individual specifically comprises: The optimal individuals are respectively recorded as the first individual, the second individual and the third individual; Calculating a second difference between the first individual and the original individual, and calculating the product of the second difference and a second variation factor to obtain a second variation; Calculating a third difference between the second individual and the original individual, and calculating the product of the third difference and a third variation factor to obtain a third variation; Calculating a fourth difference between the third individual and the original individual, and calculating the product of the fourth difference and a fourth variation factor to obtain a fourth variation; The sum of the new individual, the second variation, the third variation and the fourth variation is calculated to obtain an individual in the next generation population.

2. The positioning method according to claim 1, characterized in that: The objective function is: Among them, F(t) is the objective function of the current location t; is the maximum error range value of the Beidou satellite navigation system; f1 is the positioning error function of the Beidou satellite navigation system; max(e1) is the maximum distance error value of the inertial navigation system before the current positioning t; f2 is the distance error function of the inertial navigation system; max(e2) is the maximum direction error value of the inertial navigation system before the current positioning t; f3 is the direction error function of the inertial navigation system; f1=||pp(i,t)-sp(t)||; Where pp(i,t) is the i-th individual at the current location t; sp(t) is the first positioning data at the current location t; f2=||pp(i,t)-s(t)||; Wherein, s(t) is the second positioning data of the current positioning t; f3=|φ pp(i,t)s(t-1) -f t |; Among them, φ pp(i,t)s(t-1) is the azimuth change value between the i-th individual at the current location t and the best location data obtained at the last location t-1; φ t It is the azimuth change value measured by the inertial navigation system at the current position t.

3. The positioning method according to claim 2, characterized in that: The positioning error constraint of the Beidou satellite navigation system is: The range error constraint of the inertial navigation system is: in, is the maximum distance error value allowed by the inertial navigation system; The orientation error constraint of the inertial navigation system is: in, is the maximum direction error value allowed by the inertial navigation system; The positioning error constraint of the electronic map is: Among them, y and z are the actual coordinates in the third positioning data obtained by positioning the high-speed train through the electronic map; f1(x) and f2(x) are the fitted coordinates obtained by positioning the high-speed train according to the curve function fitted according to the point data of the electronic map.

4. The positioning method according to claim 1, characterized in that: The method of solving the problem by using the improved differential evolution algorithm specifically includes: Randomly generate an initial population according to the second positioning data; Calculating the objective function value of each individual in the initial population, and performing mutation operation, crossover operation and selection operation on the initial population in sequence according to the objective function value to obtain a new population; Determine whether the maximum number of iterations has been reached; If yes, the iteration ends, and the individual with the largest objective function value in the new population is selected as the best individual; the best individual is the best positioning data; If not, continue iterating, use the new population as the initial population in the next iteration, and return to the step of "calculating the objective function value of each individual in the initial population".

5. The positioning method according to claim 4, characterized in that: The randomly generating an initial population according to the second positioning data specifically includes: generating an initial population by adding a random value within an error range to the second positioning data.

6. The positioning method according to claim 1, characterized in that: After obtaining the optimal positioning data of the high-speed train, the positioning method further includes: performing parameter correction on the Beidou satellite navigation system and the inertial navigation system according to the optimal positioning data, and performing the next positioning using the corrected Beidou satellite navigation system and the corrected inertial navigation system.

7. A high-precision positioning system for high-speed trains, characterized in that: The positioning system comprises: A positioning data acquisition module, used to acquire first positioning data obtained by positioning the high-speed train through a Beidou satellite navigation system and second positioning data obtained by positioning the high-speed train through an inertial navigation system; An optimization module is used to use the first positioning data and the second positioning data as inputs of a multi-objective optimization model, and solve the problem using an improved differential evolution algorithm to obtain the optimal positioning data of the high-speed train; the multi-objective optimization model includes an objective function and constraints; the objective function is a weighted function of the positioning error function of the Beidou satellite navigation system, the distance error function of the inertial navigation system, and the direction error function of the inertial navigation system; the constraints include the positioning error constraint of the Beidou satellite navigation system, the distance error constraint and the direction error constraint of the inertial navigation system, and the positioning error constraint of the electronic map; The improved differential evolution algorithm is obtained by improving the mutation operation of the differential evolution algorithm; The mutation operation of the improved differential evolution algorithm is: Arrange the individuals in the current generation population in descending order according to the objective function value, and select the first three individuals as the best individuals; Randomly select three individuals from the individuals other than the optimal individual in the current generation population, and reconstruct a new individual based on the three individuals; Generate an individual in the next generation population according to the new individual and the optimal individual; Determine whether the number of individuals in the next generation population is equal to the number of individuals in the current generation population; If yes, the mutation operation is completed; If not, return to the step of "randomly selecting three individuals from the individuals other than the optimal individual in the current generation population"; The step of reconstructing a new individual according to the three individuals specifically includes: Randomly select one individual from the three individuals as the original individual; Calculating a first difference between two individuals of the three individuals except the original individual, and calculating the product of the first difference and a first variation factor to obtain a first variation; Calculate the sum of the original individual and the first variation, and reconstruct a new individual; The step of generating an individual in the next generation population according to the new individual and the optimal individual specifically comprises: The optimal individuals are respectively recorded as the first individual, the second individual and the third individual; Calculating a second difference between the first individual and the original individual, and calculating the product of the second difference and a second variation factor to obtain a second variation; Calculating a third difference between the second individual and the original individual, and calculating the product of the third difference and a third variation factor to obtain a third variation; Calculating a fourth difference between the third individual and the original individual, and calculating the product of the fourth difference and a fourth variation factor to obtain a fourth variation; The sum of the new individual, the second variation, the third variation and the fourth variation is calculated to obtain an individual in the next generation population.

Images