A train multi-source information fusion positioning method based on 5G positioning

Abstract

This invention discloses a train multi-source information fusion positioning method based on 5G positioning. It integrates multi-source data information such as 5G positioning, satellite positioning, speed sensor information, and transponder information, providing more reliable train position and speed information through redundancy and complementarity of multi-source data. This avoids the drawback of relying on satellite positioning, which is greatly affected by terrain and environment. It also solves the problem of existing technologies failing in environments where satellite signals are blocked, such as tunnels and valleys, resulting in significant errors when the system only uses wheel speed sensors for speed and distance measurement.

Description

Technical Field

[0001] This invention relates to the field of train positioning technology, and in particular to a train multi-source information fusion positioning method based on 5G positioning. Background Technology

[0002] The train control system (hereinafter referred to as the train control system) is one of the core safeguards for high-speed railway transportation safety. It uses safe and effective technical means to monitor train speed and intervals in real time and provide overspeed protection, ensuring train operation safety and improving train efficiency. The realization of the train control system's safety functions must be based on safe, accurate, and highly reliable train positioning.

[0003] Single positioning technology is insufficient to fully meet the needs of high-speed railway train operation, while multi-sensor fusion positioning technology can combine the advantages of various positioning sensors, make up for their shortcomings, and provide more reliable and accurate train position and speed information through redundancy and complementarity.

[0004] Existing technologies such as Figure 1 As shown, the train position and speed are calculated by multi-source fusion of the following sensor data: (1) Speed ​​sensor: acquires the pulse information of the wheel speed sensor, detects the current idling and coasting conditions, and calculates the train speed measurement value; (2) Satellite positioning receiving unit: receives the signal from the satellite navigation antenna and calculates the latitude and longitude position coordinates; (3) Transponder: a transponder is a point device used for ground-to-train information transmission. When the train passes the transponder installed on the ground, the transponder transmits the stored absolute position information to the train through electromagnetic induction in a certain modulation method, and the train position is determined by demodulation.

[0005] The existing technical solutions described above use a combination of transponder positioning, satellite positioning, and wheel axle speed and distance measurement for positioning. However, in environments where satellite signals are blocked, such as tunnels and valleys, satellite positioning fails, and the system relies solely on wheel axle speed sensors for speed and distance measurement. The positioning error then gradually increases with the mileage. Therefore, the existing technical solutions are only suitable for environments with unobstructed satellite signals and are ill-suited for tunnel and valley environments.

[0006] In view of this, the present invention is hereby proposed. Summary of the Invention

[0007] The purpose of this invention is to provide a train multi-source information fusion positioning method based on 5G positioning, which integrates multi-source data information such as 5G positioning information, satellite positioning information, speed sensor information, and transponder information, and provides more reliable train position and speed information through redundancy and complementarity of multi-source data information.

[0008] The objective of this invention is achieved through the following technical solution:

[0009] A train multi-source information fusion positioning method based on 5G positioning, comprising:

[0010] Acquire satellite positioning information, speed sensor information, transponder information, and 5G positioning information;

[0011] The positioning information is initialized using satellite positioning information or the train's position and direction of travel information from the previous moment; a particle filter algorithm is used to predict the position information of each particle by combining speed sensor information with the initialized positioning information; the position information of each particle is used to calculate the weight of each particle with 5G positioning information; the particle weights are used to resample the particles, the position information of the resampled particles is fused, and the transponder information is used for correction to obtain the multi-source information fusion positioning result of the train.

[0012] As can be seen from the technical solution provided by the present invention, the fusion of 5G positioning information with satellite positioning information, speed sensor information, transponder information, etc., makes up for the shortcomings of the existing technical solutions, which mainly rely on satellite positioning and are greatly affected by terrain and environment. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 The prior art principle diagram provided for the background of this invention

[0015] Figure 2 A schematic diagram illustrating the principle of a train multi-source information fusion positioning method based on 5G positioning provided in an embodiment of the present invention;

[0016] Figure 3 A flowchart of a train multi-source information fusion positioning method based on 5G positioning provided in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0018] First, the following explanations are provided for the terms that may be used in this article:

[0019] The terms “including,” “comprising,” “containing,” “having,” or other similar semantic descriptions should be interpreted as non-exclusive inclusion. For example, “including a technical feature element (such as raw material, component, ingredient, carrier, dosage form, material, size, part, component, mechanism, device, step, process, method, reaction conditions, processing conditions, parameter, algorithm, signal, data, product or article of manufacture, etc.)” should be interpreted as including not only the expressly listed technical feature element, but also other technical feature elements that are not expressly listed and are well-known in the art.

[0020] The term "composed of" excludes any technical features not expressly listed. When used in a claim, it closes the claim to exclude all technical features other than those expressly listed, except for associated conventional impurities. If the term appears only in a clause of a claim, it limits the claim to the elements expressly listed in that clause; elements recited in other clauses are not excluded from the overall claim.

[0021] The following is a detailed description of a train multi-source information fusion positioning method based on 5G positioning provided by this invention. Contents not described in detail in the embodiments of this invention are prior art known to those skilled in the art. Where specific conditions are not specified in the embodiments of this invention, they are performed according to conventional conditions in the art or conditions recommended by the manufacturer. Instruments used in the embodiments of this invention, unless otherwise specified by the manufacturer, are all conventional products that can be purchased commercially.

[0022] This invention provides a train multi-source information fusion positioning method based on 5G positioning. It integrates data from multiple sources, including 5G positioning, satellite positioning, speed sensors, and transponders. Through redundancy and complementarity of these multi-source data, it provides more reliable train position and speed information. Figure 2 The diagram illustrates its implementation principle, which mainly includes:

[0023] (1) Obtain satellite positioning information, speed sensor information, transponder information and 5G positioning information.

[0024] In this embodiment of the invention, the 5G positioning information includes: the actual location (latitude and longitude coordinates) of the 5G positioning base station, the absolute straight-line distance between the train and the 5G positioning base station, and the arrival angle of the 5G signals from each 5G positioning base station. The satellite positioning information mainly includes: satellite positioning latitude and longitude coordinates, and the direction angle of the train's movement. The speed sensor information mainly includes: the real-time speed value of the train. The transponder information mainly includes: the location information (absolute position) stored in the transponder.

[0025] (2) Initialize the positioning information using satellite positioning information or the train position information and direction of travel information from the previous moment; use the particle filtering algorithm, combined with speed sensor information and the initial positioning information, to predict the position information of each particle; use the position information of each particle and 5G positioning information to calculate the weight of each particle; use the particle weight to resample the particles, fuse the position information of the resampled particles, and correct it through the transponder information to obtain the multi-source information fusion positioning result of the train.

[0026] To more clearly demonstrate the technical solution and its effects provided by the present invention, the method provided by the embodiments of the present invention will be described in detail below with reference to specific examples.

[0027] The solution provided in this invention, based on existing technologies, integrates readily available 5G positioning data sources to avoid the drawbacks of relying on satellite positioning, which is greatly affected by terrain and environment. It solves the problem that existing technologies fail in environments where satellite signals are blocked, such as tunnels and valleys, resulting in significant errors when the system only uses wheel speed sensors for speed and distance measurement. Besides using 5G positioning, image / LiDAR positioning information can also be integrated for autonomous train positioning in environments with blocked satellite signals, such as tunnels and valleys. However, the positioning accuracy of such technologies is greatly affected by the environment (fog, dust, rain, etc.), and they suffer from drawbacks such as the core algorithm relying on an artificial intelligence "black box" model, making it difficult to accurately measure its reliability, and the high-performance GPU devices they rely on being imported, making independent control difficult.

[0028] The following is combined Figure 3 The process shown will be described in detail below.

[0029] Step 1: Initialize fusion positioning.

[0030] In this embodiment of the invention, positioning information is initialized using satellite positioning information, or the train's position and direction of travel information from the previous moment. Specifically:

[0031] (1) When the satellite positioning information meets the positioning accuracy requirements (the satellite positioning is good), the particle swarm is initialized using the satellite positioning information as the initial positioning information.

[0032] Satellite positioning information mainly includes satellite positioning latitude and longitude coordinates and the train's heading angle. Since both satellite positioning latitude and longitude coordinates and the train's heading angle follow a normal distribution, an initial distribution of the train's positioning position can be constructed, and the particle swarm can be initialized by randomly sampling this initial distribution.

[0033] (2) When the satellite positioning information does not meet the positioning accuracy requirements (poor satellite positioning), the train position information and running direction information of the previous moment are randomly sampled to complete the initialization of the particle swarm and used as the initial positioning information.

[0034] The initial particle swarm p contains n particles, denoted as p = {X} i |i=1,2,...,n}, the location information X of the i-th particle. i Let it be X i =(x i ,y i ,θ i ,ω i ), (x i ,y i ) represents the particle's position information, θ i ω is the direction angle of the particle's motion. i For particle weights.

[0035] The location information involved in the embodiments of the present invention is of the same type. For example, latitude and longitude coordinates can be used uniformly as location information.

[0036] Step 2, location prediction.

[0037] This step is mainly responsible for predicting the position of each particle at each time step. Here, a particle filtering algorithm is used, combined with velocity sensor information, to make the prediction. The position of the particle at the previous time step is needed in the prediction process. If the current time step is the first time step, then the position of the particle at the current time step is the position initialized in the previous step.

[0038] Specifically: The state transitions for each particle are performed based on velocity sensor information to predict the particle's position information; let the position information of the i-th particle at time t-1 be... The time interval to time t is T, L T This refers to the train's displacement within T seconds, calculated based on information from the speed sensor. Let be the direction angle of the i-th particle's motion, and the state equation is:

[0039]

[0040] in, This is the predicted position information of the i-th particle at time t. Let be the predicted direction angle of the i-th particle's motion at time t; when t = 1, To initialize the positioning information, the location information includes the position information of the i-th particle. The initialization location information includes the direction angle of the i-th particle's motion.

[0041] Step 3: Calculate particle weights.

[0042] In this step, the weights of each particle are mainly calculated using the position information and 5G positioning information of each particle, including:

[0043] (1) Combine the position information of each particle with the 5G positioning information to calculate the position information of each particle relative to each 5G positioning base station.

[0044] Specifically: 5G positioning information is fused into the particle filter. The 5G positioning information includes: the absolute straight-line distance between the train and each 5G base station, and the 5G signal arrival angle. The absolute straight-line distance between the train and the j-th 5G positioning base station is denoted as L. j The angle of arrival of the 5G signal from the j-th 5G positioning base station is denoted as θ. j The predicted position information of the i-th particle at time t is denoted as Then the location information of the i-th particle relative to the j-th 5G positioning base station Represented as:

[0045]

[0046] (2) For each particle, the degree of association matching with each 5G positioning base station is calculated using the calculated location information of each 5G positioning base station and the actual location information of the corresponding 5G positioning base station; the weight of the corresponding particle is obtained by combining the degree of association matching with all 5G positioning base stations.

[0047] For the i-th particle, its association matching degree P with the j-th 5G positioning base station is calculated by the following formula:

[0048]

[0049] Where e is the natural constant and π is the symbol for pi. To calculate the location information of the i-th particle relative to the j-th 5G positioning base station, (α) j ,β j ) represents the actual location information of the j-th 5G positioning base station, σ x and σ y for With (α) j ,β j Noise in the x and y directions;

[0050] Since the particle's measurement of the location of each 5G positioning base station is independent, let m be the number of observable 5G positioning base stations, then the weight ω of the i-th particle is... i for:

[0051]

[0052] (3) After calculating the weights of all particles, perform normalization to obtain the normalized weights of each particle.

[0053] For the i-th particle, perform normalization through the following formula to obtain the normalized weight

[0054]

[0055] where n is the total number of particles.

[0056] Step 4: Particle resampling.

[0057] In the resampling step, reselect particles according to the weights of the particles. After resampling, the probability of retaining particles with higher weights is greater, and the probability of particles with smaller probabilities disappearing is greater.

[0058] Calculate the sum of the weights c(L) of the first L particles:

[0059]

[0060] where is the normalized weight of the l-th particle.

[0061] Generate a sequence of random numbers {u I} I＝1,…,n that follows a uniform distribution on [0,1]. The resampling process can be represented by the following pseudocode:

[0062]

[0063] where copy(L) represents copying the L-th particle as the new particle after resampling.

[0064] The above particle resampling step can be described as:

[0065] Step (1): Initialize L = 1 and calculate the sum of weights c(L).

[0066] Step (2): Generate a sequence of random numbers {u I} I＝1,…,n that follows a uniform distribution on [0,1], and u I is the i-th random number.

[0067] Step (3): For the current random number, determine whether c(L) < u(I) is satisfied. If so, increment the value of L by 1 and calculate the sum of weights c(L); if not, copy the L-th particle as the new particle after resampling.

[0068] Step (4): Select a new random number and transfer to Step (3). After the last random number finishes executing Step (3), complete particle resampling.

[0069] Step 5: Calculate the position coordinates.

[0070] In this embodiment of the invention, the position information of the resampled particles is fused. Assuming there are Q particles after resampling, the center position of the set of Q particles is taken as the fused train position (x). train ,y train ), represented as:

[0071]

[0072] in, This is the predicted position information of the r-th particle at time t.

[0073] Step 6: Transponder Position Correction. When the train passes the transponder, the absolute position information stored in the transponder is used to correct the train's position.

[0074] Step 7: Continue iterating. Return to step 1 and continue iterating.

[0075] Through the above description of the embodiments, those skilled in the art can clearly understand that the above embodiments can be implemented by software, or by using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions of the above embodiments can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.), including several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0076] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. The information disclosed in the background section is intended only to enhance the understanding of the overall background technology of the present invention and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art.

Claims

1. A train multi-source information fusion positioning method based on 5G positioning, characterized in that, The method comprises the following steps: acquiring satellite positioning information, speed sensor information, transponder information and 5G positioning information; initializing the positioning information by using the satellite positioning information or the train position information and the running direction information at the previous moment; predicting the position information of each particle by using a particle filtering algorithm in combination with the speed sensor information and the initialized positioning information; calculating the weight of each particle by using the position information of each particle and the 5G positioning information; performing particle resampling by using the particle weight, fusing the position information of the resampled particles, and correcting the fused position information by using the transponder information to obtain a train multi-source information fusion positioning result; wherein the step of predicting the position information of each particle by using a particle filtering algorithm in combination with the speed sensor information and the initialized positioning information comprises the following steps: The state of each particle is transferred according to the speed sensor information, and the position information of the particle is predicted. The time interval from t-1 to t is T, and L T is the displacement of the train in T seconds calculated according to the speed sensor information, is the direction angle of the i-th particle, and the state equation is: wherein, is the position information of the i-th particle at time t, is the direction angle of the i-th particle motion at time t; when t = 1, is the position information of the i-th particle contained in the initialization positioning information, is the direction angle of the i-th particle motion contained in the initialization positioning information, the step of calculating the weight of each particle by using the position information of each particle and the 5G positioning information comprises the following steps: calculating the position information of each 5G positioning base station in combination with the position information of each particle and the 5G positioning information; for each particle, calculating the association matching degree with each 5G positioning base station by using the calculated position information of each 5G positioning base station and the real position information of the corresponding 5G positioning base station; obtaining the weight of the corresponding particle by comprehensively considering the association matching degrees with all the 5G positioning base stations; after the weights of all the particles are calculated, performing normalization processing to obtain the normalized weight of each particle; Calculating the position information of each particle relative to each 5G positioning base station includes: fusing 5G positioning information into the particle filter. The 5G positioning information includes: the absolute straight-line distance between the train and each 5G base station, and the 5G signal arrival angle. The absolute straight-line distance between the train and the j-th 5G positioning base station is denoted as L. j The angle of arrival of the 5G signal from the j-th 5G positioning base station is denoted as θ. j The predicted position information of the i-th particle at time t is denoted as Then the location information of the i-th particle relative to the j-th 5G positioning base station Represented as: the association matching degree P of the i-th particle with the j-th 5G positioning base station is calculated by the following formula: wherein e is a natural constant, and π is a circular constant, is the calculated position information of the i-th particle to the j-th 5G positioning base station, j ,β j ) is the real position information of the j-th 5G positioning base station, σ x and σ y are and (α j ,β j ) are the noises in the x and y directions. The number of observable 5G positioning base stations is m, and the weight ω of the i-th particle is i is:

2. The train multi-source information fusion positioning method based on 5G positioning according to claim 1, characterized in that, the step of initializing the positioning information by using the satellite positioning information or the train position information and the running direction information at the previous moment comprises the following steps: when the satellite positioning information meets the positioning accuracy requirement, initializing the particle group by using the satellite positioning information as the initialized positioning information; when the satellite positioning information does not meet the positioning accuracy requirement, initializing the particle group by randomly sampling the train position information and the running direction information at the previous moment, and taking the initialized particle group as the initialized positioning information.

3. The train multi-source information fusion positioning method based on 5G positioning according to claim 2, characterized in that, The initialized particle swarm p includes n particles, denoted as p = {X i |i = 1, 2, …, n}, the positioning information X i of the i-th particle is denoted as X i = (x i , y i , θ i , ω i ), (x i , y i ) is the position information of the particle, θ i is the direction angle of the particle motion, and ω i is the particle weight.

4. The train multi-source information fusion positioning method based on 5G positioning according to claim 1, wherein n is the total number of particles. For the i-th particle, the normalized weight is obtained by normalizing by the following equation the step of performing particle resampling by using the particle weight comprises the following steps:

5. The train multi-source information fusion positioning method based on 5G positioning according to claim 1, characterized in that, step (1), initializing L = 1, and calculating the sum c(L) of the weights: step (3), for the current random number, determining whether c(L) < u(I) is satisfied, if yes, increasing the value of L by 1 and calculating the sum c(L) of the weights, if not, copying the L-th particle as a new particle after resampling; wherein, is the weight normalized for the 1st particle; Step (2), generating a sequence of random numbers {u I} I＝1,...,n where u I is the Ith random number, and n is the total number of particles. step (4), selecting a new random number and returning to step (3), and when the last random number is executed in step (3), the particle resampling is completed. the step of fusing the position information of the resampled particles comprises the following steps:

6. The train multi-source information fusion positioning method based on 5G positioning according to claim 1, characterized in that, ​ Set resample Q particles, the set of Q particles center position as the fusion of train position (x train ,y train ), expressed as: wherein, is the position information of the rth particle at the predicted time t.

Images