Train multi-source information fusion positioning method based on 5G positioning

Abstract

The invention discloses a train multi-source information fusion positioning method based on 5G positioning, which fuses multi-source data information such as 5G positioning information, satellite positioning information, speed sensor information, transponder information and the like, and provides more reliable train position and speed information through redundancy complementation of the multi-source data information. The defect that positioning depends on satellite positioning and is greatly influenced by terrains and environments is overcome, and the problems that in the prior art, in the environments where satellite signals are shielded in tunnels, valleys and the like, satellite positioning fails, a system only uses a wheel axle speed sensor for speed measurement and distance measurement, and errors are large are solved.

Description

Technical Field

[0001] The present 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 Art

[0002] The train control system (hereinafter referred to as the train control system) is one of the core guarantees for high-speed railway transportation safety. It uses safe and effective technical means to monitor the train speed and interval in real time and prevent overspeeding, ensure train driving safety, and improve train operation efficiency. The realization of the safety function of the train control system must be based on safe, accurate, and highly reliable train positioning.

[0003] A single positioning technology is difficult to fully meet the needs of high-speed railway train operation, while the combined positioning technology of multi-sensor fusion can combine the advantages of each positioning sensor, make up for their respective shortcomings, and provide more reliable and accurate train position and speed information through redundant complementarity.

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

[0005] The above existing technical solutions use a combination of transponder positioning / satellite positioning / speed sensor axle speed and distance measurement. However, in environments where satellite signals are blocked, such as tunnels and valleys, satellite positioning fails. The system only uses the axle speed sensor for speed and distance measurement, and its positioning error will gradually increase with the increase of mileage. Therefore, the existing technical solutions are only applicable to environments where satellite signals are not blocked, and are difficult to adapt to tunnels and valleys.

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

[0007] The purpose of the present 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, transponder information, etc., and provides more reliable train position and speed information through redundant complementarity of multi-source data information.

[0008] The objective of the present invention is achieved through the following technical solutions:

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

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

[0011] Initialize the positioning information using satellite positioning information or the train position information and running direction information at the previous moment; use the particle filter algorithm to combine the speed sensor information with the initialized positioning information to predict the position information of each particle; use the position information of each particle and the 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.

[0012] It can be seen from the technical solution provided by the present invention that the 5G positioning information is integrated with the satellite positioning information, speed sensor information, transponder information, etc., which makes up for the disadvantage that the existing technical solution mainly relies on satellite positioning and is greatly affected by terrain and environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0014] Figure 1 Schematic diagram of the prior art provided as the background technology of the present invention

[0015] Figure 2 A schematic diagram of 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 is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings 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 protection scope of the present invention.

[0018] First, the terms that may be used in this article are explained as follows:

[0019] The terms "include", "comprises", "contains", "has" or other descriptions with similar semantics should be interpreted as non-exclusive inclusion. For example, including certain technical feature elements (such as raw materials, components, ingredients, carriers, dosage forms, materials, dimensions, parts, components, mechanisms, devices, steps, procedures, methods, reaction conditions, processing conditions, parameters, algorithms, signals, data, products or products, etc.) should be interpreted as including not only certain technical feature elements explicitly listed, but also other technical feature elements known in the art that are not explicitly listed.

[0020] The term "consisting of..." means excluding any technical feature elements not explicitly listed. If this term is used in a claim, it will make the claim closed, so that it does not contain technical feature elements other than the technical feature elements explicitly listed, except for the conventional impurities related to them. If this term only appears in a clause of a claim, it only limits the elements explicitly listed in the clause, and the elements recorded 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 the present invention. The contents not described in detail in the embodiments of the present invention belong to the prior art known to professional and technical personnel in this field. If no specific conditions are specified in the embodiments of the present invention, they shall be carried out in accordance with the conventional conditions in the field or the conditions recommended by the manufacturer. The instruments used in the embodiments of the present invention, for which the manufacturer is not specified, are all conventional products that can be purchased commercially.

[0022] The embodiment of the present invention provides a train multi-source information fusion positioning method based on 5G positioning, which integrates multi-source data such as 5G positioning, satellite positioning, speed sensor, transponder, etc., and provides more reliable train position and speed information through multi-source data redundancy and complementarity. Figure 2 As shown in the figure, the implementation principle is demonstrated, which mainly includes:

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

[0024] In the embodiment of the present invention, the 5G positioning information includes: the real position (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 signal from each 5G positioning base station. The satellite positioning information mainly includes: the longitude and latitude coordinates of the satellite positioning, and the direction angle of the train. The speed sensor main information 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 running direction information at the previous moment; use the particle filter algorithm to combine the speed sensor information with the initialized positioning information to predict the position information of each particle; use the position information of each particle and the 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] In order to more clearly demonstrate the technical solution and technical effects provided by the present invention, the method provided by the embodiment of the present invention is described in detail with reference to specific embodiments below.

[0027] The solution provided by the embodiment of the present invention, based on the existing technical solution, avoids the disadvantage of relying on satellite positioning and being greatly affected by terrain and environment during positioning by integrating the 5G positioning data source that is available at all times and everywhere, and solves the problem that the existing technology fails to provide satellite positioning in environments where satellite signals are blocked, such as tunnels and valleys, and the system only uses axle speed sensors to measure speed and distance, resulting in large errors. In addition to using 5G positioning, image / lidar positioning information can also be integrated to perform autonomous positioning of trains in environments where satellite signals are blocked, such as tunnels and valleys. However, the positioning accuracy of this type of technology is greatly affected by the environment (fog, dust, rainfall), etc., and there are disadvantages that the core algorithm relies on the artificial intelligence "black box" model, making it difficult to accurately measure its reliability, and the high-performance GPU devices it relies on rely on imports, making it difficult to be autonomously controllable.

[0028] Combine the following Figure 3 The process shown is used to introduce the present invention in detail.

[0029] Step 1: Initialize fusion positioning.

[0030] In the embodiment of the present invention, the positioning information is initialized using satellite positioning information, or the train position information and running direction information at 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 the latitude and longitude coordinates of satellite positioning and the direction angle of train operation. The latitude and longitude coordinates of satellite positioning and the direction angle of train operation obey the normal distribution, so the initial distribution of the train positioning position can be constructed, and the particle swarm is initialized by randomly sampling the initial distribution.

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

[0034] The initialized particle group p contains n particles, denoted as p = {X i |i=1,2,…,n}, the location information X of the i-th particle i Note: 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 particle motion, ω i is the particle weight.

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

[0036] Step 2: Position prediction.

[0037] This step is mainly responsible for predicting the position of each particle at a moment. Here, the particle filter algorithm is used in combination with the speed sensor information for prediction. The position of the particle at the previous moment needs to be used in the prediction process. If the current moment is the first moment, the position of the particle at that moment is the position after initialization in the previous step.

[0038] Specifically, we combine the information from the velocity sensor to transfer the state of each particle and predict the position information of the particle. Let the position information of the i-th particle at time t-1 be The time interval to time t is T, L T is the displacement of the train in T seconds calculated based on the speed sensor information, is the direction angle of the motion of the i-th particle, and the state equation is:

[0039]

[0040] in, is the predicted position information of the i-th particle at time t, is the predicted direction angle of the motion of the i-th particle at time t; when t = 1, To initialize the position information of the i-th particle contained in the positioning information, The direction angle of the motion of the i-th particle contained in the initial positioning information.

[0041] Step 3: Calculate particle weight.

[0042] In this step, the position information of each particle and the 5G positioning information are mainly used to calculate the weight 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, the 5G positioning information is integrated into the particle filter. The 5G positioning information includes: the absolute straight-line distance between the train and each 5G base station, the 5G signal arrival angle, and the absolute straight-line distance between the train and the jth 5G positioning base station is recorded as L j , the arrival angle of the 5G signal of the jth 5G positioning base station is recorded as θ j , the predicted position information of the i-th particle at time t is recorded as Then the location information of the i-th particle to the j-th 5G positioning base station is It is expressed as:

[0045]

[0046] (2) For each particle, the calculated location information of each 5G positioning base station and the actual location information of the corresponding 5G positioning base station are used to calculate the degree of association and matching with each 5G positioning base station; the degree of association and matching with all 5G positioning base stations is comprehensively calculated to obtain the weight of the corresponding particle.

[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] Among them, e is a natural constant, π is the symbol of pi, is the calculated location information of the i-th particle to the j-th 5G positioning base station, (α j ,β j ) is the real location information of the jth 5G positioning base station, σ x and σ y for and (α j ,β j ) noise in the x and y directions;

[0050] Since the particle's measurement of the position of each 5G positioning base station is independent, let the number of observable 5G positioning base stations be m, then the weight of the i-th particle ω 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 particles with higher weights have a greater probability of being retained, and the particles with smaller probabilities have a greater probability of disappearing.

[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 completes step (3), the particle resampling is completed.

[0069] Step 5: Calculate the position coordinates.

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

[0071]

[0072] in, is the predicted position information of the rth particle at time t.

[0073] Step 6: Balise Correction Position: When the train passes the balise, the train position is corrected using the absolute position information stored in the balise.

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

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

[0076] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims. The information disclosed in the background technology section of this article is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as an admission or in any form that the 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: Including: Obtaining satellite positioning information, speed sensor information, transponder information and 5G positioning information; Initializing positioning information using satellite positioning information, or train position information and running direction information at the previous moment; adopting a particle filter algorithm, combining speed sensor information and the initialized positioning information to predict the position information of each particle; calculating the weights of each particle using the position information of each particle and 5G positioning information; performing particle resampling using the particle weights, fusing the position information of the resampled particles, and correcting it through transponder information to obtain the train multi-source information fusion positioning result.

2. According to a 5G positioning-based train multi-source information fusion positioning method according to claim 1, it is characterized in that: The initializing positioning information using satellite positioning information, or train position information and running direction information at the previous moment includes: When the satellite positioning information meets the positioning accuracy requirements, initializing the particle swarm using the satellite positioning information as the initial positioning information; When the satellite positioning information does not meet the positioning accuracy requirements, randomly sampling the train position information and running direction information at the previous moment to complete the initialization of the particle swarm and using it as the initial positioning information.

3. According to a 5G positioning-based train multi-source information fusion positioning method according to claim 2, it is characterized in that: The initialized particle group p contains n particles, denoted as p = {X i |i=1,2,…,n}, the location information X of the i-th particle i Note: 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 particle motion, ω i is the particle weight.

4. According to a 5G positioning-based train multi-source information fusion positioning method according to claim 1, it is characterized in that: The predicting the position information of each particle by adopting a particle filter algorithm, combining speed sensor information and the initialized positioning information includes: Combined with the speed sensor information, each particle is transferred to a different state to predict the particle's position information. Suppose the position information of the i-th particle at time t-1 is The time interval to time t is T, L T is the displacement of the train in T seconds calculated based on the speed sensor information, is the direction angle of the motion of the i-th particle, and the state equation is: in, is the predicted position information of the i-th particle at time t, is the predicted direction angle of the motion of the i-th particle at time t; when t = 1, To initialize the position information of the i-th particle contained in the positioning information, The direction angle of the motion of the i-th particle contained in the initial positioning information.

5. According to a 5G positioning-based train multi-source information fusion positioning method according to claim 1, it is characterized in that: The calculating the weights of each particle using the position information of each particle and 5G positioning information includes: Combining the position information of each particle and 5G positioning information to calculate the position information of each particle relative to each 5G positioning base station; For each particle, using the calculated position information relative to each 5G positioning base station and the real position information of the corresponding 5G positioning base station, calculating the degree of association and matching with each 5G positioning base station; comprehensively considering the degree of association and matching with all 5G positioning base stations to obtain the weight of the corresponding particle; After calculating the weights of all particles, performing normalization processing to obtain the normalized weights of each particle.

6. A train multi-source information fusion positioning method based on 5G positioning according to claim 5, characterized in that: The calculating the position information of each particle relative to each 5G positioning base station includes: The 5G positioning information is integrated into the particle filter. The 5G positioning information includes: the absolute straight-line distance between the train and each 5G base station, the 5G signal arrival angle, and the absolute straight-line distance between the train and the jth 5G positioning base station is recorded as L j , the arrival angle of the 5G signal of the jth 5G positioning base station is recorded as θ j , the predicted position information of the i-th particle at time t is recorded as Then the location information of the i-th particle to the j-th 5G positioning base station is It is expressed as:

7. A train multi-source information fusion positioning method based on 5G positioning according to claim 5 or 6, characterized in that, For the i-th particle, the degree of association and matching P with the j-th 5G positioning base station is calculated by the following formula: Among them, e is a natural constant, π is the symbol of pi, is the calculated location information of the i-th particle to the j-th 5G positioning base station, (α j ,β j ) is the real location information of the jth 5G positioning base station, σ x and σ y for and (α j ,β j ) noise in the x and y directions; Let the number of observable 5G positioning base stations be m, then the weight of the i-th particle ω i for: For the i-th particle, normalize it by the following formula to obtain the normalized weight where n is the total number of particles.

8. The train multi-source information fusion positioning method based on 5G positioning according to claim 1 is characterized in that: The performing particle resampling using the particle weights includes: Step (1), initializing L = 1 and calculating the sum of weights c(L); in, is the normalized weight of the lth particle; Step (2), generate a random number sequence {u I } I＝1,…,n , where u I is the Ith random number, n is the total number of particles; Step (3), for the current random number, judging 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; Step (4), selecting a new random number and turning to step (3). When the last random number finishes step (3), the particle resampling is completed.

9. The train multi-source information fusion positioning method based on 5G positioning according to claim 1 is characterized in that: The fusing the position information of the resampled particles includes: Assume that Q particles are resampled and the center position of the set of Q particles is used as the fused train position (x train ,y train ), expressed as: in, is the predicted position information of the rth particle at time t.

Images