Multi-sensor data fusion metro train mileage positioning method and related equipment
By installing intelligent sensing terminals in subway cars, acquiring and integrating cabin acceleration data, calculating vibration time delay and estimating train running speed, the problem of subway train positioning in GPS-free environment is solved, and high-precision mileage positioning is achieved.
Patent Information
- Application Number
- CN202510023142.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-07
- Publication Date
- 2025-04-11
AI Technical Summary
Subway trains cannot receive GPS signals when operating in underground environments, and the prior art is difficult to achieve low-cost GPS-free subway train positioning in low-cost GPS-free environments, and the IMU sensor has a large mileage position error due to inertial drift.
By installing intelligent sensing terminals in the subway car, the car acceleration is obtained, the waveform matching is performed to calculate the vibration time delay, estimate the train running speed, and reduce the impact of inertial drift through data fusion method, and finally obtain the accurate mileage position through integral calculation.
It realizes low-cost and accurate mileage positioning of subway trains in a GPS environment, overcomes the error problems caused by inertial drift, and improves the accuracy of positioning.
Smart Images
Figure CN119803516A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of subway train mileage positioning, and in particular to a subway train mileage positioning method and related equipment based on multi-sensor data fusion. Background Art
[0002] With the acceleration of urbanization, subway, as an efficient public transportation mode, has gradually become an important means to solve urban traffic congestion. In order to ensure the safe operation and efficient scheduling of subway trains, it is particularly important to determine the position of trains on the track in real time and accurately.
[0003] With the advancement of science and technology, especially the development of communication and sensor technology, new positioning technologies are gradually being introduced. For example, the combination of coded odometer and beacon technology enables trains to obtain accurate location information when passing beacons, thereby improving positioning accuracy. In addition, the application of 5G technology also provides a new solution for subway positioning, which can achieve meter-level high-precision positioning to meet the needs of modern urban rail transit.
[0004] Currently, there are many technologies used to measure train speed and mileage position, such as Global Navigation Satellite System (GNSS), Doppler radar, ultra-wideband radio, and various methods based on inertial measurement unit sensors.
[0005] However, none of these existing methods is suitable for low-cost positioning of subway trains in a GPS-free environment. The above methods have the following difficulties and challenges:
[0006] 1. Subway trains mainly run in underground environments, where GPS signals cannot be received. Therefore, GNSS cannot be used for subway train mileage positioning;
[0007] 2. Doppler radar and ultra-wideband radio technologies require large or expensive system equipment, which is costly and not suitable for large-scale subway train mileage positioning;
[0008] 3. IMU sensors seem to be the most promising option, but inertial drift is the most challenging issue. Integrating the measured acceleration over a distance of several kilometers may result in an error of several hundred meters in the train mileage position. Summary of the invention
[0009] Based on the problems raised by the above background technology, the purpose of the present invention is to provide a subway train mileage positioning method and related equipment with multi-sensor data fusion, to overcome the problem that GNSS cannot be used for subway train mileage positioning due to the subway train's inability to receive GPS signals, to obtain vehicle vibration signals using intelligent sensor terminals, to overcome the problem that Doppler radar and ultra-wideband radio technologies are expensive and not suitable for large-scale subway train mileage positioning, and to overcome the problem that the train mileage position has an error of several hundred meters due to inertial drift of the IMU sensor.
[0010] The present invention is achieved through the following technical solutions:
[0011] The first aspect of the present invention provides a subway train mileage positioning method based on multi-sensor data fusion, comprising the following steps:
[0012] The acceleration of any two subway cars is obtained through the intelligent sensor terminals installed in the subway cars;
[0013] Performing waveform matching on the carriage acceleration to obtain a vibration time delay;
[0014] Calculating the vibration time delay to obtain an estimated running speed of the subway train;
[0015] The estimated running speed of the subway train is integrated based on waveform matching to obtain the subway train speed;
[0016] The subway train speed is integrated to obtain the subway train mileage.
[0017] In the above technical scheme, first, the intelligent sensor terminal is installed in different subway cars, and the intelligent sensor terminal is used to monitor the vibration of the train body. Among them, the vibration of the train is caused by the interaction between the wheels and the track. On the one hand, the vibration of the train not only affects the comfort of passengers; it may even cause safety problems such as track damage and vehicle equipment damage. On the other hand, the acceleration of the train also carries important information about the status of the train and the condition of the infrastructure along the line, which shows that the maintenance of the train and infrastructure can be arranged based on the observation of the change of train acceleration over time. Therefore, in this method, the mileage of the subway train is located by using the vibration of the vehicle, which overcomes the problem that the subway train cannot receive GPS signals and cannot use GNSS for subway train mileage positioning, and the intelligent sensor terminal is used to obtain the vehicle vibration signal, which overcomes the problem that the Doppler radar and ultra-wideband radio technology are expensive and not suitable for large-scale subway train mileage positioning.
[0018] In the process of monitoring the vibration of the train body, the acceleration of the subway car is extracted, and the waveform matching of the car acceleration is performed. The acceleration characteristics of different cars passing the same significant position (such as a small radius curve) are used to calculate the time difference of different cars passing the position to obtain the vibration time delay. Under the premise of knowing the distance between different cars, the relative running speed between the two cars is estimated by the vibration time delay. The estimated speed of each car can be determined by the relative running speed, and the estimated speed of the whole train can be constructed based on the estimated speed of each car. The estimated speed of the train contains information between the two cars. Compared with the car speed of the prior art, it is more holistic and can better feedback the overall operation of the subway train.
[0019] The estimated speed of the train is fused and estimated by using the data fusion method to obtain the final weighted estimated value of the subway train speed. The weighted estimated value of the subway train speed is integrated to obtain the mileage position of the subway train. Compared with the prior art that directly integrates the acceleration obtained by the IMU sensor, this method is not affected by inertial drift, and the final subway train mileage position is more accurate, overcoming the problem of several hundred meters of error in the train mileage position caused by inertial drift of the IMU sensor.
[0020] In an optional embodiment, waveform matching is performed on the carriage acceleration, including:
[0021] Obtain the lateral acceleration of subway car i and subway car j with the intercept length l as the center at time t, and the signal time delay between subway car i and subway car j;
[0022] The lateral acceleration and the signal time delay are calculated to obtain a vibration time delay.
[0023] In an optional embodiment, calculating the vibration time delay to obtain an estimated running speed of the subway train includes:
[0024] Obtaining the carriage distance between subway carriage i and subway carriage j, calculating the carriage distance using the vibration time delay, and obtaining the relative speed of train operation between subway carriage i and subway carriage j at time t;
[0025] The estimated running speeds of the subway trains of the subway car i and the subway car j are respectively constructed by using the train running relative speeds.
[0026] In an optional embodiment, the estimated running speed of the subway train is integrated based on waveform matching, including:
[0027] Using the vibration time delay to perform waveform matching on the carriage acceleration, to obtain a velocity weight matrix;
[0028] Optimizing the estimated running speed of the subway train by using the speed weight matrix to obtain an optimal estimated speed;
[0029] Calculating an estimated difference between the estimated running speed of the subway train and the optimal estimated speed;
[0030] The estimated difference is calculated by linear interpolation to obtain a speed correction value;
[0031] The estimated running speed of the subway train is modified by using the speed correction amount to obtain the subway train speed.
[0032] In an optional embodiment, using the vibration time delay to perform waveform matching on the carriage acceleration includes:
[0033] Obtaining acceleration waveforms of lateral accelerations of subway car i and subway car j;
[0034] Extracting a first comparison acceleration waveform having a length equal to the time window length from the acceleration waveform of the lateral acceleration of the subway car i;
[0035] A second comparative acceleration waveform having a length equal to the time window length under a vibration time delay is intercepted from the acceleration waveform of the lateral acceleration of the subway car j;
[0036] The first comparison acceleration waveform and the second comparison acceleration waveform are compared for similarity, and a velocity weight matrix is constructed using the result of the similarity comparison.
[0037] In an optional embodiment, performing a similarity comparison on the first comparison acceleration waveform and the second comparison acceleration waveform includes:
[0038] calculating waveform similarity between the first comparison acceleration waveform and the second comparison acceleration waveform;
[0039] Set a waveform similarity threshold and compare the waveform similarity with the waveform similarity threshold:
[0040] If the waveform similarity is greater than the waveform similarity threshold, assigning the waveform similarity to the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform;
[0041] If the waveform similarity is less than the waveform similarity threshold, the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform are set to 0.
[0042] In an optional embodiment, the estimated difference is calculated using a linear interpolation method, including:
[0043] Determine equal time intervals;
[0044] The estimated difference corresponding to the discrete moment and the equal interval time are calculated using a linear interpolation function to obtain a speed correction amount.
[0045] The second aspect of the present invention provides a subway train mileage positioning system using multi-sensor data fusion, comprising:
[0046] A data acquisition module, used to acquire the acceleration of any two subway cars through an intelligent sensor terminal installed in the subway car;
[0047] A time delay module, used to perform waveform matching on the carriage acceleration to obtain a vibration time delay;
[0048] A delay calculation module, used to calculate the vibration time delay to obtain an estimated running speed of the subway train;
[0049] A fusion module, used for fusing the estimated running speed of the subway train based on waveform matching to obtain the subway train speed;
[0050] The integration module is used to integrate the subway train speed to obtain the subway train mileage.
[0051] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a subway train mileage positioning method using multi-sensor data fusion when executing the computer program.
[0052] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a subway train mileage positioning method using multi-sensor data fusion.
[0053] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0054] Compared with the existing technology that uses direct integration calculation of the acceleration obtained by the IMU sensor, this method is not affected by inertial drift, and the final subway train mileage position accuracy is higher, overcoming the problem of several hundred meters error in train mileage position caused by inertial drift of the IMU sensor. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:
[0056] Figure 1 A schematic diagram of the flow of a subway train mileage positioning method using multi-sensor data fusion provided in Example 1 of the present invention;
[0057] FIG. 2(a), (b), and (c) are waveform diagrams of the longitudinal acceleration, lateral acceleration, and vertical acceleration provided in Example 1 of the present invention, respectively;
[0058] Figure 3 A schematic diagram of subway train speed estimation in a GPS-free environment provided in Example 1 of the present invention;
[0059] Figure 4 A schematic diagram of train speed estimation provided by Embodiment 1 of the present invention;
[0060] Figure 5 A schematic diagram of train mileage estimation provided in Example 1 of the present invention;
[0061] Figure 6 A schematic diagram of the structure of an electronic device provided in Example 2 of the present invention. DETAILED DESCRIPTION
[0062] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0063] Example 1
[0064] Figure 1 The flowchart of the subway train mileage positioning method using multi-sensor data fusion provided in Example 1 of the present invention is as follows: Figure 1 As shown, the subway train mileage positioning method based on multi-sensor data fusion includes the following steps:
[0065] The acceleration of any two subway cars is obtained through the intelligent sensor terminals installed in the subway cars;
[0066] Performing waveform matching on the carriage acceleration to obtain a vibration time delay;
[0067] Calculating the vibration time delay to obtain an estimated running speed of the subway train;
[0068] The estimated running speed of the subway train is integrated based on waveform matching to obtain the subway train speed;
[0069] The subway train speed is integrated to obtain the subway train mileage.
[0070] It should be noted that, first, the intelligent sensor terminals are installed in different subway cars, and the intelligent sensor terminals are used to monitor the vibration of the train body. Among them, the train vibration is caused by the interaction between the wheels and the track. On the one hand, the vibration of the train not only affects the comfort of passengers; it may even cause safety problems such as track damage and vehicle equipment damage. On the other hand, the acceleration of the train also carries important information about the status of the train and the condition of the infrastructure along the line, which shows that the maintenance of the train and infrastructure can be arranged based on the observation of the change of train acceleration over time. Therefore, in this method, the vehicle vibration is used to locate the mileage of the subway train, which overcomes the problem that the subway train cannot receive GPS signals and cannot use GNSS for subway train mileage positioning, and the intelligent sensor terminal is used to obtain the vehicle vibration signal, which overcomes the high cost of Doppler radar and ultra-wideband radio technology and is not suitable for large-scale subway train mileage positioning.
[0071] In the process of monitoring the vibration of the train body, the acceleration of the subway car is extracted, and the waveform matching of the car acceleration is performed. The acceleration characteristics of different cars passing the same significant position (such as a small radius curve) are used to calculate the time difference of different cars passing the position to obtain the vibration time delay. Under the premise of knowing the distance between different cars, the relative running speed between the two cars is estimated by the vibration time delay. The estimated speed of each car can be determined by the relative running speed, and the estimated speed of the whole train can be constructed based on the estimated speed of each car. The estimated speed of the train contains information between the two cars. Compared with the car speed of the prior art, it is more holistic and can better feedback the overall operation of the subway train.
[0072] The estimated running speed of the carriage is fused and estimated by the data fusion method to obtain the final weighted estimated value of the subway train speed. The weighted estimated value of the subway train speed is integrated to obtain the mileage position of the subway train. Compared with the prior art that uses direct integration calculation of the acceleration obtained by the IMU sensor, this method is not affected by inertial drift, and the final subway train mileage position is more accurate, overcoming the problem of several hundred meters error in the train mileage position caused by inertial drift of the IMU sensor.
[0073] In an optional embodiment, waveform matching is performed on the carriage acceleration, including:
[0074] Obtain the lateral acceleration of subway car i and subway car j with the intercept length l as the center at time t, and the signal time delay between subway car i and subway car j;
[0075] The lateral acceleration and the signal time delay are calculated to obtain a vibration time delay.
[0076] It should be noted that the vibration acceleration can be collected by the intelligent sensor terminal installed in the subway car, where the vibration acceleration includes the longitudinal acceleration a shown in Figure 2(a) x , the lateral acceleration a shown in Figure 2(b) y and the vertical acceleration a shown in Figure 2(c) z In this embodiment, the lateral acceleration a y Take the following as an example, to obtain the lateral acceleration a of subway car i and subway car j with length l intercepted at time t as the center. yi,t,l and a yj,t+τ,l . Where τ is the time deviation, the lateral acceleration of subway car j with length l intercepted at time t has a time deviation of τ compared with the lateral acceleration of subway car i with length l intercepted at time t. Where i,j=1,2,…,n, n is the train length.
[0077] The lateral acceleration and signal time delay are calculated, where the calculation formula is as follows:
[0078] δ ij,t = argmax(cov(a yi,t,l ,a yj,t+τ,l ))
[0079] When the signal time delay δ ij,t When it reaches the maximum, it corresponds to the optimal time deviation τ ij,t , which is the vibration time delay to be solved in this step. For any two subway cars, the vibration time delay τ can be obtained by matching the above waveforms. ij,t (i≠j).
[0080] In an optional embodiment, calculating the vibration time delay to obtain an estimated running speed of the subway train includes:
[0081] Obtaining the carriage distance between subway carriage i and subway carriage j, calculating the carriage distance using the vibration time delay, and obtaining the relative speed of train operation between subway carriage i and subway carriage j at time t;
[0082] The estimated running speeds of the subway trains of the subway car i and the subway car j are respectively constructed by using the train running relative speeds.
[0083] like Figure 3As shown, the distance between subway cars i and j is known, that is, Figure 3 The distance p i,j In this embodiment, the car distance refers to the distance between the smart sensor terminal installed in subway car i and the smart sensor terminal installed in subway car j. Taking subway car i as an example, the longitudinal acceleration a of subway car i at time t xi (t) double integration is performed, where the lower limit of the double integration is time t, and the upper limit of the double integration is time t and the vibration time delay τ ij,t The sum of the vehicle distance minus the double integral is divided by the signal time delay to obtain the relative speed of the trains between subway cars i and j. Specifically, the formula for calculating the relative speed of the trains is as follows:
[0084]
[0085] After obtaining the relative running speed between the two cars, starting with subway car i, the running relative speed sets between subway car i and other cars are constructed respectively, and then all the running relative speed sets of the subway cars are integrated to obtain the matrix of the estimated running speed of the subway train.
[0086] Specifically, the matrix of the estimated running speed of the subway train is constructed as follows:
[0087]
[0088] In the above formula, v i is the estimated value vector of the speed of subway car i relative to subway car j, and V is the speed estimation matrix between intelligent terminals i and j.
[0089] In an optional embodiment, the estimated running speed of the subway train is integrated based on waveform matching, including:
[0090] Using the vibration time delay to perform waveform matching on the carriage acceleration, to obtain a velocity weight matrix;
[0091] Optimizing the estimated running speed of the subway train by using the speed weight matrix to obtain an optimal estimated speed;
[0092] Calculating an estimated difference between the estimated running speed of the subway train and the optimal estimated speed;
[0093] The estimated difference is calculated by linear interpolation to obtain a speed correction value;
[0094] The estimated running speed of the subway train is modified by using the speed correction amount to obtain the subway train speed.
[0095] It should be noted that, since the estimated running speed of the subway train includes the estimated train running speed between each pair of subway cars, it is necessary to construct a speed weight matrix before the optimal speed estimation of the train speed. In this embodiment, the construction of the speed weight matrix is completed through waveform matching.
[0096] In an optional embodiment, using the vibration time delay to perform waveform matching on the carriage acceleration includes:
[0097] Obtaining acceleration waveforms of lateral accelerations of subway car i and subway car j;
[0098] Extracting a first comparison acceleration waveform having a length equal to the time window length from the acceleration waveform of the lateral acceleration of the subway car i;
[0099] A second comparative acceleration waveform having a length equal to the time window length under a vibration time delay is intercepted from the acceleration waveform of the lateral acceleration of the subway car j;
[0100] The first comparison acceleration waveform and the second comparison acceleration waveform are compared for similarity, and a velocity weight matrix is constructed using the result of the similarity comparison.
[0101] It should be noted that, firstly, the acceleration waveforms of the lateral acceleration of subway car i and subway car j are obtained, and the acceleration waveforms are intercepted with the moving window length as the boundary to obtain the first comparison acceleration waveform a yi,t,l Compare the acceleration waveform with the second
[0102] In an optional embodiment, performing a similarity comparison on the first comparison acceleration waveform and the second comparison acceleration waveform includes:
[0103] calculating waveform similarity between the first comparison acceleration waveform and the second comparison acceleration waveform;
[0104] Set a waveform similarity threshold and compare the waveform similarity with the waveform similarity threshold:
[0105] If the waveform similarity is greater than the waveform similarity threshold, assigning the waveform similarity to the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform;
[0106] If the waveform similarity is less than the waveform similarity threshold, the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform are set to 0.
[0107] In this embodiment, the first comparative acceleration waveform a is calculated. yi,t,l Compare the acceleration waveform with the second The waveform similarity ρ i,j , set the waveform similarity threshold ρ0, compare the two, if the waveform similarity ρ i,j If it is greater than the waveform similarity threshold ρ0, then the speed weight is equal to the waveform similarity ρ i,j , otherwise the speed weight is equal to 0.
[0108] Specifically, the speed weight matrix is constructed as follows:
[0109]
[0110] In the above formula, w i,j is the speed weight between subway car i and subway car j, w i is the speed weight matrix of subway car i, and W is the speed weight matrix of the subway train.
[0111] The optimal speed estimation is performed using the speed weight matrix, and the process is as follows:
[0112]
[0113] In the above formula, V * (t) is the optimal speed estimate at time t.
[0114] Further, the discrete time T=[T0,T1,T2,…,T e ], and its corresponding estimated subway train running speed v(t) and optimal speed estimate v * (t), the difference between the two is taken, and the estimated difference obtained by the difference is taken as the correction value Δv. Specifically, the calculation process is as follows:
[0115] Δv=(V * (T0)-V(T0),V * (T1)-V(T1),V * (T2)-V(T2),…,V * (T e )-V(T e ))
[0116] In the above formula, T e The waveform matching process satisfies ρ i,j >ρ0 condition.
[0117] In an optional embodiment, the estimated difference is calculated using a linear interpolation method, including:
[0118] Determine equal time intervals;
[0119] The estimated difference corresponding to the discrete moment and the equal interval time are calculated using a linear interpolation function to obtain a speed correction amount.
[0120] It should be noted that the purpose of using the linear interpolation method to calculate the estimated difference is to obtain the equally spaced discrete train speed correction value. First, determine the equal time interval, and then use the linear interpolation function to calculate the discrete time T, the estimated difference Δt corresponding to the discrete time T, and the equally spaced time to obtain the speed correction corresponding to the equally spaced Δt. Specifically, the calculation process is as follows:
[0121]
[0122] In the above formula, D(·) represents the linear interpolation function, Δt is the equal time interval, which is generally taken as 0.01s, and N is the number of time divisions.
[0123] like Figure 4 As shown in FIG. 1 , the estimated running speed of the subway train is modified by using the speed correction amount to obtain the subway train speed. The process is as follows:
[0124] v fuse =v+Δv *
[0125] In the above formula, v fuse is the speed of subway trains.
[0126] Finally, the subway train speed is integrated to obtain Figure 5 The subway train mileage at different times shown is calculated as follows:
[0127]
[0128] In the above formula, s(t) is the subway train mileage at time t.
[0129] Example 2
[0130] Embodiment 2 of the present invention provides a subway train mileage positioning system using multi-sensor data fusion, including:
[0131] A data acquisition module, used to acquire the acceleration of any two subway cars through an intelligent sensor terminal installed in the subway car;
[0132] A time delay module, used to perform waveform matching on the carriage acceleration to obtain a vibration time delay;
[0133] A delay calculation module, used to calculate the vibration time delay to obtain an estimated running speed of the subway train;
[0134] A fusion module, used for fusing the estimated running speed of the subway train based on waveform matching to obtain the subway train speed;
[0135] The integration module is used to integrate the subway train speed to obtain the subway train mileage.
[0136] Example 3
[0137] Figure 6 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention is shown in FIG. Figure 6 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 6 A processor 21 is taken as an example; the processor 21, the memory 22, the input device 23 and the output device 24 in the electronic device can be connected by a bus or other means. Figure 6 The example of connecting through bus is taken in the following.
[0138] The memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 22, that is, the subway train mileage positioning method of multi-sensor data fusion of Example 1 is implemented.
[0139] The memory 22 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0140] The input device 23 can be used to receive the ID and password input by the user, etc. The output device 24 is used to output the network configuration page.
[0141] Example 4
[0142] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement the subway train mileage positioning method using multi-sensor data fusion as provided in Embodiment 1.
[0143] An embodiment of the present invention provides a storage medium containing computer executable instructions, and its computer executable instructions are not limited to the method operations provided in Example 1, and can also execute related operations in the subway train mileage positioning method based on multi-sensor data fusion provided in any embodiment of the present invention.
[0144] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A subway train mileage positioning method based on multi-sensor data fusion, characterized in that: The steps include: The acceleration of any two subway cars is obtained through the intelligent sensor terminals installed in the subway cars; Performing waveform matching on the carriage acceleration to obtain a vibration time delay; Calculating the vibration time delay to obtain an estimated running speed of the subway train; The estimated running speed of the subway train is integrated based on waveform matching to obtain the subway train speed; The subway train speed is integrated to obtain the subway train mileage.
2. The subway train mileage positioning method based on multi-sensor data fusion according to claim 1 is characterized in that: Performing waveform matching on the carriage acceleration includes: Obtain the lateral acceleration of subway car i and subway car j with the intercept length l as the center at time t, and the signal time delay between subway car i and subway car j; The lateral acceleration and the signal time delay are calculated to obtain a vibration time delay.
3. The subway train mileage positioning method based on multi-sensor data fusion according to claim 2 is characterized in that: Calculating the vibration time delay to obtain an estimated running speed of the subway train includes: Obtaining the carriage distance between subway carriage i and subway carriage j, calculating the carriage distance using the vibration time delay, and obtaining the relative speed of train operation between subway carriage i and subway carriage j at time t; The estimated running speeds of the subway trains of the subway car i and the subway car j are respectively constructed by using the train running relative speeds.
4. The subway train mileage positioning method based on multi-sensor data fusion according to claim 1 is characterized in that: The estimated running speed of subway trains is integrated based on waveform matching, including: Using the vibration time delay to perform waveform matching on the carriage acceleration, to obtain a velocity weight matrix; Optimizing the estimated running speed of the subway train by using the speed weight matrix to obtain an optimal estimated speed; Calculating an estimated difference between the estimated running speed of the subway train and the optimal estimated speed; The estimated difference is calculated by linear interpolation to obtain a speed correction value; The estimated running speed of the subway train is modified by using the speed correction amount to obtain the subway train speed.
5. The subway train mileage positioning method based on multi-sensor data fusion according to claim 4 is characterized in that: The vibration time delay is used to perform waveform matching on the carriage acceleration, comprising: Obtaining acceleration waveforms of lateral accelerations of subway car i and subway car j; Extracting a first comparison acceleration waveform having a length equal to the time window length from the acceleration waveform of the lateral acceleration of the subway car i; A second comparative acceleration waveform having a length equal to the time window length under a vibration time delay is intercepted from the acceleration waveform of the lateral acceleration of the subway car j; The first comparison acceleration waveform and the second comparison acceleration waveform are compared for similarity, and a velocity weight matrix is constructed using the result of the similarity comparison.
6. The subway train mileage positioning method based on multi-sensor data fusion according to claim 5 is characterized in that: Comparing the first comparison acceleration waveform and the second comparison acceleration waveform for similarity, including: calculating waveform similarity between the first comparison acceleration waveform and the second comparison acceleration waveform; Set a waveform similarity threshold and compare the waveform similarity with the waveform similarity threshold: If the waveform similarity is greater than the waveform similarity threshold, assigning the waveform similarity to the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform; If the waveform similarity is less than the waveform similarity threshold, the velocity weights corresponding to the first comparison acceleration waveform and the second comparison acceleration waveform are set to 0.
7. The subway train mileage positioning method based on multi-sensor data fusion according to claim 6 is characterized in that: The estimated difference is calculated using a linear interpolation method, including: Determine equal time intervals; The estimated difference corresponding to the discrete moment and the equal interval time are calculated using a linear interpolation function to obtain a speed correction amount.
8. The subway train mileage positioning system based on multi-sensor data fusion is characterized by: include: A data acquisition module, used to acquire the acceleration of any two subway cars through an intelligent sensor terminal installed in the subway car; A time delay module, used to perform waveform matching on the carriage acceleration to obtain a vibration time delay; A delay calculation module, used to calculate the vibration time delay to obtain an estimated running speed of the subway train; A fusion module, used for fusing the estimated running speed of the subway train based on waveform matching to obtain the subway train speed; The integration module is used to integrate the subway train speed to obtain the subway train mileage.
9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for subway train mileage positioning by multi-sensor data fusion as claimed in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the subway train mileage positioning method based on multi-sensor data fusion as described in any one of claims 1 to 7 is implemented.