Method, device and equipment for estimating adhesion coefficient of railway vehicle, medium and product

Abstract

The invention provides an adhesion coefficient estimation method, device and equipment of a railway vehicle, a medium and a product, and belongs to the technical field of railway wheel detection, and the method comprises the following steps: receiving multi-source real-time sensing information collected during the movement of the railway vehicle, the multi-source real-time sensing information comprises left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data and vehicle speed measured by a radar; the multi-source real-time sensing information is fused, real-time fusion information is obtained, and the real-time fusion information comprises the wheel speed, the vehicle body speed, the traction motor output torque and the vehicle body acceleration; state estimation is carried out based on the real-time fusion information, and an adhesion coefficient real-time estimation value is obtained; and outputting the real-time estimated value of the adhesion coefficient. According to the embodiment of the invention, by fusing the multi-source real-time sensing information, the real-time fusion information which has relevance and can comprehensively reflect the movement condition of the railway vehicle is provided for the state estimation system, so that the obtained adhesion coefficient estimation value has higher accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rail wheel detection, and in particular to a rail vehicle adhesion coefficient estimation method, device, equipment, medium and product. BACKGROUND

[0002] The rail adhesion coefficient is a key parameter affecting the traction and braking efficiency of a train, but it is difficult to directly measure due to the dynamic changes of factors such as environment (such as rain and snow, oil stains), wheel-rail surface state, etc.

[0003] The prior art uses a simplified model (such as extended Kalman filtering) based adhesion coefficient estimation to solve the problem of direct measurement, but the mutual influence between multiple parameters related to the rail adhesion coefficient is not comprehensively considered in the state estimation process, resulting in low accuracy of the adhesion coefficient estimation value. SUMMARY

[0004] The present application provides a rail vehicle adhesion coefficient estimation method, device, equipment, medium and product, aiming to solve the problem of low accuracy of the adhesion coefficient estimation value caused by not comprehensively considering the mutual influence between multiple parameters related to the rail adhesion coefficient in the state estimation process.

[0005] In a first aspect, the present application provides a rail vehicle adhesion coefficient estimation method, comprising: cyclically executing the following steps: receiving multi-source real-time sensing information collected in the motion of the rail vehicle, the multi-source real-time sensing information including left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and radar measured vehicle speed; fusing the multi-source real-time sensing information to obtain real-time fusion information, the real-time fusion information including wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration; performing state estimation based on the real-time fusion information to obtain an adhesion coefficient real-time estimation value; outputting the adhesion coefficient real-time estimation value.

[0006] As one embodiment, the adhesion coefficient estimation method further comprises: updating the wheel speed fusion parameter of the current time step based on the multi-source real-time sensing information and the real-time fusion information of the previous time step.

[0007] As one embodiment, fusing the multi-source real-time sensing information to obtain the real-time fusion information specifically comprises: fusing the left wheel axle encoder data and the right wheel axle encoder data based on the wheel speed fusion parameter of the current time step to obtain wheel linear speed fusion information; fusing the radar measured vehicle speed and the vehicle body acceleration obtained from the accelerometer sensing data to obtain vehicle body speed fusion information; Fusing wheel linear velocity fusion information, vehicle body speed fusion information, output torque of the traction motor and vehicle body acceleration, real-time fusion information is obtained.

[0008] As an embodiment, the wheel speed fusion parameters include a left wheel speed weight and a right wheel speed weight, which are determined by a left wheel slip ratio at a previous time step and a right wheel slip ratio at the previous time step, respectively. The right wheel slip ratio at the previous time step is determined by the vehicle body speed fusion information at the previous time step and right wheel speed information at the previous time step; and the left wheel slip ratio at the previous time step is determined by the vehicle body speed fusion information at the previous time step and left wheel speed information at the previous time step.

[0009] As an embodiment, state estimation is performed based on an unscented Kalman filter algorithm, in the state space, the state vector includes wheel linear velocity, vehicle body speed and adhesion coefficient; and the observation includes wheel angular velocity, vehicle body acceleration and observation noise.

[0010] In a second aspect, the present application further provides an adhesion coefficient estimation device for a railway vehicle, comprising a receiving module, a fusion module, a state estimation module and an output module. The receiving module is configured to receive multi-source real-time sensing information collected in the movement of the railway vehicle, the multi-source real-time sensing information including left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data and radar-measured vehicle speed. The fusion module is configured to fuse the multi-source real-time sensing information to obtain real-time fusion information, the real-time fusion information including wheel speed, vehicle body speed, output torque of the traction motor and vehicle body acceleration. The state estimation module is configured to perform state estimation based on the real-time fusion information to obtain a real-time estimation value of the adhesion coefficient. The output module is configured to output the real-time estimation value of the adhesion coefficient.

[0011] As an embodiment, the adhesion coefficient estimation device further comprises a fusion parameter updating module, which is configured to update the wheel speed fusion parameters at a current time step based on multi-source real-time sensing information at a previous time step and real-time fusion information.

[0012] In a third aspect, the present application further provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements any of the above-mentioned adhesion coefficient estimation methods for a railway vehicle when executing the computer program.

[0013] In a fourth aspect, the present application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement any of the above-mentioned adhesion coefficient estimation methods for a railway vehicle.

[0014] In a fifth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements any of the above-mentioned adhesion coefficient estimation methods for a railway vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0016] Figure 1 is one of the flowcharts of the adhesion coefficient estimation method for a railway vehicle provided by the present application; Figure 2 is another flowchart of the adhesion coefficient estimation method for a railway vehicle provided by the present application; Figure 3 is one of the flowcharts of the real-time fusion information provided by the present application; Figure 4 is a comparison chart of simulation results of the UKF based on the traditional UKF and the UKF state estimation based on the real-time fusion information provided by the present application; Figure 5 is one of the structural schematic diagrams of the adhesion coefficient estimation device for a railway vehicle provided by the present application; Figure 6 is a structural schematic diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be described clearly and completely in the following with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without any creative effort belong to the scope of protection of the present application.

[0018] It should be noted that in the description of the present application, the terms "comprising", "containing" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0019] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally a class, not limited to the number of objects, for example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / ", generally indicates that the objects before and after are in a "or" relationship.

[0020] The following will be described in conjunction with Figures 1 to 6 The adhesion coefficient estimation method, device, equipment, medium and product of the rail vehicle provided by the present application are described.

[0021] It should be noted that the adhesion coefficient estimation method of the rail vehicle provided by the embodiments of the present application is realized based on the adhesion coefficient estimation device of the rail vehicle. The adhesion coefficient estimation method of the rail vehicle can fuse the multi-source real-time sensing information collected in the motion process of the rail vehicle, so as to comprehensively consider the correlation between various parameters in state estimation, and improve the accuracy of the adhesion coefficient estimation value.

[0022] The embodiments of the present application take the adhesion coefficient estimation device of the rail vehicle as an example to describe the adhesion coefficient estimation method of the rail vehicle.

[0023] Figure 1 is one of the flowcharts of the adhesion coefficient estimation method of the rail vehicle provided by the present application. Figure 2 is the second flowchart of the adhesion coefficient estimation method of the rail vehicle provided by the present application.

[0024] As Figure 1 shown, the adhesion coefficient estimation method of the rail vehicle provided by the present application comprises: S110: receiving the multi-source real-time sensing information collected in the motion of the rail vehicle.

[0025] S120: fusing the multi-source real-time sensing information to obtain real-time fusion information.

[0026] S130: state estimation based on real-time fusion information to obtain real-time estimation value of adhesion coefficient.

[0027] S140: output real-time estimation value of adhesion coefficient.

[0028] Then return to S110, and execute S110 to S130 in a loop.

[0029] In combination Figure 1 and Figure 2 , the adhesion coefficient estimation device of the rail vehicle obtains (for example, through the CAN bus) multi-source real-time sensing information collected in the movement of the rail vehicle from the collection system of the rail vehicle, including left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, radar measured vehicle speed, torque output by the traction motor, and rotational speed output by the traction motor, etc.

[0030] In the prior art, when using a state estimation algorithm to estimate the adhesion coefficient, the above-mentioned multi-source real-time sensing information is directly input into the state estimation system, and in the state estimation process, the correlation between these information is not fully utilized, so the accuracy of state estimation is insufficient.

[0031] Based on the above considerations, the present application first fuses these multi-source real-time sensing information, mines the correlation between these information, and obtains real-time fusion information. Among them, the real-time fusion information includes wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration. Then the real-time fusion information is input into the state estimation system, and the real-time estimation value of the adhesion coefficient is output.

[0032] The embodiment of the present application fuses multi-source real-time sensing information to provide the state estimation system with real-time fusion information that has correlation and can comprehensively reflect the movement of the rail vehicle, so that the adhesion coefficient estimation value obtained thereby has higher accuracy.

[0033] In one possible embodiment, as shown in Figure 3 , in step S120, the multi-source real-time sensing information is fused to obtain real-time fusion information, which specifically includes: S310: wheel speed fusion parameters based on the current time step Fuse left wheel axle encoder data and right wheel axle encoder data to obtain wheel linear speed fusion information : (1) wherein, is the left wheel speed information determined by the left wheel axle encoder data of the current time step, is the right wheel speed information determined by the right wheel axle encoder data of the current time step, is the left wheel speed weight of the current time step, is the right wheel speed weight of the current time step.

[0034] By fusing the left wheel axle encoder data and the right wheel axle encoder data, the correlation of the left and right wheel speeds is obtained, and by the left wheel speed weight and the right wheel speed weight, the unilateral interference and local noise are suppressed. When the unilateral sensor fails, the influence of the vehicle body linear speed is automatically reduced by the weight, and the error amplification problem caused by the traditional mean fusion is avoided.

[0035] S320: Fuse the vehicle speed measured by the radar and the vehicle body acceleration obtained from the accelerometer sensor data to obtain vehicle body speed fusion information: (2) , (3) wherein, is the vehicle body speed fusion information of the current time step, is the radar weight of the current time step, is the vehicle speed measured by the radar of the current time step, is the accelerometer weight of the current time step, is the vehicle body speed fusion information of the previous time step, is the vehicle body acceleration obtained from the accelerometer sensor data of the current time step, is the sampling time interval, is the radar signal-to-noise ratio estimation value of the current time step, is the accelerometer zero offset stability index of the current time step.

[0036] The vehicle body speed fusion information is related to the vehicle speed measured by the radar, the vehicle body acceleration, and the radar weight and the accelerometer weight, and the correlation of the vehicle speed and the vehicle body acceleration is obtained.

[0037] S330: Fuse the wheel linear speed fusion information , the vehicle body speed fusion information , the output torque of the traction motor , and the vehicle body acceleration to obtain real-time fusion information .

[0038] In one possible embodiment, the wheel linear speed fusion information, the vehicle body speed fusion information, the output torque of the traction motor, and the vehicle body acceleration are spliced to obtain the real-time fusion information.

[0039] It can be understood that other fusion methods can also be used to fuse the above information to obtain the real-time fusion information.

[0040] The embodiments of the present application obtain the correlation of the wheel speeds of the left and right wheels, the correlation of the vehicle speed and the vehicle body acceleration, and fuse the wheel linear speed fusion information, the vehicle body speed fusion information, the output torque of the traction motor, and the vehicle body acceleration together to obtain real-time fusion information, which is used to comprehensively reflect the motion characteristics of the railway vehicle.

[0041] Based on the above, in a possible embodiment, the adhesion coefficient estimation method of the present application further comprises: The wheel speed fusion parameter of the current time step is updated based on the multi-source real-time sensing information and the real-time fusion information of the previous time step. Then, S120 is performed.

[0042] The embodiments of the present application update the wheel speed fusion parameter of the current time step based on the information of the previous time step, so that the wheel speed fusion parameter is corrected in real time, the input data of the state estimation system is dynamically updated, and it is ensured that the adhesion coefficient estimation value obtained by the state estimation has real-time performance.

[0043] Specifically, in a possible embodiment, the wheel speed fusion parameter comprises a left wheel speed weight and a right wheel speed weight .

[0044] The left wheel speed weight of the current time step is determined by the left wheel slip ratio of the previous time step , the left wheel slip ratio of the previous time step is determined by the vehicle body speed fusion information of the previous time step (belonging to the real-time fusion information) and the left wheel speed information of the previous time step (belonging to the multi-source real-time sensing information): (4) (5) wherein, is a correction value.

[0045] The right wheel speed weight of the current time step is determined by the right wheel slip ratio of the previous time step , the right wheel slip ratio of the previous time step is determined by the vehicle body speed fusion information of the previous time step (belonging to the real-time fusion information) and the right wheel speed information of the previous time step (belonging to the multi-source real-time sensing information): (6) (7) In this embodiment, the slip ratio of the previous time step is determined by the vehicle speed fusion information and wheel speed information of the previous time step. Then, the wheel speed weights of the left and right wheels in the current time step are determined by the slip ratios of the left and right wheels in the previous time step, thereby determining the wheel linear velocity fusion information of the current time step. The wheel speed weights are dynamically adjusted in each time step to obtain accurate wheel linear velocity fusion information, providing an accurate data basis for state estimation.

[0046] In one possible implementation, state estimation is performed based on the Unscented Kalman Filter (UKF) algorithm. In the state space, the state vector... Including wheel linear velocity Vehicle speed and viscosity coefficient ,Right now Therefore, from this state dimension .

[0047] The nonlinear state equation is: (8) in, The output torque of the traction motor. m The equivalent mass of the vehicle. R The radius of the wheel's rolling circle. For vehicle acceleration, For process noise, To observe the noise, It is the acceleration due to gravity. C f The rolling resistance coefficient of the wheel. C r This is the vehicle running resistance coefficient. This is the adhesion coefficient attenuation factor.

[0048] Observation Including wheel angular velocity Vehicle acceleration and observation noise ,Right now ,in, This represents the angular velocity of the wheel.

[0049] In one possible embodiment, state estimation is performed based on an unscented Kalman filter algorithm, specifically including: P1: Using a symmetric sampling strategy, the estimated state vector is based on the first state vector obtained in the previous time step. The first covariance matrix obtained at the previous time step Perform Sigma point sampling to obtain There are Sigma sampling points for each state and the corresponding weights for these Sigma sampling points. The Sigma sampling points for each state include: (9) (10) (11) in, The first root of the first covariance matrix is ​​represented by the square root of the first covariance matrix. i List, It is a positive semi-definite matrix. This is the scaling parameter.

[0050] P2: Based on the nonlinear state equation, perform a nonlinear transformation on each state Sigma sampling point to obtain the predicted Sigma point corresponding to each state Sigma sampling point. The second state vector is obtained by updating the state vector and covariance matrix based on the predicted Sigma points. Second covariance matrix .

[0051] (12) (13) (14) in, Given the known external inputs of the system at the previous time step, This is the noise covariance matrix for the adaptive process.

[0052] P3: For each predicted Sigma point based on the observation function Perform a nonlinear transformation to obtain the corresponding observation sigma sampling points. : (15) in, Let be the observable function.

[0053] P4: Based on all observation sigma sampling points Calculate the mean of the observations Observation covariance matrix and the cross-covariance matrix of state and measurement : (16) (17) (18) in, , respectively are the measurement weight and the covariance weight, is the measurement noise covariance matrix.

[0054] P5: based on the measurement covariance matrix and the cross covariance matrix between the state and the measurement calculate the Kalman gain : (19) P6: update the state vector and the covariance matrix based on the Kalman gain, obtain a third state vector estimate and a third covariance matrix , as the state vector estimate and the covariance matrix of the current time step: (20) (21) wherein, is the real-time fusion information of the current time step.

[0055] P7: extract the adhesion coefficient from the third state vector estimate , as the real-time estimate of the adhesion coefficient of the current time step and output.

[0056] In the embodiments of the present application, by constructing a third-order state vector composed of the wheel linear velocity, the vehicle body velocity and the adhesion coefficient, the state estimation of the adhesion coefficient is carried out based on the UKF. The UKF algorithm is to approximate the probability density distribution of a nonlinear function, using a series of deterministic samples to approximate the posterior probability density of the state, instead of approximating the nonlinear function, which reduces the complexity of the calculation, so the UKF usually performs more accurately and robustly when dealing with nonlinear problems. On this basis, the state estimation is carried out based on the real-time fusion information, which ensures that the state estimation utilizes the correlation between the multi-source information, realizes real-time dynamic estimation, ensures the accuracy of the adhesion coefficient, and enhances the robustness and adaptability under different working conditions.

[0057] Figure 4 A simulation result comparison diagram of the adhesion coefficient state estimation based on the traditional UKF (shown as UKF in the figure) and the UKF based on the real-time fusion information of the present application (shown as multi-source fusion UKF in the figure) is shown. From Figure 4 it can be seen that, compared with the traditional UKF, the adhesion coefficient obtained by the state estimation method of the present application is closer to the real adhesion coefficient.

[0058] Based on the above, the present application also provides a rail vehicle adhesion coefficient estimation device. The rail vehicle adhesion coefficient estimation device can be mutually corresponding and referred to the above-mentioned rail vehicle adhesion coefficient estimation method.

[0059] As an embodiment, as shown in Figure 5 The adhesion coefficient estimation device of the rail vehicle includes a receiving layer, a fusion layer, a core layer, and an output layer, corresponding to the receiving module 510, the fusion module 520, the state estimation module 530, and the output module 540, respectively.

[0060] The receiving module 510 is configured to receive multi-source real-time sensing information collected in the motion of the rail vehicle, and the multi-source real-time sensing information includes left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, radar measured vehicle speed, traction motor output torque, and traction motor output speed, etc.

[0061] The fusion module 520 is configured to fuse the multi-source real-time sensing information to obtain real-time fusion information, and the real-time fusion information includes wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration.

[0062] The state estimation module 530 is configured to perform state estimation based on the real-time fusion information to obtain an adhesion coefficient real-time estimation value.

[0063] The output module 540 is configured to output the adhesion coefficient real-time estimation value.

[0064] The embodiments of the present application fuse multi-source real-time sensing information to provide the state estimation system with real-time fusion information that is relevant and can comprehensively reflect the motion of the rail vehicle, and thus the adhesion coefficient estimation value obtained has higher accuracy.

[0065] In a possible embodiment, the fusion module 520 is specifically configured to: fuse the left wheel axle encoder data and the right wheel axle encoder data based on a wheel speed fusion parameter of a current time step to obtain wheel linear speed fusion information; fuse the radar measured vehicle speed and the vehicle body acceleration obtained from the accelerometer sensing data to obtain vehicle body speed fusion information; fuse the wheel linear speed fusion information, the vehicle body speed fusion information, the output torque of the traction motor, and the vehicle body acceleration to obtain real-time fusion information.

[0066] The embodiments of the present application obtain the relevance of the wheel speeds of the left and right wheels, the relevance of the vehicle speed and the vehicle body acceleration, and fuse the wheel linear speed fusion information, the vehicle body speed fusion information, the output torque of the traction motor, and the vehicle body acceleration together to obtain real-time fusion information, which is used to comprehensively reflect the motion characteristics of the rail vehicle.

[0067] In a possible embodiment, the adhesion coefficient estimation device further includes a fusion parameter updating module, and the fusion parameter updating module is configured to update the wheel speed fusion parameter of the current time step based on multi-source real-time sensing information and real-time fusion information of a previous time step.

[0068] The embodiment of the application updates the wheel speed fusion parameter of the current time step based on the information of the last time step, so that the wheel speed fusion parameter is corrected in real time, dynamic updated input data is provided for the state estimation system, and the real-time performance of the adhesion coefficient estimated value obtained by the state estimation is ensured.

[0069] In a possible embodiment, the wheel speed fusion parameter includes a left wheel speed weight and a right wheel speed weight, and the left wheel speed weight and the right wheel speed weight are determined by the left wheel slip ratio of the last time step and the right wheel slip ratio of the last time step respectively. The right wheel slip ratio of the last time step is determined by the vehicle body speed fusion information of the last time step and the right wheel speed information of the last time step, and the left wheel slip ratio of the last time step is determined by the vehicle body speed fusion information of the last time step and the left wheel speed information of the last time step.

[0070] In the embodiment of the application, the slip ratio of the last time step is determined by the vehicle body speed fusion information of the last time step and the wheel speed information, and then the wheel speed weights of the left wheel and the right wheel of the current time step are determined by the slip ratios of the left wheel and the right wheel of the last time step, so as to determine the wheel linear speed fusion information of the current time step. The wheel speed weight is dynamically adjusted at each time step, accurate wheel linear speed fusion information is obtained, and accurate data basis is provided for the state estimation.

[0071] In a possible embodiment, the state estimation is performed based on the unscented Kalman filter algorithm. In the state space, the state vector includes the wheel linear speed, the vehicle body speed and the adhesion coefficient, and the observation quantity includes the wheel angular speed, the vehicle body acceleration and the observation noise.

[0072] In the embodiment of the application, the third-order state vector composed of the wheel linear speed, the vehicle body speed and the adhesion coefficient is constructed, and the state estimation of the adhesion coefficient is performed based on the UKF. The UKF algorithm is to approximate the probability density distribution of a nonlinear function by using a series of deterministic samples to approximate the posterior probability density of the state, instead of approximating the nonlinear function, so as to reduce the complexity of calculation. Therefore, the UKF usually performs more accurately and stably when dealing with nonlinear problems. On this basis, the state estimation is performed based on the real-time fusion information, so as to ensure that the state estimation utilizes the correlation between the multi-source information, to realize real-time dynamic estimation, ensure the accuracy of the adhesion coefficient, and enhance the robustness and adaptability under different working conditions.

[0073] Figure 6 is a structural schematic diagram of an electronic device provided by the application, as Figure 6As shown, the electronic device can include a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communications bus 640. The processor 610 can invoke a logic instruction in the memory 630 to execute an adhesion coefficient estimation method of a rail vehicle, which includes: cyclically executing the following steps: receiving multi-source real-time sensing information collected in rail vehicle movement, the multi-source real-time sensing information including left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and radar measured vehicle speed; fusing the multi-source real-time sensing information to obtain real-time fusion information, the real-time fusion information including wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration; and performing state estimation based on the real-time fusion information to obtain an adhesion coefficient real-time estimation value.

[0074] In addition, the logic instruction in the memory 630 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0075] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, and the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the adhesion coefficient estimation method of a rail vehicle provided by the above-mentioned embodiments, which includes: cyclically executing the following steps: receiving multi-source real-time sensing information collected in rail vehicle movement, the multi-source real-time sensing information including left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and radar measured vehicle speed; fusing the multi-source real-time sensing information to obtain real-time fusion information, the real-time fusion information including wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration; and performing state estimation based on the real-time fusion information to obtain an adhesion coefficient real-time estimation value.

[0076] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the method for estimating the adhesion coefficient of a rail vehicle provided by any of the above embodiments, the method comprising: cyclically performing the following steps: receiving multi-source real-time sensing information collected in the movement of the rail vehicle, the multi-source real-time sensing information comprising left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and radar-measured vehicle speed; fusing the multi-source real-time sensing information to obtain real-time fusion information, the real-time fusion information comprising wheel speed, vehicle body speed, traction motor output torque, and vehicle body acceleration; and performing state estimation based on the real-time fusion information to obtain a real-time estimated value of the adhesion coefficient.

[0077] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0078] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a read-only memory (ROM) / random access memory (RAM), a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0079] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a read-only memory (ROM) / random access memory (RAM), a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0080] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for estimating the adhesion coefficient of a rail vehicle, characterized in that, include: Repeat the following steps: The system receives multi-source real-time sensing information collected during the movement of the rail vehicle. The multi-source real-time sensing information includes left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and vehicle speed measured by radar. By fusing the multi-source real-time sensor information, real-time fused information is obtained, which includes wheel speed, vehicle speed, traction motor output torque, and vehicle acceleration. Based on the real-time fused information, state estimation is performed to obtain a real-time estimated value of the adhesion coefficient; Output a real-time estimate of the adhesion coefficient.

2. The method for estimating the adhesion coefficient of a rail vehicle according to claim 1, characterized in that, The adhesion coefficient estimation method further includes: The wheel speed fusion parameters for the current time step are updated based on the multi-source real-time sensing information and real-time fusion information from the previous time step.

3. The method for estimating the adhesion coefficient of a rail vehicle according to claim 2, characterized in that, By fusing the multi-source real-time sensing information to obtain real-time fused information, the following is specifically included: Based on the wheel speed fusion parameters of the current time step, the data of the left wheel axle encoder and the data of the right wheel axle encoder are fused to obtain wheel linear speed fusion information; By fusing the vehicle speed measured by the radar and the vehicle acceleration obtained from the accelerometer sensing data, vehicle speed fusion information is obtained; The real-time fused information is obtained by fusing the wheel linear velocity fusion information, the vehicle body velocity fusion information, the output torque of the traction motor, and the vehicle body acceleration.

4. The method for estimating the adhesion coefficient of a rail vehicle according to claim 2, characterized in that, The wheel speed fusion parameters include left wheel speed weight and right wheel speed weight, which are determined by the left wheel slip ratio and the right wheel slip ratio of the previous time step, respectively. The right wheel slip ratio of the previous time step is determined by the vehicle speed fusion information and the right wheel speed information of the previous time step; the left wheel slip ratio of the previous time step is determined by the vehicle speed fusion information and the left wheel speed information of the previous time step.

5. The method for estimating the adhesion coefficient of a rail vehicle according to claim 1, characterized in that, State estimation is performed based on the unscented Kalman filter algorithm. In the state space, the state vector includes the wheel linear velocity, vehicle velocity, and adhesion coefficient; the observations include the wheel angular velocity, vehicle acceleration, and observation noise.

6. A device for estimating the adhesion coefficient of a rail vehicle, characterized in that, It includes a receiving module, a fusion module, a state estimation module, and an output module; The receiving module is used to receive multi-source real-time sensing information collected during the movement of the rail vehicle. The multi-source real-time sensing information includes left wheel axle encoder data, right wheel axle encoder data, accelerometer sensing data, and vehicle speed measured by radar. The fusion module is used to fuse the multi-source real-time sensor information to obtain real-time fused information, which includes wheel speed, vehicle speed, traction motor output torque and vehicle acceleration. The state estimation module is used to perform state estimation based on the real-time fusion information to obtain a real-time estimated value of the adhesion coefficient. The output module is used to output a real-time estimate of the adhesion coefficient.

7. The adhesion coefficient estimation device for rail vehicles according to claim 6, characterized in that, The adhesion coefficient estimation device also includes a fusion parameter update module, which is used to update the wheel speed fusion parameters of the current time step based on the multi-source real-time sensing information and real-time fusion information of the previous time step.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for estimating the adhesion coefficient of a rail vehicle as described in any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium, wherein a computer program is stored on the non-transitory computer-readable storage medium, characterized in that, When the computer program is executed by the processor, it implements the method for estimating the adhesion coefficient of a rail vehicle as described in any one of claims 1 to 5.

10. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for estimating the adhesion coefficient of a rail vehicle as described in any one of claims 1 to 5.

Images