Air brake force prediction method and apparatus

Abstract

This invention provides a method and apparatus for predicting air braking force. The method includes: acquiring real-time data of key parameters, wherein the key parameters are parameters whose correlation coefficient with air braking force exceeds a preset correlation threshold; inputting the real-time data of the key parameters into a proportional coefficient prediction model to obtain the corresponding proportional coefficient; and determining the current decompression amount based on the magnitude of the proportional coefficient, wherein the current decompression amount is the control quantity of the air braking force.

Description

Technical Field

[0001] This invention relates to the field of vehicle control, and more particularly to a method and apparatus for predicting aerodynamic braking forces. Background Technology

[0002] Existing train braking systems generally include electric braking and air braking. Electric braking converts kinetic energy into electrical energy by a motor cutting magnetic field lines, which is then dissipated through an external resistor to achieve braking. Air braking uses compressed air as a power source to push friction blocks against the brake disc to achieve braking. Electric braking, due to the absence of physical contact, has very low operating costs and is therefore the preferred braking method. However, electric braking is very ineffective at both low and high speeds. At speeds below 10 km / h, air braking must take over completely, and at speeds above 160 km / h, air braking is also necessary to achieve the required braking effect. Although air braking involves physical contact and is more expensive, its performance is more stable than electric braking. Therefore, most trains use air braking for emergency braking.

[0003] The strength of air braking force is related to a variety of factors, a phenomenon particularly pronounced in recirculating air braking. If the braking force cannot be predicted in advance based on the current vehicle and track conditions, it will lead to unreasonable curve planning, insufficient or excessive actual braking force, resulting in phenomena such as speeding, train wear, and even coupler breakage. In severe cases, the train may even derail. Therefore, predicting air braking force has become a key research focus and challenge in the field of intelligent train driving. In recirculating air braking, predicting the magnitude of the next applied air braking force can provide a theoretical basis for intelligent driving curve planning, thereby improving the rationality and accuracy of the planned curve.

[0004] Because the strength of air braking force is related to various factors, deviations can occur in the strength of air braking force during cyclic air braking, even under the same decompression. To address this issue, this invention proposes an air braking force prediction method and apparatus, which can estimate the strength coefficient of the next air braking maneuver and serve as the basis for intelligent driving planning algorithms to plan curves under cyclic air braking conditions, thereby improving the rationality of curve planning. Summary of the Invention

[0005] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form to prepare for the more detailed descriptions that follow.

[0006] According to one aspect of the present invention, an air braking force prediction method is provided, comprising: acquiring real-time data of key parameters, wherein the key parameters are parameters whose correlation coefficient with air braking force exceeds a preset correlation threshold; inputting the real-time data of the key parameters into a proportional coefficient prediction model to obtain a corresponding proportional coefficient; and determining the current decompression amount based on the magnitude of the proportional coefficient, wherein the current decompression amount is a control amount of the air braking force.

[0007] In one embodiment, determining the current decompression amount based on the magnitude of the scaling factor includes: in response to the scaling factor being less than a first threshold, adding the increment corresponding to the scaling factor to the initial decompression amount to obtain the current decompression amount; and in response to the scaling factor being greater than a second threshold, subtracting the increment corresponding to the scaling factor from the initial decompression amount to obtain the current decompression amount, wherein the second threshold is greater than the first threshold.

[0008] In one embodiment, in response to the scaling factor being less than a first threshold, a calculation formula is used. Calculate the increment corresponding to the proportionality coefficient; and in response to the proportionality coefficient being greater than the second threshold, use the calculation formula Calculate the increment corresponding to the proportionality coefficient, where, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The first threshold, The second threshold, and It is a constant.

[0009] In one embodiment, acquiring real-time data of key parameters includes: acquiring real-time data of parameters related to aerodynamic braking force; and performing data dimensionality reduction processing on the real-time data to obtain real-time data of the key parameters.

[0010] In one embodiment, the air braking force prediction method further includes: establishing a relationship model between the key parameters and the proportional coefficient of air braking force through machine learning of large data samples as the proportional coefficient prediction model.

[0011] In one embodiment, the big data sample includes key parameters from historical data and their corresponding scaling factors.

[0012] In one embodiment, the air braking force prediction method further includes: using a calculation formula Calculate the proportional coefficients corresponding to the key parameters in the historical data, where, This represents the total actual air braking force during the historical air braking process. The sum of air braking forces calculated according to TB / T1407-1998 "Train Traction Calculation Regulations" during historical air braking processes.

[0013] In one embodiment, the acquisition of real-time data of key parameters further includes: in response to the vehicle determining that it will perform air braking during curve dynamic planning, acquiring real-time data of key parameters.

[0014] According to another aspect of the present invention, an air braking force prediction device is also provided, comprising: a memory; and a processor connected to the memory, the processor being configured to: acquire real-time data of key parameters, the key parameters being parameters whose correlation coefficient with air braking force exceeds a preset correlation threshold; input the real-time data of the key parameters into a proportional coefficient prediction model to obtain a corresponding proportional coefficient; and determine a current decompression amount based on the magnitude of the proportional coefficient, the current decompression amount being a control amount of the air braking force.

[0015] In one embodiment, the processor is further configured to: in response to the scaling factor being less than a first threshold, add the initial decompression amount to the increment corresponding to the scaling factor as the current decompression amount; and in response to the scaling factor being greater than a second threshold, subtract the increment corresponding to the scaling factor from the initial decompression amount as the current decompression amount, wherein the second threshold is greater than the first threshold.

[0016] In one embodiment, the processor is further configured to: in response to the scaling factor being less than a first threshold, utilize a calculation formula Calculate the increment corresponding to the proportionality coefficient; and in response to the proportionality coefficient being greater than the second threshold, use the calculation formula Calculate the increment corresponding to the proportionality coefficient, where, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The first threshold, The second threshold, and It is a constant.

[0017] In one embodiment, the processor is further configured to: acquire real-time data of parameters related to aerodynamic braking force; and perform data dimensionality reduction processing on the real-time data to obtain real-time data of the key parameters.

[0018] In one embodiment, the processor is further configured to: establish a relationship model between the key parameters and the proportional coefficient of the air braking force through machine learning of large data samples as a proportional coefficient prediction model.

[0019] In one embodiment, the big data sample includes key parameters from historical data and their corresponding scaling factors.

[0020] In one embodiment, the processor is further configured to: utilize a calculation formula Calculate the proportional coefficients corresponding to the key parameters in the historical data, where, This represents the total actual air braking force during the historical air braking process. The sum of air braking forces calculated according to TB / T1407-1998 "Train Traction Calculation Regulations" during historical air braking processes.

[0021] In one embodiment, the processor is further configured to: in response to the vehicle determining during curve dynamic planning that the vehicle will perform air braking, acquire real-time data of key parameters.

[0022] According to another aspect of the present invention, a computer storage medium is also provided, on which a computer program is stored, which, when executed, implements the steps of the air braking force prediction method as described in any of the above embodiments. Attached Figure Description

[0023] The above-described features and advantages of the present invention will be better understood after reading the detailed description of the embodiments of this disclosure in conjunction with the following accompanying drawings.

[0024] Figure 1 This is a flowchart illustrating an air braking force prediction method according to one aspect of the present invention;

[0025] Figure 2 This is a partial flowchart illustrating an air braking force prediction method according to one aspect of the present invention.

[0026] Figure 3 This is a partial flowchart illustrating an air braking force prediction method according to one aspect of the present invention.

[0027] Figure 4 This is a block diagram of an air braking force prediction device according to another aspect of the present invention. Detailed Implementation

[0028] The following description is provided to enable those skilled in the art to implement and use the invention and adapt it to specific application contexts. Various modifications and uses in different applications will be readily apparent to those skilled in the art, and the general principles defined herein are applicable to a wide range of embodiments. Therefore, the invention is not limited to the embodiments given herein, but should be granted the broadest scope consistent with the principles and novel features disclosed herein.

[0029] In the following detailed description, numerous specific details are set forth to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that practice of the invention is not necessarily limited to these specific details. In other words, well-known structures and devices are shown in block diagram form without being depicted in detail to avoid obscuring the invention.

[0030] Readers should note all documents and references submitted concurrently with this specification and open to public inspection, the contents of which are incorporated herein by reference. Unless otherwise expressly stated, all features disclosed in this specification (including any appended claims, abstracts, and drawings) may be replaced by alternative features for the same, equivalent, or similar purposes. Therefore, unless explicitly stated otherwise, each disclosed feature is merely one example of a set of equivalent or similar features.

[0031] Note that, where used, the markings left, right, front, back, top, bottom, front, back, clockwise, and counterclockwise are merely for convenience and do not imply any specific fixed direction. In fact, they are used to reflect the relative position and / or orientation between different parts of an object. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0032] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0033] Note that, in practice, "further," "preferably," "even further," and "more preferably" are simply starting points for describing another embodiment based on the foregoing embodiments. The combination of the content following "further," "preferably," "even further," or "more preferably" with the foregoing embodiments constitutes the complete configuration of another embodiment. Any combination of several "further," "preferably," "even further," or "more preferably" settings following the same embodiment can form yet another embodiment.

[0034] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should be noted that the aspects described below with reference to the accompanying drawings and specific embodiments are merely exemplary and should not be construed as limiting the scope of protection of the present invention in any way.

[0035] According to one aspect of the present invention, an air braking force prediction method is provided, which can be used to predict the control quantity of air braking force and then determine the magnitude of the corresponding air braking force.

[0036] In one embodiment, such as Figure 1 As shown, the air braking force prediction method 100 may include steps S110 to S130.

[0037] Step S110 involves obtaining real-time data of key parameters.

[0038] Among these, the key parameters are those whose correlation coefficient with air braking force exceeds a preset threshold. It is understandable that any change in any parameter on the vehicle can affect the required braking force, meaning there are many parameters related to air braking force. Including all parameters related to air braking force in the considerations for controlling air braking force would result in a very complex control relationship and make it difficult to obtain a precise result. Therefore, it is necessary to extract parameters with a high correlation to air braking force from all related parameters and use them as considerations for controlling air braking force; these considerations for controlling air braking force are the key parameters.

[0039] To obtain key parameters, conventional correlation calculation methods can be used to calculate the correlation coefficient between each parameter and the air braking force. The magnitude of these correlation coefficients is then used to filter out the key parameters. Commonly, a correlation threshold can be set based on the required control accuracy of the air braking force. This preset threshold is used to compare with each correlation coefficient to filter out the key parameters.

[0040] The process of filtering out key parameters described above can be called data dimensionality reduction, also known as dimensionality reduction. As the name suggests, it involves reducing the dimensionality of the data.

[0041] Data dimensionality reduction can solve the "curse of dimensionality," alleviate the current situation of "abundant information but scarce knowledge," and reduce complexity. On the other hand, it can help us better understand and comprehend data.

[0042] To date, there are many methods for data dimensionality reduction. They can be categorized in different ways depending on the perspective. The main classification methods include: based on data characteristics, they can be divided into linear and non-linear dimensionality reduction; based on whether supervised information is considered and utilized, they can be divided into unsupervised, supervised, and semi-supervised dimensionality reduction; and based on preserving data structure, they can be divided into globally preserving dimensionality reduction, locally preserving dimensionality reduction, and dimensionality reduction that maintains consistency between global and local dimensions.

[0043] In one specific embodiment, such as Figure 2 As shown, step S110 can be specified as steps S111~S112.

[0044] Step S111 involves acquiring real-time data of parameters related to air braking force.

[0045] Specifically, real-time data on various parameters related to aerodynamic braking force can be obtained from the vehicle's data acquisition or data transmission equipment, including vehicle status data and route data, etc.

[0046] Step S112 is to perform data dimensionality reduction processing on the real-time data to obtain the real-time data of the key parameters.

[0047] By using data dimensionality reduction methods, the numerous factors affecting air braking are processed to reduce the dimensionality of the data, extract the key parameters that affect the strength of air braking force, reduce the data sample size, and simplify the difficulty of predicting air braking force.

[0048] Specifically, principal component analysis, independent component analysis, or other data dimensionality reduction methods that can be used to measure the correlation between various parameters and aerodynamic braking force can be employed.

[0049] Principal Component Analysis (PCA) is a statistical procedure that transforms the original data into a single, orthogonal matrix. n The dimensionality dataset is transformed into a new dataset called principal components. In the transformed result, the first principal component has the largest variance, and each subsequent component, under the constraint of orthogonality with the aforementioned principal components, also has the largest variance. Only the first principal components are saved during dimensionality reduction. m ( m < n One principal component is enough to maintain the maximum amount of data information.

[0050] Independent Component Analysis (ICA) is a computational method for separating multivariate signals into additive sub-components. This is achieved by assuming that the sub-components are non-Gaussian signals and statistically independent of each other. ICA is a special case of blind source separation.

[0051] Furthermore, air braking force prediction is an important step in the target curve planning process. Therefore, step S110 can be optimized as follows: in response to the vehicle determining that it will perform air braking during the curve dynamic planning process, real-time data of key parameters are obtained.

[0052] After obtaining the real-time data of the key parameters, step S120 is to input the real-time data of the key parameters into the proportional coefficient prediction model to obtain the corresponding proportional coefficient.

[0053] The proportionality factor is a coefficient used to characterize the ratio of actual air braking force to theoretical air braking force.

[0054] The proportional coefficient prediction model can be a model of the relationship between key parameters and the proportional coefficient of air braking force established in the early stage through machine learning. Specifically, the relationship model between key parameters and the proportional coefficient of air braking force can be established through machine learning with large data samples, such as BP neural networks, fuzzy RBF neural networks, SVM support vector machines, or other machine learning methods that can be used to establish the relationship model between key parameters and the proportional coefficient of air braking force.

[0055] It is understandable that big data samples include key parameters from historical data and their corresponding proportional coefficients. The proportional coefficients for these key parameters in historical data can be calculated using the air braking forces within the historical data. Machine learning, on the other hand, can utilize a large number of key parameters and their corresponding proportional coefficients to simulate a model of the relationship between the key parameters and the proportional coefficients of the air braking forces—that is, a proportional coefficient prediction model.

[0056] Specifically, the proportional coefficients corresponding to the key parameters in the historical data can be calculated using equation (1).

[0057] (1)

[0058] Among them, η This is the proportionality coefficient. This represents the total actual air braking force during the historical air braking process. The sum of air braking forces calculated according to TB / T1407-1998 "Train Traction Calculation Regulations" during historical air braking processes.

[0059] TB / T1407-1998, "Train Traction Calculation Regulations," is a railway industry standard of the People's Republic of China. These regulations specify the traction calculation methods and the main technical parameters used, serving as the basis for determining traction quality, operating speed, and operating time, and also forming the foundation for calculating the electricity, coal, and water consumption of trains.

[0060] Furthermore, Equation (2) can be used for calculation.

[0061] (2)

[0062] in, For train traction / electric braking force, For train quality, To accelerate the train, As the basic resistance, For slope resistance, These parameters, representing cornering resistance, are key parameters from historical data.

[0063] The proportional coefficient prediction model can calculate the corresponding proportional coefficient based on the real-time data of the input key parameters. After calculating the proportional coefficient, the control quantity of the air braking force can be determined based on the magnitude of the proportional coefficient.

[0064] Further, step S130 is: determining the current decompression amount based on the magnitude of the proportional coefficient, wherein the current decompression amount is the control amount of the air braking force.

[0065] The increment of air braking force corresponding to the proportionality coefficient can be calculated based on the magnitude of the proportionality coefficient. Then, the actual current decompression amount is calculated based on this increment and the initial decompression amount. According to TB / T1407-1998 "Train Traction Calculation Procedure", the initial decompression amount of the air braking force is a constant. .

[0066] In one specific embodiment, such as Figure 3 As shown, step S130 can be specified as steps S131~S132.

[0067] Step S131 is as follows: In response to the proportional coefficient being less than the first threshold, the initial decompression amount is added to the increment corresponding to the proportional coefficient as the current decompression amount.

[0068] Specifically, based on the relationship between the proportional coefficient and the control amount of the air braking force, a first threshold for increasing the air braking force is set. When the calculated proportionality coefficient The proportionality coefficient can be calculated using the following formula. The corresponding increment.

[0069] (3)

[0070] in, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The first threshold is set. It is a constant.

[0071] Correspondingly, the current decompression amount at this time .

[0072] Step S132 is as follows: In response to the proportional coefficient being greater than the second threshold, the initial decompression amount is subtracted from the increment corresponding to the proportional coefficient to obtain the current decompression amount, wherein the second threshold is greater than the first threshold.

[0073] Specifically, based on the relationship between the proportional coefficient and the control amount of the air braking force, a second threshold for reducing the air braking force is set. ,and When the calculated proportionality coefficient The proportionality coefficient can be calculated using the following formula. The corresponding increment.

[0074] (4)

[0075] in, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The second threshold, It is a constant.

[0076] Correspondingly, the current decompression amount at this time .

[0077] Although the methods described above are illustrated and depicted as a series of actions for the sake of simplicity, it should be understood and appreciated that these methods are not limited by the order of the actions, as some actions may occur in a different order and / or concurrently with other actions from the illustrations and descriptions herein or not illustrated and described herein but which may be understood by those skilled in the art, according to one or more embodiments.

[0078] According to another aspect of the present invention, a computer storage medium is also provided, on which a computer program is stored, which, when executed, implements the steps of the air braking force prediction method as described in any of the above embodiments.

[0079] According to another aspect of the present invention, an air braking force prediction device is also provided, which can be used to predict the control amount of air braking force and thereby determine the magnitude of the corresponding air braking force.

[0080] In one embodiment, such as Figure 4 As shown, the air braking force prediction device 400 may include a memory 410 and a processor 420.

[0081] The memory 410 is used to store computer programs.

[0082] The processor 420 is connected to the memory 410 and is used to execute the computer program stored in the memory 410. The processor 420 is configured by the memory 410 to: acquire real-time data of key parameters; input the real-time data of the key parameters into a proportional coefficient prediction model to obtain the corresponding proportional coefficient; and determine the current decompression amount based on the magnitude of the proportional coefficient, wherein the current decompression amount is the control amount of the air braking force.

[0083] Among these, the key parameters are those whose correlation coefficient with air braking force exceeds a preset threshold. It is understandable that any change in any parameter on the vehicle can affect the required braking force, meaning there are many parameters related to air braking force. Including all parameters related to air braking force in the considerations for controlling air braking force would result in a very complex control relationship and make it difficult to obtain a precise result. Therefore, it is necessary to extract parameters with a high correlation to air braking force from all related parameters and use them as considerations for controlling air braking force; these considerations for controlling air braking force are the key parameters.

[0084] To obtain key parameters, conventional correlation calculation methods can be used to calculate the correlation coefficient between each parameter and the air braking force. The magnitude of these correlation coefficients is then used to filter out the key parameters. Commonly, a correlation threshold can be set based on the required control accuracy of the air braking force. This preset threshold is used to compare with each correlation coefficient to filter out the key parameters.

[0085] The process of filtering out key parameters described above can be called data dimensionality reduction, also known as dimensionality reduction. As the name suggests, it involves reducing the dimensionality of the data.

[0086] Data dimensionality reduction can solve the "curse of dimensionality," alleviate the current situation of "abundant information but scarce knowledge," and reduce complexity; on the other hand, it can help us better understand and comprehend data.

[0087] To date, there are many methods for data dimensionality reduction. They can be categorized in different ways depending on the perspective. The main classification methods include: based on data characteristics, they can be divided into linear and non-linear dimensionality reduction; based on whether supervised information is considered and utilized, they can be divided into unsupervised, supervised, and semi-supervised dimensionality reduction; and based on preserving data structure, they can be divided into globally preserving dimensionality reduction, locally preserving dimensionality reduction, and dimensionality reduction that maintains consistency between global and local dimensions.

[0088] In one specific embodiment, to acquire key parameters, the processor 420 is further configured to: acquire real-time data of parameters related to aerodynamic braking force; and perform data dimensionality reduction processing on the real-time data to obtain real-time data of the key parameters.

[0089] Specifically, real-time data on various parameters related to aerodynamic braking force can be obtained from the vehicle's data acquisition or data transmission equipment, including vehicle status data and route data, etc.

[0090] By using data dimensionality reduction methods, the numerous factors affecting air braking are processed to reduce the dimensionality of the data, extract the key parameters that affect the strength of air braking force, reduce the data sample size, and simplify the difficulty of predicting air braking force.

[0091] Specifically, principal component analysis, independent component analysis, or other data dimensionality reduction methods that can be used to measure the correlation between various parameters and aerodynamic braking force can be employed.

[0092] Principal Component Analysis (PCA) is a statistical procedure that transforms the original data into a single, orthogonal matrix. n The dimensionality dataset is transformed into a new dataset called principal components. In the transformed result, the first principal component has the largest variance, and each subsequent component, under the constraint of orthogonality with the aforementioned principal components, also has the largest variance. Only the first principal components are saved during dimensionality reduction. m ( m < n One principal component is enough to maintain the maximum amount of data information.

[0093] Independent Component Analysis (ICA) is a computational method for separating multivariate signals into additive sub-components. This is achieved by assuming that the sub-components are non-Gaussian signals and statistically independent of each other. ICA is a special case of blind source separation.

[0094] Furthermore, air braking force prediction is an important step in the target curve planning process. Therefore, preferably, the processor 420 can also be configured to: in response to the vehicle determining that the vehicle will perform air braking during the curve dynamic planning process, acquire real-time data of key parameters.

[0095] The proportionality factor is a coefficient used to characterize the ratio of actual air braking force to theoretical air braking force.

[0096] The proportional coefficient prediction model can be a model of the relationship between key parameters and the proportional coefficient of air braking force established in the early stage through machine learning. Specifically, the relationship model between key parameters and the proportional coefficient of air braking force can be established through machine learning with large data samples, such as BP neural networks, fuzzy RBF neural networks, SVM support vector machines, or other machine learning methods that can be used to establish the relationship model between key parameters and the proportional coefficient of air braking force.

[0097] It is understandable that big data samples include key parameters from historical data and their corresponding proportional coefficients. The proportional coefficients for these key parameters in historical data can be calculated using the air braking forces within the historical data. Machine learning, on the other hand, can utilize a large number of key parameters and their corresponding proportional coefficients to simulate a model of the relationship between the key parameters and the proportional coefficients of the air braking forces—that is, a proportional coefficient prediction model.

[0098] Specifically, the proportional coefficients corresponding to the key parameters in the historical data can be calculated using equation (1).

[0099] (1)

[0100] Among them, η This is the proportionality coefficient. This represents the total actual air braking force during the historical air braking process. The sum of air braking forces calculated according to TB / T1407-1998 "Train Traction Calculation Regulations" during historical air braking processes.

[0101] TB / T1407-1998, "Train Traction Calculation Regulations," is a railway industry standard of the People's Republic of China. These regulations specify the traction calculation methods and the main technical parameters used, serving as the basis for determining traction quality, operating speed, and operating time, and also forming the foundation for calculating the electricity, coal, and water consumption of trains.

[0102] Furthermore, Equation (2) can be used for calculation.

[0103] (2)

[0104] in, For train traction / electric braking force, For train quality, To accelerate the train, As the basic resistance, For slope resistance, These parameters, representing cornering resistance, are key parameters from historical data.

[0105] The proportional coefficient prediction model can calculate the corresponding proportional coefficient based on the real-time data of the input key parameters. After calculating the proportional coefficient, the control quantity of the air braking force can be determined based on the magnitude of the proportional coefficient.

[0106] The increment of air braking force corresponding to the proportionality coefficient can be calculated based on the magnitude of the proportionality coefficient. Then, the actual current decompression amount is calculated based on this increment and the initial decompression amount. According to TB / T1407-1998 "Train Traction Calculation Procedure", the initial decompression amount of the air braking force is a constant. .

[0107] In one specific embodiment, to calculate the current decompression amount, the processor 420 is further configured to: in response to the scaling factor being less than a first threshold, add the initial decompression amount to the increment corresponding to the scaling factor as the current decompression amount; and in response to the scaling factor being greater than a second threshold, subtract the increment corresponding to the scaling factor from the initial decompression amount as the current decompression amount, wherein the second threshold is greater than the first threshold.

[0108] Specifically, based on the relationship between the proportional coefficient and the control amount of the air braking force, a first threshold for increasing the air braking force is set. and the second threshold ,and .

[0109] When the calculated proportionality coefficient The proportionality coefficient can be calculated using the following formula. The corresponding increment.

[0110] (3)

[0111] in, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The first threshold is set. It is a constant.

[0112] Correspondingly, the current decompression amount at this time .

[0113] When the calculated proportionality coefficient The proportionality coefficient can be calculated using the following formula. The corresponding increment.

[0114] (4)

[0115] in, This refers to the scaling factor corresponding to the real-time data of the key parameter. proportionality coefficient The corresponding increment, The second threshold, It is a constant.

[0116] Correspondingly, the current decompression amount at this time .

[0117] Those skilled in the art will understand that information, signals, and data can be represented using any of a variety of different techniques and skills. For example, the data, instructions, commands, information, signals, bits, symbols, and chips described throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0118] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0119] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or performed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but in alternatives, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0120] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0121] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or through a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

[0122] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. However, it should be understood that the scope of protection of this invention should be determined by the appended claims and should not be limited to the specific structures and components of the embodiments described above. Those skilled in the art can make various changes and modifications to the embodiments within the spirit and scope of this invention, and these changes and modifications also fall within the scope of protection of this invention.

Claims

1. An air brake force prediction method, comprising: obtaining real-time data of parameters related to air brake force; performing data dimension reduction processing on the real-time data to obtain real-time data of key parameters, wherein the key parameters are parameters whose correlation coefficients with air brake force exceed a preset correlation threshold; inputting the real-time data of the key parameters into a proportional coefficient prediction model to obtain corresponding proportional coefficients; and in response to the proportional coefficient being less than a first threshold value, using a calculation formula calculating an increment corresponding to the proportional coefficient, and adding the initial pressure reduction amount and the increment corresponding to the proportional coefficient as a current pressure reduction amount; in response to the proportional coefficient being greater than a second threshold value, using a calculation formula calculating an increment corresponding to the proportional coefficient, and subtracting the increment corresponding to the proportional coefficient from the initial pressure reduction amount as the current pressure reduction amount, wherein the second threshold value is greater than the first threshold value, and the current pressure reduction amount is a control amount of the air brake force, a proportional coefficient corresponding to real-time data of the key parameter, a proportional coefficient an increment corresponding to the proportional coefficient, the first threshold value, the second threshold value, and a constant.

2. The air brake force prediction method of claim 1, wherein, further comprising: establishing a relationship model between the key parameters and the proportional coefficients of air brake force through machine learning of big data samples as the proportional coefficient prediction model.

3. The air brake force prediction method of claim 2, wherein, The big data samples include key parameters and corresponding proportional coefficients in historical data.

4. The air brake force prediction method of claim 3, wherein, Further comprising: The calculation formula is as follows The proportional coefficient corresponding to the key parameter in the historical data is calculated, wherein, is the actual air brake force sum in the historical air brake process, is the air brake force sum calculated according to TB / T1407-1998 "Train Traction Calculation Regulation" in the historical air brake process.

5. The air brake force prediction method of claim 1, wherein, The obtaining of the real-time data of the key parameters further comprises: in response to determining that the vehicle is about to perform air brake in a curve dynamic planning process, obtaining real-time data of the key parameters.

6. An air brake force prediction device, comprising: a memory; and a processor connected with the memory, the processor being configured to: obtain real-time data of parameters related to air brake force; perform data dimension reduction processing on the real-time data to obtain real-time data of key parameters, wherein the key parameters are parameters whose correlation coefficients with air brake force exceed a preset correlation threshold; input the real-time data of the key parameters into a proportional coefficient prediction model to obtain corresponding proportional coefficients; and in response to the proportional coefficient being less than a first threshold value, using a calculation formula calculating an increment corresponding to the proportional coefficient, and adding the initial pressure reduction amount and the increment corresponding to the proportional coefficient as a current pressure reduction amount; in response to the proportional coefficient being greater than a second threshold value, using a calculation formula calculating an increment corresponding to the proportional coefficient, and subtracting the increment corresponding to the proportional coefficient from the initial pressure reduction amount as the current pressure reduction amount, wherein the second threshold value is greater than the first threshold value, and the current pressure reduction amount is a control amount of the air brake force, a proportional coefficient corresponding to real-time data of the key parameter, a proportional coefficient an increment corresponding to the proportional coefficient, the first threshold value, the second threshold value, and a constant.

7. The air brake force prediction device of claim 6, wherein, the processor is further configured to: establish a relationship model between the key parameters and the proportional coefficients of air brake force through machine learning of big data samples as the proportional coefficient prediction model.

8. The air brake force prediction device of claim 7, wherein, The big data samples include key parameters and corresponding proportional coefficients in historical data.

9. The air brake force prediction device of claim 8, wherein, The processor is further configured to: The calculation formula is as follows The proportional coefficient corresponding to the key parameter in the historical data is calculated, wherein, is the actual air brake force sum in the historical air brake process, is the air brake force sum calculated according to TB / T1407-1998 "Train Traction Calculation Regulation" in the historical air brake process.

10. The air brake force prediction device of claim 6, wherein, The processor is further configured to: in response to determining that the vehicle is about to perform air brake in a curve dynamic planning process, obtain real-time data of the key parameters.

11. A computer storage medium having stored thereon a computer program, characterized in that The computer program is executed to implement the steps of the air brake force prediction method according to any one of claims 1-5.

Images