Method, device and equipment for acquiring tidal current distribution of traction power supply system of heavy haul railway

Abstract

The invention relates to a power flow distribution obtaining method, device and equipment of a heavy haul railway traction power supply system. The method comprises the following steps: acquiring historical operation data and current operation data of a heavy haul train, a traction substation, an AT substation and a section post in a target heavy haul railway traction power supply system; based on the historical operation data, the line structure information corresponding to the historical operation data, the traction network wire type information and the historical voltage and current power data, a target traction network impedance admittance model meeting the power balance constraint of the target heavy haul railway traction power supply system is obtained; and constructing a load flow calculation model corresponding to the target heavy haul railway traction power supply system, and obtaining the current load flow distribution of the target heavy haul railway traction power supply system based on the current operation data through the load flow calculation model. Through digital-analog dual-drive power flow distribution calculation, the acquisition accuracy of power flow distribution is improved.

Description

Technical Field

[0001] This application relates to the field of heavy-haul railway traction power supply technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for obtaining power flow distribution in a heavy-haul railway traction power supply system. Background Technology

[0002] Power flow calculation for traction power supply systems is a core technology for ensuring the safe and stable operation of trains, affecting the lifespan of power supply equipment, power quality optimization, and the fault early warning capability of the traction network. However, the high-power, high-impact load characteristics of heavy-haul trains can significantly impact the power flow distribution of the system.

[0003] However, current methods for obtaining power flow distribution suffer from low accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for obtaining power flow distribution in heavy-haul railway traction power supply systems, which can improve the accuracy of the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for obtaining the power flow distribution of a heavy-haul railway traction power supply system, including:

[0006] Acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0007] Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current and power data of each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained.

[0008] Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0009] Based on current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through a power flow calculation model.

[0010] In conjunction with the first aspect, in one embodiment, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed based on the target traction network impedance admittance model, including:

[0011] Based on the target traction network impedance admittance model, a calculation model for the equivalent electrical parameters of the traction network corresponding to the target heavy-haul railway traction power supply system is constructed.

[0012] Based on the calculation model of equivalent electrical parameters of the traction network, a power flow calculation model corresponding to the traction power supply system of the target heavy-haul railway is constructed.

[0013] In conjunction with the first aspect, in one embodiment, historical operating data includes historical traction network impedance admittance matrix, historical voltage, historical current, and historical power;

[0014] Based on historical operating data, corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data for each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained, including:

[0015] Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data of each station, a traction network impedance admittance model of the target heavy-haul railway traction power supply system is constructed.

[0016] Based on the traction network impedance admittance model, the traction network impedance admittance matrix of the target heavy-haul railway traction power supply system is generated.

[0017] The target model parameters are obtained by acquiring the network of pre-built parameters based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current and historical power.

[0018] The model parameters in the traction network impedance admittance model are updated to the target model parameters to obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system.

[0019] In conjunction with the first aspect, in an exemplary embodiment, the target model parameters are obtained through a pre-built parameter acquisition network based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current, and historical power, including:

[0020] The impedance admittance matrix of the traction network, historical voltage, historical current and historical power are input into the parameter acquisition network to obtain the first model parameters;

[0021] The model parameters of the traction network impedance admittance model are updated to the first model parameters to obtain the first traction network impedance admittance model.

[0022] The first traction network impedance admittance matrix is ​​generated based on the updated traction network impedance admittance model.

[0023] If the error between the first traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to a preset error threshold, the first model parameters are used as the target model parameters.

[0024] In conjunction with the first aspect, in one embodiment, the method further includes:

[0025] If the error is greater than the error threshold, the first traction network impedance admittance matrix and the first model parameters are input into the parameter acquisition network to obtain the second model parameters.

[0026] The model parameters of the first traction network impedance admittance model are updated to the second model parameters to obtain the second traction network impedance admittance model.

[0027] The second traction network impedance admittance matrix is ​​generated based on the second traction network impedance admittance model until the error between the second traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to the error threshold. The second model parameters are then used as the target model parameters.

[0028] In conjunction with the first aspect, in one embodiment, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed based on the traction network equivalent electrical parameter calculation model, including:

[0029] Based on the spatial location information of heavy-haul trains, traction substations, AT substations, and sectioning stations, the target heavy-haul railway traction power supply system is divided into multiple interconnected circuit units.

[0030] By using the equivalent electrical parameter calculation model of the traction network, the admittance matrix of the traction network node of the target heavy-haul railway traction power supply system is obtained based on each circuit unit.

[0031] Using the admittance matrix of the traction network nodes, a power flow calculation model corresponding to the traction power supply system of the target heavy-haul railway is constructed.

[0032] In conjunction with the first aspect, in an exemplary embodiment, the traction network node admittance matrix of the target heavy-haul railway traction power supply system is obtained based on each circuit unit through a traction network equivalent electrical parameter calculation model, including:

[0033] The electrical parameters of each circuit unit are input into the equivalent electrical parameter calculation model of the traction network to obtain the equivalent impedance admittance matrix of the traction network for each circuit unit.

[0034] By connecting the equivalent impedance admittance matrices of each traction network according to the connection relationship of each circuit unit, the admittance matrix of the traction network node of the target heavy-haul railway traction power supply system is obtained.

[0035] Secondly, this application also provides a power flow distribution acquisition device for a heavy-haul railway traction power supply system, comprising:

[0036] The data acquisition module is used to acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and sectioning substations in the target heavy-haul railway traction power supply system. The historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0037] The admittance model acquisition module is used to obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system based on historical operating data, the line structure information corresponding to each historical operating data, the traction network conductor type information, and the historical voltage, current and power data of each station.

[0038] The calculation model building module is used to construct the power flow calculation model corresponding to the traction power supply system of the target heavy-haul railway based on the impedance admittance model of the target traction network.

[0039] The power flow distribution acquisition module is used to obtain the current power flow distribution of the target heavy-haul railway traction power supply system based on the current operating data through the power flow calculation model.

[0040] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0041] Acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0042] Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current and power data of each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained.

[0043] Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0044] Based on current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through a power flow calculation model.

[0045] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0046] Acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0047] Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current and power data of each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained.

[0048] Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0049] Based on current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through a power flow calculation model.

[0050] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0051] Acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0052] Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current and power data of each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained.

[0053] Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0054] Based on current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through a power flow calculation model.

[0055] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for obtaining power flow distribution of the heavy-haul railway traction power supply system acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system. The historical operating data corresponds to line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation. Based on the historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained. Based on the target traction network impedance admittance model, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed. Through the power flow calculation model, based on the current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained. By utilizing historical operating data to construct the target traction network impedance admittance model, a corresponding power flow calculation model is constructed based on the target traction network impedance admittance model. According to the power flow calculation model and the current operating data, the power flow distribution of the target heavy-haul railway traction power supply system is calculated, realizing the power flow distribution calculation driven by both digital and analog models, thereby improving the accuracy of the obtained power flow distribution. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is an application environment diagram of a method for obtaining the power flow distribution of a heavy-haul railway traction power supply system in one embodiment.

[0058] Figure 2 This is a flowchart illustrating a method for obtaining the power flow distribution of a heavy-haul railway traction power supply system in one embodiment.

[0059] Figure 3 This is a flowchart of a real-time power flow calculation method for a heavy-haul railway traction power supply system based on digital model driving, as described in another embodiment.

[0060] Figure 4 Here is a flowchart of a deep reinforcement learning implementation;

[0061] Figure 5 This is a schematic diagram of the π-type equivalent circuit division of the traction network in another embodiment;

[0062] Figure 6This is a topology diagram of a heavy-haul railway traction power supply system in another embodiment;

[0063] Figure 7 This is a comparison chart of the calculation results of the offline power flow algorithm in one embodiment and the power flow algorithm of this application;

[0064] Figure 8 This is a comparison chart of the errors between the offline power flow algorithm in another embodiment and the power flow algorithm of this application;

[0065] Figure 9 This is a structural block diagram of a power flow distribution acquisition device for a heavy-haul railway traction power supply system in one embodiment.

[0066] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0068] Power flow calculation for traction power supply systems is a core technology for ensuring the safe and stable operation of trains, affecting the lifespan of power supply equipment, power quality optimization, and the traction network's fault early warning capabilities. However, the high-power, high-impact load characteristics of heavy-haul trains significantly impact the power flow distribution of the system. Therefore, accurately analyzing the power flow distribution of heavy-haul railway traction power supply systems is a crucial technology for optimizing power quality, preventing equipment overload, and ensuring the safe and stable operation of heavy-haul trains.

[0069] A current technological challenge lies in the difficulty of using real-time data to calculate power flow in physical models. With the rapid development of digital technology, a combination of data-driven and model-driven approaches has demonstrated significant potential in power system analysis. Data-driven methods can utilize vast amounts of historical data, employing reinforcement learning to train datasets while simultaneously monitoring real-time data to capture the dynamic characteristics of the system. Model-driven methods, on the other hand, are based on physical laws and can provide computational mechanisms for power flow distribution. Combining the two can fully leverage the advantages of both data and models, improving the accuracy and real-time performance of power flow calculations.

[0070] The power flow distribution acquisition method for heavy-haul railway traction power supply systems provided in this application embodiment can be applied to, for example... Figure 1The application environment is shown. The target heavy-haul railway traction power supply system includes heavy-haul trains, traction network, traction transformers (i.e., traction substations), power grid, AT substations, and sectioning stations, communicating with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102 or placed on the cloud or other network servers. Server 102 acquires historical and current operating data of heavy-haul trains, traction substations, AT substations, and sectioning stations in the target heavy-haul railway traction power supply system. The historical operating data corresponds to line structure information, traction network conductor type information, and historical voltage, current, and power data for each substation. Based on the historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained. Based on the target traction network impedance admittance model, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed. Finally, based on the current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through the power flow calculation model. Among them, server 102 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0071] In one exemplary embodiment, such as Figure 2 As shown, a method for obtaining the power flow distribution of a heavy-haul railway traction power supply system is provided, and this method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps S201 to S204. Wherein:

[0072] Step S201: Obtain historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0073] Among them, a traction substation can be understood as a dedicated substation that converts high-voltage AC power (from the power grid) into low-voltage DC or AC power suitable for the traction system and provides it to railway traction equipment. An AT substation can be understood as a substation that boosts the voltage of the railway traction network. A sectioning substation can be understood as an intermediate station or connection point that divides the traction power supply area. The operating data of heavy-haul trains can be understood as the data generated or required when heavy-haul trains are running, which may include unknown information during train operation and voltage and current data at the pantograph of the train. The operating data of traction substations, AT substations and sectioning substations can be understood as the relevant power data flowing through the traction substations, AT substations and sectioning substations during operation, which may include the output feeder voltage, current and power of the traction substations, AT substations and sectioning substations.

[0074] Optionally, server 102 obtains historical and current operating data of heavy-haul trains in the target heavy-haul railway traction power supply system through CTC (Centralized Traffic Control) system, and historical and current operating data of traction substations, AT substations and section substations in the target heavy-haul railway traction power supply system through SCADA (Supervisory Control and Data Acquisition) system. The historical operating data also includes line structure information, traction network conductor type information and historical voltage, current and power data of each substation.

[0075] Step S202: Based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data of each station, obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system.

[0076] Among them, the power balance constraint can be understood as the condition that the target heavy-haul railway traction power supply system can guarantee normal operation, which can be determined by the power data provided by the upstream power grid and the equipment of the target heavy-haul railway traction power supply system itself; the traction network impedance admittance model can be understood as a mathematical model used to describe the characteristics of power transmission in the traction power supply line.

[0077] For example, the power balance constraints of the target heavy-haul railway traction power supply system constructed by server 102 can be expressed as:

[0078]

[0079]

[0080] In the formula, This indicates that the traction substation obtains power from the power grid, and k is the substation number. This represents the power of heavy-load trains within the power supply zone corresponding to traction substation k, where i is the train number. This represents the maximum short-circuit capacity of the traction substation numbered k. First, based on historical operating data, the corresponding line structure information, and the traction network conductor type, a traction network impedance admittance model corresponding to the target heavy-haul railway traction power supply system is constructed. Then, using deep reinforcement learning, the model parameters of the traction network impedance admittance model are trained with historical operating data until a preset training termination condition is met, resulting in a target traction network impedance admittance model that satisfies the aforementioned power balance constraints of the target heavy-haul railway traction power supply system.

[0081] Step S203: Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0082] The power flow calculation model can be understood as a mathematical model that realizes the voltage and current of each node in the target heavy-haul railway traction power supply system.

[0083] Optionally, server 102 establishes a corresponding traction network equivalent electrical parameter calculation model based on the target traction network impedance admittance model, and further establishes a power flow calculation model containing the traction network equivalent based on the traction network equivalent electrical parameter calculation model, that is, the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0084] Step S204: Based on the current operating data, obtain the current power flow distribution of the target heavy-haul railway traction power supply system using the power flow calculation model.

[0085] Among them, power flow distribution can be understood as the node voltage and node current of each node in the target heavy-haul railway traction power supply system.

[0086] For example, server 102 inputs the previously collected current operating data of heavy-haul trains, traction substations, AT substations and section substations into the power flow calculation model to perform power flow calculation and obtain the current power flow distribution result of the target heavy-haul railway traction power supply system.

[0087] In the aforementioned method for obtaining the power flow distribution of a heavy-haul railway traction power supply system, historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations within the target heavy-haul railway traction power supply system are acquired. The historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data for each substation. Based on these historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data, a target traction network impedance admittance model satisfying the power balance constraints of the target heavy-haul railway traction power supply system is obtained. Based on this target traction network impedance admittance model, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed. Using this power flow calculation model, and based on the current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained. By utilizing historical operating data to construct the target traction network impedance admittance model, and then constructing the corresponding power flow calculation model based on this model, the power flow distribution of the target heavy-haul railway traction power supply system is calculated using the power flow calculation model and the current operating data. This achieves dual-drive digital-analog power flow distribution calculation, thereby improving the accuracy of the obtained power flow distribution.

[0088] In one embodiment, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed based on the target traction network impedance admittance model, including: constructing a calculation model of the equivalent electrical parameters of the traction network corresponding to the target heavy-haul railway traction power supply system based on the target traction network impedance admittance model; and constructing a power flow calculation model corresponding to the target heavy-haul railway traction power supply system based on the calculation model of the equivalent electrical parameters of the traction network.

[0089] The equivalent electrical parameter calculation model of the traction network can be understood as a mathematical model that uses simplified electrical parameters (such as impedance and admittance) to equivalently describe the complex traction power supply line.

[0090] Optionally, server 102 constructs a calculation model of the equivalent electrical parameters of the traction network corresponding to the traction power supply system of the target heavy-haul railway based on the impedance admittance model of the target traction network, which can be expressed as:

[0091]

[0092] In the formula, and This refers to the voltage and current at the output feeder of the traction substation. and This refers to the voltage and current at the feeder outlet of the AT substation.

[0093] Then, based on the aforementioned calculation model of equivalent electrical parameters of the traction network, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system containing the equivalent traction network is constructed.

[0094] According to the aforementioned implementation method, by constructing an equivalent electrical parameter calculation model based on the target traction network impedance admittance model, the electrical characteristics of the heavy-haul railway traction power supply system can be accurately described, thereby improving the accuracy of the constructed power flow calculation model and thus improving the accuracy of power flow distribution acquisition.

[0095] In one embodiment, historical operating data includes historical traction network impedance admittance matrix, historical voltage, historical current, and historical power;

[0096] Based on historical operating data, corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data for each station, a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system is obtained, including:

[0097] Based on historical operating data, corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data of each station, a traction network impedance admittance model for the target heavy-haul railway traction power supply system is constructed. Based on this model, a traction network impedance admittance matrix for the target heavy-haul railway traction power supply system is generated. Through a pre-constructed parameter acquisition network, target model parameters are obtained based on the traction network impedance admittance matrix, historical traction network impedance admittance matrices, historical voltage, historical current, and historical power. The model parameters in the traction network impedance admittance model are then updated to the target model parameters, resulting in a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system.

[0098] The parameter acquisition network can be understood as a neural network used to train the model parameters of the traction network impedance admittance model, which may include a deep reinforcement learning network. The target model parameters can be understood as the model parameters of the traction network impedance admittance model that meet the preset convergence conditions after being trained by the parameter acquisition network. The traction network impedance admittance matrix can be understood as a mathematical tool used to describe the electrical characteristics of the traction power supply line, which may include the relationship between voltage and current in the line.

[0099] For example, server 102 constructs a traction network impedance admittance model for the target heavy-haul railway traction power supply system based on historical operating data, line structure information corresponding to each historical operating data, traction network conductor type information, and historical voltage, current, and power data of each station. Then, based on the traction network impedance admittance model, it constructs a traction network impedance admittance matrix for the target heavy-haul railway traction power supply system. Through a pre-constructed parameter acquisition network, it trains the model parameters of the traction network impedance admittance model based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current, and historical power included in the historical operating data, obtains target model parameters that meet preset convergence conditions, and updates the model parameters in the traction network impedance admittance model to the target model parameters, thereby obtaining a target traction network impedance admittance model that meets the power balance constraints of the target heavy-haul railway traction power supply system.

[0100] Based on the above implementation method, the model parameters are dynamically updated using historical data to obtain a target traction network impedance admittance model that better reflects the current situation. This improves the impedance prediction accuracy of the target traction network impedance admittance model and, consequently, achieves the accuracy of the power flow distribution of the target heavy-haul railway traction power supply system.

[0101] In an exemplary embodiment, a pre-built parameter acquisition network obtains target model parameters based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current, and historical power, including:

[0102] The traction network impedance admittance matrix, historical voltage, historical current, and historical power are input into the parameter acquisition network to obtain the first model parameters. The model parameters of the traction network impedance admittance model are updated with the first model parameters to obtain the first traction network impedance admittance model. The first traction network impedance admittance matrix is ​​generated based on the updated traction network impedance admittance model. If the error between the first traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to a preset error threshold, the first model parameters are used as the target model parameters.

[0103] Optionally, server 102 uses the traction network impedance admittance matrix, historical voltage, historical current, and historical power as input parameters to train the model parameters of the parameter acquisition network, obtains the first model parameters, updates the model parameters of the traction network impedance admittance model with the first model parameters, obtains the first traction network impedance admittance model, generates the first traction network impedance admittance matrix based on the first traction network impedance admittance model, obtains the error between the first traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix, and determines that the parameter training is successful and the prediction accuracy of the traction network impedance admittance matrix has reached the preset accuracy requirement if the error is less than or equal to a preset error threshold, and uses the first model parameters as the target model parameters.

[0104] According to the aforementioned implementation method, by comparing the predicted traction network impedance admittance matrix output by the first traction network impedance admittance model with the historical traction network impedance admittance matrix at the corresponding time point, the first model parameters can be used as the target model parameters only after the error comparison is passed, thereby ensuring the prediction accuracy of the target traction network impedance admittance model.

[0105] In one embodiment, the method further includes: when the error is greater than an error threshold, obtaining a second model parameter by inputting the first traction network impedance admittance matrix and the first model parameter into a parameter acquisition network; updating the model parameters of the first traction network impedance admittance model to the second model parameter to obtain a second traction network impedance admittance model; generating a second traction network impedance admittance matrix based on the second traction network impedance admittance model until the error between the second traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to the error threshold, and using the second model parameter as the target model parameter.

[0106] For example, when the error is greater than the error threshold, that is, when the prediction accuracy of the first traction network impedance admittance model does not meet the accuracy requirement, the server 102 re-inputs the first traction network impedance admittance matrix and the first model parameters into the parameter acquisition network, thereby making corresponding adjustments and modifications to the first model parameters to obtain the second model parameters. The model parameters of the first traction network impedance admittance model are then updated to the second model parameters to obtain the second traction network impedance admittance model. The second traction network impedance admittance matrix is ​​then generated based on the second traction network impedance admittance model until the error between the second traction network impedance admittance matrix and the historical traction network impedance admittance matrix at the corresponding time point is less than or equal to the error threshold. That is, the prediction accuracy of the second traction network impedance admittance model meets the set accuracy requirement, and the second model parameters are determined as the target model parameters.

[0107] Based on the above implementation method, through error detection and iterative adjustment, the traction network impedance admittance model is continuously approximated to the actual system to ensure that the prediction accuracy meets the requirements, thereby greatly enhancing the applicability, robustness and intelligent scheduling capability of the model, and thus ensuring the calculation accuracy of the power flow calculation model subsequently constructed, thereby achieving the accuracy of the obtained power flow distribution.

[0108] In one embodiment, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed based on the traction network equivalent electrical parameter calculation model. This includes: dividing the target heavy-haul railway traction power supply system into multiple interconnected circuit units based on the spatial location information of heavy-haul trains, traction substations, AT substations, and sectioning substations; obtaining the traction network node admittance matrix of the target heavy-haul railway traction power supply system based on each circuit unit through the traction network equivalent electrical parameter calculation model; and constructing the power flow calculation model corresponding to the target heavy-haul railway traction power supply system using the traction network node admittance matrix.

[0109] Spatial location information can be understood as data information describing the position and spatial relationship of an object, point, or entity in three-dimensional space, which may include quantity and location; circuit unit can be understood as the smallest functional unit that serves as a basic component or module in a circuit system.

[0110] Optionally, server 102 divides the target heavy-haul railway traction power supply system into multiple interconnected π-type circuit units based on the spatial location information of heavy-haul trains, traction substations, AT substations, and sectioning stations. Through the traction network equivalent electrical parameter calculation model, based on the measurement data of each section of the π-type circuit units, the server calculates the traction network node admittance matrix of the target heavy-haul railway traction power supply system. Then, using the traction network node admittance matrix, the server constructs the power flow calculation model corresponding to the target heavy-haul railway traction power supply system.

[0111] According to the aforementioned implementation method, the complex heavy-haul railway traction system is divided into multiple π-type circuit units based on spatial location information. By reducing the computational load of each part, the computational difficulty of the traction network node admittance matrix is ​​reduced, thereby accelerating the power flow calculation.

[0112] In one embodiment, the traction network node admittance matrix of the target heavy-haul railway traction power supply system is obtained based on each circuit unit through the traction network equivalent electrical parameter calculation model. This includes: inputting the electrical parameters of each circuit unit into the traction network equivalent electrical parameter calculation model to obtain the traction network equivalent impedance admittance matrix of each circuit unit; and connecting the traction network equivalent impedance admittance matrices according to the connection relationship of each circuit unit to obtain the traction network node admittance matrix of the target heavy-haul railway traction power supply system.

[0113] For example, server 102 inputs each π-type circuit unit into the traction network equivalent electrical parameter calculation model to obtain the traction network equivalent impedance admittance matrix of each circuit unit, and then connects each traction network equivalent impedance admittance matrix according to the connection relationship of each π-type circuit unit to obtain the traction network node admittance matrix of the traction power supply system of the target heavy-haul railway.

[0114] Based on the above implementation method, the local accuracy of the model is guaranteed by using the equivalent impedance admittance matrix of each circuit unit. The node admittance matrix obtained after connection can fully reflect the electrical characteristics of the system, thereby improving the accuracy of the power flow distribution obtained by performing power flow calculation using the traction network admittance matrix.

[0115] In one exemplary embodiment, such as Figure 3 As shown, a flowchart of a real-time power flow calculation method for a heavy-haul railway traction power supply system based on digital model driving is provided (the following data are specific examples and are not limited to this case to implement this application). Wherein:

[0116] Step 1: Based on historical operating data of heavy-haul trains, traction substations, and AT (Automatic Substation) stations, construct an impedance admittance model of the traction network based on analytical methods:

[0117] The traction network impedance admittance model based on the analytical method can be expressed as follows:

[0118] The traction power supply system of heavy-haul railways is equivalent to a π-type equivalent circuit, with impedance per unit distance. Admittance for:

[0119]

[0120] In the formula, Z and Y are the impedance matrix and admittance matrix of the traction network per unit distance, and L is the length of the traction network conductor. Z and Y are calculated based on historical operating data of heavy-haul trains, traction substations, and AT substations, as well as the corresponding line structure and traction network conductor type.

[0121] Step 2: Based on the traction network impedance admittance model obtained in Step 1 and historical operating data, a deep reinforcement learning method is used to train the accuracy of the traction network impedance admittance calculation, and the equivalent electrical parameter calculation model of the traction network is established based on the training results.

[0122] The specific steps for model building include:

[0123] Step 2.1, constructing the power balance constraints for the heavy-haul railway traction power supply system, can be expressed as:

[0124]

[0125]

[0126] In the formula, This indicates that the traction substation obtains power from the power grid, and k is the substation number. This represents the power of heavy-load trains within the power supply zone corresponding to traction substation k, where i is the train number. This indicates the maximum short-circuit capacity of the traction substation numbered k.

[0127] Step 2.2: Based on the traction network impedance admittance model obtained in Step 1, construct the traction network impedance admittance matrix, taking heavy-haul trains, traction substations, AT substations, and sectioning substations as sections. Assuming there are m conductors constituting the traction network, it can be expressed as:

[0128] Z L = [ Z 11 Z 12 ⋯ Z 1 m Z 21 Z 22 ⋯ Z 2 m ⋮ ⋮ ⋱ ⋮ Z m 1 Z m 2 ⋯ Z mm ]

[0129] Y L 2 = [ Y 11 Y 12 ⋯ Y 1 m Y 21 Y 22 ⋯ Y 2 m ⋮ ⋮ ⋱ ⋮ Y m 1 Y m 2 ⋯ Y mm ]

[0130] Step 2.3, design the deep reinforcement learning reward function. The purpose of training is to make impedance prediction more accurate. Therefore, the reward value of DRL can be expressed as:

[0131]

[0132] In the formula, P reference and V reference are the traction substation power and train voltage from historical operating data, and P output and V output are calculated values ​​of traction substation power and train voltage based on the current impedance parameters.

[0133] Deep reinforcement learning is an algorithm that learns through interaction with its environment. Its interactive learning process is as follows: Figure 4 As shown, the Q-learning algorithm is a type of learning algorithm. Using this algorithm to design the action-value function, its update formula can be expressed as:

[0134] Q ( S t , A t ) ← Q ( S t , A t ) + a × [ R t + 1 + γ max a Q ( S t + 1 , a ) − Q ( S t , A t )]

[0135] In the formula, St and At represent the state of the environment and the action chosen by the agent at time t, respectively, and a represents the learning rate. γ represents the discount rate for future rewards. Rt+1 represents the immediate reward obtained by using action At in state St. A represents all available actions in state St+1. The estimated future reward will be calculated using the maximum reward value of the next step within the range of choices of a. St+1 is the state of the environment after choosing action At in state St.

[0136] The deep reinforcement Q-learning algorithm uses an artificial neural network as a function approximator to approximate the data in the action value table, thereby transforming the Q-table into a Q-network, i.e., Q(s,a)≈Q(s,a;θ). The loss function of the Q-network is shown in the following equation:

[0137] L ( θ i ) = 1 N ∑ k = 1 N [ R k + γ max a Q ( S ′ k , a ; θ i − ) − Q ( S k , A k ; θ i ) ] 2

[0138] Where θ i These are the weights of the Q-network. Every C steps (C is a constant), the Q-network parameters (θ) are used.i Update the target network Parameters. N is the number of samples collected during the interaction between the DRL agent and the environment. The loss function represents the expected value of the sum of the real-time reward predicted in one step, the maximum reward, and the value function.

[0139] A deep reinforcement learning approach based on continuous actions, namely deep deterministic policy gradients, is used to modify the loss function. The action network loss function is as follows:

[0140]

[0141] In the formula, μ(s) is the output value of the action network in state s. These are the weights of the action network.

[0142] Step 2.4: Based on the traction network impedance admittance model obtained in Step 1 and historical operating data, deep reinforcement learning is used to train the accuracy of the traction network impedance admittance calculation. The training results are then used to establish an equivalent electrical parameter calculation model for the traction network, which can be expressed as:

[0143]

[0144] In the formula, and This refers to the voltage and current at the output feeder of the traction substation. and This refers to the voltage and current at the feeder outlet of the AT substation.

[0145] Step 3: Based on the traction network equivalent electrical parameter calculation model obtained in Step 2, establish a power flow calculation model including the traction network equivalent:

[0146] The specific steps for model building include:

[0147] Step 3.1: Based on the number and location of heavy-haul trains, traction substations, AT substations, and sectioning substations within the power supply zone, divide the traction network into π-type equivalent circuits, such as... Figure 5 As shown.

[0148] Step 3.2: Input the measurement data of each section of the equivalent circuit of the traction network, and calculate the equivalent impedance admittance matrix of the traction network based on the calculation model of the equivalent electrical parameters of the traction network obtained in Step 2 according to the input data.

[0149] Step 3.3: Based on the equivalent impedance admittance matrix of the traction network obtained in Step 3.2, construct the admittance matrix Y of the traction network nodes.

[0150] Step 3.4: Initialize the sectional current vector I. The heavy-haul railway traction power supply system includes four types of sections: traction substation section. Cross-section of heavy-haul train AT cut surface and the tangent of the partition The current vectors in each cross-section are 6-dimensional, arranged from top to bottom as follows: upward contact line, return line, rail; downward contact line, return line, rail. This can be represented as:

[0151]

[0152] In the formula, the current flowing out of the contact wire is negative, and vice versa.

[0153] Step 3.5: Based on the initial values ​​obtained in Step 3.3, iteratively solve for the tangential voltage vector U and update the tangential current vector I until the convergence condition is met, and output the power flow calculation results. The calculation formulas for the voltage vector U and the current vector I are as follows:

[0154]

[0155]

[0156] Step 4: Real-time acquisition of various data such as voltage, current, and power of heavy-haul trains, traction substations, and AT substations in the heavy-haul railway traction power supply system:

[0157] The CTC system collects real-time location information of heavy-haul trains during operation, as well as voltage and current data at the train's pantograph. The SCADA system measures the voltage and current of the feeder lines at the traction substation and AT substation in real time.

[0158] Step 5: Based on the power flow calculation model with traction network equivalent obtained in Step 3, and using the data obtained in real time in Step 4 as the initial value, perform power flow calculation and analyze the power flow distribution of the heavy-haul railway traction power supply system in real time.

[0159] Step 5.1: Real-time acquisition of operating data of the heavy-haul railway traction power supply system obtained in Step 4, including the operating power of heavy-haul trains. Location information Voltage at the output feeder of the traction substation Current ,power Voltage at the AT output feeder Current Used as the initial value for power flow calculation.

[0160] Step 5.2: Input the data collected in Step 5.1 into the power flow calculation model with traction network equivalent obtained in Step 3 to obtain the real-time power flow distribution results of the heavy-haul railway traction power supply system.

[0161] Example of implementation method:

[0162] The topology of the traction power supply system for heavy-haul railways is as follows: Figure 6 As shown, the proposed real-time power flow calculation method for heavy-haul railway traction power supply systems based on digital simulation driving yields a power flow distribution closer to the actual system conditions compared to offline power flow algorithms. Taking the total active power of traction substations as an example, the calculation method proposed in this application yields results closer to the actual power of the traction substations than those calculated by offline power flow algorithms. Figure 7 As shown. From a statistical perspective, the comparison of box plots shows that the calculation method proposed in this application has a smaller error, such as... Figure 8 As shown.

[0163] Compared with the prior art, this application has the following technical advantages:

[0164] 1. It can realize the power flow distribution calculation of multiple trains and multiple traction substations along the entire line of the heavy-haul railway traction power supply system, and accurately analyze the operating status of heavy-haul trains, the load of traction substations, and the energy flow distribution of the entire system.

[0165] 2. Considering the impact of large traction power fluctuations on the impedance admittance of the traction network during heavy-haul train operation, a prediction model of equivalent electrical parameters of the traction network based on deep reinforcement learning is proposed. This model can accurately calculate the impedance admittance of the traction network, reduce the error in establishing the admittance matrix of the traction network nodes during power flow calculation, and effectively improve the accuracy of power flow calculation.

[0166] 3. By acquiring real-time operating data of heavy-haul trains, traction substations, and AT stations as initial values ​​for power flow calculation, the power flow distribution of the entire heavy-haul railway traction power supply system is dynamically analyzed, providing a basis for railway operators to conduct energy management.

[0167] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0168] Based on the same inventive concept, this application also provides a power flow distribution acquisition device for a heavy-haul railway traction power supply system, used to implement the power flow distribution acquisition method for the heavy-haul railway traction power supply system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the power flow distribution acquisition device for a heavy-haul railway traction power supply system provided below can be found in the limitations of the power flow distribution acquisition method for a heavy-haul railway traction power supply system described above, and will not be repeated here.

[0169] In one exemplary embodiment, such as Figure 9 As shown, a power flow distribution acquisition device for a heavy-haul railway traction power supply system is provided, comprising: a data acquisition module 901, an admittance model acquisition module 902, a calculation model construction module 903, and a power flow distribution acquisition module 904, wherein:

[0170] The data acquisition module 901 is used to acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data includes line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation.

[0171] Admittance model acquisition module 902 is used to obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system based on historical operating data, the line structure information corresponding to each historical operating data, the traction network conductor type information, and the historical voltage, current and power data of each station.

[0172] The calculation model construction module 903 is used to construct the power flow calculation model corresponding to the traction power supply system of the target heavy-haul railway based on the impedance admittance model of the target traction network.

[0173] The power flow distribution acquisition module 904 is used to obtain the current power flow distribution of the target heavy-haul railway traction power supply system based on the current operating data through the power flow calculation model.

[0174] In one embodiment, the calculation model building module 903 is further configured to construct a calculation model of the equivalent electrical parameters of the traction network corresponding to the target heavy-haul railway traction power supply system based on the target traction network impedance admittance model; and to construct a power flow calculation model corresponding to the target heavy-haul railway traction power supply system based on the calculation model of the equivalent electrical parameters of the traction network.

[0175] In one embodiment, the historical operating data includes the historical traction network impedance admittance matrix, historical voltage, historical current, and historical power. The admittance model acquisition module 902 further includes: an admittance model construction submodule, a matrix generation submodule, a model parameter acquisition submodule, and an admittance model acquisition submodule, wherein:

[0176] The admittance model construction submodule is used to construct the traction network impedance admittance model of the target heavy-haul railway traction power supply system based on historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current and power data of each station.

[0177] The matrix generation submodule is used to generate the traction network impedance admittance matrix of the target heavy-haul railway traction power supply system based on the traction network impedance admittance model.

[0178] The model parameter acquisition submodule is used to obtain the target model parameters through a pre-built parameter acquisition network, based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current, and historical power.

[0179] The admittance model acquisition submodule is used to update the model parameters in the traction network impedance admittance model to the target model parameters, so as to obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system.

[0180] In an exemplary embodiment, the model parameter acquisition submodule is further configured to input the traction network impedance admittance matrix, historical voltage, historical current, and historical power into a parameter acquisition network to obtain first model parameters; update the model parameters of the traction network impedance admittance model to the first model parameters to obtain a first traction network impedance admittance model; generate a first traction network impedance admittance matrix based on the updated traction network impedance admittance model; and, if the error between the first traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to a preset error threshold, use the first model parameters as target model parameters.

[0181] In one embodiment, the model parameter acquisition submodule is further configured to, when the error is greater than an error threshold, obtain the second model parameters by inputting the first traction network impedance admittance matrix and the first model parameter into the parameter acquisition network; update the model parameters of the first traction network impedance admittance model to the second model parameters to obtain the second traction network impedance admittance model; generate the second traction network impedance admittance matrix based on the second traction network impedance admittance model until the error between the second traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to the error threshold, and use the second model parameters as the target model parameters.

[0182] In one embodiment, the computational model construction module 903 further includes: a partitioning submodule, a matrix acquisition submodule, and a computational model construction submodule, wherein:

[0183] The sub-module is used to divide the target heavy-haul railway traction power supply system into multiple interconnected circuit units based on the spatial location information of heavy-haul trains, traction substations, AT substations and sectioning stations.

[0184] The matrix acquisition submodule is used to obtain the traction network node admittance matrix of the target heavy-haul railway traction power supply system based on each circuit unit through the traction network equivalent electrical parameter calculation model.

[0185] The computational model construction submodule is used to construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system using the admittance matrix of the traction network nodes.

[0186] In an exemplary embodiment, the matrix acquisition submodule is further used to input the electrical parameters of each circuit unit into the traction network equivalent electrical parameter calculation model to obtain the traction network equivalent impedance admittance matrix of each circuit unit; and to connect the traction network equivalent impedance admittance matrices according to the connection relationship of each circuit unit to obtain the traction network node admittance matrix of the target heavy-haul railway traction power supply system.

[0187] Each module in the power flow distribution acquisition device of the aforementioned heavy-haul railway traction power supply system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0188] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores historical and current operating data for heavy-haul trains, traction substations, AT substations, and section substations; corresponding line structure information; traction network conductor type information; historical voltage, current, and power data for each substation; and power flow distribution. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for obtaining the power flow distribution of a heavy-haul railway traction power supply system.

[0189] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0190] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the power flow distribution acquisition method of the heavy-haul railway traction power supply system described in the above embodiment.

[0191] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the power flow distribution acquisition method for the heavy-haul railway traction power supply system described above.

[0192] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the power flow distribution acquisition method for the heavy-haul railway traction power supply system described above.

[0193] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0194] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0195] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0196] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for obtaining power flow distribution in a heavy-haul railway traction power supply system, characterized in that, The method includes: Acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and section substations in the target heavy-haul railway traction power supply system; the historical operating data corresponds to line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation. Based on the historical operating data, the line structure information corresponding to the historical operating data, the traction network conductor type information, and the historical voltage, current and power data of each station, a target traction network impedance admittance model that satisfies the power balance constraint of the target heavy-haul railway traction power supply system is obtained. Based on the target traction network impedance admittance model, construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system; Based on the current operating data, the current power flow distribution of the target heavy-haul railway traction power supply system is obtained through the power flow calculation model.

2. The method according to claim 1, characterized in that, The step of constructing a power flow calculation model for the target heavy-haul railway traction power supply system based on the target traction network impedance admittance model includes: Based on the target traction network impedance admittance model, a calculation model for the equivalent electrical parameters of the traction network corresponding to the target heavy-haul railway traction power supply system is constructed. Based on the calculation model of the equivalent electrical parameters of the traction network, a power flow calculation model corresponding to the target heavy-haul railway traction power supply system is constructed.

3. The method according to any one of claims 1-2, characterized in that, The historical operating data includes the historical traction network impedance admittance matrix, historical voltage, historical current, and historical power. The process of obtaining a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system, based on the historical operating data, the corresponding line structure information, traction network conductor type information, and historical voltage, current, and power data of each station, includes: Based on the historical operating data, the line structure information corresponding to the historical operating data, the traction network conductor type information, and the historical voltage, current, and power data of each station, a traction network impedance admittance model of the target heavy-haul railway traction power supply system is constructed. Based on the traction network impedance admittance model, the traction network impedance admittance matrix of the target heavy-haul railway traction power supply system is generated. The target model parameters are obtained by acquiring the network of parameters through a pre-constructed parameter acquisition system, based on the traction network impedance admittance matrix, the historical traction network impedance admittance matrix, the historical voltage, the historical current, and the historical power. The model parameters in the traction network impedance admittance model are updated to the target model parameters to obtain the target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system.

4. The method according to claim 3, characterized in that, The method of obtaining target model parameters for the traction network impedance admittance model through a pre-constructed parameter acquisition network, based on the traction network impedance admittance matrix, historical traction network impedance admittance matrix, historical voltage, historical current, and historical power, includes: The traction network impedance admittance matrix, the historical voltage, the historical current, and the historical power are input into the parameters to obtain the network and obtain the first model parameters; The model parameters of the traction network impedance admittance model are updated to the first model parameters to obtain the first traction network impedance admittance model. The first traction network impedance admittance matrix is ​​generated based on the updated traction network impedance admittance model. If the error between the first traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to a preset error threshold, the first model parameter is used as the target model parameter.

5. The method according to claim 4, characterized in that, The method further includes: If the error is greater than the error threshold, the first traction network impedance admittance matrix and the first model parameters are input into the parameter acquisition network to obtain the second model parameters. The model parameters of the first traction network impedance admittance model are updated to the second model parameters to obtain the second traction network impedance admittance model; The second traction network impedance admittance matrix is ​​generated based on the second traction network impedance admittance model until the error between the second traction network impedance admittance matrix and the corresponding historical traction network impedance admittance matrix is ​​less than or equal to the error threshold. Then, the second model parameters are used as the target model parameters.

6. The method according to claim 2, characterized in that, The step of constructing a power flow calculation model corresponding to the target heavy-haul railway traction power supply system based on the equivalent electrical parameters calculation model of the traction network includes: Based on the spatial location information of the heavy-haul train, the traction substation, the AT substation, and the sectioning station, the target heavy-haul railway traction power supply system is divided into multiple interconnected circuit units. Based on the equivalent electrical parameters calculation model of the traction network, the admittance matrix of the traction network node of the target heavy-haul railway traction power supply system is obtained. Using the admittance matrix of the traction network nodes, a power flow calculation model corresponding to the traction power supply system of the target heavy-haul railway is constructed.

7. The method according to claim 6, characterized in that, The step of obtaining the traction network node admittance matrix of the target heavy-haul railway traction power supply system based on each circuit unit through the equivalent electrical parameter calculation model of the traction network includes: The electrical parameters of each circuit unit are input into the equivalent electrical parameter calculation model of the traction network to obtain the equivalent impedance admittance matrix of the traction network for each circuit unit. By connecting the equivalent impedance admittance matrices of each traction network according to the connection relationship of each circuit unit, the traction network node admittance matrix of the target heavy-haul railway traction power supply system is obtained.

8. A power flow distribution acquisition device for a heavy-haul railway traction power supply system, characterized in that, The device includes: The data acquisition module is used to acquire historical and current operating data of heavy-haul trains, traction substations, AT substations, and sectioning substations in the target heavy-haul railway traction power supply system; the historical operating data corresponds to line structure information, traction network conductor type information, and historical voltage, current, and power data of each substation. The admittance model acquisition module is used to obtain a target traction network impedance admittance model that satisfies the power balance constraints of the target heavy-haul railway traction power supply system based on the historical operating data, the line structure information corresponding to the historical operating data, the traction network conductor type information, and the historical voltage, current and power data of each station. The calculation model construction module is used to construct the power flow calculation model corresponding to the target heavy-haul railway traction power supply system based on the target traction network impedance admittance model. The power flow distribution acquisition module is used to obtain the current power flow distribution of the target heavy-haul railway traction power supply system based on the current operating data through the power flow calculation model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images