Operation parameter adjusting method and device of heavy haul railway power supply system, computer equipment, storage medium and computer program product

Abstract

The invention relates to an operation parameter adjusting method and device of a heavy haul railway power supply system, computer equipment, a storage medium and a computer program product. The method comprises the following steps: respectively inputting preprocessed power flow data of the heavy haul railway power supply system into a physical model and a data driving model to obtain first predicted power flow data and second predicted power flow data of the heavy haul railway power supply system; performing fusion processing on the first predicted power flow data and the second predicted power flow data to obtain target predicted power flow data of the heavy haul railway power supply system; determining operation parameter adjustment strategy information of the heavy haul railway power supply system according to the target prediction power flow data; according to the operation parameter adjusting strategy information, the current operation parameters of the heavy haul railway power supply system are correspondingly adjusted, and the adjusted operation parameters of the heavy haul railway power supply system are obtained. By adopting the method, the adjustment accuracy of the operating parameters of the heavy haul railway power supply system can be improved.

Description

Technical Field

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

[0002] Currently, in order to ensure the stability and safety of the power supply system for heavy-haul railways, it is crucial to accurately adjust the operating parameters of the power supply system for heavy-haul railways.

[0003] In traditional heavy-haul railway power supply systems, the distribution of power flow and load changes mainly rely on human experience for processing, lacking the ability to dynamically adjust operating parameters accurately, resulting in low accuracy of operating parameter adjustments for heavy-haul railway power supply systems. 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 adjusting the operating parameters of a heavy-haul railway power supply system, which can improve the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for adjusting the operating parameters of a heavy-haul railway power supply system, including:

[0006] Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0007] The preprocessed power flow data is input into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and the preprocessed power flow data is input into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0008] The first predicted power flow data and the second predicted power flow data are fused together to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0009] Based on the target predicted power flow data, the power supply assessment results of the heavy-haul railway power supply system are determined;

[0010] If the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data.

[0011] According to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0012] In one embodiment, the target predicted power flow data includes at least the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information of the heavy-haul railway power supply system;

[0013] The step of determining the power supply assessment result of the heavy-haul railway power supply system based on the target predicted power flow data includes:

[0014] Based on the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information, the power supply stability, power supply efficiency information, and potential risk information of the heavy-haul railway power supply system are determined.

[0015] Based on the power supply stability, power supply efficiency information, and potential risk information, the power supply assessment results of the heavy-haul railway power supply system are determined.

[0016] In one embodiment, determining the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data includes:

[0017] Extract the first feature vector of the first predicted power flow distribution information, the second feature vector of the first predicted load change trend information, and the third feature vector of the first predicted power demand information;

[0018] The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector of the heavy-haul railway power supply system.

[0019] Based on the fused feature vector, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined.

[0020] In one embodiment, determining the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the fused feature vector includes:

[0021] The fused feature vector is input into the trained load balancing strategy information prediction model to obtain the load balancing strategy information of the heavy-haul railway power supply system.

[0022] The fused feature vector is input into the trained power supply adjustment strategy information prediction model to obtain the power supply adjustment strategy information of the heavy-haul railway power supply system.

[0023] The fused feature vector is input into the trained energy efficiency processing strategy information prediction model to obtain the energy efficiency processing strategy information of the heavy-haul railway power supply system.

[0024] The load balancing strategy information, the power supply adjustment strategy information, and the energy efficiency processing strategy information are all used as the operating parameter adjustment strategy information.

[0025] In one embodiment, the preprocessing of the current power flow data to obtain preprocessed power flow data of the heavy-haul railway power supply system includes:

[0026] The current power flow data is cleaned to obtain the cleaned power flow data of the heavy-haul railway power supply system.

[0027] The cleaned power flow data is integrated to obtain the integrated power flow data of the heavy-haul railway power supply system.

[0028] The correlation between the integrated power flow data and the preset data is determined, and the integrated power flow data with a correlation greater than the preset correlation is selected from each of the integrated power flow data as the preprocessed power flow data of the heavy-haul railway power supply system.

[0029] In one embodiment, the trained data-driven model is obtained by training in the following manner:

[0030] Obtain sample power flow data of the sample heavy-haul railway power supply system, and preprocess the sample power flow data to obtain preprocessed sample power flow data of the sample heavy-haul railway power supply system.

[0031] The preprocessed sample power flow data is input into the data-driven model to be trained to obtain the predicted power flow data of the sample heavy-haul railway power supply system; the predicted power flow data of the sample heavy-haul railway power supply system includes at least the second predicted power flow distribution information, the second predicted load change trend information and the second predicted power demand information of the sample heavy-haul railway power supply system.

[0032] Obtain the actual power flow distribution information, actual load change trend information, and actual power supply demand information of the sample heavy-haul railway power supply system;

[0033] A first loss value is obtained based on the difference between the second predicted power flow distribution information and the actual power flow distribution information; a second loss value is obtained based on the difference between the second predicted load change trend information and the actual load change trend information; and a third loss value is obtained based on the difference between the second predicted power demand information and the actual power demand information.

[0034] The first loss value, the second loss value, and the third loss value are fused together to obtain the target loss value;

[0035] Based on the target loss value, the data-driven model to be trained is iteratively trained to obtain the trained data-driven model.

[0036] Secondly, this application also provides an operating parameter adjustment device for a heavy-haul railway power supply system, comprising:

[0037] The data processing module is used to acquire the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0038] The data prediction module is used to input the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and to input the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0039] The data fusion module is used to fuse the first predicted power flow data and the second predicted power flow data to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0040] The result determination module is used to determine the power supply assessment result of the heavy-haul railway power supply system based on the target predicted power flow data.

[0041] The strategy determination module is used to determine the operation parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data when the power supply assessment result is the preset power supply assessment result.

[0042] The parameter adjustment module is used to adjust the current operating parameters of the heavy-haul railway power supply system according to the operating parameter adjustment strategy information, so as to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0043] 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:

[0044] Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0045] The preprocessed power flow data is input into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and the preprocessed power flow data is input into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0046] The first predicted power flow data and the second predicted power flow data are fused together to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0047] Based on the target predicted power flow data, the power supply assessment results of the heavy-haul railway power supply system are determined;

[0048] If the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data.

[0049] According to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0050] 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:

[0051] Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0052] The preprocessed power flow data is input into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and the preprocessed power flow data is input into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0053] The first predicted power flow data and the second predicted power flow data are fused together to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0054] Based on the target predicted power flow data, the power supply assessment results of the heavy-haul railway power supply system are determined;

[0055] If the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data.

[0056] According to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0057] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0058] Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0059] The preprocessed power flow data is input into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and the preprocessed power flow data is input into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0060] The first predicted power flow data and the second predicted power flow data are fused together to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0061] Based on the target predicted power flow data, the power supply assessment results of the heavy-haul railway power supply system are determined;

[0062] If the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data.

[0063] According to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0064] The aforementioned method, apparatus, computer equipment, storage medium, and computer program product for adjusting the operating parameters of a heavy-haul railway power supply system first acquires the current power flow data of the heavy-haul railway power supply system. This data is then preprocessed to obtain preprocessed power flow data. The preprocessed power flow data is then input into a constructed physical model to obtain first predicted power flow data. The preprocessed power flow data is further input into a trained data-driven model to obtain second predicted power flow data. The first and second predicted power flow data are then fused to obtain target predicted power flow data. Next, based on the target predicted power flow data, a power supply assessment result for the heavy-haul railway power supply system is determined. Then, assuming the power supply assessment result matches a preset result, the operating parameter adjustment strategy information for the heavy-haul railway power supply system is determined based on the target predicted power flow data. Finally, according to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters. In this way, during the adjustment of the operating parameters of the heavy-haul railway power supply system, power flow prediction is performed on the preprocessed power flow data of the heavy-haul railway power supply system by combining physical models and data-driven models, and the predicted power flow data is fused. This allows for the accurate capture of the system's operating patterns and dynamic characteristics. Based on the fused target predicted power flow data, the power supply status is assessed, and scientific strategies for adjusting operating parameters are formulated in case of anomalies. This enables intelligent optimization and adjustment of the system's operating parameters, which is beneficial to improving the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of relying on manual experience, which lacks the ability to accurately and dynamically adjust operating parameters and leads to low accuracy in adjusting the operating parameters of the heavy-haul railway power supply system. This further improves the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system. Attached Figure Description

[0065] 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.

[0066] Figure 1 This is a flowchart illustrating a method for adjusting the operating parameters of a heavy-haul railway power supply system in one embodiment.

[0067] Figure 2 This is a flowchart illustrating a method for adjusting the operating parameters of a heavy-haul railway power supply system in another embodiment.

[0068] Figure 3 This is a flowchart illustrating the power flow prediction and power supply capacity assessment process in one embodiment.

[0069] Figure 4 This is a structural block diagram of an operating parameter adjustment device for a heavy-haul railway power supply system in one embodiment.

[0070] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0071] 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.

[0072] 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.

[0073] In one exemplary embodiment, such as Figure 1 As shown, a method for adjusting the operating parameters of a heavy-haul railway power supply system is provided. This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0074] Step S101: Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0075] Among them, the heavy-haul railway power supply system refers to the system that provides power supply for railway lines carrying heavy axle loads, high density, and long-formation freight trains.

[0076] Among them, the current power flow data refers to the real-time power flow data of the heavy-haul railway power supply system, including the voltage data, current data, and power data of the heavy-haul railway power supply system at the current time, as well as the status data of equipment such as the catenary, substation, and power supply zone.

[0077] Among them, the preprocessed power flow data refers to the current power flow data after preprocessing.

[0078] For example, the server collects voltage, current, and power data of the heavy-haul railway power supply system in real time through a SCADA (Supervisory Control and Data Acquisition) system associated with the system. It also collects status data of key equipment such as the overhead contact line, substations, and power supply zones in real time through sensors at critical equipment nodes within the system. The server then uses this data as the current power flow data for the heavy-haul railway power supply system. Finally, the server performs data cleaning, data integration, and feature extraction on this current power flow data to obtain preprocessed power flow data for the heavy-haul railway power supply system.

[0079] Step S102: Input the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and input the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0080] Among them, the physical model refers to the model built based on the basic principles of the power system (such as Kirchhoff's laws and Ohm's law).

[0081] The first predicted power flow data refers to the predicted power flow data of the heavy-haul railway power supply system obtained by predicting the preprocessed power flow data based on the completed physical model.

[0082] Among them, data-driven models refer to network models built using machine learning algorithms (such as neural networks, support vector machines, random forests, long short-term memory networks, etc.).

[0083] The second predicted power flow data refers to the predicted power flow data of the heavy-haul railway power supply system obtained by predicting the preprocessed power flow data based on the trained data-driven model.

[0084] For example, the server determines the topology, load characteristics, and component type information of the heavy-haul railway power supply system, constructs a physical model corresponding to the heavy-haul railway power supply system, and obtains the completed physical model. Then, the server determines the data type of the preprocessed power flow data and queries the correspondence between the data type and the feature extraction model to obtain the feature extraction model that matches the data type of the preprocessed power flow data, which serves as the target feature extraction model corresponding to the preprocessed power flow data. Next, the server inputs the preprocessed power flow data into the target feature extraction model for feature extraction processing to obtain the feature vector of the preprocessed power flow data. Then, the server inputs the feature vector of the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and inputs the feature vector of the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0085] Step S103: The first predicted power flow data and the second predicted power flow data are fused to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0086] Among them, the target predicted tidal flow data refers to the predicted tidal flow data obtained by fusing the first predicted tidal flow data and the second predicted tidal flow data.

[0087] For example, the server determines the prediction accuracy of the trained data-driven model and, based on the prediction accuracy of the trained data-driven model, determines the preset weights corresponding to the second predicted power flow data. Then, the server obtains the basic weights corresponding to the first predicted power flow data and normalizes the basic weights and preset weights to obtain the first weights corresponding to the first predicted power flow data and the second weights corresponding to the second predicted power flow data. Then, the server performs fusion processing on the first predicted power flow data and the second predicted power flow data according to the first weights and the second weights to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0088] Step S104: Determine the power supply assessment results of the heavy-haul railway power supply system based on the target predicted power flow data.

[0089] The power supply assessment results are used to represent the power supply capacity of the heavy-haul railway power supply system and predict potential risks, including the power supply stability, power supply efficiency information and potential risk information of the heavy-haul railway power supply system.

[0090] For example, the server determines the prediction probability of the heavy-haul railway power supply system under each candidate power supply evaluation result based on the target predicted power flow data; then, the server selects the candidate power supply evaluation result with the highest prediction probability from each candidate power supply evaluation result as the power supply evaluation result of the heavy-haul railway power supply system.

[0091] Step S105: If the power supply assessment result is the preset power supply assessment result, determine the operation parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data.

[0092] The preset power supply assessment result refers to the pre-defined power supply assessment result, such as an anomaly. It should be noted that the preset power supply assessment result depends on the specific circumstances.

[0093] Among them, the operating parameter adjustment strategy information is used to indicate the specific operation plan information for adjusting the operating parameters of the heavy-haul railway power supply system, including the adjustment target (such as reducing the voltage deviation rate from 12% to 10%), the adjustment object (such as the transformer tap), and the adjustment method (such as lowering the transformer tap by 1 level).

[0094] For example, the server judges the power supply assessment result; if the power supply assessment result is the preset power supply assessment result, the server performs feature extraction processing on the target predicted power flow data to obtain the feature vector of the target predicted power flow data, and inputs the feature vector of the target predicted power flow data into the trained operating parameter adjustment strategy information to obtain the prediction probability of the heavy-haul railway power supply system under each preset operating parameter adjustment strategy information; then, the server selects the preset operating parameter adjustment strategy information with the highest prediction probability from each preset operating parameter adjustment strategy information as the operating parameter adjustment strategy information of the heavy-haul railway power supply system.

[0095] Furthermore, if the power supply assessment result is not the preset power supply assessment result, the server maintains the current operating parameters of the heavy-haul railway power supply system.

[0096] Step S106: According to the operating parameter adjustment strategy information, adjust the current operating parameters of the heavy-haul railway power supply system accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0097] The current operating parameters refer to the operating parameters of the heavy-haul railway power supply system at the current time.

[0098] The adjusted operating parameters refer to the operating parameters obtained by adjusting the current operating parameters of the heavy-haul railway power supply system.

[0099] For example, the server generates an operating parameter adjustment instruction for the heavy-haul railway power supply system based on the operating parameter adjustment strategy information; then, the server adjusts the current operating parameters of the heavy-haul railway power supply system according to the operating parameter adjustment instruction to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0100] In the above-mentioned method for adjusting the operating parameters of a heavy-haul railway power supply system, the current power flow data of the heavy-haul railway power supply system is first acquired. This data is then preprocessed to obtain preprocessed power flow data. The preprocessed power flow data is then input into a constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system. The preprocessed power flow data is then input into a trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system. The first and second predicted power flow data are then fused to obtain the target predicted power flow data of the heavy-haul railway power supply system. Next, based on the target predicted power flow data, the power supply assessment result of the heavy-haul railway power supply system is determined. Then, if the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data. Finally, according to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system. In this way, during the adjustment of the operating parameters of the heavy-haul railway power supply system, power flow prediction is performed on the preprocessed power flow data of the heavy-haul railway power supply system by combining physical models and data-driven models, and the predicted power flow data is fused. This allows for the accurate capture of the system's operating patterns and dynamic characteristics. Based on the fused target predicted power flow data, the power supply status is assessed, and scientific strategies for adjusting operating parameters are formulated in case of anomalies. This enables intelligent optimization and adjustment of the system's operating parameters, which is beneficial to improving the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of relying on manual experience, which lacks the ability to accurately and dynamically adjust operating parameters and leads to low accuracy in adjusting the operating parameters of the heavy-haul railway power supply system. This further improves the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system.

[0101] In an exemplary embodiment, the target predicted power flow data includes at least the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information of the heavy-haul railway power supply system.

[0102] Therefore, in step S104 above, the power supply assessment result of the heavy-haul railway power supply system is determined based on the target predicted power flow data. Specifically, this includes the following: determining the power supply stability, power supply efficiency, and potential risk information of the heavy-haul railway power supply system based on the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information; and determining the power supply assessment result of the heavy-haul railway power supply system based on the power supply stability, power supply efficiency, and potential risk information.

[0103] Among them, the first predicted power flow distribution information refers to the predicted power flow distribution information of the heavy-haul railway power supply system in the future, including the distribution of parameters such as voltage, current and power of each power supply zone of the heavy-haul railway power supply system in the future.

[0104] Among them, the first predicted load change trend information refers to the load change trend information of the heavy-haul railway power supply system in the future.

[0105] The first predicted power demand information refers to the power demand information of the heavy-haul railway power supply system in the future, including the train operation plan information of the heavy-haul railway power supply system in the future.

[0106] For example, the server inputs the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information into a trained power supply stability prediction model to obtain the power supply stability of the heavy-haul railway power supply system; then, the server inputs the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information into a trained power supply efficiency information prediction model to obtain the power supply efficiency information of the heavy-haul railway power supply system; next, the server inputs the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information into a trained potential risk information prediction model to obtain the potential risk information of the heavy-haul railway power supply system; then, the server queries the correspondence between power supply stability and power supply assessment results to obtain the power supply assessment result corresponding to the power supply stability, which serves as the first power supply assessment result of the heavy-haul railway power supply system; then... The server queries the correspondence between power supply efficiency information and power supply assessment results to obtain the power supply assessment result corresponding to the power supply efficiency information, which serves as the second power supply assessment result for the heavy-haul railway power supply system. Next, the server queries the correspondence between potential risk information and power supply assessment results to obtain the power supply assessment result corresponding to the potential risk information, which serves as the third power supply assessment result for the heavy-haul railway power supply system. Then, the server determines the final power supply assessment result for the heavy-haul railway power supply system based on the first, second, and third power supply assessment results. For example, if the first, second, and third power supply assessment results are all normal, the power supply assessment result for the heavy-haul railway power supply system is normal; if the first, second, and third power supply assessment results are all normal, but the third power supply assessment result is abnormal, the power supply assessment result for the heavy-haul railway power supply system is abnormal.

[0107] In this embodiment, by fusing and analyzing multi-dimensional data such as predicted power flow distribution, load change trends, and power supply demand, a comprehensive quantitative assessment of the operating status of the power supply system of heavy-haul railways is achieved. This avoids the one-sidedness of assessment based on a single indicator, provides a scientific basis for the dynamic optimization and risk warning of the power supply system, and helps to improve the reliability of power supply assessment for heavy-haul railways.

[0108] In an exemplary embodiment, step S105 above, which determines the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data, specifically includes the following: extracting a first feature vector of the first predicted power flow distribution information, a second feature vector of the first predicted load change trend information, and a third feature vector of the first predicted power supply demand information; fusing the first feature vector, the second feature vector, and the third feature vector to obtain a fused feature vector of the heavy-haul railway power supply system; and determining the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the fused feature vector.

[0109] The first feature vector refers to the representation vector of the first predicted power flow distribution information.

[0110] The second feature vector refers to the representation vector of the first predicted load change trend information.

[0111] The third feature vector refers to the representation vector of the first predicted power demand information.

[0112] Among them, the fused feature vector refers to the feature vector obtained by fusing the first feature vector, the second feature vector, and the third feature vector.

[0113] For example, the server uses the first predicted power flow distribution information as the primary data and the first predicted load change trend information and the first predicted power demand information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a first feature vector of the first predicted power flow distribution information; then, the server uses the first predicted load change trend information as the primary data and the first predicted power flow distribution information and the first predicted power demand information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a second feature vector of the first predicted load change trend information; finally, the server uses the first predicted power demand information as the primary data and the first predicted power flow distribution information and the first predicted load change trend information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a third feature vector of the first predicted power demand information. The server then determines the first importance of the first predicted power flow distribution information and assigns a weight to the first eigenvector based on that importance. Next, the server determines the second importance of the first predicted load change trend information and assigns a weight to the second eigenvector based on that importance. Then, the server determines the third importance of the first predicted power demand information and assigns a weight to the third eigenvector based on that importance. Finally, the server sums the first, second, and third eigenvectors according to their respective weights to obtain a fused eigenvector for the heavy-haul railway power supply system. Finally, the server uses this fused eigenvector to determine the operating parameter adjustment strategy information for the heavy-haul railway power supply system.

[0114] In this embodiment, by transforming the core features of power flow distribution, load change trends and power supply demand into a unified fusion feature vector, and using this as a basis to determine the operating parameter adjustment strategy, it not only realizes the collaborative analysis of multi-source heterogeneous data, but also captures the complex dynamic characteristics of system operation by means of feature fusion, which is conducive to improving the accuracy and adaptability of power supply system parameter optimization.

[0115] In an exemplary embodiment, the operation parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the fused feature vector. Specifically, this includes: inputting the fused feature vector into a trained load balancing strategy information prediction model to obtain the load balancing strategy information of the heavy-haul railway power supply system; inputting the fused feature vector into a trained power supply adjustment strategy information prediction model to obtain the power supply adjustment strategy information of the heavy-haul railway power supply system; inputting the fused feature vector into a trained energy efficiency management strategy information prediction model to obtain the energy efficiency management strategy information of the heavy-haul railway power supply system; and using the load balancing strategy information, power supply adjustment strategy information, and energy efficiency management strategy information as the operation parameter adjustment strategy information.

[0116] Among them, the load balancing strategy information prediction model refers to a network model that can obtain the load balancing strategy information of the heavy-haul railway power supply system by using fused feature vectors, such as the random forest model.

[0117] Among them, load balancing strategy information refers to the specific load adjustment scheme of the heavy-haul railway power supply system, including the load distribution ratio adjustment suggestions between the power supply areas of the heavy-haul railway power supply system (such as load transfer between traction substations), and the load threshold setting of key equipment (such as transformers and lines).

[0118] Among them, the power supply adjustment strategy information prediction model refers to a network model that can obtain the power supply adjustment strategy information of the heavy-haul railway power supply system by using fused feature vectors, such as the long short-term memory network model.

[0119] Among them, power supply adjustment strategy information refers to the power supply system optimization scheme of the heavy-haul railway power supply system, including the dynamic adjustment parameters of the power supply voltage of the heavy-haul railway power supply system (such as the traction network voltage compensation strategy), the timing and capacity configuration of the backup power supply.

[0120] Among them, the energy efficiency processing strategy information prediction model refers to a network model that can obtain the energy efficiency processing strategy information of the heavy-haul railway power supply system by using fused feature vectors, such as a deep neural network model.

[0121] Among them, energy efficiency management strategy information refers to the energy efficiency optimization scheme of the heavy-haul railway power supply system, including suggestions for optimizing the operating efficiency of the equipment of the heavy-haul railway power supply system (such as switching the economic operation mode of transformers) and energy efficiency optimization selection of power supply paths (such as prioritizing power supply to low-loss lines).

[0122] For example, the server inputs the fused feature vector into the trained load balancing strategy information prediction model to obtain the predicted probability of the heavy-haul railway power supply system under various preset load balancing strategy information. Then, the server selects the preset load balancing strategy information with the highest predicted probability from among the preset load balancing strategy information, using it as the load balancing strategy information for the heavy-haul railway power supply system. Next, the server inputs the fused feature vector into the trained power supply adjustment strategy information prediction model to obtain the predicted probability of the heavy-haul railway power supply system under various preset power supply adjustment strategy information. Finally, the server selects the preset power supply adjustment strategy information with the highest predicted probability from among the preset power supply adjustment strategy information, using it as the load balancing strategy information for the heavy-haul railway power supply system. The server first obtains power supply adjustment strategy information; then, it inputs the fused feature vector into the trained energy efficiency management strategy information prediction model to obtain the predicted probability of the heavy-haul railway power supply system under each preset energy efficiency management strategy information. From these preset energy efficiency management strategies, the server selects the preset energy efficiency management strategy information with the highest predicted probability as the energy efficiency management strategy information for the heavy-haul railway power supply system. Next, the server determines the compatibility between the load balancing strategy information, power supply adjustment strategy information, and energy efficiency management strategy information. If the compatibility is greater than the preset compatibility, all three are used as operating parameter adjustment strategy information.

[0123] In this embodiment, three different prediction models are used to perform corresponding prediction processing based on fused feature vectors. Targeted load balancing, power supply adjustment and energy efficiency strategies can be output. This not only gives full play to the deep analysis capabilities of each model in specific fields, but also forms a complete solution covering system stability, reliability and economy through the parallel output of multiple strategies, avoiding the decision blind spots of a single strategy.

[0124] In an exemplary embodiment, step S101 above, which preprocesses the current power flow data to obtain preprocessed power flow data of the heavy-haul railway power supply system, specifically includes the following: performing data cleaning on the current power flow data to obtain cleaned power flow data of the heavy-haul railway power supply system; performing data integration on the cleaned power flow data to obtain integrated power flow data of the heavy-haul railway power supply system; determining the correlation between the integrated power flow data and preset data, and selecting integrated power flow data with a correlation greater than the preset correlation from each integrated power flow data as the preprocessed power flow data of the heavy-haul railway power supply system.

[0125] Among them, the cleaned power flow data refers to the current power flow data after data cleaning processing.

[0126] Among them, the integrated current flow data refers to the cleaned current flow data after data integration and processing.

[0127] Among them, preset data refers to characteristic data related to power flow (such as load change rate, voltage fluctuation, harmonics, etc.).

[0128] Among them, correlation refers to the degree of correlation between the integrated trend data and the preset data.

[0129] The preset correlation degree refers to a pre-set correlation degree threshold. It should be noted that the preset correlation degree depends on the situation.

[0130] For example, the server performs time-series correlation repair processing (e.g., interpolating missing data at the minute level using a neural network combined with historical data from the same period) and topological correlation repair processing on the current power flow data (e.g., calculating compensation values ​​using voltage values ​​from adjacent substations and contact network impedance models for missing voltage data at a monitoring point) to obtain cleaned power flow data for the heavy-haul railway power supply system. Then, the server performs data integration processing on the cleaned power flow data according to a preset data format and preset time series to obtain integrated power flow data for the heavy-haul railway power supply system. Next, the server inputs the integrated power flow data and preset data into a trained correlation prediction model to obtain the correlation between the integrated power flow data and the preset data. Then, the server selects integrated power flow data with a correlation greater than the preset correlation from each integrated power flow data set and uses these integrated power flow data sets as preprocessed power flow data for the heavy-haul railway power supply system.

[0131] In this embodiment, noise and outliers are removed through cleaning to ensure the accuracy of basic data. The scattered data are associated with multi-dimensional features through integration processing to enhance the data's representation ability. High-value data is screened based on correlation, so that the input of subsequent load balancing, power supply adjustment and other strategy models is more in line with actual working conditions and reduces interference from irrelevant information.

[0132] In an exemplary embodiment, the method for adjusting the operating parameters of a heavy-haul railway power supply system provided in this application further includes a training step of a trained data-driven model, specifically including the following: acquiring sample power flow data of a sample heavy-haul railway power supply system; preprocessing the sample power flow data to obtain preprocessed sample power flow data of the sample heavy-haul railway power supply system; inputting the preprocessed sample power flow data into the data-driven model to be trained to obtain predicted power flow data of the sample heavy-haul railway power supply system; the predicted power flow data of the sample heavy-haul railway power supply system includes at least the second predicted power flow distribution information, the second predicted load change trend information, and the second predicted power demand information of the sample heavy-haul railway power supply system. The process involves: acquiring actual power flow distribution information, actual load change trend information, and actual power supply demand information of the sample heavy-haul railway power supply system; obtaining a first loss value based on the difference between the second predicted power flow distribution information and the actual power flow distribution information; obtaining a second loss value based on the difference between the second predicted load change trend information and the actual load change trend information; obtaining a third loss value based on the difference between the second predicted power supply demand information and the actual power supply demand information; fusing the first, second, and third loss values ​​to obtain a target loss value; and iteratively training the data-driven model to be trained based on the target loss value to obtain the trained data-driven model.

[0133] Among them, the sample heavy-haul railway power supply system refers to the heavy-haul railway power supply system used to train the data-driven model to be trained.

[0134] Among them, sample power flow data refers to power flow data used to train the data-driven model to be trained.

[0135] Among them, preprocessed sample power flow data refers to sample power flow data after preprocessing.

[0136] Among them, the predicted power flow data of the sample heavy-haul railway power supply system is used to represent the prediction results output by the data-driven model to be trained based on the preprocessed sample data.

[0137] The second predicted power flow distribution information refers to the predicted power flow distribution information of the sample heavy-haul railway power supply system in the future, including the distribution of parameters such as voltage, current, and power of each power supply zone of the sample heavy-haul railway power supply system in the future.

[0138] The second predicted load change trend information refers to the load change trend information of the sample heavy-haul railway power supply system in the future.

[0139] The second predicted power demand information refers to the power demand information of the sample heavy-haul railway power supply system in the future, including the train operation plan information of the sample heavy-haul railway power supply system in the future.

[0140] Among them, the actual power flow distribution information refers to the true value of the power flow distribution information of the sample heavy-haul railway power supply system in the future period of time.

[0141] Among them, the actual load change trend information refers to the true value of the load change trend information of the sample heavy-haul railway power supply system in the future period of time.

[0142] Among them, actual power supply demand information refers to the true value of power supply demand information of the sample heavy-haul railway power supply system in the future period of time.

[0143] The first loss value refers to the loss value obtained based on the difference between the second predicted power flow distribution information and the actual power flow distribution information.

[0144] The second loss value refers to the loss value obtained based on the difference between the second predicted load change trend information and the actual load change trend information.

[0145] The third loss value refers to the loss value obtained based on the difference between the second predicted power demand information and the actual power demand information.

[0146] The target loss value refers to the loss value obtained by fusing the first loss value, the second loss value, and the third loss value.

[0147] For example, in response to a model training instruction for a data-driven model to be trained, the server obtains sample power flow data of a sample heavy-haul railway power supply system from the data, and preprocesses the sample power flow data to obtain preprocessed sample power flow data of the sample heavy-haul railway power supply system; then, the server inputs the preprocessed sample power flow data into the data-driven model to be trained to obtain predicted power flow data of the sample heavy-haul railway power supply system; wherein, the predicted power flow data of the sample heavy-haul railway power supply system includes at least the second predicted power flow distribution information, the second predicted load change trend information, and the second predicted power demand information of the sample heavy-haul railway power supply system; then, the server obtains the actual power flow distribution information, the actual load change trend information, and the actual power demand information of the sample heavy-haul railway power supply system; then, the server, according to the... The server calculates a first loss value based on the difference between the predicted power flow distribution information and the actual power flow distribution information. A second loss value is calculated based on the difference between the predicted load change trend information and the actual load change trend information. A third loss value is calculated based on the difference between the predicted power demand information and the actual power demand information. The server then fuses these three loss values ​​to obtain a target loss value. Next, the server adjusts the model parameters of the data-driven model to be trained based on the target loss value. The server then retrains the data-driven model with adjusted parameters until the target loss value obtained by the trained data-driven model is less than the loss value threshold. Training then stops, and this trained data-driven model is considered the completed data-driven model.

[0148] In this embodiment, by pre-training the data-driven model, it is convenient to predict the future power flow data of the heavy-haul railway power supply system after obtaining the pre-processed power flow data of the heavy-haul railway power supply system in practical applications. Moreover, the data-driven model receives new data in each iteration, and performs internal model improvement and optimization, which makes it easier to make predictions more effectively and improves the prediction accuracy of the data-driven model.

[0149] In one exemplary embodiment, such as Figure 2 As shown, another method for adjusting the operating parameters of a heavy-haul railway power supply system is provided. Taking the application of this method to a server as an example, the specific steps include:

[0150] Step S201: Obtain the current power flow data of the heavy-haul railway power supply system.

[0151] Step S202: Perform data cleaning on the current power flow data to obtain cleaned power flow data of the heavy-haul railway power supply system; perform data integration on the cleaned power flow data to obtain integrated power flow data of the heavy-haul railway power supply system.

[0152] Step S203: Determine the correlation between the integrated power flow data and the preset data, and select the integrated power flow data with a correlation greater than the preset correlation from each integrated power flow data as the preprocessed power flow data of the heavy-haul railway power supply system.

[0153] Step S204: Input the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and input the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0154] Step S205: The first predicted power flow data and the second predicted power flow data are fused to obtain the target predicted power flow data of the heavy-haul railway power supply system; the target predicted power flow data includes at least the first predicted power flow distribution information, the first predicted load change trend information and the first predicted power supply demand information of the heavy-haul railway power supply system.

[0155] Step S206: Based on the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information, determine the power supply stability, power supply efficiency, and potential risk information of the heavy-haul railway power supply system; based on the power supply stability, power supply efficiency, and potential risk information, determine the power supply assessment result of the heavy-haul railway power supply system.

[0156] Step S207: Extract the first feature vector of the first predicted power flow distribution information, the second feature vector of the first predicted load change trend information, and the third feature vector of the first predicted power supply demand information.

[0157] Step S208: The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector of the heavy-haul railway power supply system.

[0158] Step S209: Input the fused feature vector into the trained load balancing strategy information prediction model to obtain the load balancing strategy information of the heavy-haul railway power supply system; input the fused feature vector into the trained power supply adjustment strategy information prediction model to obtain the power supply adjustment strategy information of the heavy-haul railway power supply system; input the fused feature vector into the trained energy efficiency processing strategy information prediction model to obtain the energy efficiency processing strategy information of the heavy-haul railway power supply system.

[0159] Step S210: The load balancing strategy information, power supply adjustment strategy information, and energy efficiency processing strategy information are all used as operating parameter adjustment strategy information.

[0160] Step S211: According to the operating parameter adjustment strategy information, adjust the current operating parameters of the heavy-haul railway power supply system accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0161] In the aforementioned method for adjusting the operating parameters of a heavy-haul railway power supply system, during the adjustment process, power flow prediction is performed on the preprocessed power flow data of the heavy-haul railway power supply system by combining physical models and data-driven models. The predicted power flow data is then fused, thereby accurately capturing the system's operating patterns and dynamic characteristics. Based on the fused target predicted power flow data, the power supply status is assessed, and a scientific strategy for adjusting operating parameters is formulated in case of anomalies. This achieves intelligent optimization and adjustment of the system's operating parameters, improving the accuracy of the adjustment. Furthermore, the entire process requires no manual intervention, avoiding the shortcomings of relying on manual experience, which lacks the ability to accurately and dynamically adjust operating parameters, resulting in low accuracy in adjusting the operating parameters of the heavy-haul railway power supply system. This further improves the accuracy of the adjustment of the operating parameters of the heavy-haul railway power supply system.

[0162] In an exemplary embodiment, to more clearly illustrate the method for adjusting the operating parameters of a heavy-haul railway power supply system provided in this application, the following specific embodiment will be used to describe the method in detail. In one embodiment, this application also provides a method for predicting, evaluating, and intelligently managing the power flow of a heavy-haul railway based on digital model-driven approaches. Specifically, it includes the following:

[0163] 1. Data acquisition mainly includes real-time data collected from SCADA systems and sensors at key nodes, as well as recorded historical data.

[0164] (1) SCADA system: Real-time acquisition of data such as voltage, current, and power.

[0165] (2) Sensor network: monitors the operating status of equipment such as overhead contact lines, substations, and power supply zones.

[0166] (3) Historical data: including train operation plans, load changes, etc.

[0167] 2. Data preprocessing, including data cleaning, data integration, and feature extraction.

[0168] (1) Data cleaning: Remove data noise, outliers and missing values.

[0169] (2) Data integration: Integrate multi-source data in a unified format and time series.

[0170] (3) Feature extraction: Extract feature data related to power flow (such as load change rate, voltage fluctuation, harmonics, etc.).

[0171] 3. Predictive model building: learning patterns from historical and real-time data.

[0172] (1) Physical model: Based on the basic principles of power systems (such as Kirchhoff's laws and Ohm's law), a model is constructed to describe the distribution and variation of power flow.

[0173] (2) Data-driven model: Using machine learning algorithms (such as neural networks, support vector machines, random forests, long short-term memory networks, etc.) to learn complex nonlinear relationships from historical data to predict future power flow.

[0174] (3) Hybrid model: Combining the advantages of physical model and data-driven model, the physical model provides theoretical constraints, and the data-driven model performs refined predictions to improve prediction accuracy.

[0175] 4. Power flow forecasting: Predicting future power flow distribution, load change trends, and power supply demand.

[0176] (1) Power flow distribution: Predict the distribution of parameters such as voltage, current and power in each power supply zone.

[0177] (2) Load change trend: Predict the load change trend in the future and identify potential overload risks.

[0178] (3) Power supply demand: Based on train operation plans and historical data, predict changes in the power supply system demand.

[0179] 5. Power supply capacity assessment: Assess the system's power supply capacity and predict potential risks.

[0180] (1) Power supply stability: Evaluate indicators such as voltage fluctuation, frequency deviation, and harmonics.

[0181] (2) Power supply efficiency: Evaluate indicators such as power loss and load balance.

[0182] (3) Potential risks: assess indicators such as overload risk, voltage exceeding standard, and vehicle-network instability.

[0183] 6. Intelligent management and control: Through automated and intelligent control strategies, the operating status of the power supply system is optimized, and the stability, efficiency and security of the system are improved.

[0184] (1) Dynamically adjust the power supply strategy: Based on the prediction results and evaluation results, optimize the distribution of power flow and the operating status of the power supply system.

[0185] (2) Risk warning and fault prevention: Through real-time monitoring and data analysis, potential risks can be identified in advance and preventive measures can be taken to reduce the possibility of faults.

[0186] (3) Automated interlocking control: realize the interlocking control of the signal system and the power system, ensure the consistency of train operation and power supply status, ensure the coordination of train operation and power supply status, and improve operating efficiency.

[0187] 7. Results feedback.

[0188] (1) Visualization: Key indicators and operating status are displayed through tools such as dashboards and reports.

[0189] (2) Decision support: Feedback the results of prediction, evaluation and intelligent management to the dispatchers and operation and maintenance team to support decision making.

[0190] 8. Continuously improve to better adapt to complex operating environments, increase operating efficiency, reduce the occurrence of failures, and provide strong support for the safe and efficient operation of heavy-haul railways.

[0191] (1) Parameter optimization: Adjust the operating parameters of the power supply system to optimize the distribution of power flow and power supply efficiency.

[0192] (2) Model optimization: Based on actual operating data and feedback results, continuously optimize the prediction model and evaluation method.

[0193] (3) Algorithm update: Improve prediction accuracy and evaluation effect through the self-learning ability of machine learning algorithms.

[0194] (4) Operation strategy optimization: Optimize the operation strategy of the power supply system to improve the flexibility and adaptability of the system.

[0195] (5) Risk control optimization: Optimize risk control strategies (load balancing and dynamic power supply adjustment strategies) to avoid local overload, and detect potential faults in advance by monitoring equipment status and predictive maintenance, thereby reducing the occurrence rate of equipment failures and reducing potential risks to the power supply system.

[0196] (6) Energy efficiency management optimization: Regularly assess the energy efficiency level of the power supply system, identify areas for improvement, optimize energy efficiency management strategies, and improve the energy utilization efficiency of the power supply system.

[0197] In the above embodiments, during the adjustment of the operating parameters of the heavy-haul railway power supply system, power flow prediction is performed on the preprocessed power flow data of the heavy-haul railway power supply system by combining physical models and data-driven models, and the predicted power flow data is fused. This allows for the accurate capture of the system's operating patterns and dynamic characteristics. Based on the fused target predicted power flow data, the power supply status is assessed, and a scientific strategy for adjusting operating parameters is formulated in case of anomalies. This enables intelligent optimization and adjustment of the system's operating parameters, which is beneficial for improving the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of relying on manual experience, which lacks the ability to accurately and dynamically adjust operating parameters and leads to low accuracy in adjusting the operating parameters of the heavy-haul railway power supply system. This further improves the accuracy of adjusting the operating parameters of the heavy-haul railway power supply system.

[0198] It should be understood that although the steps in the flowcharts of the above embodiments 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 above embodiments 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.

[0199] Based on the same inventive concept, this application also provides an operating parameter adjustment device for a heavy-haul railway power supply system for implementing the above-mentioned method for adjusting operating parameters of a heavy-haul railway power supply system. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the operating parameter adjustment device for a heavy-haul railway power supply system provided below can be found in the limitations of the operating parameter adjustment method for a heavy-haul railway power supply system described above, and will not be repeated here.

[0200] In one exemplary embodiment, such as Figure 4 As shown, a device for adjusting operating parameters of a heavy-haul railway power supply system is provided, comprising: a data processing module 401, a data prediction module 402, a data fusion module 403, a result determination module 404, a strategy determination module 405, and a parameter adjustment module 406, wherein:

[0201] The data processing module 401 is used to acquire the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system.

[0202] The data prediction module 402 is used to input the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and to input the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system.

[0203] The data fusion module 403 is used to fuse the first predicted power flow data and the second predicted power flow data to obtain the target predicted power flow data of the heavy-haul railway power supply system.

[0204] The result determination module 404 is used to determine the power supply assessment results of the heavy-haul railway power supply system based on the target predicted power flow data.

[0205] The strategy determination module 405 is used to determine the operation parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data, when the power supply assessment result is the preset power supply assessment result.

[0206] The parameter adjustment module 406 is used to adjust the current operating parameters of the heavy-haul railway power supply system according to the operating parameter adjustment strategy information, so as to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

[0207] In an exemplary embodiment, the result determination module 404 is further configured to determine the power supply stability, power supply efficiency, and potential risk information of the heavy-haul railway power supply system based on the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information; and to determine the power supply assessment result of the heavy-haul railway power supply system based on the power supply stability, power supply efficiency, and potential risk information.

[0208] In an exemplary embodiment, the strategy determination module 405 is further configured to extract a first feature vector of the first predicted power flow distribution information, a second feature vector of the first predicted load change trend information, and a third feature vector of the first predicted power supply demand information; perform fusion processing on the first feature vector, the second feature vector, and the third feature vector to obtain a fused feature vector of the heavy-haul railway power supply system; and determine the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the fused feature vector.

[0209] In an exemplary embodiment, the strategy determination module 405 is further configured to input the fused feature vector into the trained load balancing strategy information prediction model to obtain load balancing strategy information of the heavy-haul railway power supply system; input the fused feature vector into the trained power supply adjustment strategy information prediction model to obtain power supply adjustment strategy information of the heavy-haul railway power supply system; input the fused feature vector into the trained energy efficiency processing strategy information prediction model to obtain energy efficiency processing strategy information of the heavy-haul railway power supply system; and use the load balancing strategy information, power supply adjustment strategy information, and energy efficiency processing strategy information as operating parameter adjustment strategy information.

[0210] In an exemplary embodiment, the data processing module 401 is further configured to perform data cleaning on the current power flow data to obtain cleaned power flow data of the heavy-haul railway power supply system; perform data integration on the cleaned power flow data to obtain integrated power flow data of the heavy-haul railway power supply system; determine the correlation between the integrated power flow data and preset data, and select integrated power flow data with a correlation greater than the preset correlation from each integrated power flow data as preprocessed power flow data of the heavy-haul railway power supply system.

[0211] In an exemplary embodiment, the operating parameter adjustment device for the heavy-haul railway power supply system further includes a model training module, used to acquire sample power flow data of the sample heavy-haul railway power supply system, preprocess the sample power flow data to obtain preprocessed sample power flow data of the sample heavy-haul railway power supply system; input the preprocessed sample power flow data into the data-driven model to be trained to obtain predicted power flow data of the sample heavy-haul railway power supply system; the predicted power flow data of the sample heavy-haul railway power supply system includes at least the second predicted power flow distribution information, the second predicted load change trend information, and the second predicted power supply demand information of the sample heavy-haul railway power supply system; acquire sample heavy-haul railway power flow data... The system obtains the actual power flow distribution information, actual load change trend information, and actual power supply demand information of the power system; based on the difference between the second predicted power flow distribution information and the actual power flow distribution information, a first loss value is obtained; based on the difference between the second predicted load change trend information and the actual load change trend information, a second loss value is obtained; and based on the difference between the second predicted power supply demand information and the actual power supply demand information, a third loss value is obtained; the first loss value, the second loss value, and the third loss value are fused to obtain the target loss value; based on the target loss value, the data-driven model to be trained is iteratively trained to obtain the trained data-driven model.

[0212] Each module in the aforementioned operating parameter adjustment device for the heavy-haul railway 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.

[0213] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As 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 stored in the non-volatile storage media. The database stores current power flow data, predicted power flow data, etc. The I / O interfaces are used for exchanging information 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 adjusting the operating parameters of a heavy-haul railway power supply system.

[0214] Those skilled in the art will understand that Figure 5 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.

[0215] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0216] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0217] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0218] Those skilled in the art will understand that all or part of the processes in 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. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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, etc., and are not limited to these.

[0219] 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 specification.

[0220] 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 adjusting operating parameters of a heavy-haul railway power supply system, characterized in that, The method includes: Obtain the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system. The preprocessed power flow data is input into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and the preprocessed power flow data is input into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system. The first predicted power flow data and the second predicted power flow data are fused together to obtain the target predicted power flow data of the heavy-haul railway power supply system. Based on the target predicted power flow data, the power supply assessment results of the heavy-haul railway power supply system are determined; If the power supply assessment result is the preset power supply assessment result, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined based on the target predicted power flow data. According to the operating parameter adjustment strategy information, the current operating parameters of the heavy-haul railway power supply system are adjusted accordingly to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

2. The method according to claim 1, characterized in that, The target predicted power flow data includes at least the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power demand information of the heavy-haul railway power supply system. The step of determining the power supply assessment result of the heavy-haul railway power supply system based on the target predicted power flow data includes: Based on the first predicted power flow distribution information, the first predicted load change trend information, and the first predicted power supply demand information, the power supply stability, power supply efficiency information, and potential risk information of the heavy-haul railway power supply system are determined. Based on the power supply stability, power supply efficiency information, and potential risk information, the power supply assessment results of the heavy-haul railway power supply system are determined.

3. The method according to claim 2, characterized in that, The step of determining the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data includes: Extract the first feature vector of the first predicted power flow distribution information, the second feature vector of the first predicted load change trend information, and the third feature vector of the first predicted power demand information; The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector of the heavy-haul railway power supply system. Based on the fused feature vector, the operating parameter adjustment strategy information of the heavy-haul railway power supply system is determined.

4. The method according to claim 3, characterized in that, The step of determining the operating parameter adjustment strategy information of the heavy-haul railway power supply system based on the fused feature vector includes: The fused feature vector is input into the trained load balancing strategy information prediction model to obtain the load balancing strategy information of the heavy-haul railway power supply system. The fused feature vector is input into the trained power supply adjustment strategy information prediction model to obtain the power supply adjustment strategy information of the heavy-haul railway power supply system. The fused feature vector is input into the trained energy efficiency processing strategy information prediction model to obtain the energy efficiency processing strategy information of the heavy-haul railway power supply system. The load balancing strategy information, the power supply adjustment strategy information, and the energy efficiency processing strategy information are all used as the operating parameter adjustment strategy information.

5. The method according to claim 1, characterized in that, The preprocessing of the current power flow data to obtain the preprocessed power flow data of the heavy-haul railway power supply system includes: The current power flow data is cleaned to obtain the cleaned power flow data of the heavy-haul railway power supply system. The cleaned power flow data is integrated to obtain the integrated power flow data of the heavy-haul railway power supply system. The correlation between the integrated power flow data and the preset data is determined, and the integrated power flow data with a correlation greater than the preset correlation is selected from each of the integrated power flow data as the preprocessed power flow data of the heavy-haul railway power supply system.

6. The method according to any one of claims 1 to 5, characterized in that, The trained data-driven model was obtained through the following method: Obtain sample power flow data of the sample heavy-haul railway power supply system, and preprocess the sample power flow data to obtain preprocessed sample power flow data of the sample heavy-haul railway power supply system. The preprocessed sample power flow data is input into the data-driven model to be trained to obtain the predicted power flow data of the sample heavy-haul railway power supply system; the predicted power flow data of the sample heavy-haul railway power supply system includes at least the second predicted power flow distribution information, the second predicted load change trend information and the second predicted power demand information of the sample heavy-haul railway power supply system. Obtain the actual power flow distribution information, actual load change trend information, and actual power supply demand information of the sample heavy-haul railway power supply system; A first loss value is obtained based on the difference between the second predicted power flow distribution information and the actual power flow distribution information; a second loss value is obtained based on the difference between the second predicted load change trend information and the actual load change trend information; and a third loss value is obtained based on the difference between the second predicted power demand information and the actual power demand information. The first loss value, the second loss value, and the third loss value are fused together to obtain the target loss value; Based on the target loss value, the data-driven model to be trained is iteratively trained to obtain the trained data-driven model.

7. A device for adjusting operating parameters of a heavy-haul railway power supply system, characterized in that, The device includes: The data processing module is used to acquire the current power flow data of the heavy-haul railway power supply system, preprocess the current power flow data, and obtain the preprocessed power flow data of the heavy-haul railway power supply system. The data prediction module is used to input the preprocessed power flow data into the constructed physical model to obtain the first predicted power flow data of the heavy-haul railway power supply system, and to input the preprocessed power flow data into the trained data-driven model to obtain the second predicted power flow data of the heavy-haul railway power supply system. The data fusion module is used to fuse the first predicted power flow data and the second predicted power flow data to obtain the target predicted power flow data of the heavy-haul railway power supply system. The result determination module is used to determine the power supply assessment result of the heavy-haul railway power supply system based on the target predicted power flow data. The strategy determination module is used to determine the operation parameter adjustment strategy information of the heavy-haul railway power supply system based on the target predicted power flow data when the power supply assessment result is the preset power supply assessment result. The parameter adjustment module is used to adjust the current operating parameters of the heavy-haul railway power supply system according to the operating parameter adjustment strategy information, so as to obtain the adjusted operating parameters of the heavy-haul railway power supply system.

8. 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 6.

9. 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 6.

10. 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 6.

Images