Bidirectional converter equipment control method based on train operation state information

Abstract

The invention discloses a bidirectional converter equipment control method based on train operation state information, and relates to the technical field of train operation control, the train operation state information and the current position data of a train are acquired in real time and uploaded to a central server for load calculation, and the total load of a power supply interval is obtained. And according to the total load of the power supply section, the working condition of the train in the power supply section is judged, and meanwhile, the working mode of the bidirectional converter equipment is dynamically adjusted based on the total load of the power supply section. And training and building a bidirectional converter equipment control parallel channel based on the train working condition and the working mode of the power supply interval, performing control parameter analysis on the total load of the power supply interval to obtain a bidirectional converter equipment control strategy parameter, and performing power supply cooperative closed-loop control based on the bidirectional converter equipment control strategy parameter. The technical problems of low electric energy recovery rate and poor harmonic suppression capability of a power grid in the actual operation process of bidirectional converter equipment in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field related to train operation control, and in particular to a method for controlling bidirectional converter equipment based on train operation status information. Background Art

[0002] In modern rail transit systems, train energy management and power system stability are crucial. Bidirectional converters play a key role in the train's traction and braking processes. During traction, the converters convert AC power from the grid into DC power required by the train through rectification. During braking, the regenerative energy generated during braking is absorbed by the converters and converted into electrical energy that is fed back to the grid. Traditional methods use fixed thresholds to determine power supply conditions, resulting in insufficient regenerative braking energy feedback efficiency and weak grid harmonic suppression capabilities.

[0003] Therefore, in the existing technology, during actual operation, it is difficult for bidirectional converter equipment to efficiently and dynamically adjust the working mode and control strategy according to the real-time operating status of the train, the total load of the power supply section, and the harmonic conditions of the power grid, resulting in technical problems such as low energy recovery rate and poor power grid harmonic suppression capability. Summary of the Invention

[0004] This application provides a bidirectional converter device control method based on train operation status information, solving the technical problem in the prior art that bidirectional converter devices, during actual operation, have difficulty efficiently and dynamically adjusting their operating modes and control strategies based on the real-time train operation status, the total load of the power supply section, and the harmonic conditions of the power grid, resulting in low power recovery rates and poor power grid harmonic suppression capabilities. This bidirectional converter device control method based on train operation status information enables real-time adjustment of the device's operating mode and power feedback strategy, which not only improves the stability and efficiency of train operation, but also optimizes power grid load distribution, reduces power grid harmonics, and improves the overall power system's operating quality.

[0005] The present application provides a bidirectional converter device control method based on train operation status information, the method comprising: real-time acquisition of train operation status information and train current position data, uploading the train operation status information and train current position data to a central server for load calculation to obtain the total load of the power supply section; determining the train operating condition of the power supply section based on the total load of the power supply section, the train operating condition of the power supply section including traction and braking, and dynamically adjusting the working mode of the bidirectional converter device based on the total load of the power supply section, the working mode including rectification and inversion; training and building a bidirectional converter device control parallel channel based on the train operating condition and the working mode of the power supply section, the bidirectional converter device control parallel channel including a traction rectification control strategy channel and a braking inversion control strategy channel; using the bidirectional converter device control parallel channel to perform control parameter analysis on the total load of the power supply section to obtain bidirectional converter device control strategy parameters, and performing power supply collaborative closed-loop control based on the bidirectional converter device control strategy parameters.

[0006] In the implementation method, the real-time collection and acquisition of train operation status information and train current position data includes: installing and deploying a sensor group on the train according to the train operation requirements, and collecting and acquiring the train operation status information in real time through the sensor group; obtaining a train positioning link set, and the train positioning link set includes GPS positioning technology, CBTC system and wireless communication technology; performing a criticality assessment on each positioning link in the train positioning link set to obtain a positioning link criticality coefficient set; using the train positioning link set to collect and acquire a train position set, and performing weighted fusion on the train position set based on the positioning link criticality coefficient set to obtain the train current position data.

[0007] In the implementation method, uploading the train operation status information and the train current position data to the central server includes: obtaining data transmission requirement factors, the data transmission requirement factors including transmission rate, transmission distance and data sensitivity; using the data transmission requirement factors to perform multi-dimensional analysis on the train operation status information and the train current position data to obtain data transmission requirement factor parameters; configuring a data wireless transmission line according to the data transmission requirement factor parameters; and uploading the train operation status information and the train current position data to the central server based on the data wireless transmission line.

[0008] In the implementation method, obtaining the total load of the power supply section includes: determining the train distribution power supply section based on the current position data of the train; dividing and integrating the train operation status information according to the train distribution power supply section to obtain the power supply section train operation status set; calling the target load calculation model through the central server, and calculating the load demand of the power supply section train operation status set based on the target load calculation model to obtain the train real-time power load set; accumulating the train real-time power load set to obtain the total load of the power supply section.

[0009] In the implementation method, calling the target load calculation model through the central server includes: obtaining a set of load-related factors, wherein the set of load-related factors includes train operation status, train characteristic parameters, line condition parameters and environmental factors; collecting historical data based on the set of load-related factors to obtain a train-related factor load historical data set; performing regression fitting processing on the train-related factor load historical data set to obtain an initial load calculation model; verifying and optimizing the initial load calculation model to obtain a target load calculation model and storing it in the central server.

[0010] In the implementation method, the training to build a bidirectional converter device control parallel channel includes: determining the traction rectifier control strategy and the braking inverter control strategy based on the train operating conditions in the power supply section and the working mode; performing bidirectional converter device control data mining based on the traction rectifier control strategy and the braking inverter control strategy to obtain a traction rectifier control strategy data set and a braking inverter control strategy data set; performing feature identification training on the traction rectifier control strategy data set and the braking inverter control strategy data set respectively to obtain a traction rectifier control strategy channel and a braking inverter control strategy channel; integrating the traction rectifier control strategy channel and the braking inverter control strategy channel to build the bidirectional converter device control parallel channel.

[0011] In the implementation method, the obtaining of the traction rectifier control strategy channel and the braking inverter control strategy channel includes: obtaining a set of bidirectional converter device control effect indicators, using the bidirectional converter device control effect indicator set to evaluate the effects of the traction rectifier control strategy data set and the braking inverter control strategy data set to obtain a bidirectional converter device control data effect set; screening the traction rectifier control strategy data set and the braking inverter control strategy data set based on the bidirectional converter device control data effect set to obtain a target traction rectifier control strategy data set and a target braking inverter control strategy data set; performing feature identification training on the target traction rectifier control strategy data set and the target braking inverter control strategy data set respectively to obtain a traction rectifier control strategy channel and a braking inverter control strategy channel.

[0012] In the implementation method, the obtaining of the traction rectifier control strategy channel and the braking inverter control strategy channel includes: selecting a traction rectifier deep learning network and a braking inverter deep learning network according to data characteristic information of the target traction rectifier control strategy data set and the target braking inverter control strategy data set; performing feature dimensionality reduction and identification processing on the target traction rectifier control strategy data set and the target braking inverter control strategy data set to obtain a traction rectifier control strategy sample set and a braking inverter control strategy sample set; using the traction rectifier deep learning network and the braking inverter deep learning network to perform control training on the traction rectifier control strategy sample set and the braking inverter control strategy sample set respectively to obtain the traction rectifier control strategy channel and the braking inverter control strategy channel.

[0013] In the implementation method, the power supply coordinated closed-loop control based on the bidirectional converter device control strategy parameters includes: performing train power supply coordinated control based on the bidirectional converter device control strategy parameters to obtain train power supply feedback state parameters; performing regulation and optimization analysis on the bidirectional converter device control strategy parameters through the train power supply feedback state parameters to determine parameter fine-tuning variables; using the parameter fine-tuning variables to fine-tune and update the bidirectional converter device control strategy parameters, and performing power supply coordinated closed-loop control through the updated bidirectional converter device control strategy parameters.

[0014] In the implementation, the method further includes: real-time monitoring of power grid harmonic status information, suppression analysis of the power grid harmonic status information, and obtaining harmonic suppression strategy parameters; and collaborative additional correction of the bidirectional converter control strategy parameters based on the harmonic suppression strategy parameters.

[0015] The bidirectional converter device control method based on train operation status information proposed in this application is intended to obtain train operation status information and train current position data through real-time collection, upload the train operation status information and train current position data to the central server for load calculation, and obtain the total load of the power supply section; according to the total load of the power supply section, the train operating condition of the power supply section is determined, and the train operating condition of the power supply section includes traction and braking. At the same time, based on the total load of the power supply section, the working mode of the bidirectional converter device is dynamically adjusted, and the working mode includes rectification and inversion; based on the train operating condition and the working mode of the power supply section, a bidirectional converter device control parallel channel is trained and constructed, and the bidirectional converter device control parallel channel includes a traction rectification control strategy channel and a braking inversion control strategy channel; the bidirectional converter device control parallel channel is used to perform control parameter analysis on the total load of the power supply section to obtain the bidirectional converter device control strategy parameters, and power supply collaborative closed-loop control is performed based on the bidirectional converter device control strategy parameters. This solves the technical problem in existing technologies where bidirectional converter equipment, during actual operation, struggles to efficiently and dynamically adjust its operating mode and control strategy based on the train's real-time operating status, the total load in the power supply section, and the grid's harmonics, resulting in low energy recovery rates and poor grid harmonic suppression. This bidirectional converter equipment control method, based on train operating status information, enables real-time adjustment of the equipment's operating mode and energy feedback strategy, improving not only the stability and efficiency of train operation but also optimizing grid load distribution, reducing grid harmonics, and enhancing the overall operational quality of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of a bidirectional converter device control method based on train operation status information provided in an embodiment of the present application;

[0018] Figure 2 A flow chart of a bidirectional converter device control method for obtaining the current position data of a train based on train operation status information provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0022] The embodiment of the present application provides a bidirectional converter device control method based on train running status information, such as Figure 1 As shown, the method includes:

[0023] The train operation status information and the train current position data are collected and acquired in real time, and the train operation status information and the train current position data are uploaded to the central server for load calculation to obtain the total load of the power supply section; based on the total load of the power supply section, the train operating conditions of the power supply section are determined, and the train operating conditions of the power supply section include traction and braking; at the same time, based on the total load of the power supply section, the working mode of the bidirectional converter equipment is dynamically adjusted, and the working mode includes rectification and inversion.

[0024] During train operation, sensors installed on the train collect real-time train operating status information, including traction status, braking status, and operating speed. The train's current position data is also located via a train positioning link. Furthermore, this train operating status information and current position data are uploaded to a central server to calculate the load of the train's current power supply section and obtain total load data for the current power supply section. The central server uses the transmitted train position data to determine the power supply section in which the train is located. Subsequently, the load data corresponding to each train is obtained based on the total load of the power supply section, thereby determining the train operating condition within the power supply section. The power supply section train operating conditions include traction and braking. In traction mode, the bidirectional converter operates in rectification mode, converting grid power into power required for train traction. In braking mode, the regenerative energy generated by the train's braking is absorbed by the bidirectional converter, converted into electrical energy, and fed back to the grid. Simultaneously, the bidirectional converter's operating mode is dynamically adjusted based on the total load of the power supply section. These operating modes include rectification and inversion. In the inversion mode, an inverter control strategy is designed specifically for braking conditions to ensure efficient feedback of braking energy to the grid. The rectification working mode optimizes the control strategy for traction conditions to ensure stable power demand during train traction.

[0025] like Figure 2 As shown, the method provided in the embodiment of the present application also includes: installing and deploying a sensor group on the train according to the train operation requirements, and acquiring the train operation status information in real time through the sensor group; acquiring a train positioning link set, the train positioning link set including GPS positioning technology, CBTC system and wireless communication technology; performing a criticality assessment on each positioning link in the train positioning link set to obtain a positioning link criticality coefficient set; utilizing the train positioning link set to acquire a train position set, performing weighted fusion on the train position set based on the positioning link criticality coefficient set, and acquiring the train current position data.

[0026] The real-time acquisition of train operating status information and current train location data includes: installing a sensor group on the train according to train operating requirements. The sensor group consists of multiple sensors, such as speed sensors, acceleration sensors, and current sensors. The sensor group collects real-time train operating status information, including the train's traction status, braking status, and operating speed. Subsequently, a train positioning link set is acquired. The train positioning link set includes GPS positioning technology, a CBTC system, and wireless communication technology. GPS positioning technology uses satellite signals to determine the train's latitude and longitude. The CBTC system uses wireless communication between the ground and the train to acquire the train's location in real time and can operate normally even in environments without GPS signals. Wireless communication technology exchanges location information between the train and the ground via wireless communication links, thereby enhancing positioning accuracy. A criticality assessment is performed on each positioning link in the train positioning link set to determine the accuracy of each positioning method in different scenarios. Based on the accuracy of each positioning method in different scenarios, a weight coefficient for the corresponding scenario is determined. The weight coefficient for each positioning method across all scenarios is averaged to obtain a positioning link criticality coefficient set. Finally, the train position set is acquired by using the train positioning link set, and the train position set is weightedly fused based on the positioning link critical coefficient set, that is, the train positions collected by each method are weighted summed up to obtain the current train position data.

[0027] The method provided in an embodiment of the present application also includes: obtaining data transmission requirement factors, the data transmission requirement factors including transmission rate, transmission distance and data sensitivity; using the data transmission requirement factors to perform multi-dimensional analysis on the train operation status information and the train current position data to obtain data transmission requirement factor parameters; configuring a data wireless transmission line according to the data transmission requirement factor parameters; and uploading the train operation status information and the train current position data to a central server based on the data wireless transmission line.

[0028] Uploading the train operation status information and the train's current position data to the central server includes obtaining data transmission requirement factors, including transmission rate, transmission distance, and data sensitivity. The transmission rate is the speed of data transmission. The transmission distance is the distance between the train and the ground wireless communication base station. Data sensitivity refers to the importance and sensitivity of the train operation status data. For example, data such as the train's traction current and voltage are directly related to the train's operational safety and stability. Therefore, the transmission of this data has higher requirements, requiring low latency and high accuracy. Different data categories are preset with corresponding data sensitivities. Higher data sensitivities correspond to higher importance and sensitivity, and higher transmission accuracy requirements. Subsequently, the data transmission requirement factors are used to perform a multi-dimensional analysis of the train operation status information and the train's current position data. Specifically, the optimal transmission rate is matched based on the train operation status information, the actual transmission distance is determined based on the train's current position data, and the corresponding transmission mode, such as encrypted transmission or standard transmission, is determined based on the data sensitivity corresponding to each data category in the train operation status information and the train's current position data. Different data sensitivities correspond to different transmission modes. After completing the multi-dimensional analysis, the parameters of the data transmission requirement factors are obtained. According to the data transmission requirement factor parameters, a data wireless transmission line that matches the data transmission requirement factor parameters is configured, and then the train operation status information and the train current position data are uploaded to the central server based on the data wireless transmission line.

[0029] The method provided in the embodiment of the present application also includes: determining the train distribution power supply section based on the current position data of the train; dividing and integrating the train operation status information according to the train distribution power supply section to obtain a power supply section train operation status set; calling the target load calculation model through the central server, and calculating the load demand of the power supply section train operation status set based on the target load calculation model to obtain a real-time power load set of the train; and accumulating the real-time power load set of the train to obtain a total load of the power supply section.

[0030] The method of obtaining the total load of the power supply section includes: determining the power supply section where the train is located based on the current position data of the train. The power supply section refers to the area in the power system that is responsible for providing electric energy to the train. Furthermore, the train operation status information is divided and integrated according to the power supply sections where the trains are distributed, and all trains in the same power supply section are integrated together, thereby obtaining a power supply section train operation status set. The power supply section train operation status set contains the operation status information of all trains in each power supply section. Furthermore, through the integrated train operation status set, the central server calls the target load calculation model. The target load calculation model is developed through historical data accumulation and machine learning technology, and is used to calculate the power demand under a specific train operation state. Based on the target load calculation model, the load demand of the power supply section train operation status set is calculated to obtain the train real-time power load set. Finally, the train real-time power load set is accumulated and calculated to obtain the total load of the power supply section.

[0031] The method provided in an embodiment of the present application also includes: obtaining a set of load-related factors, wherein the set of load-related factors includes train operating status, train characteristic parameters, line condition parameters and environmental factors; collecting historical data based on the set of load-related factors to obtain a train-related factor load historical data set; performing regression fitting processing on the train-related factor load historical data set to obtain an initial load calculation model; verifying and optimizing the initial load calculation model to obtain a target load calculation model and storing it in the central server.

[0032] Calling the target load calculation model via the central server includes obtaining a set of load-related factors, including train operating status, train characteristic parameters, line condition parameters, and environmental factors. The train operating status refers to the actual operating state of the train, such as traction, braking, or no-load operation. Different operating states correspond to different power requirements. Train characteristic parameters include train type, vehicle weight, and power requirements. Line condition parameters include track slope, curve radius, and other parameters. Environmental factors refer to operating environmental parameters such as temperature and humidity. Historical data is collected based on the set of load-related factors to obtain a train-related factor load history dataset. The train-related factor load history dataset contains historical data on train-related factor loads for different trains under the influence of various load-related factors. Furthermore, regression fitting is performed on the train-related factor load history dataset to model the relationships between multiple factors and derive a preliminary load calculation model. After obtaining the preliminary load calculation model, the preliminary load calculation model is verified and optimized to obtain a target load calculation model, which is stored in the central server. The target load calculation model is used to perform load forecasting based on train operating status information, providing an accurate basis for controlling bidirectional converter equipment.

[0033] Based on the train operating conditions and the working mode in the power supply section, training is performed to build a bidirectional converter device control parallel channel, which includes a traction rectifier control strategy channel and a braking inverter control strategy channel; the bidirectional converter device control parallel channel is used to analyze the control parameters of the total load in the power supply section to obtain the bidirectional converter device control strategy parameters, and power supply coordinated closed-loop control is performed based on the bidirectional converter device control strategy parameters.

[0034] Based on the train operating conditions and operating mode within the power supply section, a traction rectifier control strategy dataset and a brake inverter control strategy dataset are obtained. A target traction rectifier control strategy dataset and a target brake inverter control strategy dataset are obtained after processing the traction rectifier control strategy dataset and the brake inverter control strategy dataset. A bidirectional converter control parallel channel is trained and constructed. The bidirectional converter control parallel channel includes a traction rectifier control strategy channel and a brake inverter control strategy channel. Finally, the bidirectional converter control parallel channel is used to analyze control parameters for the total load within the power supply section. The control strategy parameters output by all trains through the bidirectional converter control parallel channel are obtained, resulting in bidirectional converter control strategy parameters. Power supply coordinated closed-loop control is then performed based on the bidirectional converter control strategy parameters. This solves the technical problem in the prior art that bidirectional converter devices, during actual operation, have difficulty efficiently and dynamically adjusting their operating modes and control strategies based on the real-time train operating status, the total load within the power supply section, and the power grid harmonic conditions, resulting in low energy recovery and poor power grid harmonic suppression capabilities. Through the bidirectional converter equipment control method based on train operation status information, the equipment's operating mode and power feedback strategy can be adjusted in real time, which not only improves the stability and efficiency of train operation, but also optimizes the grid load distribution, reduces grid harmonics, and improves the overall power system operation quality.

[0035] The method provided in the embodiment of the present application also includes: determining the traction rectifier control strategy and the braking inverter control strategy based on the train operating conditions in the power supply section and the working mode; performing bidirectional converter device control data mining based on the traction rectifier control strategy and the braking inverter control strategy to obtain a traction rectifier control strategy data set and a braking inverter control strategy data set; performing feature identification training on the traction rectifier control strategy data set and the braking inverter control strategy data set respectively to obtain a traction rectifier control strategy channel and a braking inverter control strategy channel; integrating the traction rectifier control strategy channel and the braking inverter control strategy channel to build the bidirectional converter device control parallel channel.

[0036] The training and establishment of a bidirectional converter device control parallel channel includes: determining a traction rectifier control strategy and a braking inverter control strategy based on the train operating conditions and the operating mode in the power supply section. Bidirectional converter device control data mining is performed based on the traction rectifier control strategy and the braking inverter control strategy to obtain control strategies under historical operating conditions, thereby obtaining a traction rectifier control strategy dataset and a braking inverter control strategy dataset. Feature identification training is performed on the traction rectifier control strategy dataset and the braking inverter control strategy dataset, respectively, to obtain a traction rectifier control strategy channel and a braking inverter control strategy channel. The traction rectifier control strategy channel is used to obtain control parameters such as current, voltage, and power under traction conditions based on load parameters under traction conditions. The braking inverter control strategy channel is used to obtain control parameters such as feedback power control, current and voltage control under braking conditions based on load parameters under braking conditions. The traction rectifier control strategy channel and the braking inverter control strategy channel are integrated to establish the bidirectional converter device control parallel channel.

[0037] The method provided in an embodiment of the present application also includes: obtaining a set of control effect indicators of a bidirectional converter device, using the bidirectional converter device control effect indicator set to evaluate the effects of the traction rectifier control strategy data set and the braking inverter control strategy data set to obtain a bidirectional converter device control data effect set; screening the traction rectifier control strategy data set and the braking inverter control strategy data set based on the bidirectional converter device control data effect set to obtain a target traction rectifier control strategy data set and a target braking inverter control strategy data set; performing feature identification training on the target traction rectifier control strategy data set and the target braking inverter control strategy data set respectively to obtain a traction rectifier control strategy channel and a braking inverter control strategy channel.

[0038] Obtaining the traction rectifier control strategy channel and the braking inverter control strategy channel includes obtaining a set of bidirectional converter device control performance indicators, including energy efficiency, voltage fluctuation, and other indicators. The bidirectional converter device control performance indicator set is used to evaluate the performance of the traction rectifier control strategy dataset and the braking inverter control strategy dataset, obtaining bidirectional converter device control performance indicators for the traction rectifier control strategy dataset and the braking inverter control strategy dataset, and obtaining a bidirectional converter device control data effect set. Exemplarily, target traction rectifier control strategy datasets and target braking inverter control strategy datasets with energy efficiency greater than 96% and voltage fluctuation less than or equal to 8% are selected. Furthermore, feature identification training is performed on the target traction rectifier control strategy dataset and the target braking inverter control strategy dataset, respectively, to obtain the traction rectifier control strategy channel and the braking inverter control strategy channel.

[0039] The method provided in an embodiment of the present application also includes: selecting a traction rectifier deep learning network and a braking inverter deep learning network based on data characteristic information of the target traction rectifier control strategy data set and the target braking inverter control strategy data set; performing feature dimensionality reduction and identification processing on the target traction rectifier control strategy data set and the target braking inverter control strategy data set to obtain a traction rectifier control strategy sample set and a braking inverter control strategy sample set; using the traction rectifier deep learning network and the braking inverter deep learning network to perform control training on the traction rectifier control strategy sample set and the braking inverter control strategy sample set respectively to obtain the traction rectifier control strategy channel and the braking inverter control strategy channel.

[0040] According to the data characteristic information of the target traction rectifier control strategy data set and the target braking inverter control strategy data set, a traction rectifier deep learning network and a braking inverter deep learning network are selected. Subsequently, the target traction rectifier control strategy data set and the target braking inverter control strategy data set are subjected to data feature dimensionality reduction and identification processing, the control strategy data therein are identified, and the processed traction rectifier control strategy sample set and braking inverter control strategy sample set are obtained. The traction rectifier control strategy sample set includes the load parameters, train operating conditions and corresponding parameter control strategies of each train. The traction rectifier control strategy includes current control parameters, power control parameters, etc. The braking inverter control strategy includes current and voltage control parameters, feedback power control parameters, etc. Finally, the traction rectifier deep learning network and the braking inverter deep learning network are used to perform control supervision training on the traction rectifier control strategy sample set and the braking inverter control strategy sample set respectively. The traction rectifier deep learning network and the braking inverter deep learning network are both constructed based on the feedforward neural network model. The supervised training of the model is performed by inputting the traction rectifier control strategy sample set and the braking inverter control strategy sample set into the initialized traction rectifier deep learning network and the braking inverter deep learning network respectively until the accuracy of the control strategy output by the model meets the requirements, and the traction rectifier control strategy channel and the braking inverter control strategy channel are obtained.

[0041] The method provided in an embodiment of the present application also includes: performing coordinated control of train power supply based on the bidirectional converter device control strategy parameters to obtain train power supply feedback state parameters; regulating and optimizing the bidirectional converter device control strategy parameters through the train power supply feedback state parameters to determine parameter fine-tuning variables; using the parameter fine-tuning variables to fine-tune and update the bidirectional converter device control strategy parameters, and performing coordinated closed-loop control of power supply through the updated bidirectional converter device control strategy parameters.

[0042] The coordinated closed-loop power supply control based on the bidirectional converter device control strategy parameters includes: performing coordinated train power supply control based on the bidirectional converter device control strategy parameters to obtain train power supply feedback state parameters. Using the train power supply feedback state parameters, a new round of bidirectional converter device control strategy acquisition is performed to determine fine-tuning variables for the bidirectional converter device control strategy parameters. Finally, the fine-tuning variables are used to fine-tune and update the bidirectional converter device control strategy parameters, and coordinated closed-loop power supply control is performed using the updated bidirectional converter device control strategy parameters.

[0043] The method provided in the embodiment of the present application also includes: real-time monitoring of power grid harmonic status information, suppression analysis of the power grid harmonic status information, and obtaining harmonic suppression strategy parameters; and collaborative additional correction of the bidirectional converter device control strategy parameters based on the harmonic suppression strategy parameters.

[0044] By monitoring the harmonic status of the power grid in real time, relevant data on grid harmonics is obtained. This information primarily includes the amplitude, frequency, and total harmonic distortion of the harmonic current. Based on big data analysis of the harmonic issues currently existing in the power grid, a specific suppression strategy is determined, and corresponding harmonic suppression strategy parameters are generated. These strategy parameters include how to adjust the operating mode of the bidirectional converter equipment to reduce generated harmonics and ensure power quality in the power grid. Finally, based on the harmonic suppression strategy parameters, the control strategy parameters of the bidirectional converter equipment are collaboratively modified.

[0045] The technical solution provided by the embodiment of the present invention obtains the train operation status information and the train current position data through real-time collection and uploads them to the central server for load calculation to obtain the total load of the power supply section. According to the total load of the power supply section, the train working condition of the power supply section is determined, and the working mode of the bidirectional converter device is dynamically adjusted based on the total load of the power supply section. Based on the train working condition of the power supply section and the working mode, a bidirectional converter device control parallel channel is trained and constructed. The control parameter of the total load of the power supply section is analyzed using the bidirectional converter device control parallel channel to obtain the bidirectional converter device control strategy parameters, and the power supply coordinated closed-loop control is performed based on the bidirectional converter device control strategy parameters. This solves the technical problem in the prior art that it is difficult for bidirectional converter devices to efficiently and dynamically adjust the working mode and control strategy according to the real-time operating status of the train, the total load of the power supply section and the harmonic conditions of the power grid during actual operation, resulting in low energy recovery rate and poor power grid harmonic suppression capability. Through the bidirectional converter equipment control method based on train operation status information, the equipment's operating mode and power feedback strategy can be adjusted in real time, which not only improves the stability and efficiency of train operation, but also optimizes the grid load distribution, reduces grid harmonics, and improves the overall power system operation quality.

[0046] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A bidirectional converter control method based on train operation status information, characterized in that: The method comprises: Real-time acquisition of train operation status information and train current location data, uploading the train operation status information and train current location data to a central server for load calculation to obtain the total load of the power supply section; determining a train operating condition in the power supply section according to the total load of the power supply section, wherein the train operating condition in the power supply section includes traction and braking, and dynamically adjusting an operating mode of a bidirectional converter device based on the total load of the power supply section, wherein the operating mode includes rectification and inversion; Based on the train operating conditions and the working mode in the power supply section, training is performed to establish a bidirectional converter device control parallel channel, wherein the bidirectional converter device control parallel channel includes a traction rectifier control strategy channel and a brake inverter control strategy channel; The bidirectional converter device is used to control the parallel channel to perform control parameter analysis on the total load of the power supply section to obtain bidirectional converter device control strategy parameters, and power supply coordinated closed-loop control is performed based on the bidirectional converter device control strategy parameters.

2. The bidirectional converter control method based on train operation status information according to claim 1, characterized in that: The real-time acquisition of train operation status information and train current position data includes: Installing and deploying sensor groups on the train according to train operation requirements, and acquiring train operation status information in real time through the sensor groups; Acquire a train positioning link set, wherein the train positioning link set includes GPS positioning technology, CBTC system and wireless communication technology; Performing a criticality assessment on each positioning link in the train positioning link set to obtain a positioning link criticality coefficient set; The train location set is acquired by utilizing the train location link set, and the train location set is weightedly fused based on the positioning link criticality coefficient set to acquire the current location data of the train.

3. The bidirectional converter control method based on train operation status information according to claim 1, characterized in that: The uploading of the train operation status information and the train current position data to the central server includes: Obtaining data transmission requirement factors, wherein the data transmission requirement factors include transmission rate, transmission distance, and data sensitivity; Performing a multi-dimensional analysis on the train operation status information and the train current position data using the data transmission requirement factors to obtain data transmission requirement factor parameters; Configuring a wireless data transmission line according to the data transmission requirement factor parameters; The train operation status information and the train current position data are uploaded to the central server based on the data wireless transmission line.

4. The method for controlling a bidirectional converter device based on train operation status information according to claim 1, wherein: Obtaining the total load of the power supply section includes: Determining a distributed power supply section of the train based on the current position data of the train; Dividing and integrating the train operation status information according to the train distribution power supply interval to obtain a power supply interval train operation status set; The target load calculation model is called by the central server, and the load demand of the train operation status set in the power supply section is calculated based on the target load calculation model to obtain the real-time power load set of the train; The real-time power load set of the train is accumulated and calculated to obtain the total load of the power supply section.

5. The bidirectional converter device control method based on train operation status information according to claim 4, characterized in that: The calling of the target load calculation model by the central server includes: Obtaining a set of load-related factors, wherein the set of load-related factors includes train operation status, train characteristic parameters, line condition parameters, and environmental factors; Collect historical data based on the load-related factor set to obtain a train-related factor load historical data set; Performing regression fitting processing on the train-related factor load historical data set to obtain an initial load calculation model; The initial load calculation model is verified and optimized to obtain a target load calculation model and store it in the central server.

6. The method for controlling a bidirectional converter device based on train operation status information according to claim 1, wherein: The training to build a bidirectional converter device to control parallel channels includes: Determining a traction rectification control strategy and a braking inversion control strategy according to the train operating condition in the power supply section and the operating mode; Performing bidirectional converter device control data mining based on the traction rectifier control strategy and the braking inverter control strategy to obtain a traction rectifier control strategy data set and a braking inverter control strategy data set; Performing feature identification training on the traction rectification control strategy data set and the braking inversion control strategy data set respectively to obtain a traction rectification control strategy channel and a braking inversion control strategy channel; The traction rectification control strategy channel and the braking inversion control strategy channel are integrated to build the bidirectional converter device control parallel channel.

7. The method for controlling a bidirectional converter device based on train operation status information according to claim 6, wherein: The obtaining of the traction rectification control strategy channel and the braking inversion control strategy channel includes: Obtaining a bidirectional converter device control effect index set, and using the bidirectional converter device control effect index set to evaluate the effects of the traction rectifier control strategy data set and the brake inverter control strategy data set to obtain a bidirectional converter device control data effect set; Filtering the traction rectifier control strategy data set and the braking inverter control strategy data set based on the bidirectional converter device control data effect set to obtain a target traction rectifier control strategy data set and a target braking inverter control strategy data set; Feature identification training is performed on the target traction rectification control strategy data set and the target braking inversion control strategy data set respectively to obtain a traction rectification control strategy channel and a braking inversion control strategy channel.

8. The method for controlling a bidirectional converter device based on train operation status information according to claim 7, wherein: The obtaining of the traction rectification control strategy channel and the braking inversion control strategy channel includes: Selecting a traction rectifier deep learning network and a brake inverter deep learning network according to data characteristic information of the target traction rectifier control strategy data set and the target brake inverter control strategy data set; Performing feature dimension reduction and identification processing on the target traction rectification control strategy data set and the target braking inverter control strategy data set to obtain a traction rectification control strategy sample set and a braking inverter control strategy sample set; The traction rectifier deep learning network and the braking inverter deep learning network are used to perform control training on the traction rectifier control strategy sample set and the braking inverter control strategy sample set respectively to obtain the traction rectifier control strategy channel and the braking inverter control strategy channel.

9. The method for controlling a bidirectional converter device based on train operation status information according to claim 1, wherein: The power supply coordinated closed-loop control based on the bidirectional converter device control strategy parameters includes: Performing train power supply coordinated control based on the bidirectional converter device control strategy parameters to obtain train power supply feedback state parameters; Performing regulation and optimization analysis on the control strategy parameters of the bidirectional converter device through the train power supply feedback state parameters to determine parameter fine-tuning variables; The parameter fine-tuning variables are used to fine-tune and update the control strategy parameters of the bidirectional converter device, and the updated control strategy parameters of the bidirectional converter device are used to perform power supply coordinated closed-loop control.

10. The method for controlling bidirectional converter equipment based on train operation status information according to claim 1, characterized in that: The method further comprises: Real-time monitoring of power grid harmonic status information, suppression analysis of the power grid harmonic status information, and obtaining harmonic suppression strategy parameters; The control strategy parameters of the bidirectional converter device are collaboratively additionally corrected based on the harmonic suppression strategy parameters.

Images