Power supply optimization method and device for railway traction system

Abstract

The embodiment of the invention provides a power supply optimization method and device for a railway traction system, and the method comprises the steps: inputting a current voltage fluctuation parameter of the railway traction system into a pre-constructed fluctuation prediction model, and obtaining a corresponding expected voltage fluctuation parameter, the fluctuation prediction model comprises a linear regression model or a first neural network model, and the current voltage fluctuation parameter comprises a current voltage parameter and a previous fluctuation voltage parameter; determining a control parameter of the inverter of the railway traction system according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; controlling the inverter to adjust the corresponding output voltage according to the control parameter until the deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range; according to the method, the problem of power instability caused by power grid voltage fluctuation in the operation process of the high-speed train can be solved, and the safety and reliability of train operation are guaranteed.

Description

Technical Field

[0001] The present application relates to the field of power supply for traction systems, and in particular to a method and device for optimizing power supply for railway traction systems. Background Art

[0002] Railway traction power supply systems are susceptible to grid voltage fluctuations during high-speed train operation. This is primarily due to high current surges during train starts and stops, grid load variations, power line impedance characteristics, and external environmental factors such as inclement weather. Failure to promptly adjust voltage fluctuations can lead to abnormal train power output, equipment overload or damage, and compromise power supply system stability.

[0003] Traditional traction power supply systems use static compensation devices or PID control methods for voltage regulation. However, static compensation devices have slow response times and struggle to adapt to rapidly changing loads. PID control with fixed parameters is prone to overshoot or undershoot under complex operating conditions, making it difficult to consistently maintain optimal regulation. Furthermore, existing systems often rely on real-time feedback regulation, lacking the ability to predict future voltage fluctuations and making it difficult to proactively compensate in a timely manner.

[0004] Therefore, a control method is needed that can sense voltage fluctuations in real time and, in combination with multiple optimization algorithms, dynamically adjust the inverter output voltage and frequency to improve the stability of the traction power supply system. Furthermore, the system must be adaptable to complex operating conditions and able to respond quickly to sudden changes in train load or external environmental conditions, ensuring that the grid voltage remains within a reasonable range and preventing equipment from operating abnormally due to voltage fluctuations. Summary of the Invention

[0005] In response to the problems in the existing technology, the present application provides a power supply optimization method and device for a railway traction system, which can solve the problem of power instability caused by grid voltage fluctuations during the operation of high-speed trains and ensure the safety and reliability of train operation.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] According to a first aspect of an embodiment of the present application, the present application provides a method for optimizing power supply of a railway traction system, comprising:

[0008] Inputting current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0009] determining a control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0010] The inverter is controlled to adjust the corresponding output voltage according to the control parameter until a deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0011] According to any embodiment of the present application, after controlling the inverter to adjust the corresponding output voltage according to the control parameter, the method further includes:

[0012] determining a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0013] The control parameters of the inverter are updated according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

[0014] According to any embodiment of the present application, inputting the current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain the corresponding expected voltage fluctuation parameters includes:

[0015] The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

[0016] According to any embodiment of the present application, determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes:

[0017] Calculate the current voltage error value, cumulative error value, and error change rate based on the current voltage fluctuation parameter and the expected voltage fluctuation parameter using the proportional, integral, and differential adjustment modules of the PID controller;

[0018] The control parameters of the railway traction system inverter are determined according to the current error value, the accumulated error value and the error change rate.

[0019] According to any embodiment of the present application, it also includes:

[0020] determining an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0021] A control parameter of the inverter is determined according to the frequency adjustment amount.

[0022] According to any embodiment of the present application, it also includes:

[0023] Inputting the expected voltage fluctuation parameter into a pre-built second neural network model to obtain a future voltage fluctuation trend;

[0024] The control parameters of the inverter are determined according to the future voltage fluctuation trend adjustment amount.

[0025] According to any embodiment of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0026] The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

[0027] According to any embodiment of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0028] Smoothing the current voltage fluctuation parameter and the expected voltage fluctuation parameter by a sliding window averaging algorithm;

[0029] The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes:

[0030] The smoothed voltage fluctuation data is input into a fuzzy control algorithm to obtain control parameters of the railway traction system inverter.

[0031] According to any embodiment of the present application, determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes:

[0032] If a voltage deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold, determining a voltage adjustment amount according to the voltage deviation and a preset first coefficient;

[0033] If the frequency deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold, determining a frequency adjustment amount according to the voltage deviation and a preset second coefficient;

[0034] If a load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold, determining a voltage adjustment amount according to the voltage deviation value and a preset third coefficient;

[0035] If the power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold, a voltage adjustment amount is determined according to the voltage deviation value and a preset fourth coefficient.

[0036] According to a second aspect of an embodiment of the present application, the present application provides a power supply optimization device for a railway traction system, comprising:

[0037] a voltage fluctuation prediction module, configured to input current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0038] a control parameter calculation module, configured to determine a control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0039] The inverter adjustment module is used to control the inverter to adjust the corresponding output voltage according to the control parameter until the deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0040] According to any embodiment of the present application, a regulation optimization module is further included, including:

[0041] a gain matrix calculation unit, configured to determine a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0042] A control parameter updating unit is configured to update the control parameters of the inverter according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

[0043] According to any embodiment of the present application, the voltage fluctuation prediction module is specifically used to:

[0044] The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

[0045] According to any embodiment of the present application, the control parameter calculation module includes:

[0046] an error calculation unit, configured to calculate the error value, cumulative error value, and error change rate of the current voltage based on the current voltage fluctuation parameter and the expected voltage fluctuation parameter and the proportional, integral, and differential adjustment modules of the PID controller;

[0047] A parameter determination unit is used to determine the control parameters of the railway traction system inverter according to the current error value, the accumulated error value and the error change rate.

[0048] According to any embodiment of the present application, the control parameter calculation module includes:

[0049] a frequency adjustment unit, configured to determine an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0050] A parameter calculation unit is used to determine a control parameter of the inverter according to the frequency adjustment amount.

[0051] According to any embodiment of the present application, the control parameter calculation module includes:

[0052] a neural network calculation unit, configured to input the expected voltage fluctuation parameter into a pre-built second neural network model to obtain a future voltage fluctuation trend;

[0053] The trend adjustment unit is used to determine the control parameters of the inverter according to the future voltage fluctuation trend adjustment amount.

[0054] According to any embodiment of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0055] The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

[0056] According to any embodiment of the present application, it also includes:

[0057] a sliding window calculation unit, configured to smooth the current voltage fluctuation parameter and the expected voltage fluctuation parameter using a sliding window averaging algorithm;

[0058] The fuzzy control calculation unit is used to input the smoothed current voltage fluctuation parameter and the expected voltage fluctuation parameter into the fuzzy control algorithm.

[0059] According to any embodiment of the present application, the control parameter calculation module includes:

[0060] a voltage adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset first coefficient if a voltage deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold;

[0061] a frequency adjustment calculation unit, configured to determine a frequency adjustment amount according to the voltage deviation value and a preset second coefficient if a frequency deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold;

[0062] a load adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset third coefficient if a load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold;

[0063] The power adjustment calculation unit is configured to determine a voltage adjustment amount according to the voltage deviation value and a preset fourth coefficient if a power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold.

[0064] According to the third aspect of the embodiment of the present application, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the steps of the power supply optimization method of the railway traction system are implemented.

[0065] According to a fourth aspect of the embodiments of the present application, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the power supply optimization method for the railway traction system.

[0066] According to a fifth aspect of the embodiments of the present application, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the power supply optimization method for the railway traction system.

[0067] It can be seen from the above technical solution that the present application provides a power supply optimization method and device for a railway traction system, by inputting the current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain the corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include the current voltage parameters and the previous fluctuation voltage parameters; the control parameters of the railway traction system inverter are determined according to the current voltage fluctuation parameters and the expected voltage fluctuation parameters; the inverter is controlled to adjust the corresponding output voltage according to the control parameters until the deviation value between the current voltage fluctuation parameters and the expected voltage fluctuation parameters is within a preset deviation range, which can solve the power instability problem caused by grid voltage fluctuation during the operation of high-speed trains and ensure the safety and reliability of train operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0069] Figure 1 This is a flow chart of a method for optimizing power supply for a railway traction system according to an embodiment of the present application;

[0070] Figure 2This is a second flow chart of the method for optimizing power supply for a railway traction system in an embodiment of the present application;

[0071] Figure 3 This is a third flow chart of the method for optimizing power supply for a railway traction system in an embodiment of the present application;

[0072] Figure 4 This is a fourth flow chart of the method for optimizing power supply for a railway traction system in an embodiment of the present application;

[0073] Figure 5 This is a fifth flow chart of the method for optimizing power supply for a railway traction system in an embodiment of the present application;

[0074] Figure 6 This is a sixth flow chart of the method for optimizing power supply for a railway traction system in an embodiment of the present application;

[0075] Figure 7 This is a structural diagram of a power supply optimization device for a railway traction system in an embodiment of the present application;

[0076] Figure 8 Schematic diagram of the structure of the electronic device in the embodiment of the present application. DETAILED DESCRIPTION

[0077] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0078] The acquisition, storage, use, and processing of data in the technical solution of this application comply with relevant laws and regulations.

[0079] Taking into account the problems related to the existing technology, the present application provides a power supply optimization method and device for a railway traction system to solve the problem of power instability caused by grid voltage fluctuations during the operation of high-speed trains, thereby ensuring the safety and reliability of train operation.

[0080] In order to solve the problem of power instability caused by grid voltage fluctuation during the operation of high-speed trains and ensure the safety and reliability of train operation, the present application provides an embodiment of a power supply optimization method for a railway traction system, see Figure 1 The power supply optimization method of the railway traction system specifically includes the following contents:

[0081] Step S101: Input the current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include the current voltage parameters and the previous fluctuation voltage parameters.

[0082] In the power supply optimization process, it is first necessary to obtain the current voltage fluctuation parameters and calculate the expected voltage fluctuation parameters through the pre-built fluctuation prediction model. This application uses a linear regression model or a first neural network model as a prediction tool to analyze historical voltage fluctuation data and predict future voltage change trends in advance. The input of the prediction model includes the current voltage parameters and the previous voltage fluctuation parameters, and a reasonable historical data window is set in combination with time series analysis. For example, in one embodiment, voltage data for the past 30 minutes is used as input to predict voltage fluctuations in the next 10 minutes. The core goal of the prediction model is to minimize the prediction error, which is usually optimized using the mean square error (MSE) formula:

[0083]

[0084] Among them, y i Represents the actual voltage fluctuation value, y ^ i Represents the predicted value, and N is the number of samples. By adjusting the model parameters (such as weights, historical data window length, etc.), the prediction error can be reduced and the prediction accuracy can be improved, so that the system can perceive the upcoming voltage fluctuations in advance and provide a basis for subsequent regulation (1)

[0085] Step S102: determining control parameters of the railway traction system inverter according to the current voltage fluctuation parameters and the expected voltage fluctuation parameters.

[0086] After obtaining the expected voltage fluctuation parameters, the system compares them with the currently collected voltage fluctuation parameters to calculate the voltage deviation. Voltage deviation is a key parameter for adjusting the inverter output, directly determining the direction and magnitude of voltage regulation. For example, if the currently collected voltage fluctuation value is 120V, and the predicted voltage fluctuation value calculated by the prediction model is 118V, the voltage deviation is 2V. If this deviation exceeds a set threshold (e.g., 2%), the system will perform an adjustment.

[0087] At this point, based on the voltage deviation, the system calculates the inverter's control parameters, including output voltage and frequency adjustments. The adjustment strategy is based on PID control or adaptive control algorithms to ensure that the adjustments meet grid requirements.

[0088] Step S103: controlling the inverter to adjust the corresponding output voltage according to the control parameter until the deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0089] The output voltage and output frequency of the inverter should be adjusted based on the current input value and dynamically corrected in combination with the calculated voltage deviation and frequency deviation. The adjustment formula should be:

[0090] V out =V in +K v ×(V ref -V in ) (2)

[0091] f out =f in +K f ×(f ref -f in ) (3)

[0093] in:

[0094] V out is the adjusted inverter output voltage, V in is the current input voltage;

[0095] V ref is the target voltage, K v is the voltage adjustment gain factor;

[0096] f out is the adjusted inverter output frequency, f in is the current input frequency;

[0097] f ref is the target frequency, K f Adjust the gain factor for frequency.

[0098] From the above description, it can be seen that the power supply optimization method of this application achieves precise control of voltage fluctuations in the railway traction system through three core steps: real-time monitoring, predictive analysis, and dynamic adjustment. First, the system uses time series analysis and prediction models to obtain future voltage fluctuation trends, providing a basis for subsequent adjustments; second, it calculates the current voltage deviation and determines the optimal adjustment amount based on PID control or adaptive algorithms; finally, it controls the inverter output voltage and frequency to ensure that the system operates within a reasonable range. This method can effectively reduce the impact of grid voltage fluctuations on the traction system and improve the stability and reliability of the power supply system.

[0099] In one embodiment of the power supply optimization method for the railway traction system of the present application, see Figure 2After controlling the inverter to adjust the corresponding output voltage according to the control parameter, the method further includes:

[0100] Step S104: determining a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter.

[0101] After the system obtains the current and expected voltage fluctuation parameters and initially adjusts the inverter output, it further dynamically evaluates system performance using the Recursive Least Squares (RLS) algorithm. This algorithm calculates the error between the current system input and output and determines the gain matrix used to adjust the control parameters.

[0102] Specifically, the system first constructs the input vector x(k) from the current input data (such as historical voltage deviation, load current, and grid state parameters) and uses the expected voltage output by the prediction model as the system target output y(k). The voltage error gain matrix K(k) is then calculated using the following formula.

[0103] K(k)=P(k)x(k) / [1+x(k) T P(k)x(k)] (4)

[0104] Where P(k) is the covariance matrix, which is used to measure the degree of uncertainty in the current model. The gain matrix represents the impact of the current error on the control parameter update and is the core basis for subsequent control parameter updates.

[0105] Step S105: updating the control parameters of the inverter according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

[0106] After obtaining the gain matrix K(k), the system further updates the control parameters of the inverter based on the following formula:

[0107] w(k+1)=w(k)+K(k)[y(k)-x(k) T w(k)] (5)

[0109] Here, w(k) is the current control parameter vector, which includes key parameters such as voltage adjustment gain and frequency compensation coefficient. The current prediction error is corrected using the gain matrix to obtain the updated control parameter w(k+1), enabling the inverter to more accurately respond to voltage deviations based on the new control strategy.

[0110] In one embodiment of the power supply optimization method for a railway traction system of the present application, the step of inputting the current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain the corresponding expected voltage fluctuation parameters includes:

[0111] The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

[0112] To accurately predict future voltage fluctuation trends, the system first calculates expected voltage fluctuations based on current voltage parameters and parameters from previous voltage fluctuations, combined with a pre-built fluctuation prediction model. This fluctuation prediction model is a weighted linear model that comprehensively considers the current real-time voltage status and historical voltage fluctuation trends, resulting in predictions that are more accurate to actual operating conditions.

[0113] Specifically, this step is processed based on the following calculation formula:

[0114] Expected voltage fluctuation = a × current voltage + b × previous voltage fluctuation (6)

[0115] Among them, the current voltage represents the actual measured voltage value of the power grid at the current moment, reflecting the current operating status of the power system;

[0116] The previous fluctuation voltage indicates the voltage fluctuation recorded by the system at the last moment or in the historical window, and is used to capture the short-term dynamic trend of the power grid;

[0117] The coefficient a is the weight of the current voltage, and b is the weight of the previous fluctuation voltage. The coefficients a and b are generally between 0 and 1, and satisfy a+b=1 (this condition may be relaxed in some implementations).

[0118] By adjusting parameters a and b, the system can flexibly adjust the model's reliance on "immediate status" and "historical trends" based on actual application scenarios. For example, in scenarios with frequent grid fluctuations, the weight of the current voltage can be increased (e.g., setting a = 0.8, b = 0.2) to enhance responsiveness to the current state; whereas in scenarios with more pronounced trend fluctuations, the weight of the previous voltage fluctuation can be appropriately increased.

[0119] In one embodiment of the power supply optimization method for the railway traction system of the present application, see Figure 3 , the determining of the control parameters of the railway traction system inverter according to the current voltage fluctuation parameters and the expected voltage fluctuation parameters includes:

[0120] Step S102A: Calculate the error value, cumulative error value and error change rate of the current voltage based on the proportional, integral and differential adjustment modules of the PID controller according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter.

[0121] The system compares the current voltage fluctuation parameters with the predicted expected voltage fluctuation parameters to form a voltage error value. Subsequently, the PID controller calculates the proportional (P), integral (I) and differential (D) terms based on the error data:

[0122] The proportional part is used to respond to the current error value immediately and achieve rapid adjustment;

[0123] The integral part corrects long-term deviations by accumulating error values to achieve steady-state balance;

[0124] The derivative part makes predictive corrections based on the error rate of change to prevent over-adjustments caused by rapid changes.

[0125] Step S102B: determining control parameters of the railway traction system inverter according to the current error value, the accumulated error value, and the error change rate.

[0126] After obtaining the current error value, historical error accumulation, and error change rate, the inverter control parameters are calculated based on these three factors to adjust the output voltage. These control parameters are used to drive the inverter to correct the output voltage to compensate for the deviation between the predicted and actual values.

[0127] Once the adjustment is complete, the output voltage is fed back to the system in real time for continuous monitoring, forming a closed-loop regulation process. The system continuously compares and corrects the adjustment results to ensure that the inverter output voltage remains close to the target value, maintaining voltage stability in the traction power supply system.

[0128] Assume that the actual measured voltage at a certain moment is 220V, and the previously recorded voltage fluctuation is 5V. If the prediction model weights the current voltage to 0.7 and the previous fluctuation to 0.3, the expected voltage fluctuation is calculated to be 155.5V. At this point, the PID controller adjusts based on the deviation between the expected value and the current voltage, driving the inverter output voltage toward the target value. This output is continuously fed back to the system for monitoring and readjustment to ensure stable operation.

[0129] In one embodiment of the power supply optimization method for the railway traction system of the present application, see Figure 4 , also includes:

[0130] Step S102C: determining an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter.

[0131] After obtaining the current voltage fluctuation parameters and the expected voltage fluctuation parameters generated by the prediction model, the system compares the two and determines whether frequency adjustment is necessary. If the voltage fluctuation exceeds the set fluctuation range, the frequency optimization process is initiated.

[0132] The adaptive filtering algorithm then analyzes the expected voltage fluctuation trends and dynamically adjusts the filter's internal parameters to calculate the output frequency adjustment appropriate for the current voltage fluctuation. This algorithm automatically optimizes the adjustment coefficient based on real-time changes in the input signal (i.e., expected voltage fluctuations), ensuring excellent tracking capabilities, adapting to transient grid disturbances, and mitigating the impact of frequency fluctuations on system stability.

[0133] Step S102D: determining a control parameter of the inverter according to the frequency adjustment amount.

[0134] After obtaining the output frequency adjustment, this adjustment is used as a core input to update the inverter's control parameters. The inverter control module adjusts its output frequency based on these parameters to offset frequency disturbances caused by voltage fluctuations and ensure the continuity and stability of the electrical system's operating frequency.

[0135] In one embodiment of the power supply optimization method for the railway traction system of the present application, see Figure 5 , also includes:

[0136] Step S102E: inputting the expected voltage fluctuation parameters into a pre-built second neural network model to obtain a future voltage fluctuation trend.

[0137] After obtaining the current voltage fluctuation parameters and the expected voltage fluctuation parameters initially calculated by the prediction model, the system further inputs the expected parameters into a pre-trained second neural network model. This model, through learning from historical voltage data, has acquired the ability to identify voltage fluctuation patterns and trends, and can infer possible voltage fluctuations in the future based on the current state.

[0138] The neural network model used can be a multi-layer feedforward neural network (MLP), a convolutional neural network (CNN), or a long short-term memory network (LSTM). The specific choice depends on the training data structure and the temporal characteristics of voltage fluctuations. The model training phase typically uses a large amount of historical voltage sampling data as input and optimizes the network weights through supervised learning to minimize the error between the predicted value and the actual value.

[0139] For example, in a typical embodiment, the system has used tens of thousands of voltage fluctuation data under train operating conditions to train the neural network. Given a 30-minute voltage data window, the model can predict the voltage change trend in the next 10 minutes, including the amplitude and rate of voltage increase or decrease.

[0140] The prediction output can be in the form of voltage estimates for a series of future time points, or an aggregated trend assessment indicator (such as "rapid decline" or "small fluctuation", etc.), and the system will formulate an adjustment strategy based on this.

[0141] Step S102F: determining the control parameters of the inverter according to the future voltage fluctuation trend adjustment amount.

[0142] After obtaining the future voltage fluctuation trend, the system presets the inverter output strategy based on factors such as the trend direction, change amplitude and duration in the prediction results, that is, adjusts the control parameters in advance to cope with the upcoming voltage disturbance.

[0143] For example, when the prediction results show that there will be a significant voltage drop trend in the next 5 minutes, the system can instruct the inverter to moderately increase the output voltage and frequency to compensate before the fluctuation actually occurs, thereby reducing the impact of transient fluctuations; conversely, if it is predicted that the voltage will rise rapidly, the output voltage can be reduced in advance to reduce the load pressure on the system.

[0144] The inverter control parameters generated in this step include, but are not limited to, output voltage setpoint, frequency setpoint, regulation slope limit, response time setting, etc. Control parameters can be set according to a hierarchical strategy based on the predicted fluctuation intensity, such as triggering a high-level response when the voltage change rate exceeds a certain threshold.

[0145] This approach eliminates the need for passive adjustments based solely on real-time error feedback and instead implements proactive, predictive-driven control, enhancing the predictive nature of voltage regulation and overall system stability. This approach is particularly well-suited for typical voltage disturbances, such as train starts and stops and sudden changes in traction loads, effectively reducing the risk of system disruption.

[0146] In one embodiment of the power supply optimization method for a railway traction system of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0147] The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

[0148] After calculating the expected voltage fluctuation parameters based on historical data and the fluctuation model, the system uses this preliminary prediction as observation input and passes it into an adaptive Kalman filter for filtering. This filter, a recursive algorithm based on state-space estimation theory, dynamically estimates and corrects for system noise and measurement errors. It automatically optimizes the filter gain in response to system parameter changes or external interference, achieving a more accurate estimate of the actual voltage fluctuation state.

[0149] Unlike traditional Kalman filtering, the adaptive Kalman filter dynamically adjusts the noise covariance matrix (such as the measurement noise matrix R and the process noise matrix Q) according to the statistical characteristics of the system state residual in each filtering iteration, thereby improving the tracking performance in non-steady-state environments and avoiding filtering failure due to fixed parameters.

[0150] In one embodiment of the power supply optimization method for a railway traction system of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0151] The current voltage fluctuation parameter and the expected voltage fluctuation parameter are smoothed by a sliding window averaging algorithm.

[0152] After obtaining the current and expected voltage fluctuation parameters, the system first smooths the voltage fluctuation data sequence using a sliding window averaging algorithm to eliminate sampling errors and short-term abnormal fluctuations. The sliding window averaging algorithm is a commonly used data denoising method. Its basic principle is to select a window length and then average the voltage fluctuation data at several consecutive time points within the window, calculating the average value as the smoothed output at that time point.

[0153] In one specific embodiment, the system sets the sliding window length to 5 time units, averaging the voltage fluctuation values at every five consecutive time points. For example, if the voltage fluctuation values collected continuously before and after a certain moment are [4.8, 5.1, 5.3, 4.9, 5.0], the smoothed voltage fluctuation value at that moment is 5.02V. This method effectively filters short-term interference signals, ensuring that the data relied upon by subsequent control algorithms is more stable and representative.

[0154] The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes:

[0155] The smoothed voltage fluctuation data is input into a fuzzy control algorithm to obtain control parameters of the railway traction system inverter.

[0156] Among them, fuzzy control is an intelligent control method suitable for dealing with uncertainty and nonlinear systems. Its basic idea is to use language rules and membership functions to fuzzy the input variables, and then output corresponding adjustment instructions according to the preset control rule table.

[0157] For example, the system will fuzzy the voltage fluctuation level into levels such as "small", "moderate", "large", etc., and generate a response strategy based on empirical rules. For example:

[0158] If the voltage fluctuation is "large", increase the output frequency and boost the voltage;

[0159] If the voltage fluctuation is "small", the current output remains unchanged;

[0160] If the voltage fluctuation rate of change is "rapid rise", reduce the output to avoid overshoot.

[0161] After defuzzification, the fuzzy control output generates quantifiable control parameters, which are directly used to adjust the output voltage and frequency of the inverter.

[0162] In one embodiment of the power supply optimization method for the railway traction system of the present application, see Figure 6 , after obtaining the corresponding expected voltage fluctuation parameters, it also includes:

[0163] The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes:

[0164] Step S102G: If the voltage deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold, determine a voltage adjustment amount according to the voltage deviation and a preset first coefficient.

[0165] First, obtain the current grid voltage value U and the target voltage value U0.

[0166] The system collects the current voltage data in real time through sensors and compares it with the set target voltage. For example, in one embodiment, the current voltage U is 225V and the target voltage U is 220V.

[0167] Next, it is determined whether the voltage deviation exceeds the set threshold value Ut.

[0168] The absolute value of the voltage deviation is:

[0169] ∣U-U0∣=∣225V-220V∣=5V

[0170] The voltage deviation threshold Ut is set to 2 V. Since 5 V > 2 V, the deviation has exceeded the acceptable range of the system, and the system needs to trigger the adjustment mechanism.

[0171] Next, the required voltage adjustment amount ΔU is calculated based on the proportionality coefficient k.

[0172] The proportional coefficient k is preset to 0.3, according to the formula:

[0173] ΔU=k×(U-U0) (7)

[0174] Substitute specific values:

[0175] ΔU=0.3×(225V-220V)=0.3×5V=1.5V

[0176] Therefore, the system regulates the voltage down by 1.5V.

[0177] Finally, the inverter output voltage is adjusted to U=U+ΔU.

[0178] Since the current voltage is higher than the target value, the adjustment direction is to reduce the voltage. The new inverter output voltage is:

[0179] 225V-1.5V=223.5V

[0180] Step S102H: If the frequency deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold, a frequency adjustment amount is determined according to the voltage deviation and a preset second coefficient.

[0181] First, the grid frequency fluctuation amplitude data F is acquired. The system collects real-time grid frequency data using a frequency monitoring device installed in the traction power supply network. By monitoring current and voltage changes and combining it with a digital signal processing module, the system can accurately calculate the deviation between the current grid frequency and the reference frequency. For example, in one embodiment, the system uses a high-precision frequency sensor and a data acquisition card to collect frequency data at a millisecond-level period. When a high-speed train starts or accelerates, a frequency fluctuation value F = 0.7 Hz is detected.

[0182] Next, it is determined whether the frequency fluctuation exceeds a preset threshold Fth.

[0183] The system presets a frequency fluctuation threshold Fth to determine whether frequency adjustment is necessary. This threshold is typically set within the range of ±0.2Hz to ±1.0Hz, with an optimal value of ±0.5Hz.

[0184] In the above embodiment, if Fth is set to 0.5 Hz and the current frequency fluctuation is 0.7 Hz, then:

[0185] F=0.7Hz>Fth=0.5Hz

[0186] If the adjustment conditions are met, the system proceeds to the next step.

[0187] Third, the frequency adjustment amount Δf is calculated based on the proportional coefficient γ.

[0188] The system adopts proportional control method according to the formula:

[0189] Δf=γ×F

[0190] Wherein, γ is the second coefficient preset by the system, which is used to adjust the sensitivity of the frequency adjustment, and is usually between 0.5 and 2.0, with an optimal value of 1.0. In this embodiment, if γ is set to 1.0, then:

[0191] Δf=1.0×0.7Hz=0.7Hz

[0192] Finally, the output frequency of the inverter is updated to f=f+Δf.

[0193] The system adds the calculated frequency change Δf\DeltafΔf to the current inverter output frequency to form a new output value. For example, if the inverter's current output frequency is 50Hz, then:

[0194] f = 50 Hz + 0.7 Hz = 50.7 Hz

[0195] Step S102I: If the load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold, a voltage adjustment amount is determined according to the voltage deviation value and a preset third coefficient.

[0196] First, the current grid voltage U and load power P are acquired. The system uses voltage and current sensors and data acquisition equipment installed in the traction grid to monitor the grid's operating status in real time. The voltage U reflects the current power supply level, while the load power P represents the current load demand of the traction system and serves as the basis for determining overload.

[0197] For example, in one embodiment, the system collects that the current grid voltage is 220V and the current load power is 110kW.

[0198] Secondly, it determines whether the load power P exceeds the set safety threshold Pth. The system compares the current load power with a preset load power safety threshold Pth, which is usually determined based on the maximum load capacity of the inverter, to determine whether voltage regulation is required.

[0199] In the above embodiment, if Pth is set to 100kW, then:

[0200] P=110kW>Pth=100kW

[0201] Therefore, the system determines that the current load has exceeded the safe range and needs to trigger voltage adjustment to compensate.

[0202] Next, the voltage adjustment amount is calculated according to the formula ΔU=η×(P-Pth).

[0203] Here, η is a preset third coefficient, which is usually in the range of 0.1 to 0.5 and is used to control the influence of overload on voltage regulation.

[0204] Continuing with the above example, if η is set to 0.3, then:

[0205] ΔU=0.3×(110-100)=3V

[0206] That is, the system needs to increase the inverter output voltage by 3V to cope with the voltage drop caused by the increased load.

[0207] Finally, the inverter output voltage is adjusted to U=U+ΔU.

[0208] Based on the calculation results in the previous step, the system instructs the inverter to adjust the output voltage from the current 220V to:

[0209] U=220V+3V=223V

[0210] Step S102J: If the power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold, a voltage adjustment amount is determined according to the voltage deviation value and a preset fourth coefficient.

[0211] First, the current grid voltage value U, the target voltage value U0, and the load current I are obtained.

[0212] The system uses high-precision voltage and current sensors deployed in the traction network to collect real-time data on the current voltage U, target reference voltage U0, and real-time current I, and feeds this data back to the central dispatching unit through the controller.

[0213] In a practical embodiment, when a high-speed train starts, the system collects:

[0214] Current voltage U=24.5kV; target voltage U0=25kV; current I=100A.

[0215] Secondly, the power deviation caused by the voltage deviation is calculated and whether it exceeds the set threshold Wth is determined. The system calculates:

[0216] (U-U0)×I=(24.5-25.0)kV×100A=-0.5kV×100A=-50kW

[0217] The power fluctuation threshold Wth is set to 50kW. Determine whether to trigger adjustment:

[0218] ∣-50kW∣=50kW≥Wth=50kW

[0219] The results show that the power deviation has reached the adjustment condition.

[0220] Then, the required voltage adjustment amount is calculated according to the formula ΔU=ψ×(U-U0).

[0221] Here, ψ is a fourth proportional coefficient set by the system, which is used to reflect the amplification effect of power deviation on voltage adjustment and is generally set in the range of 0.1 to 0.5.

[0222] Continuing with the above example, if ψ=0.3, we have:

[0223] ΔU=0.3×(-0.5kV)×100A=-15V

[0224] Finally, the inverter output voltage is adjusted to U=U+ΔU.

[0225] The current inverter output voltage is 24.5kV, which is adjusted to:

[0226] U=24.5kV+(-15V)=24.485kV

[0227] Through the above-mentioned specific implementation methods, when the system detects that the power deviation exceeds the set range, it can calculate the compensation voltage in a timely manner based on the proportional adjustment model, and control the inverter to adjust the output in real time, effectively suppressing the load instability problem caused by voltage fluctuations, ensuring the traction system to continue to operate stably under critical working conditions (such as train start-up and acceleration), and improving the reliability and responsiveness of the power supply system.

[0228] In order to solve the problem of power instability caused by grid voltage fluctuation during the operation of high-speed trains and ensure the safety and reliability of train operation, the present application provides an embodiment of a power supply optimization device for a railway traction system for implementing all or part of the power supply optimization method for a railway traction system, see Figure 7 The power supply optimization device for the railway traction system specifically includes the following contents:

[0229] A voltage fluctuation prediction module 1101 is configured to input current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0230] a control parameter calculation module 1102, configured to determine a control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0231] The inverter adjustment module 1103 is configured to control the inverter to adjust the corresponding output voltage according to the control parameter until the deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter falls within a preset deviation range.

[0232] According to any embodiment of the present application, a regulation optimization module is further included, including:

[0233] a gain matrix calculation unit, configured to determine a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0234] A control parameter updating unit is configured to update the control parameters of the inverter according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

[0235] According to any embodiment of the present application, the voltage fluctuation prediction module is specifically used to:

[0236] The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

[0237] According to any embodiment of the present application, the control parameter calculation module includes:

[0238] an error calculation unit, configured to calculate the error value, cumulative error value, and error change rate of the current voltage based on the current voltage fluctuation parameter and the expected voltage fluctuation parameter and the proportional, integral, and differential adjustment modules of the PID controller;

[0239] A parameter determination unit is used to determine the control parameters of the railway traction system inverter according to the current error value, the accumulated error value and the error change rate.

[0240] According to any embodiment of the present application, the control parameter calculation module includes:

[0241] a frequency adjustment unit, configured to determine an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0242] A parameter calculation unit is used to determine a control parameter of the inverter according to the frequency adjustment amount.

[0243] According to any embodiment of the present application, the control parameter calculation module includes:

[0244] a neural network calculation unit, configured to input the expected voltage fluctuation parameter into a pre-built second neural network model to obtain a future voltage fluctuation trend;

[0245] The trend adjustment unit is used to determine the control parameters of the inverter according to the future voltage fluctuation trend adjustment amount.

[0246] According to any embodiment of the present application, after obtaining the corresponding expected voltage fluctuation parameter, the method further includes:

[0247] The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

[0248] According to any embodiment of the present application, it also includes:

[0249] a sliding window calculation unit, configured to smooth the current voltage fluctuation parameter and the expected voltage fluctuation parameter using a sliding window averaging algorithm;

[0250] The fuzzy control calculation unit is used to input the smoothed current voltage fluctuation parameter and the expected voltage fluctuation parameter into the fuzzy control algorithm.

[0251] According to any embodiment of the present application, the control parameter calculation module includes:

[0252] a voltage adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset first coefficient if a voltage deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold;

[0253] a frequency adjustment calculation unit, configured to determine a frequency adjustment amount according to the voltage deviation value and a preset second coefficient if a frequency deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold;

[0254] a load adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset third coefficient if a load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold;

[0255] The power adjustment calculation unit is configured to determine a voltage adjustment amount according to the voltage deviation value and a preset fourth coefficient if a power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold.

[0256] From a hardware perspective, in order to address the power instability issue caused by grid voltage fluctuations during high-speed train operation and ensure the safety and reliability of train operation, the present application provides an embodiment of an electronic device for implementing all or part of the power supply optimization method for a railway traction system. The electronic device specifically includes the following:

[0257] A processor, a memory, a communications interface, and a bus; wherein the processor, the memory, and the communications interface communicate with each other via the bus; the communications interface is used to transmit information between the power supply optimization device of the railway traction system and related devices such as the core business system, the user terminal, and related databases; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiment of the power supply optimization method for the railway traction system and the embodiment of the power supply optimization device for the railway traction system in the embodiment, and their contents are incorporated herein, and repeated parts are not repeated.

[0258] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0259] In practical applications, portions of the railway traction system power supply optimization method can be executed on the electronic device side as described above, or all operations can be performed on the client device. The specific selection can be based on the processing capabilities of the client device and the limitations of the user's usage scenario. This application does not impose any restrictions on this. If all operations are performed on the client device, the client device may also include a processor.

[0260] The client device may include a communication module (i.e., a communication unit) that can establish a communication connection with a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0261] Figure 8 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 8As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 8 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0262] In one embodiment, the power supply optimization method function of the railway traction system can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0263] Step S101: inputting current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0264] Step S102: determining control parameters of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0265] Step S103: controlling the inverter to adjust the corresponding output voltage according to the control parameter until the deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0266] As can be seen from the above description, the electronic device provided in the embodiment of the present application solves the problem of power instability caused by grid voltage fluctuations during the operation of high-speed trains, thereby ensuring the safety and reliability of train operation.

[0267] In another embodiment, the power supply optimization device of the railway traction system can be configured separately from the central processor 9100. For example, the power supply optimization device of the railway traction system can be configured as a chip connected to the central processor 9100, and the power supply optimization method function of the railway traction system can be realized through the control of the central processor.

[0268] like Figure 8 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 8 In addition, the electronic device 9600 may also include all components shown in Figure 8 For components not shown, reference may be made to the prior art.

[0269] like Figure 8As shown, the central processing unit 9100 is sometimes also referred to as a controller or operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0270] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0271] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0272] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0273] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0274] The communication module 9110 is a transmitter / receiver that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0275] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0276] Embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the power supply optimization method for a railway traction system in the above-mentioned embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all steps of the power supply optimization method for a railway traction system in the above-mentioned embodiment, where the execution subject is a server or a client, are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0277] Step S101: inputting current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0278] Step S102: determining control parameters of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0279] Step S103: controlling the inverter to adjust the corresponding output voltage according to the control parameter until the deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0280] As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application solves the problem of power instability caused by grid voltage fluctuations during the operation of high-speed trains, thereby ensuring the safety and reliability of train operation.

[0281] Embodiments of the present application also provide a computer program product capable of implementing all steps of the method for optimizing power supply for a railway traction system in the above-mentioned embodiment, where the execution subject is a server or a client. When the computer program / instructions are executed by a processor, the computer program / instructions implement the steps of the method for optimizing power supply for a railway traction system. For example, the computer program / instructions implement the following steps:

[0282] Step S101: inputting current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters;

[0283] Step S102: determining control parameters of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter;

[0284] Step S103: controlling the inverter to adjust the corresponding output voltage according to the control parameter until the deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

[0285] As can be seen from the above description, the computer program product provided in the embodiment of the present application solves the problem of power instability caused by grid voltage fluctuations during the operation of high-speed trains, thereby ensuring the safety and reliability of train operation.

[0286] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0287] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0288] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0289] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0290] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A method for optimizing power supply of a railway traction system, characterized in that: The method comprises: Inputting current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters; determining a control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; The inverter is controlled to adjust the corresponding output voltage according to the control parameter until a deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

2. The power supply optimization method for a railway traction system according to claim 1, characterized in that: After controlling the inverter to adjust the corresponding output voltage according to the control parameter, the method further includes: determining a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; The control parameters of the inverter are updated according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

3. The power supply optimization method for a railway traction system according to claim 1, characterized in that: The current voltage fluctuation parameters of the railway traction system are input into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, including: The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

4. The power supply optimization method for a railway traction system according to claim 1, characterized in that: The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes: Calculate the current voltage error value, cumulative error value, and error change rate based on the current voltage fluctuation parameter and the expected voltage fluctuation parameter using the proportional, integral, and differential adjustment modules of the PID controller; The control parameter is determined according to the current error value, the accumulated error value and the error change rate.

5. The power supply optimization method for a railway traction system according to claim 1, characterized in that: Also includes: determining an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; A control parameter of the inverter is determined according to the frequency adjustment amount.

6. The power supply optimization method for a railway traction system according to claim 1, characterized in that: Also includes: Inputting the expected voltage fluctuation parameter into a pre-built second neural network model to obtain a future voltage fluctuation trend; The control parameters of the inverter are determined according to the future voltage fluctuation trend adjustment amount.

7. The power supply optimization method for a railway traction system according to claim 1, characterized in that: After obtaining the corresponding expected voltage fluctuation parameter, the method further includes: The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

8. The power supply optimization method for a railway traction system according to claim 1, characterized in that: After obtaining the corresponding expected voltage fluctuation parameter, the method further includes: Smoothing the current voltage fluctuation parameter and the expected voltage fluctuation parameter by a sliding window averaging algorithm; The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes: The smoothed current voltage fluctuation parameter and the expected voltage fluctuation parameter are input into a fuzzy control algorithm to obtain the control parameters of the railway traction system inverter.

9. The method for optimizing power supply of a railway traction system according to claim 1, wherein: The determining the control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter includes: If a voltage deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold, determining a voltage adjustment amount according to the voltage deviation and a preset first coefficient; If the frequency deviation between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold, determining a frequency adjustment amount according to the voltage deviation and a preset second coefficient; If a load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold, determining a voltage adjustment amount according to the voltage deviation value and a preset third coefficient; If the power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold, a voltage adjustment amount is determined according to the voltage deviation value and a preset fourth coefficient.

10. A power supply optimization device for a railway traction system, characterized in that: The device comprises: a voltage fluctuation prediction module, configured to input current voltage fluctuation parameters of the railway traction system into a pre-built fluctuation prediction model to obtain corresponding expected voltage fluctuation parameters, wherein the fluctuation prediction model includes a linear regression model or a first neural network model, and the current voltage fluctuation parameters include current voltage parameters and previous fluctuation voltage parameters; a control parameter calculation module, configured to determine a control parameter of the railway traction system inverter according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; The inverter adjustment module is used to control the inverter to adjust the corresponding output voltage according to the control parameter until the deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter is within a preset deviation range.

11. The power supply optimization device for a railway traction system according to claim 10, characterized in that: Also includes a tuning optimization module, including: a gain matrix calculation unit, configured to determine a voltage error gain matrix according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; A control parameter updating unit is configured to update the control parameters of the inverter according to the gain matrix, so that the inverter adjusts the corresponding output voltage based on the control parameters.

12. The power supply optimization device for a railway traction system according to claim 10, characterized in that: The voltage fluctuation prediction module is specifically used for: The expected voltage fluctuation parameter is determined according to the current voltage parameter and the previous voltage fluctuation parameter, as well as the current voltage fluctuation weight and the previous voltage fluctuation weight preset in the pre-built fluctuation prediction model.

13. The power supply optimization device for a railway traction system according to claim 10, characterized in that: The control parameter calculation module includes: an error calculation unit, configured to calculate the error value, cumulative error value, and error change rate of the current voltage based on the current voltage fluctuation parameter and the expected voltage fluctuation parameter and the proportional, integral, and differential adjustment modules of the PID controller; A parameter determination unit is used to determine the control parameters of the railway traction system inverter according to the current error value, the accumulated error value and the error change rate.

14. The power supply optimization device for a railway traction system according to claim 10, characterized in that: The control parameter calculation module includes: a frequency adjustment unit, configured to determine an output frequency adjustment amount based on an adaptive filtering algorithm according to the current voltage fluctuation parameter and the expected voltage fluctuation parameter; A parameter calculation unit is used to determine a control parameter of the inverter according to the frequency adjustment amount.

15. The power supply optimization device for a railway traction system according to claim 10, characterized in that: The control parameter calculation module includes: a neural network calculation unit, configured to input the expected voltage fluctuation parameter into a pre-built second neural network model to obtain a future voltage fluctuation trend; The trend adjustment unit is used to determine the control parameters of the inverter according to the future voltage fluctuation trend adjustment amount.

16. The power supply optimization device for a railway traction system according to claim 10, characterized in that: After obtaining the corresponding expected voltage fluctuation parameters, it also includes: The expected voltage fluctuation parameter is filtered based on an adaptive Kalman filter.

17. The power supply optimization device for a railway traction system according to claim 10, characterized in that: Also includes: a sliding window calculation unit, configured to smooth the current voltage fluctuation parameter and the expected voltage fluctuation parameter using a sliding window averaging algorithm; The fuzzy control calculation unit is used to input the smoothed current voltage fluctuation parameter and the expected voltage fluctuation parameter into the fuzzy control algorithm.

18. The power supply optimization device for a railway traction system according to claim 10, characterized in that: The control parameter calculation module includes: a voltage adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset first coefficient if a voltage deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset first fluctuation threshold; a frequency adjustment calculation unit, configured to determine a frequency adjustment amount according to the voltage deviation value and a preset second coefficient if a frequency deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset second fluctuation threshold; a load adjustment calculation unit, configured to determine a voltage adjustment amount according to the voltage deviation value and a preset third coefficient if a load deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset third fluctuation threshold; The power adjustment calculation unit is configured to determine a voltage adjustment amount according to the voltage deviation value and a preset fourth coefficient if a power deviation value between the current voltage fluctuation parameter and the expected voltage fluctuation parameter exceeds a preset fourth fluctuation threshold.

19. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the power supply optimization method for a railway traction system according to any one of claims 1 to 9 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing power supply for a railway traction system according to any one of claims 1 to 9 are implemented.

21. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for optimizing power supply for a railway traction system according to any one of claims 1 to 9 are implemented.

Images