Access method, device and equipment of emergency power supply vehicle, medium and product

Abstract

The invention provides an emergency power supply vehicle access method, device and equipment, a medium and a product. The method comprises the following steps: acquiring a power grid voltage signal and an output voltage signal of the emergency power supply vehicle; performing anti-aliasing filtering processing on the power grid voltage signal and the output voltage signal to obtain an updated power grid voltage signal and an updated output voltage signal; inputting the updated power grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference; generating a target pulse width modulation signal according to the voltage phase difference and the updated power grid voltage signal; and according to the updated output voltage signal, the target pulse width modulation signal is sent to the emergency power supply vehicle, so that the emergency power supply vehicle is accessed to the power grid, and the access accuracy of the emergency power supply vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to an access method, device, equipment, medium and product for an emergency power supply vehicle. Background Art

[0002] With the acceleration of urbanization and the stringent requirements of critical infrastructure for power stability, emergency power supply vehicles have come into being. As the core backup power source in the event of distribution network failure, they are equipped with fast grid-connected control technology and can supply power to the distribution network at the moment of power outage, effectively reducing the losses and impacts caused by power outages. They are a key technology to ensure power supply reliability.

[0003] In the prior art, when an emergency power supply vehicle is connected to a power grid, a phase-locked loop (PLL) technology is usually used to detect the grid voltage phase, so as to achieve synchronization and stable grid-connected operation between the emergency power supply vehicle and the distribution network.

[0004] However, the detection accuracy of the above voltage phase is low, which reduces the access accuracy of the emergency power supply vehicle. Summary of the Invention

[0005] The present application provides an access method, device, equipment, medium and product for an emergency power supply vehicle, which are used to solve the technical problems in the prior art of low accuracy and large errors when the emergency power supply vehicle is connected to the power grid.

[0006] In a first aspect, the present application provides a method for connecting an emergency power supply vehicle, comprising:

[0007] Collect grid voltage signals and output voltage signals of emergency power supply vehicles;

[0008] performing anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal;

[0009] Inputting the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference;

[0010] generating a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal;

[0011] The target pulse width modulation signal is sent to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

[0012] Furthermore, generating a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal includes:

[0013] Performing frequency band and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal;

[0014] A target pulse width modulation signal is generated according to the voltage phase difference and the target grid voltage signal.

[0015] Further, performing frequency band decomposition and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal includes:

[0016] Performing frequency band decomposition processing on the updated grid voltage signal to determine frequency band energy ratio information of the updated grid voltage signal;

[0017] constructing a sparse basis matrix of the updated grid voltage signal according to the frequency band energy proportion information, wherein the sparse basis matrix is ​​used to represent the sparse characteristics of the updated grid voltage signal;

[0018] The updated grid voltage signal is harmonically processed according to the sparse base matrix to obtain a target grid voltage signal.

[0019] Furthermore, generating a target pulse width modulation signal according to the voltage phase difference and the target grid voltage signal includes:

[0020] Determining grid voltage status information and power supply switching status information based on the voltage phase difference and the target grid voltage signal, wherein the power supply switching status information refers to switching status information between the grid power supply and the emergency power supply vehicle;

[0021] Analyze the grid voltage state information and the power supply switching state information based on a deep learning algorithm to determine a voltage regulation weight and a switching rate weight;

[0022] A target pulse width modulation signal is generated according to the voltage regulation weight and the switching rate weight.

[0023] Furthermore, according to the updated output voltage signal, the target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid, including:

[0024] determining output power information of the emergency power supply vehicle according to the updated output voltage signal;

[0025] If the output power information of the emergency power supply vehicle meets the predicted power requirement, the target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid.

[0026] Furthermore, the step of sending the target pulse width modulation signal to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid includes:

[0027] sending the target pulse width modulation signal to the emergency power supply vehicle to adjust the switching state of the semiconductor module in the emergency power supply vehicle;

[0028] connecting the emergency power supply vehicle to the power grid according to the switching state of the semiconductor module;

[0029] The semiconductor module includes a gallium nitride switch and a silicon carbide switch.

[0030] Furthermore, the method of connecting the emergency power supply vehicle to a power grid according to the switching state of the semiconductor module further includes:

[0031] collecting electrode voltage information of the semiconductor module according to the switching state of the semiconductor module;

[0032] determining electrode voltage change information of the semiconductor module according to electrode voltage information of the semiconductor module;

[0033] If the electrode voltage change information of the semiconductor module meets the preset voltage change requirement, adjusting the switching parameters of the semiconductor module according to the Kalman filter algorithm to obtain an updated switching state of the semiconductor module;

[0034] The emergency power supply vehicle is connected to a power grid according to the updated switch state of the semiconductor module.

[0035] In a second aspect, the present application provides an access device for an emergency power supply vehicle, comprising:

[0036] Signal acquisition module, used to collect grid voltage signals and output voltage signals of emergency power supply vehicles;

[0037] an update signal obtaining module, configured to perform anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal;

[0038] a voltage phase difference obtaining module, configured to input the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference;

[0039] a target pulse width modulation signal generating module, configured to generate a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal;

[0040] The emergency power supply vehicle access module is used to send the target pulse width modulation signal to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

[0041] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0042] The memory stores computer-executable instructions;

[0043] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0045] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which implements the method as described in any one of the first aspects when executed by a processor.

[0046] The present application provides a method, device, equipment, medium, and product for connecting an emergency power supply vehicle. The method includes: collecting a grid voltage signal and an output voltage signal of the emergency power supply vehicle; performing anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal; inputting the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference; generating a target pulse width modulation signal based on the voltage phase difference and the updated grid voltage signal; and sending the target pulse width modulation signal to the emergency power supply vehicle based on the updated output voltage signal to connect the emergency power supply vehicle to the grid, thereby improving the connection accuracy of the emergency power supply vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] Figure 1 This is a flow chart of the first embodiment of the method for connecting an emergency power supply vehicle proposed in this application;

[0049] Figure 2 This is a flow chart of the second embodiment of the method for connecting an emergency power supply vehicle proposed in this application;

[0050] Figure 3 This is a flow chart of the third embodiment of the method for connecting an emergency power supply vehicle proposed in this application;

[0051] Figure 4 This is a flow chart of a fourth embodiment of the method for connecting an emergency power supply vehicle proposed in this application;

[0052] Figure 5 This is a flow chart of Embodiment 5 of the method for connecting an emergency power supply vehicle proposed in this application;

[0053] Figure 6 This is a schematic diagram of the structure of the access device of the emergency power supply vehicle proposed in this application;

[0054] Figure 7 This is a schematic diagram of the structure of the electronic device proposed in this application.

[0055] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0056] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0057] Existing emergency power supply grid-connected control solutions often use a fixed number of decomposition layers and static filtering strategies, making it difficult to adaptively adjust processing granularity based on changing signal characteristics, resulting in insufficient harmonic suppression. Furthermore, these systems lack real-time perception of grid status and power switching behavior, making them prone to insufficient control accuracy, response delays, and reduced thermal stability under variable loads and high temperatures. This limits the robustness and intelligence of the emergency power supply vehicle during connection.

[0058] To address these issues, this paper proposes a grid-connected control method for emergency power supply vehicles that integrates multi-agent reinforcement learning, extended Kalman filtering, and dynamic wavelet decomposition. By introducing a decomposition layer adaptive mechanism based on the rate of change of frequency band energy, a synergistic balance between signal processing accuracy and computational efficiency is achieved. Combining phase difference with grid status information, the reinforcement learning framework dynamically allocates pulse-width modulation signals and switching rate weights, improving the real-time and robustness of grid-connected control.

[0059] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0060] Figure 1 This is a flow chart of an embodiment 1 of a method for accessing an emergency power supply vehicle provided by this application. Figure 1 Shown, including:

[0061] S101. Collecting grid voltage signals and output voltage signals of emergency power supply vehicles.

[0062] In an embodiment of the present application, in order to achieve synchronous acquisition of the grid voltage signal in the low-voltage power supply area and the output voltage signal of the emergency power supply vehicle, the present application adopts the collaborative working mode of the Rogowski coil and the isolation amplifier to detect and process the voltage signal.

[0063] Rogowski coils are used for passive sensing to acquire the rate of change of AC voltage signals. They offer fast response, wide bandwidth, and a compact size, making them suitable for contactless sampling of voltages on the grid and emergency power supply sides. Differential isolation amplifiers perform differential amplification on the voltage signals output by the Rogowski coils and provide the necessary electrical isolation to ensure safe isolation between the high-voltage and low-voltage control sides, while maintaining signal transmission integrity.

[0064] Specifically, Rogowski coils are placed in the grid power supply circuit and the emergency power supply vehicle output circuit to sense AC voltage changes in each circuit. The collected raw analog signal is processed by a differential isolation amplifier and converted into a stable analog voltage signal. This signal is then input into a data acquisition module (such as an ADC or edge computing unit) for subsequent voltage amplitude and phase analysis.

[0065] Through the above method, high-precision, low-latency synchronous acquisition of the grid voltage signal and the emergency power supply vehicle output voltage signal can be achieved, providing a reliable electrical signal foundation for subsequent phase difference calculation, power grid connection control, dynamic weight allocation and other functions.

[0066] S102 : performing anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal.

[0067] In an embodiment of the present application, in order to ensure the accuracy of sampling and processing of the grid voltage signal and the emergency power supply vehicle output voltage signal, and to prevent high-frequency noise or non-target frequency band signals from interfering with subsequent signal analysis, this step performs anti-aliasing filtering on the above two types of voltage signals respectively.

[0068] Specifically, the collected grid voltage signal and output voltage signal are input into the anti-aliasing filter unit, which can be a low-pass filter with a cutoff frequency matching the sampling frequency to effectively filter out interference components above the Nyquist frequency (i.e., half the sampling frequency) and suppress the occurrence of aliasing effects.

[0069] The filtered signals are recorded as the updated grid voltage signal and the updated output voltage signal, respectively. These serve as preprocessing data for subsequent phase difference analysis, voltage amplitude calculation, or grid-connected control. This filtering step significantly improves signal quality, enhancing signal processing stability and anti-interference capabilities.

[0070] S103 : Inputting the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference.

[0071] In this embodiment, to achieve real-time estimation of the phase difference between the grid voltage signal and the emergency power supply vehicle output signal, the preprocessed updated grid voltage signal and the updated output voltage signal can be input into the phase prediction model of the long short-term memory network. The phase prediction model is used to extract the time series characteristics of the input signal and predict the voltage phase difference at the current moment through the hidden state of the model. Specifically, it mainly includes:

[0072] The input features at the current moment [h t-1 ,U′ grid (t)-U′ ess (t)] and the weight matrix W h , bias term b h Working together, the hidden state h is obtained through the activation function σ t :

[0073] h t =σ(W h ×[h t-1 , U′ grid (t)-U′ ess (t)]]b h )

[0074] Among them, U′ grid (t) represents the updated grid voltage, U′ ess (t) represents the updated output voltage. Finally, the output weight W o and the bias term b o , mapping the hidden state to the phase difference prediction value Δθ(t):

[0075] Δθ(t)=W o ×h t +b o

[0076] Through the above structure, the phase prediction model can extract the characteristic changes of the current voltage signal while considering the influence of historical states, thereby realizing dynamic prediction of the phase difference between the two voltage signals.

[0077] S104 : Generate a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal.

[0078] In this embodiment, in order to achieve inverter control of the output voltage of the emergency power supply vehicle and further improve the grid connection quality, a target pulse width modulation signal can be generated based on the above-mentioned predicted voltage phase difference and the updated grid voltage signal to drive the inverter unit of the emergency power supply vehicle to output a synchronous voltage.

[0079] Furthermore, generating a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal includes:

[0080] Perform frequency band and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal;

[0081] A target pulse width modulation signal is generated according to the voltage phase difference and the target grid voltage signal.

[0082] Specifically, before generating the target pulse-width modulation signal, the updated grid voltage signal is first subjected to frequency band filtering and harmonic suppression to obtain the target grid voltage signal. Frequency band processing is used to extract the fundamental component and suppress high-frequency harmonics and noise interference, thereby improving the waveform quality and prediction accuracy of the target grid voltage signal.

[0083] S105 . Send a target pulse width modulation signal to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

[0084] In this embodiment, in order to achieve high-quality grid-connected control between the emergency power supply vehicle and the power grid, the generated target pulse width modulation signal can be sent to the inverter control module of the emergency power supply vehicle to drive its power inverter unit to generate a synchronous output voltage.

[0085] Specifically, after the emergency power supply vehicle receives the target pulse width modulation signal, the semiconductor module inside it can perform switching operations according to the signal to generate an AC voltage output that matches the grid voltage phase and frequency, thereby achieving a shock-free, low-harmonic, and highly synchronized grid integration process.

[0086] Through the embodiments of the present application, dynamic grid-connected control of the emergency power supply vehicle is effectively realized, ensuring that its output power can be safely and stably connected to the power grid in the low-voltage power supply area, thereby improving the power utilization efficiency and the robustness of the power supply system.

[0087] Figure 2 This is a flow chart of the second embodiment of the method for accessing the emergency power supply vehicle provided by this application. Figure 2 As shown, in Figure 1 Based on the embodiment, frequency band decomposition and harmonic processing are performed on the updated grid voltage signal to obtain a target grid voltage signal, including:

[0088] S201 : Perform frequency band decomposition processing on an updated grid voltage signal to determine frequency band energy ratio information of the updated grid voltage signal.

[0089] In this step, to extract and update the frequency domain characteristics of the grid voltage signal, the present embodiment uses wavelet packet decomposition to perform frequency band decomposition on the signal. Wavelet packet decomposition is a multi-resolution analysis tool that can finely divide the voltage signal into multiple frequency bandwidths, making it suitable for extracting complex frequency components from grid signals.

[0090] Specifically, the updated grid voltage signal is input into the wavelet packet decomposition module. At different decomposition levels, the energy proportion information of each frequency band is calculated respectively. The frequency band energy proportion information is used to measure the importance of each frequency band in the voltage signal.

[0091] For example, the updated grid voltage signal U′ grid (t) Perform wavelet packet decomposition and calculate the k ,f k+1 ] calculate the energy ratio E k And its rate of energy change over time:

[0092]

[0093] Wherein, Δt is the preset sampling time, and t is the current sampling moment.

[0094] When a certain frequency band k meets the following conditions of intense energy change: E k >0.15×∑E k And ΔE k >0.1×E k , it is determined that the frequency band has significant dynamic characteristics, and the current wavelet decomposition level is increased by one level: N←N+1.

[0095] If the total number of decomposed frequency bands exceeds the preset upper limit N max , some frequency bands are merged (adjacent frequency bands whose bandwidth is less than the minimum threshold are preferentially merged), and the sparse basis matrix Φ used for subsequent sparse representation is updated. For details, see S202.

[0096] S202: Construct a sparse basis matrix for updating the grid voltage signal according to the frequency band energy ratio information.

[0097] In this step, in order to achieve sparse expression of the signal in the compressed sensing model, a sparse basis matrix Φ may be constructed based on the frequency band energy proportion information obtained in S201.

[0098] Exemplarily, from the current frequency band decomposition result, the first M wavelet node coefficients with the highest energy proportion are selected and extracted as the principal component basis vectors.

[0099] The Gram-Schmidt intersection algorithm is used to process these principal component basis vectors to generate an orthogonal basis vector group Φ orth, in order to improve the stability and solvability of subsequent sparse expressions.

[0100] The orthogonal basis set Φ orth Combined with the preset redundant dictionary D, a complete sparse basis matrix Φ = [Φ orth , D], where the redundant dictionary D is usually composed of the convolution of Gaussian kernel function and rectangular window function, which is used to enhance the ability to capture non-stationary features.

[0101] The sparse basis matrix Φ is used to represent the sparse characteristics of the updated grid voltage signal. It is a linear transformation that projects the original signal into the sparse domain. The matrix is ​​constructed based on the wavelet packet basis function. Its structure can dynamically adjust the priority and configuration according to the frequency band energy. After the construction is completed, the updated grid voltage signal can be expressed as:

[0102] U′ grid (t)≈Φ×U″ grid (t)

[0103] Among them, U grid (t) is the signal coefficient under sparse representation, that is, the target grid voltage signal finally obtained in this embodiment.

[0104] S203 . Perform harmonic processing on the updated grid voltage signal according to the sparse basis matrix to obtain a target grid voltage signal.

[0105] In this step, based on the sparse basis matrix Φ constructed in S202, the grid voltage signal U′ is updated. grid (t) Perform harmonic suppression processing and reconstruct the signal through compressed sensing method to obtain the target grid voltage signal.

[0106] Specifically, in order to further improve the harmonic suppression capability and signal reconstruction accuracy, this embodiment solves the following optimization problem under the compressed sensing framework:

[0107] min||φ×″ grid (t)||1s.t.||U′ grid (t)Φ×U″ grid (t)||2≤ε

[0108] Among them, ||Φ×U″ grid (t)||1 represents minimizing the L1 norm of the sparse coefficients to enhance the sparsity of the representation, thereby highlighting the main components and weakening harmonic interference.

[0109] ||U′ grid (t)-Φ×U″ grid (t)||2≤ε is the reconstruction error constraint, which ensures that the reconstructed signal is close to the original updated grid voltage signal in amplitude and phase.

[0110] After the solution is completed, the sparse coefficient vector U″ grid (t) Inverse transformation under sparse basis Φ (i.e. Φ×U″ grid (t)), the target grid voltage signal with effectively suppressed harmonics is obtained. This signal not only has high waveform fidelity but also eliminates most high-order harmonics and noise interference, providing reliable support for the subsequent generation of a precise target pulse-width modulation signal based on this target voltage signal.

[0111] Through the embodiments of this application, the updated grid voltage signal is processed through frequency band decomposition, sparse basis construction, and compressed sensing reconstruction. This effectively extracts the main frequency components of the signal, suppresses high-order harmonics and interference noise, and improves signal purity and controllability. This processing method has high adaptability and signal fidelity, providing a high-quality target grid voltage signal foundation for subsequent pulse width modulation signal generation and emergency power grid connection control, thereby improving the system's power quality and dynamic response performance.

[0112] Figure 3 This is a flow chart of the third embodiment of the access method for the emergency power supply vehicle to be withdrawn from this application. Figure 3 As shown, in Figure 1 Based on the embodiment, generating a target pulse width modulation signal according to the voltage phase difference and the target grid voltage signal includes:

[0113] S301 : Determine grid voltage status information and power supply switching status information according to a voltage phase difference and a target grid voltage signal.

[0114] This step determines two key information in the current operating state based on the acquired voltage phase difference and the target grid voltage signal, including grid voltage state information and power supply switching state information.

[0115] Among them, the grid voltage status information includes the amplitude, frequency fluctuation, harmonic characteristics and phase change trend of the target grid voltage; the power supply switching status information is used to indicate whether the current power supply is provided by the main grid, or whether it is in the switching stage where the emergency power supply vehicle takes over the power supply, or is in the grid synchronization.

[0116] The above state information can be constructed into a state vector S through the feature extraction module for use as the state input of the subsequent deep reinforcement learning model. The process of constructing the state vector is not shown in detail in this step.

[0117] S302: Analyze the grid voltage status information and the power supply switching status information based on a deep learning algorithm to determine a voltage regulation weight and a switching rate weight.

[0118] In this step, based on the above state vector s, a multi-agent reinforcement learning algorithm can be used to dynamically allocate two key parameters in the control strategy, namely the voltage regulation weight and the switching rate weight, to achieve grid-connected control decision-making.

[0119] Specifically, each agent corresponds to a single sub-control strategy, such as the voltage regulation agent that adjusts the pulse width modulation duty cycle and the switching rate agent that adjusts the switching frequency. The agent updates its Q-value function through training, which is as follows:

[0120]

[0121] Among them, Q RL represents the expected cumulative reward of taking action a in state s; α represents the learning rate; γ represents the discount factor; r t represents the immediate reward function, which is composed of factors including power error, phase difference error, energy efficiency, etc.; s t+1 Indicates the new state after state transition.

[0122] In addition, the immediate reward function r t Harmonic penalty coefficient k harm The adjustment method may include the following steps:

[0123] Real-time calculation of the harmonic distortion rate THD of the emergency power supply vehicle output current I (t);

[0124] According to THD I (t) and THD(U″) grid (t)) difference ΔTHD(t), dynamic correction k harm value:

[0125]

[0126] Among them, θ th To preset the harmonic distortion threshold, THD grid (t) represents the total harmonic distortion rate of the reconstructed grid voltage signal at time t.

[0127] In order to improve the safety performance of grid-connected control, the embodiment of the present application uses the reward function r t The power penalty coefficient h is introduced in power This coefficient is used to dynamically adjust the instant reward value of the voltage regulation and switching rate related strategies to prevent the emergency power supply vehicle from overloading.

[0128] Specifically, the power penalty coefficient is calculated as follows:

[0129]

[0130] Among them, P ess (t) represents the output power of the emergency power supply vehicle at time t, P th is the set output power threshold; k0 is the reference power penalty coefficient. ess When (t) is less than or equal to the threshold, a linear function is used to enhance the effect of output power on the reward value; when P ess When (t) exceeds the threshold, a logarithmic function is used to control the growth rate to limit the aggressive control behavior of the system under high load conditions, thereby ensuring the safety and energy efficiency optimization of the emergency power supply system during the grid connection process.

[0131] Through this differentiated processing strategy, the strategy update direction of each control agent in reinforcement learning can be adaptively adjusted according to the current output load situation, effectively improving the robustness and responsiveness of the grid-connected control system in multi-state scenarios.

[0132] S303 : Generate a target pulse width modulation signal according to the voltage adjustment weight and the switching rate weight.

[0133] In this step, based on the voltage regulation weight and switching rate weight output by the multi-agent reinforcement learning algorithm in S302, a target pulse width modulation signal is comprehensively generated to drive the emergency power supply vehicle to complete grid access control.

[0134] Specifically, the voltage regulation weight controls the duty cycle of the pulse-width modulation signal, which determines the amplitude regulation capability of the inverter output voltage to meet the synchronization requirements of the target grid voltage waveform; while the switching rate weight controls the switching frequency of the pulse-width modulation signal, which affects the dynamic response speed and harmonic performance of the inverter output, and has a significant impact on the power quality, especially during power switching.

[0135] Based on this, the control module dynamically adjusts the pulse width modulator's control signal according to the two weight parameters, generating an adaptive target pulse width modulation signal. This target pulse width modulation signal is transmitted in real time to the emergency power supply vehicle's power device control terminal, ensuring that the inverter output voltage driven by the target pulse width modulation signal quickly responds to changes in the target grid voltage, achieving high-precision tracking control of voltage, frequency, and phase.

[0136] The embodiment of the present application constructs a grid state perception and power switching identification mechanism based on the voltage phase difference and the target grid voltage signal, combines the multi-agent reinforcement learning algorithm, dynamically allocates voltage regulation weights and switching rate weights, and generates a pulse width modulation control signal with adaptive capabilities, thereby achieving high-precision control of the inverter process of the emergency power supply vehicle, while ensuring voltage synchronization, optimizing the dynamic response and energy efficiency performance of the power switching process, thereby improving the grid system's non-sensing grid connection capability, power quality and operational stability.

[0137] Figure 4 This is a flow chart of the fourth embodiment of the access method for the emergency power supply vehicle to be withdrawn from this application. Figure 4 As shown, in Figure 1 Based on the embodiment, according to the updated output voltage signal, a target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid, including:

[0138] S401. Determine output power information of the emergency power supply vehicle according to the updated output voltage signal.

[0139] In the embodiment of the present application, the updated output voltage signal is first used, and combined with the actual output current of the emergency power supply vehicle obtained by the current sensor, the formula is as follows:

[0140] P ess (t) = U ess (t)×I ess (t)

[0141] The above formula can calculate the output power P of the emergency power supply vehicle at the current time t in real time. ess (t), this power information not only reflects the current load status of the emergency power supply vehicle, but also provides a basic basis for judging whether it has the ability to be connected to the grid.

[0142] S402: If the output power information of the emergency power supply vehicle meets the predicted power requirement, a target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid.

[0143] In this step, the calculated output power information of the emergency power supply vehicle is compared with the preset predicted power range [P min , P max ] for comparison, when the following formula is satisfied:

[0144] P min ≤P ess (t)≤P max

[0145] It is judged that the current emergency power supply vehicle has the ability to provide stable power supply, and the target pulse width modulation signal can be sent to start the emergency power supply vehicle to connect to the power grid. min Indicates the minimum power, P max Indicates the maximum power.

[0146] S403: Send the target pulse width modulation signal to the emergency power supply vehicle to adjust the switching state of the semiconductor module in the emergency power supply vehicle.

[0147] Based on S402, the target pulse width modulation signal is mainly used to drive the power device module inside the emergency power supply vehicle, mainly including gallium nitride switches and silicon carbide switches. The target pulse width modulation signal can control the switch state of the controller, and then adjust the output power, phase and amplitude of the emergency power supply vehicle to achieve synchronization with the power grid.

[0148] S404: Connect the emergency power supply vehicle to the power grid according to the switch status of the semiconductor module.

[0149] In this step, when the gallium nitride switch and silicon carbide switch in the semiconductor module enter the stable on and off state under the control of the target pulse width modulation signal, the voltage waveform output by the emergency power supply vehicle is easy to synchronize with the target grid voltage. At this time, the grid connection operation of the low-voltage substation can be completed, and the "seamless access" of the emergency power supply vehicle can be realized.

[0150] The embodiment of this application calculates the output power of the emergency power supply vehicle in real time based on the updated output voltage signal, and determines whether it meets the grid connection conditions. On this basis, it generates and sends the target pulse width modulation signal, accurately drives high-performance power devices such as silicon carbide switches and gallium nitride switches, controls their switching behavior, and achieves rapid synchronization of voltage, frequency, and phase. This solution can effectively improve the intelligence and reliability of the emergency power supply vehicle's access to the grid, realize dynamic power evaluation and efficient, imperceptible grid connection control, and ensure the power supply stability and energy efficiency performance of the low-voltage power supply area.

[0151] Figure 5 This is a flow chart of the fifth embodiment of the method for accessing the emergency power supply vehicle for withdrawal of this application. Figure 5 As shown, in Figure 4 Based on the embodiment, the emergency power supply vehicle is connected to the power grid according to the switch state of the semiconductor module, and the method further includes:

[0152] S501 : Collect electrode voltage information of the semiconductor module according to the switching state of the semiconductor module.

[0153] In this step, the drain-source voltage V ds (t) is used as the key observation variable of the extended Kalman filter algorithm to provide the actual measurement data basis for subsequent filtering calculations.

[0154] S502 : Determine electrode voltage change information of the semiconductor module according to electrode voltage information of the semiconductor module.

[0155] In this step, the collected By performing time mentor calculation, we can get its rate of change The rate of change represents the dynamic response speed of the device's conduction state change. The change in response speed can indicate that the device is currently in a high dynamic load or unstable operation stage.

[0156] S503: If the electrode voltage change information of the semiconductor module meets the preset voltage change requirement, the switching parameters of the semiconductor module are adjusted according to the Kalman filter algorithm to obtain an updated switching state of the semiconductor module.

[0157] Based on the electrode voltage change information of the semiconductor module determined in S502, it is determined Whether it exceeds the preset threshold, or the emergency power supply output power P ess (t) exceeds the set ratio of rated power, the observation noise covariance matrix R is dynamically adjusted according to the following rules:

[0158]

[0159] At the same time, in order to enhance the adaptability of the emergency power supply vehicle to high temperature environment, the semiconductor switch temperature T j Dynamically adjust the process noise covariance matrix Q in the Kalman filter proc :

[0160]

[0161] Among them, T th is the junction temperature threshold, Q0 is the initial covariance matrix at room temperature 25°C, Q proc represents the statistical parameters of process noise in the system model in the extended Kalman filter algorithm. This allows for more accurate semiconductor switch states to be obtained, and updated switch control instructions to be generated accordingly.

[0162] S504: Connect the emergency power supply vehicle to the power grid according to the updated switch status of the semiconductor module.

[0163] In this step, the switching behavior of the SiC and GaN modules is adjusted based on the updated switching state obtained in S503, ultimately driving the inverter circuit to output AC power that matches the grid, achieving highly synchronized grid connection. The entire process dynamically responds to environmental changes (such as temperature and load), ensuring a safe, stable, and disturbance-free grid connection.

[0164] Based on the collection and trend analysis of key semiconductor device electrode voltages (such as drain-source voltage), this embodiment of the application constructs an extended Kalman filter algorithm to accurately estimate the dynamic switching state of power devices. This algorithm also introduces a dynamic adjustment mechanism for the process and observation noise covariance based on the device temperature and operating voltage change rate, thereby achieving robust control under high temperature and high load conditions. Furthermore, the pulse width modulation signal output is further adjusted using updated control parameters, ensuring that grid-connected control maintains rapid response and thermal stability under complex operating conditions, significantly improving grid connection accuracy and system operational reliability.

[0165] Figure 6 This is a schematic diagram of the structure of the access device of the emergency power supply vehicle provided in this application. Figure 6 As shown, the access device 60 of the emergency power supply vehicle includes:

[0166] Signal acquisition module 601, used to collect grid voltage signals and output voltage signals of emergency power supply vehicles;

[0167] An updated signal obtaining module 602 is configured to perform anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal;

[0168] A voltage phase difference obtaining module 603 is configured to input the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference;

[0169] A target pulse width modulation signal generating module 604 is configured to generate a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal;

[0170] The emergency power supply vehicle access module 605 is configured to send a target pulse width modulation signal to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

[0171] Furthermore, the target pulse width modulation signal generating module 604 is further specifically configured to:

[0172] Perform frequency band and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal;

[0173] A target pulse width modulation signal is generated according to the voltage phase difference and the target grid voltage signal.

[0174] Furthermore, the target pulse width modulation signal generating module 604 is further specifically configured to:

[0175] Performing frequency band decomposition processing on the updated grid voltage signal to determine frequency band energy ratio information of the updated grid voltage signal;

[0176] According to the frequency band energy ratio information, a sparse basis matrix for updating the grid voltage signal is constructed. The sparse basis matrix is ​​used to represent the sparse characteristics of the updated grid voltage signal.

[0177] According to the sparse basis matrix, the updated grid voltage signal is harmonically processed to obtain the target grid voltage signal.

[0178] Furthermore, the target pulse width modulation signal generating module 604 is further specifically configured to:

[0179] Determine the grid voltage status information and power supply switching status information based on the voltage phase difference and the target grid voltage signal. The power supply switching status information refers to the switching status information between the grid power supply and the emergency power supply vehicle.

[0180] Analyze the grid voltage status information and power supply switching status information based on deep learning algorithms to determine the voltage regulation weight and switching rate weight;

[0181] A target pulse width modulation signal is generated according to the voltage regulation weight and the switching rate weight.

[0182] Furthermore, the emergency power supply vehicle access module 605 is also specifically used for:

[0183] Determine the output power information of the emergency power supply vehicle according to the updated output voltage signal;

[0184] If the output power information of the emergency power supply vehicle meets the predicted power requirement, the target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid.

[0185] Furthermore, the emergency power supply vehicle access module 605 is also specifically used for:

[0186] Sending a target pulse width modulation signal to the emergency power supply vehicle to adjust the switching state of the semiconductor module in the emergency power supply vehicle;

[0187] Connect the emergency power supply vehicle to the power grid according to the switching status of the semiconductor module;

[0188] Among them, the semiconductor module includes gallium nitride switches and silicon carbide switches.

[0189] Furthermore, the emergency power supply vehicle access module 605 is also specifically used for:

[0190] Collecting electrode voltage information of the semiconductor module according to the switching state of the semiconductor module;

[0191] Determining electrode voltage change information of the semiconductor module based on electrode voltage information of the semiconductor module;

[0192] If the electrode voltage change information of the semiconductor module meets the preset voltage change requirement, the switching parameters of the semiconductor module are adjusted according to the Kalman filter algorithm to obtain an updated switching state of the semiconductor module;

[0193] The emergency power supply vehicle is connected to the power grid according to the updated switch status of the semiconductor module.

[0194] Figure 7 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 includes:

[0195] The electronic device 70 may include one or more processors 701 , one or more computer-readable storage media memories 702 , a communication component 703 , and other components. The processor 701 , the memory 702 , and the communication component 703 are connected via a bus 704 .

[0196] During the specific implementation process, at least one processor 701 executes the computer execution instructions stored in the memory 702, so that the at least one processor 701 executes the above-mentioned emergency power supply vehicle access method.

[0197] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0198] In the above Figure 7 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0199] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0200] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0201] In some embodiments, a computer program product is further proposed, including a computer program or instructions, which, when executed by a processor, implements the steps in any of the above-mentioned emergency power supply vehicle access methods.

[0202] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0203] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0204] To this end, an embodiment of the present application provides a computer-readable storage medium, which stores multiple instructions that can be loaded by a processor to execute the steps in any emergency power supply vehicle access method provided in the embodiment of the present application.

[0205] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0206] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0207] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0208] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0209] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0210] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0211] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0212] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0213] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0214] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0215] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for connecting an emergency power supply vehicle, characterized in that: include: Collect grid voltage signals and output voltage signals of emergency power supply vehicles; performing anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal; Inputting the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference; generating a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal; The target pulse width modulation signal is sent to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

2. The access method according to claim 1, wherein: Generating a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal includes: Performing frequency band and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal; A target pulse width modulation signal is generated according to the voltage phase difference and the target grid voltage signal.

3. The access method according to any one of claims 1 or 2, characterized in that: Performing frequency band decomposition and harmonic processing on the updated grid voltage signal to obtain a target grid voltage signal includes: Performing frequency band decomposition processing on the updated grid voltage signal to determine frequency band energy ratio information of the updated grid voltage signal; constructing a sparse basis matrix of the updated grid voltage signal according to the frequency band energy proportion information, wherein the sparse basis matrix is ​​used to represent the sparse characteristics of the updated grid voltage signal; The updated grid voltage signal is harmonically processed according to the sparse base matrix to obtain a target grid voltage signal.

4. The access method according to any one of claims 1 or 2, characterized in that: Generating a target pulse width modulation signal according to the voltage phase difference and the target grid voltage signal, comprising: Determining grid voltage status information and power supply switching status information based on the voltage phase difference and the target grid voltage signal, wherein the power supply switching status information refers to switching status information between the grid power supply and the emergency power supply vehicle; Analyze the grid voltage state information and the power supply switching state information based on a deep learning algorithm to determine a voltage regulation weight and a switching rate weight; A target pulse width modulation signal is generated according to the voltage regulation weight and the switching rate weight.

5. The access method according to claim 1, wherein: Sending the target pulse width modulation signal to the emergency power supply vehicle according to the updated output voltage signal to connect the emergency power supply vehicle to the power grid includes: determining output power information of the emergency power supply vehicle according to the updated output voltage signal; If the output power information of the emergency power supply vehicle meets the predicted power requirement, the target pulse width modulation signal is sent to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid.

6. The access method according to claim 5, characterized in that: Sending the target pulse width modulation signal to the emergency power supply vehicle to connect the emergency power supply vehicle to the power grid includes: sending the target pulse width modulation signal to the emergency power supply vehicle to adjust the switching state of the semiconductor module in the emergency power supply vehicle; connecting the emergency power supply vehicle to the power grid according to the switching state of the semiconductor module; The semiconductor module includes a gallium nitride switch and a silicon carbide switch.

7. The access method according to claim 6, characterized in that: The method further comprises connecting the emergency power supply vehicle to a power grid according to the switch state of the semiconductor module: collecting electrode voltage information of the semiconductor module according to the switching state of the semiconductor module; determining electrode voltage change information of the semiconductor module according to electrode voltage information of the semiconductor module; If the electrode voltage change information of the semiconductor module meets the preset voltage change requirement, adjusting the switching parameters of the semiconductor module according to the Kalman filter algorithm to obtain an updated switching state of the semiconductor module; The emergency power supply vehicle is connected to a power grid according to the updated switch state of the semiconductor module.

8. An access device for an emergency power supply vehicle, characterized in that: include: Signal acquisition module, used to collect grid voltage signals and output voltage signals of emergency power supply vehicles; an update signal obtaining module, configured to perform anti-aliasing filtering on the grid voltage signal and the output voltage signal to obtain an updated grid voltage signal and an updated output voltage signal; a voltage phase difference obtaining module, configured to input the updated grid voltage signal and the updated output voltage signal into a phase prediction model to obtain a voltage phase difference; a target pulse width modulation signal generating module, configured to generate a target pulse width modulation signal according to the voltage phase difference and the updated grid voltage signal; The emergency power supply vehicle access module is used to send the target pulse width modulation signal to the emergency power supply vehicle according to the updated output voltage signal, so as to connect the emergency power supply vehicle to the power grid.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images