Load type identification method, device, and non-volatile storage medium

Abstract

This invention discloses a load type identification method, apparatus, and non-volatile storage medium. The method includes: injecting a disturbance signal when a solid-state transformer is in a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain a target voltage signal and a target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; and determining the load electrical fingerprint feature vector. This invention solves the technical problems of low accuracy in passive identification of existing solid-state transformers and the inability of fixed control strategies to adapt to diverse loads, resulting in output characteristic mismatch, inefficient equipment operation, and susceptibility to damage.

Description

Technical Field

[0001] This invention relates to the fields of new energy and energy-saving technology, and more specifically, to a load type identification method, device, and non-volatile storage medium. Background Technology

[0002] Solid-state transformers, as a new generation of power electronic transformers, offer advantages such as flexible and controllable output voltage, frequency, and waveform. However, existing solid-state transformers typically employ fixed output control strategies, which cannot adapt to the diversity of mixed loads (such as asynchronous motors, switching power supplies, and frequency converters) in actual power distribution rooms. If the output characteristics do not match the load demand, it may lead to low equipment operating efficiency, overheating, or even damage.

[0003] In addition, existing load identification methods mainly rely on passive monitoring of operating data. This approach is greatly affected by actual load conditions, has limited identification accuracy, and requires a long period of data accumulation to obtain reliable results, making it impossible to achieve rapid adaptive adjustment of equipment.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a load type identification method, apparatus, and non-volatile storage medium to at least solve the technical problems of output characteristic mismatch, inefficient equipment operation, and easy damage caused by the low passive identification accuracy of existing solid-state transformers and the inability of fixed control strategies to adapt to load diversity.

[0006] According to one aspect of the present invention, a load type identification method is provided, comprising: injecting a disturbance signal when a solid-state transformer is in a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain a target voltage signal and a target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; determining a load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; and performing similarity matching between the load electrical fingerprint feature vector and multiple load characteristics in a preset load characteristic database to determine the load type corresponding to the output terminal of the solid-state transformer, wherein the preset load characteristic database includes multiple load characteristics and the load types corresponding to each of the multiple load characteristics.

[0007] Optionally, the disturbance signal is based on a superposition of sinusoidal signals of multiple frequencies.

[0008] Optionally, frequency domain transformation is performed on the target voltage signal and the target current signal to determine the impedance frequency response characteristics, including: performing frequency domain transformation on the target voltage signal and the target current signal to determine the complex frequency domain components of multiple disturbance frequency points corresponding to each of the target voltage signal and the target current signal; based on the complex frequency domain components at the disturbance frequencies corresponding to each of the target voltage signal and the target current signal, calculating the complex impedance amplitude and phase angle at at least three disturbance frequency points corresponding to each of the target voltage signal and the target current signal to obtain the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal; and determining the impedance frequency response characteristics based on the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal.

[0009] Optionally, the load electrical fingerprint feature vector is matched with multiple templates in a pre-set load feature database to determine the load type corresponding to the output terminal of the solid-state transformer. This includes: calculating the Euclidean distance between the load electrical fingerprint feature vector and multiple templates to determine the Euclidean distances corresponding to multiple load features; normalizing the Euclidean distances corresponding to multiple load features to determine the similarity of each load feature; and determining the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to the load features whose similarity meets preset conditions, according to the pre-set load feature database.

[0010] Optionally, based on a pre-set load feature database, the load type corresponding to the output terminal of the solid-state transformer is determined according to the load type corresponding to the load features whose similarity meets a preset condition. This includes: sorting multiple load features according to their similarity order to obtain a load feature sequence; determining the first load feature in the load feature sequence as a candidate load feature; calculating the similarity difference between the first and second load features in the load feature sequence; determining the confidence level based on the similarity difference; and, if the confidence level exceeds a preset threshold, determining the load type corresponding to the candidate load feature as the load type corresponding to the output terminal of the solid-state transformer based on the pre-set load feature database.

[0011] Optionally, based on the load type, a target parameter set corresponding to the solid-state transformer is determined according to a preset control parameter mapping table. The target parameter set includes output impedance, voltage support strength, harmonic suppression threshold, and dynamic response speed. A preset exponential transition function is used to smoothly interpolate multiple parameters in the target parameter set to generate control command sequences corresponding to each parameter. The control command sequences corresponding to each parameter are then injected into the voltage loop controller and current loop controller of the solid-state transformer.

[0012] According to another aspect of the present invention, a load type identification device is also provided, comprising: an injection module for injecting a disturbance signal when a solid-state transformer is in a preset time period; an acquisition module for acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; a processing module for filtering the output voltage response signal and load current response signal to obtain a target voltage signal and a target current signal; a first determination module for performing frequency domain transformation on the target voltage signal and target current signal to determine impedance frequency response characteristics; an extraction module for extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; a second determination module for determining a load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; and a matching module for performing similarity matching between the load electrical fingerprint feature vector and multiple load characteristics in a preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer, wherein the preset load feature database includes multiple load characteristics and the load types corresponding to each of the multiple load characteristics.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, it controls the device where the non-volatile storage medium is located to execute any of the above-described load type identification methods.

[0014] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor for running a program, wherein the program executes any of the above-described load type identification methods during runtime.

[0015] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described load type identification methods.

[0016] In this embodiment of the invention, a load type identification method is employed. This involves injecting a disturbance signal into the solid-state transformer during a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain the target voltage signal and target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; and determining the load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics. The electrical fingerprint feature vector is matched with multiple load features in a pre-set load feature database to determine the load type corresponding to the output of the solid-state transformer. The pre-set load feature database includes multiple load features and their corresponding load types. This achieves the goal of quickly and accurately extracting multi-dimensional features and identifying the load type at the back end by actively injecting disturbance signals. This significantly improves the accuracy and speed of load identification and enables the solid-state transformer to achieve "plug-and-play" adaptive parameter matching. It also solves the technical problems of low passive identification accuracy of existing solid-state transformers and the inability of fixed control strategies to adapt to load diversity, which leads to output characteristic mismatch, inefficient equipment operation, and easy damage. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing a load type identification method is shown.

[0019] Figure 2 This is a flowchart illustrating the load type identification method provided according to an embodiment of the present invention;

[0020] Figure 3 This is a structural block diagram of a load type identification device provided according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of the present invention, a method embodiment for load type identification is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a load type identification method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1The different configurations shown.

[0025] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the load type identification method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned application load type identification method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0027] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0028] Figure 2 This is a flowchart illustrating the load type identification method provided according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0029] Step S202: When the solid-state transformer is in a preset time period, a disturbance signal is injected.

[0030] The preset time period typically covers three application scenarios: the initial commissioning of solid-state transformers when they are first connected to the grid, after the system detects significant changes in the back-end load, and during the period when the system performs routine periodic inspection tasks.

[0031] In this step, during a preset time period, the solid-state transformer's controller actively injects a carefully designed, minute disturbance signal into its output port. To acquire rich feature information without affecting the normal and safe operation of downstream electrical equipment, this disturbance signal is strictly controlled in terms of waveform, frequency, and amplitude.

[0032] Specifically, the disturbance signal is preferably a superposition of multiple sinusoidal waves of different frequencies, typically set between 1Hz and 200Hz. Simultaneously, the system usually employs an amplitude coefficient of 0.5% to 3%, for example, preferably 1% of the rated voltage for voltage disturbances and 2% of the rated current for current disturbances. This ensures the required signal-to-noise ratio for the algorithm while minimizing the physical impact on the actual load. Furthermore, in complex industrial environments, to resist random noise interference, the system can perform 3 to 5 consecutive injections of the same signal for subsequent averaging and filtering.

[0033] Through the above steps, the system can be transformed from passively waiting for long-term historical sample collection to actively probing the internal state of the load. It can instantly stimulate the inherent electrical response of complex loads at different frequency bands with extremely high efficiency and extremely low system risk.

[0034] Step S204: Collect the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period.

[0035] In this step, within the synchronization window of the injected disturbance signal, the system's underlying analog-to-digital converter performs high-frequency synchronous sampling of the instantaneous voltage and current at the port at a sampling rate much higher than the highest frequency of the disturbance. This high-fidelity synchronous acquisition ensures that the absolute time reference does not drift when subsequently calculating the phase difference between voltage and current, providing raw data support for extracting extremely high-precision frequency and time domain features.

[0036] Specifically, the key to ensuring identification accuracy without affecting the normal operation of the load is the reasonable design of the disturbance signal. The main considerations for designing the disturbance signal are the disturbance waveform, disturbance frequency, disturbance amplitude, and disturbance duration.

[0037] The disturbance signal can use various waveforms, selected according to the application scenario:

[0038] Sine waves: have concentrated energy in the frequency domain and are easy to analyze, but the amount of information per frequency is limited, making them suitable for simple load identification;

[0039] Square waves or pulses contain abundant high-frequency components, but have dispersed energy and low signal-to-noise ratio, making them suitable for transient response analysis.

[0040] Pseudo-random sequences (PRBS): contain a large amount of information and are highly resistant to interference, but are complex to implement and are suitable for high-precision identification;

[0041] Multi-frequency superimposed sine waves: can achieve simultaneous measurement of multiple frequency points, but have a large peak factor, and are suitable for impedance spectrum analysis.

[0042] The preferred approach is to inject multiple superimposed sinusoidal signals of different frequencies, and simultaneously obtain the impedance characteristics of the load at different frequency points to form an "impedance fingerprint".

[0043] The selection of the disturbance frequency should also follow these principles: avoid the system resonant frequency to prevent oscillations; cover the load characteristic frequency band, such as the low frequency corresponding to the rotor time constant of the motor; avoid the power frequency and its integer multiples of harmonics to avoid confusion with normal operation. The recommended frequency range is 1Hz to 200Hz, and specific frequencies can be preset according to the load type.

[0044] Disturbance amplitude A balance needs to be struck between the signal-to-noise ratio and the impact on the load. The specific formula is as follows:

[0045] ;

[0046] in Rated voltage or current, This is the amplitude factor, typically ranging from 0.5% to 3%. For voltage disturbances, 1% is preferred; for current disturbances, 2% is preferred.

[0047] The duration of the disturbance needs to be determined based on the time constant of the load:

[0048] Resistive load: 1-2 power frequency cycles;

[0049] For motor-type loads: the rotor mechanical time constant must be covered, typically 0.1-1 seconds;

[0050] For switching power supplies: steady-state response needs to be observed, typically 0.2-0.5 seconds.

[0051] To improve the signal-to-noise ratio, the same perturbation signal can be injected multiple times, and the response results can be averaged to eliminate the influence of random noise. The number of injections is generally 3-5 times.

[0052] Step S206: Filter the output voltage response signal and the load current response signal to obtain the target voltage signal and the target current signal.

[0053] In this step, because real industrial power distribution networks are always subject to high-frequency glitches and electromagnetic interference generated by nonlinear switching equipment, the weak disturbance response is easily drowned out by background noise if the raw sampled data is used directly. Therefore, this step uses a preset digital filter, such as a band-stop filter or a low-pass filter, to perform smoothing, denoising, and anti-aliasing processing on the raw signal, thereby separating the pure "target voltage signal" and "target current signal". This step improves the signal-to-noise ratio of the micro-disturbance signal and prevents misjudgment of features caused by interference signals.

[0054] Step S208: Perform frequency domain transformation on the target voltage signal and the target current signal to determine the impedance frequency response characteristics.

[0055] In this step, the system performs a Fast Fourier Transform (FFT) on the filtered and denoised target voltage and current signals, simultaneously extracting the complex frequency domain components at the corresponding injection frequency points. Subsequently, complex division is used to calculate the impedance magnitude and phase angle at each characteristic frequency point. It should be noted that the voltage and current signals after the FFT transformation are converted from one-dimensional scalars to complex numbers containing real and imaginary parts (i.e., magnitude and phase angle). Therefore, the "complex division" operation includes: the system obtaining the absolute impedance magnitude (i.e., impedance amplitude) at that frequency point by calculating the quotient of the complex magnitude of the voltage and the complex magnitude of the current; and the system extracting the phase deflection between the voltage and current at that frequency band (i.e., impedance phase angle) by calculating the difference between the complex phase angle of the voltage and the complex phase angle of the current. By mapping and combining the amplitude and phase data at the above discrete frequency points, an impedance spectrum sequence reflecting the essential characteristics of the load is finally formed.

[0056] Step S210: Based on the target voltage signal and the target current signal, extract transient response features, power change rate features, and harmonic response features.

[0057] Besides the frequency domain response, the transient response waveforms and power jump trajectories of various loads to small disturbances also exhibit strong individual differences. In this step, the system simultaneously extracts three sets of data: First, transient response characteristics, which directly extract the time constant, overshoot, and steady-state error by fitting the response curve, thereby inferring the damping characteristics of the load's underlying layer; second, the power change rate, which directly calculates the abrupt change slope of active and reactive power during the disturbance; and finally, for nonlinear devices prone to waveform distortion, the system also specifically extracts the amplitude of each harmonic current and the total harmonic distortion (THD). Specifically, the THD index can intuitively quantify the degree of 'distortion' of a device to a pure sine wave and is a criterion for identifying switching power supplies, frequency converters, and other equipment.

[0058] Step S212: Determine the load electrical fingerprint feature vector based on impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics.

[0059] In this step, the system concatenates multiple parameters, including impedance amplitude spectrum, phase spectrum, time constant, power change rate, and THD, into a high-dimensional array structure, namely the "load electrical fingerprint feature vector," according to preset weights and a specific arrangement order. This feature vector fully maps the true electrical attributes of the currently connected device from the frequency domain to the time domain, thus providing standardized data input for subsequent classification algorithms.

[0060] Specifically, the voltage and current responses of the load side to disturbance signals are collected, and the following features are extracted:

[0061] (1) Impedance frequency response characteristics, calculate the impedance amplitude and phase at each frequency point:

[0062]

[0063]

[0064] in, It represents the impedance characteristics of a load at a specific frequency, which is also known as the "voltage-to-current ratio". This indicates the amplitude of the voltage signal measured at the output port of the solid-state transformer at that frequency. This indicates the amplitude of the current signal measured at the load terminal at that frequency. This represents the phase difference angle between the voltage waveform and the current waveform at a given frequency. This represents the phase angle of the voltage signal waveform at that frequency, that is, the "advance or lag angle" of the voltage relative to the reference time zero point. This represents the phase angle of the current signal waveform at that frequency, that is, the "advance or lag angle" of the current relative to the same reference time zero point.

[0065] The impedance amplitude spectrum is formed using the above formula. and phase spectrum This constitutes the "impedance fingerprint" of the load.

[0066] (2) Transient response characteristics: For pulse or step disturbances, the following transient characteristics are extracted: time constant Overshoot is obtained by fitting the response curve. : Reflects the damping characteristics of the system; steady-state error : Reflects the gain characteristics of the system; rise time Peak time .

[0067] (3) Power response characteristics: Calculate the response of active and reactive power to disturbances, and obtain the following characteristics: Active power change rate Rate of change of reactive power Power factor variation .

[0068] (4) Harmonic response characteristics: For nonlinear loads, the harmonic changes after disturbance are extracted, and the following characteristics are obtained: amplitude of each harmonic current. Total Harmonic Distortion Harmonic energy in a specific frequency band.

[0069] (5) Feature vector construction: The above features are combined into a multi-dimensional feature vector, namely the load electrical fingerprint feature vector:

[0070]

[0071] By cross-comparing these time-domain and harmonic parameters, it is possible to avoid misjudging the system based solely on a single impedance characteristic when facing mixed operating conditions in the field.

[0072] Step S214: Perform similarity matching between the load electrical fingerprint feature vector and multiple load features in the preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer. The preset load feature database includes multiple load features and the load types corresponding to each load feature.

[0073] In this step, the system sends the real-time generated feature vectors into a pre-set load feature database for comparison and retrieval. This database contains a large amount of standard template data of typical loads under various operating conditions. The algorithm derives the similarity score between the measured vector and each template by calculating the multi-dimensional spatial distance between them and various standard loads.

[0074] In particular, the system also introduces a confidence assessment mechanism based on multi-dimensional feature differences. Specifically, when the difference between the maximum and second-highest similarity scores is less than a preset threshold, it indicates that the current load characteristics are severely mixed or belong to new equipment outside the database. At this time, the system no longer forcibly classifies it, but instead determines it as an "unknown load" and switches to the default conservative control mode. This method can effectively avoid the issuance of erroneous parameters due to incomplete feature database coverage, ensuring the hardware safety of the solid-state transformer under unknown operating conditions.

[0075] Specifically, the following characteristic templates for common load types are pre-defined and can be obtained through experimental testing or simulation modeling:

[0076] Asynchronous motors (including direct start and variable frequency drive): have low-frequency inductance, large time constant, impedance spectrum showing high impedance at low frequencies and phase close to 90°, and transient characteristics such as large starting current and long starting time.

[0077] Permanent magnet motors (including direct drive and servo motors): have significant back electromotive force, impedance that varies with speed, fast transient response, and small overshoot.

[0078] Switching power supplies (computers, servers, charging stations): nonlinear, rich in harmonics, low high-frequency impedance, and subject to impact upon initial connection.

[0079] Resistive loads (heaters, lighting): pure resistive characteristics, constant impedance, 0° phase, no transients, and fast response.

[0080] Variable frequency drives (VVVF, vector control): nonlinear, generate harmonics, have rectifier characteristics on the input side, and the startup process is controllable.

[0081] Lighting loads (LED, fluorescent lamps): non-linear, low power, low high-frequency impedance, and fast start-up.

[0082] Through the above steps, the true electrical characteristics of the device can be actively extracted and locked, thereby providing reliable data support for the adaptive adjustment of the output parameters of the solid-state transformer.

[0083] As an optional embodiment, this can be achieved through the following steps: the disturbance signal is based on a superposition of sinusoidal signals of multiple frequencies.

[0084] Optionally, by using the superposition of multi-frequency sine waves, it is possible to obtain wideband response characteristics covering multiple frequency bands at once within an extremely short test window, thereby effectively avoiding the excitation limitations of single high-frequency or low-frequency tests on specific nonlinear or large-inertia devices.

[0085] As an optional embodiment, this can be achieved through the following steps: performing frequency domain transformation on the target voltage signal and the target current signal to determine the impedance frequency response characteristics, including: performing frequency domain transformation on the target voltage signal and the target current signal to determine the complex frequency domain components of multiple disturbance frequency points corresponding to each of the target voltage signal and the target current signal; based on the complex frequency domain components at the disturbance frequencies corresponding to each of the target voltage signal and the target current signal, calculating the complex impedance amplitude and phase angle at at least three disturbance frequency points corresponding to each of the target voltage signal and the target current signal, to obtain the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal; and determining the impedance frequency response characteristics based on the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal.

[0086] Optionally, through the above-mentioned solution logic in the complex domain, the system not only extracts the absolute impedance amplitude, but also precisely extracts the phase angle characterizing the capacitive-inductive deflection of the load, thereby completely transforming the abstract frequency domain transformation result into underlying electrical parameters with clear physical meaning, laying the foundation for the subsequent construction of accurate feature vectors.

[0087] As an optional embodiment, this can be achieved through the following steps: matching the load electrical fingerprint feature vector with multiple templates in a preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer, including: calculating the Euclidean distance between the load electrical fingerprint feature vector and multiple templates, and determining the Euclidean distances corresponding to multiple load features; normalizing the Euclidean distances corresponding to multiple load features to determine the similarity of each load feature; and determining the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to the load features whose similarity meets preset conditions, according to the preset load feature database.

[0088] Optionally, since the electrical fingerprint feature vector incorporates physical parameters with extremely large dimensional and numerical ranges, such as impedance and time constant, direct comparison can easily lead to large-value features overshadowing small-value features. Therefore, this embodiment first normalizes various heterogeneous parameters to a standard dimensionless interval; then, it uses the Euclidean distance algorithm to accurately measure the absolute spatial deviation between the measured vector and the standard template in multidimensional space. This method effectively eliminates the computational bias caused by dimensional differences, ensuring the weight balance and objectivity of each underlying electrical parameter in the final similarity assessment.

[0089] As an optional embodiment, this can be achieved through the following steps: Based on a preset load feature database, determine the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to load features whose similarity meets preset conditions, including: sorting multiple load features according to their similarity order to obtain a load feature sequence; determining the first load feature in the load feature sequence as a candidate load feature; calculating the similarity difference between the first and second load features in the load feature sequence; determining the confidence level based on the similarity difference; and, if the confidence level exceeds a preset threshold, determining the load type corresponding to the candidate load feature as the load type corresponding to the output terminal of the solid-state transformer based on the preset load feature database.

[0090] Optionally, in complex mixed-load scenarios, the measured features are very likely to produce similar matching degrees with multiple templates in the database. By extracting the difference between the maximum and second-largest similarities to verify the confidence level, the system's anti-false-judgment performance can be enhanced, preventing the algorithm from forcibly outputting incorrect classification results at ambiguous decision edges.

[0091] Specifically, the measured feature vector, i.e., the electrical fingerprint feature vector... With database template Perform matching and calculate similarity:

[0092] Euclidean distance: The smaller the distance, the more similar they are;

[0093] Mahalanobis distance: Considers the correlation between features. ;

[0094] When the confidence level is lower than the preset threshold (e.g., 0.7), "unknown load" can be output, and the default conservative control mode can be adopted.

[0095] As an optional embodiment, this can be achieved through the following steps: Based on the load type, determine the target parameter set corresponding to the solid-state transformer according to a preset control parameter mapping table, wherein the target parameter set includes output impedance, voltage support strength, harmonic suppression threshold, and dynamic response speed; use a preset exponential transition function to smoothly interpolate multiple parameters in the target parameter set to generate control command sequences corresponding to each of the multiple parameters; inject the control command sequences corresponding to each of the multiple parameters into the voltage loop controller and current loop controller of the solid-state transformer.

[0096] Optionally, when performing the underlying control reconfiguration, an exponential transition function is introduced to generate a smooth interpolation instruction sequence, which can completely avoid the surge in grid voltage or overcurrent impact at the equipment end caused by the instantaneous jump in control parameters, thus ensuring the dynamic safety and hardware physical safety of the solid-state transformer during the adaptive switching process.

[0097] Based on the identified load type, the output control parameters of the SST are dynamically adjusted. For example, control parameter mapping is used for different load types, and corresponding control parameters are set for different load types:

[0098] Asynchronous motors: Output impedance should be low (<0.1pu), voltage support strength should be strong (droop factor <2%), harmonic limit should be 5%, dynamic response should be fast (<10ms), and efficiency priority should be medium.

[0099] Switching power supplies: low output impedance, strong voltage support, strict harmonic limits (<3%), fast dynamic response, and medium efficiency priority.

[0100] Resistive loads: output impedance can be high (>0.2pu), voltage support is weak, harmonic limits are lenient, dynamic response is slow, and efficiency is a high priority.

[0101] Frequency converters: medium output impedance, medium voltage support, strict harmonic limits and active filtering required, medium dynamic response, and medium efficiency priority.

[0102] Mixed loads: Prioritize and compromise, with harmonic limits set at the highest requirement, dynamic response set at the highest requirement, and efficiency set at the average.

[0103] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the load type identification method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0105] According to an embodiment of the present invention, a load type identification device for implementing the above-described load type identification method is also provided. Figure 3 This is a structural block diagram of a load type identification device provided according to an embodiment of the present invention, such as... Figure 3 As shown, the load type identification device includes: an injection module 302, an acquisition module 304, a processing module 306, a first determination module 308, an extraction module 310, a second determination module 312, and a matching module 314. The load type identification device will be described below.

[0106] The injection module 302 is used to actively inject a disturbance signal into the output port of the solid-state transformer when it is in a preset time period. Specifically, this module integrates a disturbance waveform generator, which can generate a composite signal containing multiple characteristic frequency points according to system instructions. In order to ensure that the disturbance does not affect the normal operation of the downstream precision equipment, the module strictly limits the disturbance amplitude to within 1% to 3% of the rated value through the underlying PWM modulation logic, and ensures that the injection time is near the zero crossing point of the system voltage waveform, so as to minimize the electromagnetic shock at the moment of grid connection.

[0107] The acquisition module 304 is used for high-frequency synchronous acquisition of the output voltage response signal and load current response signal of the solid-state transformer during disturbances. This module includes a multi-channel synchronous sampling circuit (ADC), whose sampling frequency is set to more than 10 times the highest frequency of the disturbance. The module uses a hardware synchronous triggering mechanism to ensure that the voltage and current sampling sequences are strictly aligned on the time axis, effectively avoiding impedance phase calculation deviations caused by asynchronous sampling.

[0108] Processing module 306 performs filtering and noise reduction on the output voltage response signal and load current response signal to obtain the target voltage signal and target current signal. The module internally deploys a digital signal conditioner, which uses a notch filter to remove background interference from the 50Hz power frequency and its strong harmonics, and a low-pass filter to remove high-frequency random noise during the sampling process. The signal processed by this module significantly improves the signal-to-noise ratio of the disturbance characteristics while maintaining the integrity of the phase characteristics, providing a high-purity data source for subsequent precise calculations.

[0109] The first determining module 308 is used to perform frequency domain transformation and complex number calculation on the target voltage signal and target current signal to determine the impedance frequency response characteristics under multiple frequency bands. The core algorithm unit of this module performs Fast Fourier Transform (FFT) to map the time domain waveform to the frequency domain space and performs complex division operation for a specific injection frequency point. It not only calculates the magnitude of the impedance, but also locks the impedance phase angle through complex phase difference extraction technology, thereby completely characterizing the inductive or capacitive damping properties of the load under different frequency excitation in the complex domain.

[0110] Extraction module 310 is used to simultaneously extract the transient response characteristics, power change rate characteristics, and harmonic response characteristics of the load based on the target voltage signal and the target current signal. This module extracts the time constant and overshoot of the transient response through envelope detection; quantifies the abrupt change slopes of active and reactive power in real time through differential operations; and obtains the total harmonic distortion (THD) through full-wave harmonic analysis. These multi-physical dimension characteristic parameters constitute complementary identification criteria, effectively overcoming the identification bottleneck of single-frequency domain characteristics in the face of complex nonlinear loads.

[0111] The second determining module 312 is used to perform structured fusion based on impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics to determine the load electrical fingerprint feature vector. This module performs pre-normalization processing to eliminate the interference of different physical dimensions on the determination results. The module encapsulates heterogeneous electrical parameters into a high-dimensional feature sequence according to a preset topology, thereby transforming discrete physical quantities into a standardized data interface that can be directly called by the algorithm classifier.

[0112] The matching module 314 is used to calculate the similarity and confidence of the load electrical fingerprint feature vector with multiple templates in a pre-set load feature database, ultimately determining the load type corresponding to the output terminal of the solid-state transformer. This module integrates a pattern recognition comparison engine, which calculates the multi-dimensional spatial distance (such as Euclidean distance) between the measured feature vector and the standard template library to obtain preliminary identification results. Simultaneously, this module has dual verification logic: when the difference between the maximum similarity score and the second-largest score is insufficient to support a reliable judgment, the module will proactively trigger an unknown load warning and drive the solid-state transformer to switch to a safe operating mode, ensuring the robustness of system control from a decision-making perspective.

[0113] It should be noted that the injection module 302, acquisition module 304, processing module 306, first determination module 308, extraction module 310, and second determination module matching module 314 mentioned above correspond to steps S202 to S214 in the embodiments. Multiple modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0114] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0115] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the load type identification method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned load type identification method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0116] The processor can invoke information and application programs stored in the memory via a transmission device to perform the following steps: injecting a disturbance signal when the solid-state transformer is in a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain the target voltage signal and target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; determining the load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; performing similarity matching between the load electrical fingerprint feature vector and multiple load characteristics in a preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer, wherein the preset load feature database includes multiple load characteristics and the load types corresponding to each of the multiple load characteristics.

[0117] Optionally, the processor may also execute program code that performs the following steps: As an optional embodiment, this can be achieved by the following steps: the disturbance signal is based on a superposition of sinusoidal signals of multiple frequencies.

[0118] Optionally, the processor may also execute program code for the following steps: performing frequency domain transformation on the target voltage signal and the target current signal to determine the impedance frequency response characteristics, including: performing frequency domain transformation on the target voltage signal and the target current signal to determine the complex frequency domain components of multiple disturbance frequency points corresponding to each of the target voltage signal and the target current signal; calculating the complex impedance amplitude and phase angle of at least three disturbance frequency points corresponding to each of the target voltage signal and the target current signal based on the complex frequency domain components at the disturbance frequencies corresponding to each of the target voltage signal and the target current signal, to obtain the complex impedance amplitude and phase angle of the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal; and determining the impedance frequency response characteristics based on the complex impedance amplitude and phase angle of the target disturbance frequency points corresponding to each of the target voltage signal and the target current signal.

[0119] Optionally, the processor may also execute program code for the following steps: performing similarity matching between the load electrical fingerprint feature vector and multiple templates in a preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer, including: calculating the Euclidean distance between the load electrical fingerprint feature vector and multiple templates, and determining the Euclidean distances corresponding to multiple load features; normalizing the Euclidean distances corresponding to multiple load features to determine the similarity of each load feature; and determining the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to the load features whose similarity meets preset conditions, according to the preset load feature database.

[0120] Optionally, the processor may also execute program code for the following steps: Based on a preset load feature database, determine the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to the load features whose similarity meets preset conditions, including: sorting multiple load features in order of similarity to obtain a load feature sequence; determining the first load feature in the load feature sequence as a candidate load feature; calculating the similarity difference between the first and second load features in the load feature sequence; determining the confidence level based on the similarity difference; and, if the confidence level exceeds a preset threshold, determining the load type corresponding to the candidate load feature as the load type corresponding to the output terminal of the solid-state transformer based on the preset load feature database.

[0121] Optionally, the processor may also execute program code for the following steps: based on the load type, determine the target parameter set corresponding to the solid-state transformer according to a preset control parameter mapping table, wherein the target parameter set includes output impedance, voltage support strength, harmonic suppression threshold, and dynamic response speed; use a preset exponential transition function to smoothly interpolate multiple parameters in the target parameter set to generate control command sequences corresponding to each of the multiple parameters; inject the control command sequences corresponding to each of the multiple parameters into the voltage loop controller and current loop controller of the solid-state transformer.

[0122] This invention provides a scheme for adaptive load control of solid-state transformers based on active disturbance detection and multi-dimensional electrical fingerprint matching. The scheme involves injecting a disturbance signal into the solid-state transformer during a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain the target voltage signal and target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; determining the load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; and matching the load electrical fingerprint feature vector with a preset load. The similarity matching of multiple load features in the feature database determines the load type corresponding to the output of the solid-state transformer. The preset load feature database includes multiple load features and their corresponding load types. This achieves the goal of quickly and accurately extracting multi-dimensional features and identifying the load type at the back end by actively injecting disturbance signals. This significantly improves the accuracy and speed of load identification and enables the solid-state transformer to achieve "plug-and-play" adaptive parameter matching. It also solves the technical problems of low passive identification accuracy of existing solid-state transformers and the inability of fixed control strategies to adapt to load diversity, which leads to output characteristic mismatch, inefficient equipment operation, and easy damage.

[0123] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0124] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the load type identification method provided in the above embodiments.

[0125] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0126] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: injecting a disturbance signal when the solid-state transformer is in a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain a target voltage signal and a target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; determining the load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; performing similarity matching between the load electrical fingerprint feature vector and multiple load characteristics in a preset load characteristic database to determine the load type corresponding to the output terminal of the solid-state transformer, wherein the preset load characteristic database includes multiple load characteristics and the load types corresponding to each of the multiple load characteristics.

[0127] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can perform the following: injecting a disturbance signal when the solid-state transformer is in a preset time period; acquiring the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; filtering the output voltage response signal and load current response signal to obtain a target voltage signal and a target current signal; performing frequency domain transformation on the target voltage signal and target current signal to determine the impedance frequency response characteristics; extracting transient response characteristics, power change rate characteristics, and harmonic response characteristics based on the target voltage signal and target current signal; determining the load electrical fingerprint feature vector based on the impedance frequency response characteristics, transient response characteristics, power change rate characteristics, and harmonic response characteristics; and performing similarity matching between the load electrical fingerprint feature vector and multiple load characteristics in a preset load characteristic database to determine the load type corresponding to the output terminal of the solid-state transformer, wherein the preset load characteristic database includes multiple load characteristics and the load types corresponding to each of the multiple load characteristics.

[0128] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0129] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0133] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0134] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying load type, characterized in that, include: When the solid-state transformer is in a preset time period, a disturbance signal is injected; The output voltage response signal and load current response signal of the solid-state transformer during the disturbance period are acquired; The output voltage response signal and the load current response signal are filtered to obtain the target voltage signal and the target current signal; The target voltage signal and the target current signal are subjected to frequency domain transformation to determine the impedance frequency response characteristics; Based on the target voltage signal and the target current signal, extract transient response features, power change rate features, and harmonic response features; Based on the impedance frequency response characteristics, the transient response characteristics, the power change rate characteristics, and the harmonic response characteristics, the load electrical fingerprint feature vector is determined; The load electrical fingerprint feature vector is matched with multiple load features in a preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer. The preset load feature database includes the multiple load features and the load types corresponding to each of the multiple load features.

2. The method according to claim 1, characterized in that, in, The disturbance signal is based on a superposition of sinusoidal signals of multiple frequencies.

3. The method according to claim 1, characterized in that, The step of performing frequency domain transformation on the target voltage signal and the target current signal to determine the impedance frequency response characteristics includes: The target voltage signal and the target current signal are subjected to frequency domain transformation to determine the complex frequency domain components of multiple disturbance frequency points corresponding to each of the target voltage signal and the target current signal; Based on the complex frequency domain components at the disturbance frequencies corresponding to the target voltage signal and the target current signal, the complex impedance amplitude and phase angle at at least three disturbance frequency points corresponding to the target voltage signal and the target current signal are calculated to obtain the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to the target voltage signal and the target current signal. The impedance frequency response characteristics are determined based on the complex impedance amplitude and phase angle at the target disturbance frequency points corresponding to the target voltage signal and the target current signal, respectively.

4. The method according to claim 1, characterized in that, The step of matching the load electrical fingerprint feature vector with multiple templates in a pre-set load feature database to determine the load type corresponding to the output terminal of the solid-state transformer includes: Calculate the Euclidean distance between the load electrical fingerprint feature vector and the plurality of templates, and determine the Euclidean distance corresponding to the plurality of load features; The Euclidean distances corresponding to the multiple load features are normalized to determine the similarity of each load feature. Based on the preset load feature database, the load type corresponding to the output terminal of the solid-state transformer is determined according to the load type corresponding to the load features that meet the preset similarity conditions.

5. The method according to claim 4, characterized in that, The step of determining the load type corresponding to the output terminal of the solid-state transformer based on the load type corresponding to load characteristics that meet preset similarity conditions according to the preset load feature database includes: The multiple load features are sorted according to their similarity to obtain a load feature sequence; The first load feature in the load feature sequence is identified as a candidate load feature; Calculate the similarity difference between the first and second load features in the load feature sequence; The confidence level is determined based on the similarity difference. If the confidence level exceeds a preset threshold, the load type corresponding to the candidate load feature is determined to be the load type corresponding to the output terminal of the solid-state transformer based on the preset load feature database.

6. The method according to any one of claims 1 to 5, characterized in that, Also includes: Based on the load type, according to the preset control parameter mapping table, the target parameter set corresponding to the solid-state transformer is determined, wherein the target parameter set includes output impedance, voltage support strength, harmonic suppression threshold and dynamic response speed; A preset exponential transition function is used to smoothly interpolate multiple parameters in the target parameter set to generate control command sequences corresponding to each of the multiple parameters. The control command sequences corresponding to each of the multiple parameters are injected into the voltage loop controller and current loop controller of the solid-state transformer.

7. A load type identification device, characterized in that, include: The injection module is used to inject a disturbance signal when the solid-state transformer is in a preset time period. The acquisition module is used to acquire the output voltage response signal and load current response signal of the solid-state transformer during the disturbance period; The processing module is used to filter the output voltage response signal and the load current response signal to obtain the target voltage signal and the target current signal; The first determining module is used to perform frequency domain transformation on the target voltage signal and the target current signal to determine the impedance frequency response characteristics; The extraction module is used to extract transient response features, power change rate features, and harmonic response features based on the target voltage signal and the target current signal. The second determining module is used to determine the load electrical fingerprint feature vector based on the impedance frequency response characteristics, the transient response characteristics, the power change rate characteristics, and the harmonic response characteristics; The matching module is used to perform similarity matching between the load electrical fingerprint feature vector and multiple load features in the preset load feature database to determine the load type corresponding to the output terminal of the solid-state transformer. The preset load feature database includes the multiple load features and the load types corresponding to each of the multiple load features.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the load type identification method according to any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the load type identification method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the load type identification method according to any one of claims 1 to 6.

Images