A power swing intelligent monitoring method and system, an electronic device, and a storage medium

Abstract

The application discloses a kind of power oscillation intelligent monitoring method, system, electronic equipment and storage medium, belong to electric power system simulation technical field, the method includes: using the random process model with mean reversion characteristics to the benchmark power noise of thermal power unit modeling, obtain benchmark noise signal;According to the disturbance type and disturbance configuration parameter generation disturbance signal, and superimpose disturbance signal to benchmark noise signal, obtain analog power signal and store in data buffer;The detection index of analog power signal in the preset time window in data buffer is calculated, compared with threshold value to judge whether trigger alarm.The application uses the random process model with mean reversion characteristics to model the benchmark power noise of thermal power unit under undisturbed condition, improves the authenticity of benchmark power noise, supports multiple detection criteria, realizes the integration of simulation, disturbance injection and detection verification.It is suitable for thermal power unit power oscillation monitoring.

Description

Technical Field

[0001] This invention belongs to the field of power system simulation technology, specifically relating to a power oscillation intelligent monitoring method, system, electronic device, and storage medium. Background Technology

[0002] In power system operation and research, high-fidelity simulation of the power output characteristics of generator units, especially thermal power units, and early and accurate detection of potential power oscillations are of great significance for ensuring power grid safety and preventing the escalation of accidents.

[0003] For power simulation, existing technologies have limitations in reproducing the real noise characteristics of thermal power units under undisturbed operating conditions, and there are discrepancies between the simulation output and the fluctuation behavior of real units under undisturbed operating conditions. For power oscillation monitoring, existing monitoring methods need to be improved when faced with the complex and diverse oscillation patterns of actual power grids.

[0004] In addition, the simulation and monitoring / verification processes are currently relatively independent in terms of operation, which makes it inconvenient for technical personnel to conduct comprehensive evaluations. Summary of the Invention

[0005] To address the aforementioned problems in the prior art, this invention provides a method, system, electronic device, and storage medium for intelligent monitoring of power oscillations. The technical problem to be solved by this invention is achieved through the following technical solution: In a first aspect, the present invention provides a method for intelligent monitoring of power oscillations, comprising: Using a stochastic process model with mean regression characteristics, the reference power noise of thermal power units under undisturbed operating conditions is modeled to obtain the reference noise signal at the current time step. A disturbance signal is generated based on the disturbance type and disturbance configuration parameters, and the disturbance signal is superimposed on the reference noise signal to obtain an analog power signal and store it in the data buffer. Calculate the detection index of the analog power signal within a preset time window in the data buffer; The detection index is compared with a preset threshold to determine whether an oscillation alarm is triggered.

[0006] In one embodiment of the present invention, the step of modeling the reference power noise of a thermal power unit under undisturbed operating conditions using a stochastic process model with mean regression characteristics to obtain the reference noise signal at the current time step includes: The Ornstein-Uhlenbeck stochastic process model is used to model the reference power noise of thermal power units under undisturbed operating conditions. Based on the reference noise signal of the previous time step, the mean recovery rate, the long-term mean, the volatility parameter, and the random increment of the current time step, the reference noise signal of the current time step is iteratively calculated.

[0007] In one embodiment of the present invention, the mean recovery rate, the long-term mean, and the volatility parameters are dynamically adjusted in real time using adjustment controls provided by a graphical user interface.

[0008] In one embodiment of the present invention, the steps of generating a disturbance signal according to the disturbance type and disturbance configuration parameters, superimposing the disturbance signal onto the reference noise signal to obtain an analog power signal and storing it in a data buffer include: Receive the disturbance type and corresponding disturbance configuration parameters selected by the user through the graphical user interface; The disturbance signal is generated based on the disturbance type and the disturbance configuration parameters, and the disturbance signal is added to the disturbance list; Traverse the disturbance list, superimpose the disturbance signal that is within its own duration at the current time step onto the reference noise signal to obtain the analog power signal and store it in the data buffer.

[0009] In one embodiment of the present invention, the disturbance type includes at least one of sine wave, square wave, triangle wave and pulse, and the disturbance configuration parameters include at least one of amplitude, frequency, duration and phase.

[0010] In one embodiment of the present invention, the step of calculating the detection index of the analog power signal within a preset time window in the data buffer includes: Calculate at least one of the following: the short-time standard deviation of the analog power signal within the preset time window, the energy value of the analog power signal within the preset time window in the specified frequency band, and the spectral peak value of the analog power signal within the preset time window.

[0011] In one embodiment of the present invention, it further includes: The power curve of the analog power signal is plotted in real time through a graphical user interface; When the oscillation alarm is not triggered, the power curve is plotted in the first display state; when the oscillation alarm is triggered, the power curve is plotted in a second display state that is different from the first display state. In the information display area of ​​the graphical user interface, the operation logs and alarm information are displayed in a scrolling format in the form of timestamps.

[0012] In a second aspect, the present invention provides a power oscillation intelligent monitoring system, comprising: The noise modeling module is used to model the reference power noise of thermal power units under undisturbed operating conditions using a stochastic process model with mean regression characteristics, and obtain the reference noise signal. The signal generation module is used to generate a disturbance signal according to the disturbance type and disturbance configuration parameters, and to superimpose the disturbance signal onto the reference noise signal to obtain an analog power signal and store it in the data buffer. The detection calculation module is used to calculate the detection index of the analog power signal within a preset time window in the data buffer; The alarm judgment module is used to compare the detection index with a preset threshold to determine whether an oscillation alarm is triggered.

[0013] Thirdly, the present invention also provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes the program stored in the memory, it implements the steps of the method described in the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention employs a stochastic process model with mean regression characteristics to model the baseline power noise of thermal power units under undisturbed operating conditions. The generated baseline noise signal is smooth, continuous, and time-dependent, reflecting the true noise characteristics of the thermal power unit under constraints such as boiler thermal inertia and turbine mechanical inertia. Power oscillation detection based on this baseline noise signal helps reduce false alarms and missed alarms.

[0016] 2. This invention provides calculation methods for various detection indicators, such as short-time standard deviation, energy value within a specified frequency band, and spectral peak value. Users can select different detection algorithms through a graphical user interface to apply different criteria for detecting different types of power oscillations (such as periodic oscillations and sudden pulses) in the actual power grid, thus improving the detection capability for different oscillation types.

[0017] 3. This invention integrates real-time power curve simulation, multi-type disturbance injection, and detection algorithm verification into a single graphical user interface. Users can adjust noise parameters, configure disturbance types and parameters, switch detection algorithms, and observe detection results within a unified interface, eliminating the need to switch between different tools. When an alarm is triggered, the power curve distinguishes between normal and abnormal operating conditions using different display states. The information display area records operation logs and alarm information in timestamp format, facilitating the tracking of abnormal events.

[0018] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0019] Figure 1 This is a flowchart of a power oscillation intelligent monitoring method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the graphical user interface provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of a power oscillation intelligent monitoring system provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] High-fidelity simulation of the power output characteristics of thermal power units and effective monitoring of power oscillations are important technical means to ensure power grid security. However, existing technical solutions still face several bottlenecks in practical applications. Firstly, in terms of simulation modeling, traditional power simulation models typically use an ideal sine wave superimposed with white noise to generate a baseline curve. White noise is characterized by a flat spectrum and sharp instantaneous value changes, while real thermal power units, under undisturbed operating conditions, are constrained by inertial elements such as boiler combustion and turbine regulation, resulting in a smooth, low-frequency, and time-dependent background noise. The two have fundamentally different statistical characteristics, leading to an unrealistic simulation baseline that may mask weak oscillation signals or trigger false alarms. Secondly, regarding monitoring algorithms, existing methods mostly rely on a single criterion, such as simple threshold comparison or fixed-band energy monitoring. Threshold comparison methods are sensitive to noise fluctuations, prone to false alarms during normal load fluctuations, and may miss alarms in the early stages of slowly increasing oscillations. Fixed-band energy methods can only detect oscillations near a preset frequency, lacking the ability to detect oscillations with unknown frequencies or time-varying frequencies (such as subsynchronous oscillations), and are difficult to cope with the complex and varied oscillation patterns in the power grid (such as sine waves, square waves, pulses, irregular noise, etc.). Thirdly, regarding tool integration, existing simulation, interference injection, and detection algorithm verification are separate processes. Technical personnel lack an integrated platform that can flexibly customize and inject multiple oscillation types and observe the response performance of different detection algorithms in real time, which is not conducive to rapid verification and optimization of detection strategies.

[0021] To address the above problems, the present invention provides a method, system, storage medium, and electronic device for intelligent monitoring of power oscillations.

[0022] The present invention will be further described in detail below with reference to specific embodiments, but the implementation of the present invention is not limited thereto.

[0023] Figure 1 This is a flowchart of a power oscillation intelligent monitoring method provided in an embodiment of the present invention. Figure 1 As shown, this embodiment of the invention provides a power oscillation intelligent monitoring method, including: S1. Using a stochastic process model with mean regression characteristics, the reference power noise of the thermal power unit under undisturbed operating conditions is modeled to obtain the reference noise signal at the current time step.

[0024] In one embodiment, the aforementioned stochastic process model is the OU (Ornstein-Uhlenbeck) stochastic process model. This model possesses mean regression characteristics and can naturally generate smooth, continuous, and time-dependent fluctuation curves, which highly match the background noise characteristics exhibited by thermal power units under physical constraints such as boiler thermal inertia and turbine mechanical inertia. Taking the OU stochastic process model as an example, its discretization iterative formula is: ; in, Indicates the previous time step The reference noise signal, The reference noise signal representing the current time step. This indicates the preset simulation step size. This is the long-term mean, used to characterize the level of noise around the center of the fluctuation. The mean recovery rate is used to characterize the noise's regression towards the long-term mean. The rate of regression, The larger the value, the smoother the noise fluctuation and the faster the regression to the mean. This is a volatility parameter used to control the amplitude of noise fluctuations and is a key parameter that determines the smoothness of noise. Let be a random increment at the current time step, with a mean of 0 and a variance of . The normal distribution can be obtained by combining standard normal random numbers with... The square root of the product is obtained by multiplying the product of the square roots.

[0025] As can be seen from the above formula, each simulation step size Within this time step, the new reference noise signal is determined by three parts: the reference noise signal from the previous time step. Towards the long-term mean Drift term of regression and random disturbance terms The drift term causes the noise value to continuously shift towards the long-term mean. The noise is generated by converging to produce a smooth mean regression; the random disturbance term injects unpredictable natural fluctuations into the noise. The combination of the two allows the generated noise sequence to have both a continuous and smooth time structure and maintain a certain degree of randomness, thus remaining consistent with the actual operating noise characteristics of thermal power units.

[0026] For example, , , , In one embodiment, the parameters can be dynamically adjusted in real time using the adjustment controls provided by the graphical user interface, allowing users to flexibly adjust the noise characteristics during simulation to simulate the operating states of different units.

[0027] In other implementations, the stochastic process model may also employ a fractional Brownian motion (FBM) model, an autoregressive (AR) model, an autoregressive moving average (ARMA) model, a colored noise model, a generalized Gaussian noise model, or a mixed noise model driven by a hidden Markov model (HMM).

[0028] S2. Generate a disturbance signal based on the disturbance type and disturbance configuration parameters, and superimpose the disturbance signal onto the reference noise signal to obtain an analog power signal and store it in the data buffer.

[0029] Specifically, the disturbance types include sine waves, square waves, triangle waves, and pulses, and the disturbance configuration parameters include at least one of amplitude, frequency, duration, and phase. Users can select the disturbance type and set the corresponding configuration parameters through a graphical user interface, and then generate the corresponding disturbance signal and add it to the disturbance list according to the user's selection.

[0030] Furthermore, the disturbance list is traversed, and disturbance signals within their duration at the current time step are superimposed onto the reference noise signal at the current time step to obtain the analog power signal at the current time step, which is then stored in the data buffer. In other words, if the duration of a disturbance has not yet ended at the current time step, the disturbance signal will participate in the superposition; conversely, if the current time step exceeds the duration of a disturbance, the disturbance no longer affects the analog power signal and therefore does not participate in the superposition.

[0031] S3. Calculate the detection index of the analog power signal within the preset time window in the data buffer.

[0032] The preset time window is the length of time covered by the most recent time steps (e.g., 2 seconds). The analog power signal within the preset time window is extracted from the data buffer, and at least one of the following detection metrics is calculated: (1) Short-time standard deviation. The standard deviation of each analog power signal value within a preset time window is calculated to reflect the changes in the power fluctuation amplitude, which is suitable for detecting oscillations with significant amplitude changes.

[0033] (2) Energy value within a specified frequency band. Perform power spectrum estimation on the analog power signal within a preset time window (e.g., using the Welch algorithm) to calculate the total energy within a frequency band centered at a specified center frequency and with a specified half-width. This is suitable for detecting periodic oscillations in known frequency bands.

[0034] (3) Spectral peaks. Calculate the power spectrum and search spectral peaks of the analog power signal within a preset time window. Spectral peaks that appear in the frequency range above the preset minimum frequency and whose height exceeds the preset peak height threshold will be used as detection indicators. This is suitable for discovering resonant signals with unknown frequencies.

[0035] In one embodiment, a user can select a detection algorithm using a detection algorithm selection control (such as a drop-down box) provided by a graphical user interface, thereby determining the corresponding detection index based on the selected detection algorithm.

[0036] S4. Compare the detection indicators with the preset thresholds to determine whether an oscillation alarm is triggered.

[0037] For example, when the detection index is the short-time standard deviation, the calculated standard deviation is compared with a preset standard deviation threshold; when the detection index is the frequency band energy value, the calculated energy value is compared with a preset frequency band energy threshold; when the detection index is the spectral peak value, the searched spectral peak height is compared with a preset peak height threshold. If the detection index exceeds the corresponding preset threshold, an oscillation alarm is triggered.

[0038] In one embodiment, a duration criterion can be used, requiring the detection index to continuously exceed a preset threshold for a certain duration or multiple consecutive time steps before triggering an oscillation alarm, in order to avoid false alarms caused by instantaneous random fluctuations.

[0039] In addition, the aforementioned intelligent power oscillation monitoring method also includes: displaying simulation and detection results in real time through a graphical user interface. For example, the power curve of the simulated power signal is plotted in real time in the drawing area of ​​the graphical user interface; when no oscillation alarm is triggered, the power curve is plotted in a first display state (such as a green curve); when an oscillation alarm is triggered, the power curve is plotted in a second display state (such as a red curve), which is different from the first display state. Furthermore, the operation log and alarm information are displayed in a scrolling format in the information display area of ​​the graphical user interface in the form of timestamps, and the alarm information can be highlighted in red for easy user attention.

[0040] In one implementation, the graphical user interface control panel is divided into the following sections: a noise parameter adjustment area, providing adjustment controls for parameters such as mean recovery rate, long-term mean, and volatility; a disturbance injection configuration area, providing a drop-down box for disturbance type selection and input boxes for parameters such as amplitude, frequency, duration, and phase; a disturbance list area, displaying parameter information and activation status of all added disturbances; and a detection algorithm and parameter selection area, providing a drop-down box for detection algorithm selection and setting controls for corresponding parameters.

[0041] Figure 2 This is a schematic diagram of the graphical user interface provided in an embodiment of the present invention. Figure 2 As shown, the left side of the interface displays a real-time power curve plotting area. The horizontal axis represents time (in seconds), and the vertical axis represents the active power of the thermal power unit (in MW). The green curve presents the simulated power signal superimposed with the reference noise signal and the disturbance signal. The upper right area of ​​the interface is the OU noise parameter control area, which includes adjustment controls for three parameters: volatility, mean recovery rate, and long-term mean, as well as a button to reset the OU parameters to their default values. Below the OU noise parameter control area is the oscillation injection configuration area, which provides settings for noise parameters such as disturbance type, amplitude, frequency, duration, and initial phase, as well as an "Add and Inject" button. Below the oscillation injection configuration area is a disturbance list, which displays the added disturbance signals. It includes a "Remove Selected" button. Users can select a disturbance signal in the list and click this button to remove it from the list, preventing it from participating in the subsequent power signal superposition in the simulation. Below the disturbance injection configuration area is the oscillation detection configuration area, which includes a drop-down menu for selecting the detection algorithm, short-time standard deviation threshold, duration, and other parameter settings. It can display in real-time the detection metric (such as short-time standard deviation) determined using the selected detection algorithm and its comparison with a preset threshold (such as the short-time standard deviation threshold). Below the oscillation detection configuration area is the message bar / alarm area, which displays the operation log and alarm information in a scrolling format using timestamps. Figure 2In the operating state shown, the user has injected a noise (custom noise) type disturbance (amplitude Amp=2.00MW, frequency Freq=1.00Hz, duration Dur=4.00s), with a start time of start=35.4s. The short-time standard deviation is calculated in real time to be 0.6463MW. By comparing it with the preset short-time standard deviation threshold of 0.6000MW, it can be determined whether to trigger an oscillation alarm.

[0042] Figure 3 This is a structural block diagram of a power oscillation intelligent monitoring system provided in an embodiment of the present invention. For example... Figure 3 As shown, this embodiment of the invention also provides a power oscillation intelligent monitoring system 300, comprising: The noise modeling module 301 is used to model the reference power noise of thermal power units under undisturbed operating conditions using a stochastic process model with mean regression characteristics, and obtain the reference noise signal. The signal generation module 302 is used to generate a disturbance signal according to the disturbance type and disturbance configuration parameters, and to superimpose the disturbance signal onto the reference noise signal to obtain an analog power signal and store it in the data buffer. The detection calculation module 303 is used to calculate the detection index of the analog power signal within a preset time window in the data buffer; The alarm judgment module 304 is used to compare the detection index with the preset threshold to determine whether an oscillation alarm is triggered.

[0043] This invention also provides an electronic device, such as... Figure 4 As shown, it includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404. Memory 403 is used to store computer programs; When processor 401 executes the program stored in memory 403, it performs the following steps: Using a stochastic process model with mean regression characteristics, the reference power noise of thermal power units under undisturbed operating conditions is modeled to obtain the reference noise signal at the current time step. A disturbance signal is generated based on the disturbance type and disturbance configuration parameters, and the disturbance signal is superimposed on the reference noise signal to obtain an analog power signal and store it in the data buffer. Calculate the detection index of the analog power signal within a preset time window in the data buffer; The detection index is compared with a preset threshold to determine whether an oscillation alarm is triggered.

[0044] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0045] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0046] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0047] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0048] This invention also provides a storage medium storing a computer program, which, when executed by a processor, performs the following method steps: Using a stochastic process model with mean regression characteristics, the reference power noise of thermal power units under undisturbed operating conditions is modeled to obtain the reference noise signal at the current time step. A disturbance signal is generated based on the disturbance type and disturbance configuration parameters, and the disturbance signal is superimposed on the reference noise signal to obtain an analog power signal and store it in the data buffer. Calculate the detection index of the analog power signal within a preset time window in the data buffer; The detection index is compared with a preset threshold to determine whether an oscillation alarm is triggered.

[0049] As the storage medium embodiment is basically similar to the method embodiment, it is described in a relatively simple way. For relevant details, please refer to the description of the method embodiment.

[0050] It should be noted that the system, electronic device and storage medium in the embodiments of the present invention are respectively the system, electronic device and storage medium applying the above-described intelligent power oscillation monitoring method. Therefore, all embodiments of the above-described intelligent power oscillation monitoring method are applicable to the system, electronic device and storage medium, and can achieve the same or similar beneficial effects.

[0051] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0052] The use of terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples" indicates that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0053] Although this application has been described herein in conjunction with various embodiments, other variations of the disclosed embodiments can be understood and implemented by those skilled in the art in carrying out the claimed application by reviewing the accompanying drawings, the disclosure, and the appended claims.

[0054] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A method for intelligent monitoring of power oscillations, characterized in that, include: Using a stochastic process model with mean regression characteristics, the reference power noise of thermal power units under undisturbed operating conditions is modeled to obtain the reference noise signal at the current time step. A disturbance signal is generated based on the disturbance type and disturbance configuration parameters, and the disturbance signal is superimposed on the reference noise signal to obtain an analog power signal and store it in the data buffer. Calculate the detection index of the analog power signal within a preset time window in the data buffer; The detection index is compared with a preset threshold to determine whether an oscillation alarm is triggered.

2. The intelligent power oscillation monitoring method according to claim 1, characterized in that, The steps for modeling the reference power noise of a thermal power unit under undisturbed operating conditions using a stochastic process model with mean regression characteristics, and obtaining the reference noise signal at the current time step, include: The Ornstein-Uhlenbeck stochastic process model is used to model the reference power noise of thermal power units under undisturbed operating conditions. Based on the reference noise signal of the previous time step, the mean recovery rate, the long-term mean, the volatility parameter, and the random increment of the current time step, the reference noise signal of the current time step is iteratively calculated.

3. The intelligent power oscillation monitoring method according to claim 2, characterized in that, The mean recovery rate, the long-term mean, and the volatility parameters are dynamically adjusted in real time using adjustment controls provided by the graphical user interface.

4. The intelligent power oscillation monitoring method according to claim 2, characterized in that, The steps of generating a disturbance signal based on the disturbance type and disturbance configuration parameters, superimposing the disturbance signal onto the reference noise signal to obtain an analog power signal, and storing it in a data buffer include: Receive the disturbance type and corresponding disturbance configuration parameters selected by the user through the graphical user interface; The disturbance signal is generated based on the disturbance type and the disturbance configuration parameters, and the disturbance signal is added to the disturbance list; Traverse the disturbance list, superimpose the disturbance signal that is within its own duration at the current time step onto the reference noise signal to obtain the analog power signal and store it in the data buffer.

5. The intelligent power oscillation monitoring method according to claim 4, characterized in that, The disturbance type includes at least one of sine wave, square wave, triangle wave and pulse, and the disturbance configuration parameters include at least one of amplitude, frequency, duration and phase.

6. The intelligent power oscillation monitoring method according to claim 1, characterized in that, The steps for calculating the detection index of the analog power signal within a preset time window in the data buffer include: Calculate at least one of the following: the short-time standard deviation of the analog power signal within the preset time window, the energy value of the analog power signal within the preset time window in the specified frequency band, and the spectral peak value of the analog power signal within the preset time window.

7. The intelligent power oscillation monitoring method according to claim 1, characterized in that, Also includes: The power curve of the analog power signal is plotted in real time through a graphical user interface; When the oscillation alarm is not triggered, the power curve is plotted in the first display state; When the oscillation alarm is triggered, the power curve is plotted in a second display state that is different from the first display state; In the information display area of ​​the graphical user interface, the operation logs and alarm information are displayed in a scrolling format in the form of timestamps.

8. A power oscillation intelligent monitoring system, characterized in that, include: The noise modeling module is used to model the reference power noise of thermal power units under undisturbed operating conditions using a stochastic process model with mean regression characteristics, and obtain the reference noise signal. The signal generation module is used to generate a disturbance signal according to the disturbance type and disturbance configuration parameters, and to superimpose the disturbance signal onto the reference noise signal to obtain an analog power signal and store it in the data buffer. The detection calculation module is used to calculate the detection index of the analog power signal within a preset time window in the data buffer; The alarm judgment module is used to compare the detection index with a preset threshold to determine whether an oscillation alarm is triggered.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory is used to store computer programs; When the processor executes the program stored in the memory, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images