Method and device for estimating power oscillation signal parameters, storage medium, and equipment
By using the neural network-based adaptive Prony method, the complexity and computational burden of power oscillation signal parameter estimation in power systems are solved, achieving high-precision and low-cost power oscillation signal parameter estimation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- POWER SUPPLY SERVICE & MANAGEMENT CENT STATE GRID JIANGXI ELECTRIC POWER CO LTD
- Filing Date
- 2022-12-21
- Publication Date
- 2026-07-03
AI Technical Summary
Existing technologies struggle to effectively estimate power oscillation signal parameters in complex scenarios within power systems. Furthermore, the Prony method alone incurs significant computational burden, and its complexity increases when combined with other methods.
An adaptive Prony method based on neural networks is adopted. The signal is processed by a preset sliding window, and the order of the characteristic polynomial of the Prony method is adaptively determined by a B-spline neural network. The calculation process is optimized by combining the signal estimation formula and the order update formula.
While maintaining high robustness, it reduces computational complexity and cost, and improves the accuracy and efficiency of power oscillation signal parameter estimation.
Smart Images
Figure CN115828067B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power system technology, and in particular to a method, apparatus, storage medium, and device for estimating parameters of power oscillation signals. Background Technology
[0002] The increasing energy demand leads to severe imbalances in the planning and operation of power systems, which can cause significant disturbances and power oscillations. This results in large fluctuations in signal parameters used to assess the health of the power system. Due to the interconnection of new renewable energy sources (RES), the system may be exposed to critical operating conditions during fault-induced transient states, further causing power oscillations. Therefore, reliable indicators are crucial for establishing power system analysis under critical conditions. Summary of the Invention
[0003] In view of this, this application provides a method, apparatus, storage medium, and device for estimating parameters of power oscillation signals.
[0004] According to one aspect of this application, a method for estimating parameters of a power oscillation signal is provided, the method comprising:
[0005] Step 1: Process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal;
[0006] Step 2: Perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal;
[0007] Step 3: Fit the estimated oscillation signal according to the preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal;
[0008] Step 4: Substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression;
[0009] Step 5: Based on the sliding window oscillation signal and the reconstructed oscillation signal, determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system.
[0010] Optionally, step 5 includes:
[0011] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance, then repeat steps 1 to 4 until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 reaches a preset second number.
[0012] Optionally, step 5 also includes:
[0013] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then the order of the preset oscillation signal expression is updated, and the process returns to step 3.
[0014] Optionally, the order of updating the preset oscillation signal expression includes:
[0015] The order of the preset oscillation signal expression is updated using a preset order update formula, where the order update formula is: β is a row vector containing the output of the basis function, W represents the row vector of weights, k represents the number of times the order of the preset oscillation signal expression is updated, e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal, and ζ represents the learning rate.
[0016] Optionally, the preset oscillation signal expression is: A m f represents the initial increase. k Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m = 1, 2...p, where p represents the order.
[0017] Optionally, after step 2, the method further includes:
[0018] The estimated oscillation signal is updated using a signal estimation formula, wherein the signal estimation formula is: z0=y0,z i =y i ,z n+i =y i ',y i Let represent the harmonic component of the i-th sliding window oscillation signal, i = 1, 2, ..., n, where n is the number of sliding window oscillation signals, and e represents the difference between the sliding window oscillation signal and the initial estimated oscillation signal.
[0019] According to another aspect of this application, an apparatus for estimating parameters of a power oscillation signal is provided, the apparatus comprising:
[0020] The signal acquisition module is used to process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal;
[0021] The signal estimation module is used to perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal.
[0022] The parameter calculation module is used to fit the estimated oscillation signal according to a preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal;
[0023] The signal reconstruction module is used to substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and to obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression;
[0024] The parameter determination module is used to determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system based on the sliding window oscillation signal and the reconstructed oscillation signal.
[0025] Optionally, the parameter determination module is also used for:
[0026] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance, then repeat steps 1 to 4 until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 reaches a preset second number.
[0027] Optionally, the parameter determination module is also used for:
[0028] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then the order of the preset oscillation signal expression is updated, and the parameter calculation module is returned to perform the calculation.
[0029] Optionally, the parameter determination module is further configured to:
[0030] The order of the preset oscillation signal expression is updated using a preset order update formula, where the order update formula is: β is a row vector containing the output of the basis functions, W represents the row vector of weights, k represents the number of times the order of the preset oscillation signal expression is updated, and e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal. This represents the learning rate.
[0031] Optionally, the preset oscillation signal expression is: A m f represents the initial increase. k Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m = 1, 2...p, where p represents the order.
[0032] Optionally, the signal estimation module is also used for:
[0033] The estimated oscillation signal is updated using a signal estimation formula, wherein the signal estimation formula is: z0=y0,z i =y i ,z n+i =y i ',y i Let represent the harmonic component of the i-th sliding window oscillation signal, i = 1, 2, ..., n, where n is the number of sliding window oscillation signals, and e represents the difference between the sliding window oscillation signal and the initial estimated oscillation signal.
[0034] According to another aspect of this application, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for estimating the parameters of the power oscillation signal.
[0035] According to another aspect of this application, an apparatus is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the above-described method for estimating the parameters of the power oscillation signal.
[0036] By means of the above technical solution, this application provides a method, apparatus, storage medium, and device for estimating power oscillation signal parameters. Through the signal pre-estimation part, the B-spline neural network adaptively determines the order of the characteristic polynomial of the Prony method, thereby improving the accuracy and robustness of the algorithm, while comprehensively considering the computation time and cost of the algorithm.
[0037] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description
[0038] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0039] Figure 1 A flowchart illustrating a method for estimating parameters of a power oscillation signal provided in an embodiment of this application is shown.
[0040] Figure 2 A schematic diagram of the structure of an estimation device for power oscillation signal parameters provided in an embodiment of this application is shown;
[0041] Figure 3 A schematic diagram of the device structure of an embodiment of this application is shown. Detailed Implementation
[0042] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.
[0043] This embodiment provides a method for estimating parameters of a power oscillation signal, such as... Figure 1 As shown, the method includes:
[0044] Step 1: Process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal.
[0045] The classic approach to analyzing the transient stability of electrical systems is based on linear power system models; however, with continuous load changes in system topology, nonlinear problems need to be addressed to ensure the transient stability of any power system. This leads to the development of different recommendations using online and offline analyses primarily based on transient stability indices. The use of measurements allows for the development of new online and offline applications that can be used to obtain model parameters, and parameter validation can be performed through both online and offline processes. Oscillation modes can be extracted from signal parameters. Therefore, the estimation of signal parameters is crucial for determining the damping characteristics of a power system. On the other hand, measurements can be used to develop new online and offline applications that can be employed to obtain model parameters. An important algorithm for estimating oscillating signal parameters based on measurement results is the Prony method. However, it is often combined with other strategies to achieve the desired results. But this not only increases the complexity of the scheme but also incurs a significant computational burden in the preprocessing stage, especially for schemes based on optimization methods. There are two main problems with the Prony method for parameter estimation in power oscillating systems: 1) the Prony method alone cannot cope with increasingly complex power scenarios; 2) combining it with other methods to achieve better results makes the method more complex and computationally burdensome.
[0046] To address the aforementioned issues, this application proposes an adaptive Prony method based on neural networks, which can maintain high robustness at extremely low cost while coping with complex scenarios.
[0047] Using a sliding window to process the input signal, the input signal is segmented. This divides the oscillation signal input from the power grid measurement into a small time interval [t0, t1]. The sliding window oscillation signal can be represented as... Among them B i It is the signal amplification, ω i Represents angular frequency, φ i X0 is the phase angle associated with the i-th harmonic component, and X0 represents the DC offset. The signal can consist of a DC component X0 and n harmonic components.
[0048] Step 2: Perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal.
[0049] A flexible algorithm is used to perform flexible calculations on the sliding window oscillation signal, and the calculated estimated oscillation signal is updated using a signal estimation formula, wherein the signal estimation formula is as follows: z0 = y0, z i =y i ,z n+i =y i ',y i Let represent the harmonic component of the i-th sliding window oscillation signal, i = 1, 2, ..., n, where n is the number of sliding window oscillation signals, and e represents the difference between the sliding window oscillation signal and the initial estimated oscillation signal.
[0050] Step 3: Fit the estimated oscillation signal according to the preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal. The preset oscillation signal expression is: A m f represents the initial increase. k Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m = 1, 2...p, where p represents the order.
[0051] The pre-defined oscillation signal expression is constructed using the Prony method, with an initial order of p=3, and the estimated signal is then evaluated. By fitting the data, the estimated signal is obtained. Feature parameters (A) k ,θ k ,α k ,f k ).
[0052] Step 4: Substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression.
[0053] After obtaining the characteristic parameters, they can be used through the formula Perform signal restoration to determine the reconstructed oscillation signal, where A k , representing the initial increase, f k Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), which is the time between one sample and the next sample, α k The damping coefficient is expressed in terms of S-1, θ kThis is the initial phase, expressed in radians, k = 1, 2...p, where p represents the order of the Prony method. Therefore, any oscillating signal can be obtained through A... k ,α k ,f k ,θ k These parameters are used to describe it.
[0054] Step 5: Based on the sliding window oscillation signal and the reconstructed oscillation signal, determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system.
[0055] Optionally, step 5 includes: if the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to a preset tolerance, then repeat steps 1 to 4 until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 reaches a preset second number; if the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then update the order of the preset oscillation signal expression and return to step 3.
[0056] The step of updating the order of the preset oscillation signal expression includes: updating the order of the preset oscillation signal expression using a preset order update formula, wherein the order update formula is as follows: β is a row vector containing the output of the basis functions, W represents the row vector of weights, k represents the number of times the order of the preset oscillation signal expression is updated, and e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal. This represents the learning rate.
[0057] To determine whether the estimated signal has reached the optimal level, we can specifically judge whether the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance. If it is less than the preset tolerance, we can assume that no parameter adjustment is needed at present, return to step 1 to continue to obtain the sliding window oscillation signal and repeat the above process. If the judgment result is that no parameter adjustment is needed for several consecutive times, then we can assume that the optimal parameter has been reached. Alternatively, if the number of repetitions of the above process reaches a certain number, we can stop iterating and take the final parameter as the optimal parameter.
[0058] If the aforementioned difference exceeds the preset tolerance, then the order of the oscillation signal expression needs to be updated. Specifically, based on the adaptive algorithm of the B-spline neural network, the parameter p is updated and defined as follows: Where β is a row vector containing the output of the basis functions, and W represents the row vector of weights. Based on a three-weight architecture, the expected adaptive performance is achieved, so in this case, each vector will have three elements. The learning process is defined by the weight vector. in represents the learning rate, and k-1 represents the previous values of the weight vector.
[0059] By applying the technical solution of this embodiment, the B-spline neural network adaptively determines the order of the characteristic polynomial of the Prony method through the signal pre-estimation part, thereby improving the accuracy and robustness of the algorithm, while comprehensively considering the computation time and cost of the algorithm.
[0060] Furthermore, as Figure 1 In terms of specific implementation, this application provides an estimation device for power oscillation signal parameters, such as... Figure 2 As shown, the device includes:
[0061] The signal acquisition module is used to process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal;
[0062] The signal estimation module is used to perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal.
[0063] The parameter calculation module is used to fit the estimated oscillation signal according to a preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal;
[0064] The signal reconstruction module is used to substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and to obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression;
[0065] The parameter determination module is used to determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system based on the sliding window oscillation signal and the reconstructed oscillation signal.
[0066] Optionally, the parameter determination module is also used for:
[0067] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance, then repeat steps 1 to 4 until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 reaches a preset second number.
[0068] Optionally, the parameter determination module is also used for:
[0069] If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then the order of the preset oscillation signal expression is updated, and the parameter calculation module is returned to perform the calculation.
[0070] Optionally, the parameter determination module is further configured to:
[0071] The order of the preset oscillation signal expression is updated using a preset order update formula, where the order update formula is: β is a row vector containing the output of the basis functions, W represents the row vector of weights, k represents the number of times the order of the preset oscillation signal expression is updated, and e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal. This represents the learning rate.
[0072] Optionally, the preset oscillation signal expression is: A m f represents the initial increase. k Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m = 1, 2...p, where p represents the order.
[0073] Optionally, the signal estimation module is also used for:
[0074] The estimated oscillation signal is updated using a signal estimation formula, wherein the signal estimation formula is: z0=y0,z i =y i ,z n+i =y i ',y i Let represent the harmonic component of the i-th sliding window oscillation signal, i = 1, 2, ..., n, where n is the number of sliding window oscillation signals, and e represents the difference between the sliding window oscillation signal and the initial estimated oscillation signal.
[0075] It should be noted that other corresponding descriptions of the functional units involved in the power oscillation signal parameter estimation device provided in this application embodiment can be found in the following references. Figure 1 The corresponding descriptions in the method will not be repeated here.
[0076] This application also provides a device, which can be a personal computer, server, network device, etc. Figure 3 As shown, the device includes a bus, a processor, memory, and a communication interface, and may also include input / output interfaces and a display device. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores location information. The network interface allows communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the various method embodiments.
[0077] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the device to which the present application is applied. Specific devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.
[0078] In one embodiment, a computer-readable storage medium is provided, which may be non-volatile or volatile, having stored thereon a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0079] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0080] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0081] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0082] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0083] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for estimating parameters of an electric oscillation signal, characterized in that, The method includes: Step 1: Process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal; Step 2: Perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal; Step 3: Fit the estimated oscillation signal according to the preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal; Step 4: Substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression; Step 5: Based on the sliding window oscillation signal and the reconstructed oscillation signal, determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system; Step 5 includes: If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance, then repeat steps 1 to 4 above until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 above reaches a preset second number. If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then update the order of the preset oscillation signal expression and return to step 3; The order of updating the preset oscillation signal expression includes: The order of the preset oscillation signal expression is updated using a preset order update formula, where the order update formula is: , , It is a row vector that contains the outputs of the basis functions. The row vector represents the weights, k represents the number of times the order of the preset oscillation signal expression is updated, and e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal. This represents the learning rate.
2. The method according to claim 1, characterized in that, The preset oscillation signal expression is as follows: A m f represents the initial increase. m Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m=1,2...p, where p represents the order and n is the number of sliding window oscillation signals.
3. An apparatus for estimating power oscillation signal parameters in a method for estimating power oscillation signal parameters as described in claim 1 or 2, characterized in that, The device includes: The signal acquisition module is used to process the oscillation signal of the power system through a preset sliding window to obtain the sliding window oscillation signal; The signal estimation module is used to perform flexible calculations on the sliding window oscillation signal to obtain the estimated oscillation signal corresponding to the sliding window oscillation signal. The parameter calculation module is used to fit the estimated oscillation signal according to a preset oscillation signal expression to determine the characteristic parameters corresponding to the estimated oscillation signal; The signal reconstruction module is used to substitute the feature parameters into the preset oscillation signal expression to obtain the target oscillation signal expression, and to obtain the reconstructed oscillation signal corresponding to the target oscillation signal expression; The parameter determination module is used to determine whether the characteristic parameter is the optimal power oscillation signal parameter of the power system based on the sliding window oscillation signal and the reconstructed oscillation signal. The parameter determination module is also used for: If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is less than or equal to the preset tolerance, then repeat steps 1 to 4 above until the difference between the sliding window oscillation signal and the corresponding reconstructed oscillation signal is less than or equal to the preset tolerance for a consecutive preset first number of times, or until the number of repetitions of steps 1 to 4 above reaches a preset second number. If the difference between the sliding window oscillation signal and the reconstructed oscillation signal is greater than the preset tolerance, then the order of the preset oscillation signal expression is updated, and the parameter calculation module is returned to perform the calculation. The parameter determination module is also used for: The order of the preset oscillation signal expression is updated using a preset order update formula, where the order update formula is: , , It is a row vector that contains the outputs of the basis functions. The row vector represents the weights, k represents the number of times the order of the preset oscillation signal expression is updated, and e represents the difference between the sliding window oscillation signal and the reconstructed oscillation signal. This represents the learning rate.
4. The apparatus according to claim 3, characterized in that, The preset oscillation signal expression is as follows: A m f represents the initial increase. m Represents the corresponding frequency (Hz), T is the sampling period in seconds (s), and α m θ represents the damping coefficient. m The initial phase is expressed in radians, m=1,2...p, where p represents the order and n is the number of sliding window oscillation signals.
5. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of claim 1 or 2.
6. An apparatus comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of claim 1 or 2.