A frequency modulation intelligent control method and system for an ultra-capacitance coupled thermal power unit

Abstract

The present invention discloses a supercapacitor-coupled intelligent frequency modulation control method and system for thermal power units, which relates to the technical field of power grid frequency modulation. The method includes collecting data of thermal power units, predicting data changes to determine input data, reducing prediction data errors through complementary compensation, and performing adjacent correction on the data based on frequency domain analysis and disorder degree. It is determined whether there is an equilibrium state in the data, and error compensation is performed on the data with an equilibrium state. The supercapacitor-coupled intelligent frequency modulation control method provided by the present invention reduces prediction data errors through complementary compensation, analyzes and corrects in the frequency domain, improves the accuracy of prediction data, enhances the precision and stability of data processing, and more truly reflects the state of the unit. The results of single prediction are corrected from three dimensions, improving the accuracy of the prediction results. The present invention achieves better effects in terms of accuracy and stability.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid frequency modulation, and specifically to a frequency modulation intelligent control method and system for a supercapacitor-coupled thermal power unit. Background Art

[0002] With the development of the power system and the continuous maturity of the power market, thermal power units still play an important role in the power system. However, traditional frequency modulation control methods for thermal power units have many deficiencies in dealing with frequency fluctuations and power demands of modern power grids. With the introduction of new energy and the diversification of power loads, the frequency stability of the power grid faces greater challenges, and traditional frequency modulation control methods can no longer meet the requirements of modern power grids for rapid response and high-precision frequency modulation. In this context, it becomes particularly important to conduct research on frequency modulation control of thermal power units by combining new technologies and new methods.

[0003] Currently, the frequency modulation of thermal power units mainly relies on inertia and primary frequency modulation control. However, due to the physical characteristics of thermal power units, their inertia response speed is slow, and it is difficult to effectively respond to frequency fluctuations in a short time. Superconducting energy storage technology has become an effective auxiliary frequency modulation means due to its high power density and fast response ability. However, the existing technologies face the following problems in practical applications: First, in terms of data acquisition and processing, due to the complexity and diversity of the operating data of thermal power units, traditional data processing methods are difficult to predict and analyze data in real time and accurately; Second, in terms of frequency modulation control strategies, the existing frequency modulation methods have deficiencies in data prediction accuracy and response speed, and it is difficult to meet the requirements of a high-frequency and rapidly changing power grid environment. Therefore, how to effectively utilize advanced data processing technologies and control strategies to improve the accuracy and response speed of thermal power unit frequency modulation has become the focus and difficulty of current research. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the frequency modulation control method of thermal power units has a slow response speed, low data processing accuracy, and how to improve the instability of the frequency modulation effect.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A frequency modulation intelligent control method for a supercapacitor-coupled thermal power unit, including collecting data of the thermal power unit and predicting changes in the data to determine input data; reducing prediction data errors through complementary compensation, and performing adjacent correction on the data based on frequency domain analysis and disorder degree; determining whether there is an equilibrium state in the data, and making error compensation for the data with an equilibrium state.

[0007] As a preferred embodiment of the intelligent control method for frequency modulation of the ultra-capacitance coupled thermal power unit according to the present invention, wherein: collecting the data of the thermal power unit includes collecting the historical frequency data P1 and the output data P2 of the thermal power unit in real time through the monitoring system of the thermal power unit, and preprocessing the collected data to remove noise and outliers.

[0008] As a preferred embodiment of the intelligent control method for frequency modulation of the ultra-capacitance coupled thermal power unit according to the present invention, wherein: determining the input data by predicting the change of the data includes using the preprocessed historical frequency data P1 to predict the frequency change through the long short-term memory network LSTM, and obtaining the predicted frequency change data Expressed as:

[0009]

[0010] Using the regression model to predict the output change and obtaining the predicted output change data Expressed as:

[0011]

[0012] Adapting and adjusting the parameters of the prediction model by real-time monitoring data, expressed as:

[0013]

[0014] Wherein, θ * is the optimal parameter, is the predicted value of the model at time t, θ represents the parameter vector of the prediction model, θ j is the j-th component in the parameter vector θ, y t is the actual value at time t, λ is the regularization parameter, T represents the total number of time steps of the time series data, P represents the total number of parameters in the prediction model, and after obtaining the optimal parameters, feedback optimization is performed to determine the optimized and Calculating the predicted data P3 of the power borne by the super capacitor, expressed as:

[0015]

[0016] As a preferred embodiment of the intelligent control method for frequency modulation of the ultra-capacitance coupled thermal power unit according to the present invention, wherein: reducing the prediction data error through complementary compensation includes performing complementary compensation with the difference between the known actual value and the predicted value. Let the actual value be f(t) and the predicted value be f'(t), and the complementary compensation is expressed as:

[0017]

[0018] Among them, a, b, and c are preset time change points, σ is the degree of data dispersion, μ is the mean value, ω and P3(t) are multiplied to obtain P3’, and P3’ is set as the actual value.

[0019] As a preferred solution of the intelligent frequency modulation control method for the supercapacitor-coupled thermal power unit described in the present invention, wherein: the adjacent correction of data based on frequency-domain analysis and disorder degree includes converting the time-domain signal into a frequency-domain signal and performing frequency-domain analysis, which is expressed as:

[0020]

[0021] Among them, F represents the Fourier transform;

[0022] Calculate the disorder degree based on the frequency-domain analysis result, which is expressed as:

[0023]

[0024] Among them, ω max represents the maximum value of the frequency after frequency-domain conversion of the sequence, ω min represents the minimum value of the frequency after frequency-domain conversion of the sequence, ω mid represents the median. When the disorder degree is greater than or equal to 12, adjacent correction is performed. When the disorder degree is lower than 12, the time-domain equilibrium state is judged.

[0025] As a preferred solution of the intelligent frequency modulation control method for the supercapacitor-coupled thermal power unit described in the present invention, wherein: the adjacent correction includes performing stretching transformation on each frequency ω on the spectrum, translating the maximum and minimum values. The maximum value is translated forward by The amount by which the minimum value is translated negatively is i represents the number of times the entire frequency-domain sequence needs to be adjusted. After completing the translation of the maximum value, translate the second-maximum and second-minimum sequences, and translate them positively and negatively by ω 、 max is the second-maximum frequency, ω 、 min is the second-minimum frequency, and process each pair of frequencies in turn;

[0026] For the amplitude A corresponding to each ω, perform corresponding compression to become the original

[0027] As a preferred solution of the intelligent frequency modulation control method for the supercapacitor-coupled thermal power unit described in the present invention, wherein: the equilibrium state judgment includes setting the sequence output after adjacent correction as p4, using a fitting function for fitting, selecting a polynomial fitting function, and determining the fitting parameters by minimizing the sum of the squares of the errors between the predicted value and the actual value through the least squares method. The fitting result is f p4(x) is differentiated, and the Lyapunov function is used to judge the dynamic stability. When the output is greater than or equal to 0 and the state is unstable, error compensation is performed, which is expressed as:

[0028]

[0029] Among them, f″(x) represents the compensated random pseudo-sequence. When the output is less than 0, the thermal power unit system is regarded as asymptotically stable. Another object of the present invention is to provide a frequency modulation intelligent control system for a super-capacitance coupled thermal power unit, which can effectively judge the dynamic stability of the thermal power unit system through the equilibrium state judgment method based on the Lyapunov function, further optimize the frequency modulation control strategy, and definitely solve the problem of insufficient stability in the current thermal power unit frequency modulation technology. Another object of the present invention is to provide a frequency modulation intelligent control system for a super-capacitance coupled thermal power unit, which can effectively judge the dynamic stability of the thermal power unit system through the equilibrium state judgment method based on the Lyapunov function, further optimize the frequency modulation control strategy, and definitely solve the problem of insufficient stability in the current thermal power unit frequency modulation technology.

[0030] As a preferred scheme of the frequency modulation intelligent control system for the super-capacitance coupled thermal power unit described in the present invention, it includes: a data acquisition module, a data processing module, and an equilibrium analysis module; the data acquisition module is used to collect thermal power unit data and determine the input data through change prediction; the data processing module is used to reduce the prediction data error through complementary compensation and perform adjacent correction on the data based on frequency domain analysis and disorder degree; the equilibrium analysis module is used to determine whether there is an equilibrium state in the data and perform error compensation on the data with an equilibrium state.

[0031] The beneficial effects of the present invention: The frequency modulation intelligent control method for the super-capacitance coupled thermal power unit provided by the present invention reduces the prediction data error through complementary compensation, analyzes and corrects it in the frequency domain, improves the accuracy of the prediction data, enhances the precision and stability of data processing, and more truly reflects the state of the unit. The results of single prediction are corrected from 3 dimensions, improving the accuracy of the prediction results. The present invention has achieved better effects in terms of accuracy and stability. Description of the Drawings

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1The overall flowchart of a frequency modulation intelligent control method for an ultra-capacitor coupled thermal power unit provided in the first embodiment of the present invention.

[0034] Figure 2 The overall flowchart of a frequency modulation intelligent control system for an ultra-capacitor coupled thermal power unit provided in the third embodiment of the present invention. Specific embodiments

[0035] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] Embodiment 1

[0037] Referring to Figure 1 , for an embodiment of the present invention, a frequency modulation intelligent control method for an ultra-capacitor coupled thermal power unit is provided, including:

[0038] S1: Collect data of the thermal power unit and predict the changes in the data to determine the input data.

[0039] Furthermore, collecting data of the thermal power unit includes real-time collecting the historical frequency data P1 and output data P2 of the thermal power unit through the monitoring system of the thermal power unit, and preprocessing the collected data to remove noise and outliers.

[0040] It should be noted that predicting the changes in the data to determine the input data includes using the preprocessed historical frequency data P1 to predict the frequency changes through a long short-term memory network (LSTM) to obtain the predicted frequency change data Expressed as:

[0041]

[0042] Using a regression model to predict the output changes to obtain the predicted output change data Expressed as:

[0043]

[0044] Adapting and adjusting the parameters of the prediction model through real-time monitoring data, expressed as:

[0045]

[0046] Where θ * is the optimal parameter, is the predicted value of the model at time t, θ represents the parameter vector of the prediction model, θ j is the j-th component in the parameter vector θ, y t is the actual value at time t, λ is the regularization parameter, T represents the total number of time steps of the time series data, P represents the total number of parameters in the prediction model. After obtaining the optimal parameters, feedback optimization is used to determine the optimized and Calculate the power prediction data P3 borne by the supercapacitor, which is expressed as:

[0047]

[0048] The LSTM model can effectively handle the complex dependencies in time series data, provide high-precision frequency change prediction, improve the accuracy of frequency change prediction, enhance the real-time performance and accuracy of frequency modulation control, and ensure the frequency stability of the power system.

[0049] S2: Reduce the prediction data error through complementary compensation, and perform adjacent correction on the data based on frequency domain analysis and disorder degree.

[0050] Furthermore, reducing the prediction data error through complementary compensation includes using the difference between the known actual value and the predicted value for complementary compensation. Let the actual value be f(t) and the predicted value be f′(t), and the complementary compensation is expressed as:

[0051]

[0052] Among them, a, b, and c are preset time change points, σ is the data dispersion degree, μ is the mean value. Multiply ω and P3(t) to obtain P3’, and let P3’ be f(t). Through frequency domain analysis, the frequency components and change trends in the data are revealed. There are many disadvantages in time domain analysis that cannot be exposed. Frequency domain analysis can better capture the periodic changes in the data. By calculating the disorder degree, the stability and change degree of the data are measured. Frequency domain analysis and disorder degree calculation improve the depth and breadth of data processing, and can more accurately judge the change trend and stability of the data, so as to optimize the frequency modulation control strategy.

[0053] It should be noted that the adjacent correction of the data based on frequency domain analysis and disorder degree includes converting the time domain signal into a frequency domain signal and performing frequency domain analysis, which is expressed as:

[0054]

[0055] Among them, F represents the Fourier transform;

[0056] Calculate the disorder degree based on the frequency domain analysis result, which is expressed as:

[0057]

[0058] Among them, ω max represents the maximum value of the frequency after frequency-domain transformation of the sequence, and ω min represents the minimum value of the frequency after frequency-domain transformation of the sequence, and ω mid represents the median. When the disorder degree is greater than or equal to 12, adjacent modification is performed. When the disorder degree is lower than 12, the time-domain equilibrium state is judged.

[0059] It should also be noted that the adjacent modification includes performing stretching transformation on each frequency ω on the spectrum, translating the maximum and minimum ones, and the positive translation of the maximum value is and the negative translation amount of the minimum value is i represents the number of times the entire frequency-domain sequence needs to be adjusted. After completing the translation of the maximum value, the second-largest and second-smallest sequences are translated, with positive and negative translations of ω 、 max being the second-largest frequency, and ω 、 min being the second-smallest frequency, and each pair of frequencies is processed in turn;

[0060] For the amplitude A corresponding to each ω, the corresponding compression is performed to become the original

[0061] S3: Determine whether there is an equilibrium state in the data, and compensate for the errors in the data with an equilibrium state.

[0062] Furthermore, the equilibrium state judgment includes assuming that the sequence output after adjacent modification is p4, fitting with a fitting function, selecting a polynomial fitting function, and determining the fitting parameters by minimizing the sum of the squares of the errors between the predicted value and the actual value through the least squares method. The fitting obtains f p4 (x) is differentiated, and the Lyapunov function is used to judge the dynamic stability. When the output is greater than or equal to 0, the state is unstable and error compensation is performed, which is expressed as:

[0063]

[0064] Among them, f″(x) represents the random pseudo-sequence for compensation. When the output is less than 0, the thermal power unit system is regarded as asymptotically stable.

[0065] It should be noted that the Lyapunov function is a tool commonly used for the stability analysis of nonlinear systems and can effectively judge the dynamic stability of the system. Through the Lyapunov function, the stability of the thermal power unit system in different states can be judged to ensure the safe operation of the system. When the system is in an unstable state, the analysis result of the Lyapunov function is used as the basis for triggering the system to perform error correction, and by adjusting the error, the system is ensured to reach a stable state again.

[0066] Example 2

[0067] An embodiment of the present invention provides a frequency modulation intelligent control method for an ultra-capacitor coupled thermal power unit. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0068] First, in order to verify the effect of the frequency modulation intelligent control method for the ultra-capacitor coupled thermal power unit, experiments are conducted to demonstrate the advantages of this method compared with the prior art. First, typical thermal power units are selected for real-time data collection, including historical frequency data and output data. These data are collected in real time through the monitoring system of the thermal power unit and then preprocessed to remove noise and outliers to ensure the accuracy and reliability of the data.

[0069] To ensure the practical application effect of the inventive method. Throughout the experiment, the same method is used for data collection, and three groups of data are collected as input.

[0070] Table 1 Comparison table of experimental data

[0071]

[0072]

[0073] In terms of frequency modulation error compensation, the invention of the present side shows a lower error compensation value, which indicates that the invention of the present side is more sensitive and efficient in dealing with dynamic load changes. In Experiment 2, the frequency modulation error compensation of the invention of the present side is 0.08 MW, far lower than 0.25 MW of the prior art, which shows that the invention of the present side can adjust the output more accurately to match the actual load demand, thereby improving the stability and energy efficiency of the system.

[0074] Example 3

[0075] Refer to Figure 2 , an embodiment of the present invention provides an ultra-capacitor coupled thermal power unit frequency modulation intelligent control system, including a data collection module, a data processing module, and a balance analysis module.

[0076] Among them, the data collection module is used to collect thermal power unit data and determine the input data through change prediction; the data processing module is used to reduce the prediction data error through complementary compensation and perform adjacent correction on the data based on frequency domain analysis and disorder degree; the balance analysis module is used to determine whether there is a balanced state in the data and make error compensation for the data with a balanced state.

[0077] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable 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 a part of this 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 for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0078] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions. It can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0079] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0080] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques well known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A frequency modulation intelligent control method for an ultra-capacitance coupled thermal power unit, characterized in that Including: Collecting data of thermal power units, and predicting data changes to determine input data; Reducing prediction data errors through complementary compensation, and performing adjacent correction on actual value data based on frequency domain analysis and disorder degree; Determining whether there is an equilibrium state in the data, and making up for errors in the data with an equilibrium state; The determination of the input data for change prediction of data includes using the preprocessed historical frequency data P1, and performing frequency change prediction through a long short-term memory network (LSTM) to obtain the predicted frequency change data It is expressed as: Use a regression model to predict the output change and obtain the predicted output change data It is expressed as: Adapting the parameters of the prediction model by real-time monitoring of data, expressed as: where, θ* is the optimal parameter, is the predicted value of the model at time t, θ represents the parameter vector of the prediction model, θ j is the j-th component in the parameter vector θ, y t is the actual value at time t, y t is the actual value at time t, λ is the regularization parameter, T represents the total number of time steps of the time series data, P represents the total number of parameters in the prediction model, and after obtaining the optimal parameter, feedback optimization is used to determine the optimized and Calculate the predicted data P3 of the power borne by the supercapacitor, expressed as: The reducing prediction data errors through complementary compensation includes performing complementary compensation with the difference between the known actual value and the predicted value. Let the initial actual value be f(t), the predicted value be f′(t), and the complementary compensation is expressed as: Where a, b, and c are preset time change points, σ is the data dispersion degree, μ is the mean value, multiplying the complementary compensation by P3(t) to obtain P3’, and setting P3’ as the actual value; The performing adjacent correction on actual value data based on frequency domain analysis and disorder degree includes converting the time domain signal into a frequency domain signal and performing frequency domain analysis, expressed as: Where F represents the Fourier transform; Calculating the disorder degree based on the frequency domain analysis result, expressed as: Among them, ω max Indicates the maximum frequency of the sequence after frequency domain conversion, ω min Indicates the minimum frequency after converting the sequence into frequency domain, ω mid Indicates the median. When the disorder degree is greater than or equal to 12, the adjacent correction is performed. When the disorder degree is less than 12, the time domain equilibrium state is judged. The adjacent correction includes performing a stretching transformation on each frequency ω on the spectrum, translating the maximum and minimum values, and the amount of positive translation of the maximum value is The amount of negative translation of the minimum value is i represents the number of times the entire frequency domain sequence needs to be adjusted. After translating the maximum value, translate the second maximum and second minimum sequences, with positive and negative translations respectively ω` max is the second maximum frequency, ω` min is the second minimum frequency, and process each pair of frequencies in turn; For the amplitude A corresponding to each ω, perform the corresponding compression to become The equilibrium state judgment includes assuming that the sequence output after adjacent modification is p4, using a fitting function for fitting, selecting a polynomial fitting function, and determining the fitting parameters by minimizing the sum of the squares of the errors between the predicted value and the actual value through the least squares method, and obtaining the fitting f p4 (x) is differentiated, and the Lyapunov function is used to judge the dynamic stability. When the output is greater than or equal to 0, the state is unstable, and error compensation is performed, which is expressed as: Where f″(x) represents the compensated random pseudo-sequence, and when the output is less than 0, it is regarded as the thermal power unit system being asymptotically stable.

2. The intelligent control method for frequency modulation of the supercapacitor-coupled thermal power generation unit according to claim 1, wherein: The collecting data of thermal power units includes real-time collecting the historical frequency data P1 and output data P2 of the thermal power units through the monitoring system of the thermal power units, and preprocessing the collected data to remove noise and outliers.

3. A system adopting the frequency modulation intelligent control method of a supercapacitor-coupled thermal power unit as described in any one of claims 1 and 2, characterized in that: Including a data acquisition module, a data processing module, and a balance analysis module; The data acquisition module is used to collect data of thermal power units and predict data changes to determine input data; The data processing module is used to reduce prediction data errors through complementary compensation and perform adjacent correction on the data based on frequency domain analysis and disorder degree; The balance analysis module is used to determine whether there is an equilibrium state in the data and make up for errors in the data with an equilibrium state.

Images