Power regulation and control method and system for thermal power generation system

Abstract

The invention discloses a power regulation and control method and system for a thermal power generation system, and relates to the field of power regulation, and the method comprises the steps: collecting real-time information, and calculating state data according to the real-time information; predicting a damping ratio by using the state data and a stability prediction model, obtaining a damping ratio variable quantity according to the damping ratio, obtaining a power adjustment quantity based on the damping ratio variable quantity and a power adjustment model, determining a correction adjustment quantity according to the power adjustment quantity, and adjusting the power according to the correction adjustment quantity. And distributing the power adjustment amount by using the correction adjustment amount and the adjustable capacity to realize power regulation and control. The stability of the thermal power generation system can be predicted more accurately, and the accuracy of power regulation and control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power regulation, and in particular to a power regulation method and system for a thermal power generation system. Background Art

[0002] The stability of thermal power generation systems is a key factor in ensuring the continuity and reliability of power supply. It is closely related to the system's operating parameters, equipment status, and external environmental conditions. Therefore, it has obvious time-varying and nonlinear characteristics, making it difficult to accurately predict and effectively control.

[0003] At present, the small disturbance stability prediction and adjustment methods of thermal power generation systems have the following problems: 1. After being subjected to small disturbances, the dynamic response of the stability of the thermal power generation system is complex and difficult to accurately predict using traditional methods; 2. Existing stability prediction methods mostly rely on empirical formulas or simplified models, which cannot fully consider the actual operating status of the system and the influence of multiple factors; 3. Existing stability adjustment technologies often require a lot of manual intervention and empirical judgment, with low adjustment efficiency and difficulty in achieving optimal adjustment. Summary of the invention

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

[0005] Therefore, the technical problem solved by the present invention is: the existing prediction and adjustment methods have the problem of low prediction accuracy in small disturbance stability prediction and regulation of thermal power generation systems and how to improve the regulation efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a power control method of a thermal power generation system, comprising:

[0007] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0008] Collecting first characteristic data of the first object in the first state, and calculating first state data according to the first characteristic data;

[0009] Obtaining first stable data through first state data to construct a first state prediction model for prediction;

[0010] Obtaining first adjustment data through the first state data and the first state prediction model;

[0011] A first correction amount is determined according to the first adjustment data so as to achieve a first target distribution.

[0012] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0013] The first characteristic data includes operating parameters of the first object in a first state;

[0014] The first state data includes a first electrical parameter set of a first object in a first state.

[0015] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0016] The first stable data includes constructing a first stable model through the operating parameters of each sub-part of each first object during operation, and inputting the first state data into the first stable model to obtain the first stable data.

[0017] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0018] The first adjustment data includes a physical quantity that is the same as the first target effect data and that is exhibited by the adjusted object during operation.

[0019] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0020] The first correction amount includes: the correction amount of each sub-part when the first object is corrected according to the first adjustment data to achieve the first goal;

[0021] The first target allocation includes: regulating the adjustment amount of the first object in the first state according to the first correction amount and the first adjustment data to achieve the first target.

[0022] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0023] The constructing of the first stable model includes, specifically, constructing a convolutional neural network, a long short-term memory network and an attention mechanism.

[0024] As a preferred solution of the power control method of the thermal power generation system described in the present invention, wherein:

[0025] The first adjustment data includes, specifically, inputting the sensitivity of each generator to the damping ratio into a power adjustment model to obtain the first adjustment data.

[0026] Another object of the present invention is to provide a power control system for a thermal power generation system, which can obtain the damping ratio of the thermal power generation system by collecting real-time information of the thermal power generation system and calculating the state data of the thermal power generation system according to the real-time information. The power adjustment amount is obtained based on the adjustment model and the correction adjustment amount is determined according to the power adjustment amount. The power adjustment amount is allocated using the correction adjustment amount and the adjustable capacity of each generator to achieve power control of the thermal power generation system. The current traditional thermal power generation technology contains the prediction of the stability of the power generation system with small disturbances, the low accuracy of the prediction of the control, and how to improve the control efficiency.

[0027] As a preferred solution of the power control system of the thermal power generation system of the present invention, it includes: the acquisition module is used to collect real-time information of the thermal power generation system; the real-time information includes real-time information before the generator is disturbed and real-time information after the generator is disturbed;

[0028] The calculation module is used to calculate the state data of the thermal power generation system according to the real-time information; the state data includes the state data before the generator is disturbed and the state data after the generator is disturbed;

[0029] The prediction module is used to predict the damping ratio of the thermal power generation system using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system; the damping ratio of the thermal power generation system includes the sum of the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance.

[0030] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a power control method for a thermal power generation system.

[0031] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a power control method for a thermal power generation system.

[0032] Beneficial effects of the present invention: The power control method of the thermal power generation system collects the real-time information of the thermal power generation system, calculates the state data of the thermal power generation system according to the real-time information, and obtains the damping ratio of the thermal power generation system. Compared with the power control method of the traditional thermal power generation system, the power adjustment amount is obtained based on the adjustment model and the correction adjustment amount is determined according to the power adjustment amount. Compared with the power control method of the traditional thermal power generation system, the response speed is faster and the adaptability is stronger. The power adjustment amount is distributed by using the correction adjustment amount and the adjustable capacity of each generator to realize the power control of the thermal power generation system. Compared with the power control method of the traditional thermal power generation system, the power distribution is more even. The present application can more accurately predict the stability of the thermal power generation system and improve the accuracy of power control. Compared with the power control method of the traditional thermal power generation system, the stability prediction is more accurate, the power control response speed is faster, and the control accuracy is higher. The present invention has achieved better results in more accurately predicting the stability of the thermal power generation system and improving the accuracy of power control. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0034] Figure 1 An overall flow chart of a power control method for a thermal power generation system provided in the first embodiment of the present invention.

[0035] Figure 2 This is a diagram of an application environment of a power control method for a thermal power generation system provided in the first embodiment of the present invention.

[0036] Figure 3 A schematic flow chart of a power control method for a thermal power generation system provided in the first embodiment of the present invention.

[0037] Figure 4 A damping ratio prediction curve diagram of a power control method for a thermal power generation system provided in the first embodiment of the present invention.

[0038] Figure 5 A schematic diagram of functional modules of a power control system of a thermal power generation system provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0040] Example 1, reference Figure 1-4 , which is an embodiment of the present invention, provides a preferred solution for power control of a thermal power generation system, including:

[0041] S1: Collect first feature data of a first object in a first state, and calculate first state data according to the first feature data.

[0042] Specifically: the first state data includes: the first object collects real-time information of the first object in the first state, and calculates the first state data of the first object according to the real-time information. In this embodiment: specifically, it is the real-time information of the thermal power generation system in the operating state, and the state data of the thermal power generation system is calculated according to the real-time information.

[0043] In this embodiment, the first object is a thermal power generation system, the first characteristic parameter is real-time information before the generator is disturbed and real-time information after the generator is disturbed, and further, the first state data includes the node voltage amplitude and node voltage phase angle of the first object. The node voltage amplitude includes the steady-state voltage amplitude, the transient voltage amplitude, the maximum allowable voltage amplitude, the minimum allowable voltage amplitude, the rated voltage amplitude, etc. The node voltage phase angle includes the steady-state voltage phase angle, the transient voltage phase angle, the phase angle offset, the phase angle fluctuation range, etc.

[0044] In an optional embodiment, the first object may also be a distributed energy unit or an energy storage system. For these two types of energy devices, their quantitative characteristic data may include the following operating parameters and design parameters: Distributed energy unit, operating parameters: output power, voltage fluctuation rate, frequency deviation, transient response time, etc. Design parameters: rated power, rated voltage, efficiency, grid-connected interface characteristics, etc. Energy storage system, operating parameters: charge and discharge power, remaining capacity, energy conversion efficiency, temperature, etc. Design parameters: energy storage capacity, maximum charge and discharge rate, battery type, life cycle, etc.

[0045] S2: Obtain first stable data through the first state data to construct a first state prediction model for prediction.

[0046] Specifically: the first state prediction model includes constructing a first object stability prediction model through each subroutine equation, training the first object stability prediction model using the first state data and the first stability data, and obtaining a trained first state stability prediction model. In this embodiment, the sample state data is input into the small disturbance stability model of the thermal power generation system to obtain the damping ratio of the thermal power generation system, and the thermal power generation system stability prediction model is trained using the sample state data and the sample stability data to obtain a trained thermal power generation system stability prediction model.

[0047] In this embodiment, the first stable data is to input the sample state data into the small disturbance stability model of the thermal power generation system to obtain the sample stable data of the thermal power generation system, the first state prediction model is a convolutional neural network, a long short-term memory network and an attention mechanism, and further the first stable data includes the damping ratio and the system oscillation frequency of the first object. The damping ratio includes underdamping, critical damping, overdamping, etc. The system oscillation frequency includes system oscillation frequency, high frequency oscillation, etc.

[0048] In an optional embodiment, the first target effect data may also be heating effect data or pressure regulation effect data. For these two types of data, the quantitative characteristic data may include the following performance parameters and operating state parameters: heating effect data, performance parameters: heating rate, target temperature reaching time, uniformity parameters, etc. Operating state parameters: power consumption, heat loss, equipment state, etc. of the heating equipment. Pressure regulation effect data, performance parameters: pressure stability, regulation time, pressure relief efficiency, etc. Operating state parameters: pipeline pressure difference, valve opening degree, system load state, etc.

[0049] S3: Obtain first adjustment data through the first state data and the first state prediction model.

[0050] Specifically: the first adjustment data includes, based on the first state data and based on the first state prediction model, an adjustment amount of the first object required to be adjusted to achieve the first goal. In this embodiment, the damping ratio change is obtained based on the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance, and the power adjustment amount of the thermal power generation system is obtained based on the damping ratio change and the power adjustment model.

[0051] In this embodiment, the first adjustment data is specifically obtained by inputting the sensitivity of each generator to the damping ratio into the power adjustment model. Further, the first adjustment data includes an adjustment amplitude and an adjustment time. The adjustment amplitude includes a maximum adjustment amplitude, a minimum adjustment amplitude, a sensitivity factor, etc. The adjustment time includes an adjustment delay time, a response time, a steady-state time, etc.

[0052] In an optional embodiment, the first adjustment data may also be adjustment accuracy or adjustment frequency. For these two types of adjustment data, the quantitative characteristic data may include the following performance parameters and operating state parameters: adjustment accuracy, performance parameters: minimum adjustment unit, error range, adjustment accuracy requirements, etc. Operating state parameters: adjustment stability, accuracy fluctuation, etc. Adjustment frequency, performance parameters: maximum adjustment frequency, minimum adjustment frequency, adjustment cycle, etc. Operating state parameters: adjustment response time, frequency variation range, etc.

[0053] S4: Determine a first correction amount according to the first adjustment data to achieve a first target distribution.

[0054] Specifically: a first correction amount is determined according to the first adjustment data, and the first correction amount and the adjustable capacity of each sub-device are used for allocation to achieve the first target allocation of the first object. In this embodiment, a correction adjustment amount is determined according to the power adjustment amount, and the power adjustment amount is allocated using the correction adjustment amount and the adjustable capacity of each generator to achieve power regulation of the thermal power generation system.

[0055] In this embodiment, the first target allocation is specifically to determine the correction adjustment amount according to the power adjustment amount, and to allocate the power adjustment amount using the correction adjustment amount. Further, the first target allocation includes an adjustment strategy and an adjustment result. The adjustment strategy includes a correction coefficient, a weight allocation ratio, etc. The adjustment result includes a power allocation amount, an adjustment effect, etc.

[0056] In an optional embodiment, the first adjustment data may also be a power adjustment amount or an adjustment time. For these two types of adjustment data, the quantitative characteristic data may include the following performance parameters and operating state parameters: power adjustment amount, performance parameters: power adjustment rate, adjustment accuracy, power fluctuation range, etc. Operating state parameters: power consumption during adjustment, system load, adjustment efficiency, etc. Adjustment time, performance parameters: response time, adjustment time fluctuation, steady-state time, etc. Operating state parameters: stability of system response, energy loss during adjustment, etc.

[0057] B1: The power control method of thermal power generation system can be applied to Figure 2In the application environment shown, the environment terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the real-time information of the thermal power generation system to the server 104. After the server 104 receives the real-time information, for the real-time information, the server 104 calculates the state data of the thermal power generation system based on the real-time information, and predicts the damping ratio of the thermal power generation system using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system, and obtains the damping ratio change according to the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance. Based on the damping ratio change and the power adjustment model, the power adjustment of the thermal power generation system is obtained; the correction adjustment is determined according to the power adjustment; the power adjustment is distributed using the correction adjustment and the adjustable capacity of each generator to achieve power regulation of the thermal power generation system. The server 104 may feed back the distribution result of the power adjustment amount to the terminal 102. In addition, in some embodiments, the power control method of the thermal power generation system may also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 may directly process the real-time information of the thermal power generation system, or the server 104 may obtain the real-time information of the thermal power generation system from the data storage system and distribute the power adjustment amount according to the real-time information of the thermal power generation system.

[0058] It should be noted that the terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, and portable wearable devices, and the portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented by an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0059] B2: If Figure 3 As shown, a power control method for a thermal power generation system is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to the server 104 as an example for description, including the following steps 201 to 207, wherein:

[0060] Step 201: Acquire real-time information of a thermal power generation system.

[0061] Specifically, the real-time information of the thermal power generation system is collected through the wide area measurement system, and the real-time information includes the real-time information before the generator is disturbed and the real-time information after the generator is disturbed.

[0062] Step 202: Calculate status data of the thermal power generation system according to the real-time information.

[0063] Specifically, the state data of the thermal power generation system includes the state data before the generator is disturbed and the state data after the generator is disturbed.

[0064] Step 203: predict the damping ratio of the thermal power generation system using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system; the damping ratio of the thermal power generation system includes the sum of the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance, and the thermal power generation system stability prediction model includes a convolutional neural network, a long short-term memory network and an attention mechanism module.

[0065] Step 204: Obtain a damping ratio change according to the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance.

[0066] Step 205: Based on the damping ratio variation and the power adjustment model, the power adjustment amount of the thermal power generation system is obtained. The power adjustment model is constructed with the goal of minimizing the square of the power adjustment amount of the generator.

[0067] Step 206: Determine a correction adjustment amount according to the power adjustment amount.

[0068] Step 207: Distribute the power adjustment amount using the correction adjustment amount and the adjustable capacity of each generator to achieve power control of the thermal power generation system.

[0069] By implementing the above steps 201 to 207, the present application can accurately predict the stability of the thermal power generation system and more accurately regulate the power of the thermal power generation system.

[0070] Furthermore, in another exemplary embodiment of the present application, the above step 202 includes steps 301 to 302:

[0071] Step 301: Calculate the node voltage amplitude and the node voltage phase angle according to the line impedance, the real-time generator power and the real-time load power.

[0072] The real-time information before the generator disturbance and the real-time information after the generator disturbance obtained in the above step 201 both include line impedance, real-time generator power and real-time load power. Line impedance is a composite parameter of resistance and reactance, the real part is resistance, the imaginary part is reactance, susceptance is the derivative of reactance, and conductance is the reciprocal of resistance. The state data are node voltage amplitude, node voltage phase angle, line power and line current.

[0073] The line impedance, real-time generator power and real-time load power are input into the power balance formula (1)-(2) for power flow calculation to obtain the node voltage amplitude and node voltage phase angle.

[0074] The power balance formula for power flow calculation is as follows:

[0075]

[0076] Among them, P g Inject active power into node g; Q g is the reactive power injected into node r; V g is the voltage amplitude of node g; V r is the voltage amplitude of node r; G gr is the line conductance from node g to node r; B gr is the line susceptance from node g to node r; θ gr is the phase angle difference of the voltage at the g and r nodes.

[0077] Step 302: Obtain the line power and line current of each line by using the node voltage amplitude and the node voltage phase angle.

[0078]

[0079]

[0080] Further: Among them: S rg is the line power; is the voltage phasor of node r; is the conjugate complex number of the grounding admittance of the r node; is the conjugate complex number of the node admittance from r to g; is the conjugate complex number of the voltage phasor at node r; is the conjugate complex number of the voltage phasor at node g; V r is the voltage amplitude of node r; θ r is the voltage phase angle of node r; I rg is the line current.

[0081] B3: Further, 400 constructs a thermal power generation system stability prediction model, and trains the thermal power generation system stability prediction model to obtain a trained thermal power generation system stability prediction model.

[0082] Step 400 specifically includes:

[0083] Step 401, constructing a small disturbance stability model of a thermal power generation system; the small disturbance stability model of a thermal power generation system includes a rotor motion equation of a thermal power unit, an electromagnetic power equation of a generator, a stator equation, a coordinate transformation equation, a network equation and a load model equation.

[0084] Step 402: Input the sample state data into a small disturbance stability model of the thermal power generation system to obtain sample stability data of the thermal power generation system.

[0085] Specifically, the stability data is the damping ratio of the thermal power generation system. If the damping ratio of the thermal power generation system is less than 0, it indicates that the thermal power generation system is unstable; if the damping ratio is between 0 and 0.03, it indicates that the thermal power generation system is in a metastable state; if the damping ratio of the thermal power generation system is greater than 0.03, it indicates that the thermal power generation system is in a stable state.

[0086] The historical state data actually measured during the operation of the thermal power generation system is used as sample state data, and the sample state data is input into the small disturbance stability model of the thermal power generation system, and the small disturbance stability model of the thermal power generation system outputs sample stability data (i.e., the actual value of the stability data).

[0087] Step 403: train the thermal power generation system stability prediction model using the sample state data and the sample stability data to obtain a trained thermal power generation system stability prediction model.

[0088] The sample state data and the sample stability data form a sample set, the sample set is divided into a training set and a test set, the initial parameters of the thermal power generation system stability prediction model are determined by using the training set, and the parameters of the thermal power generation system stability prediction model are updated by using the test set to obtain a trained thermal power generation system stability prediction model, specifically including:

[0089] The sample state data in the test set is input into the thermal power generation system stability prediction model for prediction to obtain the predicted value of the stable data; the loss is calculated according to the predicted value of the stable data and the actual value of the stable data, and the parameters of the thermal power generation system stability prediction model are updated according to the loss. The iterative execution is carried out until the loss reaches the preset range, and the trained thermal power generation system stability prediction model is obtained.

[0090] The state data and sample stability data above constitute a sample data set. The sample state data and the sample stability data obtained in step 402 above are normalized and preprocessed. The processing formula is:

[0091]

[0092] Where: k * is the data obtained by normalization, k is the data to be normalized, k max is the maximum corresponding data of the sample data set, k min is the minimum corresponding data of the sample data set.

[0093] The evaluation indicators are mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square percentage error (RMSPE), R squared coefficient of determination (R 2 ), Residual Prediction Error Detection (RPD).

[0094] Table 1-Summary of evaluation indicators of the thermal power generation system stability prediction model after training

[0095] Evaluation indicators Stability prediction model for thermal power generation system MSE 0.00044271 MSE 3.9569e-07 RMSEP 0.00062904 RPD 7.5802 MAPE 0.017914 R2 0.98074

[0096] Further: Figure 4 As shown, the evaluation indexes R2=0.98074, RMSE=0.00062904, MSE=3.9569e-07, and RPD=7.5802, and the prediction results of the thermal power generation system stability prediction model for predicting the damping ratio are obtained using the test set.

[0097] The expressions of the rotor motion equation of the thermal power unit, the electromagnetic power equation of the generator, the stator equation, the coordinate transformation equation, the network equation and the load model equation in the small disturbance stability model of the thermal power generation system constructed in the above step 402 are respectively:

[0098] The rotor motion equation of a thermal power unit is:

[0099]

[0100] Among them, δ is the generator power angle, t is the time, ω, ω s are the generator speed and initial speed respectively, P e is the electromagnetic power of the generator, P m is the mechanical power of the generator, D, T j are the damping coefficient and inertia time constant of the generator respectively.

[0101] The electromagnetic power equation of the generator is:

[0102]

[0103] Among them, V Gx 、VGy are the x-axis and y-axis components of the generator terminal voltage, I Gx ,I Gy are the x-axis and y-axis components of the generator current, R a is the generator stator resistance.

[0104] The stator equation is:

[0105]

[0106] Among them, V q 、V d are the quadrature-axis component and direct-axis component of the generator stator voltage, I q ,I d are the quadrature-axis and direct-axis components of the generator stator current, R a is the stator resistance of the generator, E q "、E d " are the sub-transient electromotive force of the generator quadrature axis and direct axis, x d " is the subtransient reactance of the generator direct axis, x q " is the subtransient reactance of the generator quadrature axis.

[0107] The coordinate transformation equation is:

[0108]

[0109] Among them, δ0 is the initial power angle of the generator.

[0110] The network equation is:

[0111]

[0112] Among them, I g is the current at node g, V g is the voltage at node g, is the admittance between nodes, and n1 is the number of system nodes.

[0113] The load model equation is:

[0114]

[0115] Among them, Y L is the load admittance, is the conjugate of the load power, V L is the load node voltage.

[0116] The expression of the power adjustment model is:

[0117]

[0118] The constraints of the power adjustment model are:

[0119]

[0120] in, and is the lower and upper power limits of the Jth generator, is the initial power of the Jth generator, is the power adjustment of the Jth generator, ξ0 is the initial damping ratio, Δξ is the change in damping ratio, ξ is the damping ratio, C J is the sensitivity of the Jth generator to the damping ratio, and n is the number of generators.

[0121] The expression of the proportional-integral control correction adjustment model is:

[0122] ΔP′=K p ΔP M +K I ΔP I

[0123] Among them, ΔP' is the correction adjustment amount, ΔP M is the power adjustment, ΔP I is the deviation caused by the last regulation, K p is the proportionality coefficient, K I is the integration coefficient.

[0124] Step 4021, set the state vector, select the state variables in formula (7)-(12) as the state vector, the state variables include the generator power angle, the generator speed, the sub-transient electromotive force of the generator quadrature axis, the sub-transient electromotive force of the generator direct axis, the transient electromotive force of the generator quadrature axis and the transient electromotive force of the generator quadrature axis.

[0125] Step 4022: Obtain a state matrix of the thermal power generation system according to the state vector and the small disturbance stability model of the thermal power generation system.

[0126] Specifically, the state matrix of the thermal power generation system is derived using the above-set state vector and the small disturbance stability model of the thermal power generation system.

[0127]

[0128]

[0129] According to formula (14)-formula (18), the following formula (19)-(24) are obtained:

[0130]

[0131] In the formula, for The real part of for The imaginary part of the generator, Δδ is the change in the generator power angle, Δω is the change in the generator speed, T′ q0 is the generator quadrature axis transient open circuit time constant, T" q0 is the subtransient open-circuit time constant of the generator quadrature axis; T d '0 is the generator direct axis transient open circuit time constant; T d "0 is the generator direct-axis subtransient open-circuit time constant, ΔE q ", ΔE d " are the changes of the sub-transient electromotive force of the generator quadrature axis and direct axis, ΔE' q , ΔE' d are the changes of the transient electromotive force of the generator quadrature axis and the transient electromotive force of the direct axis respectively; S G is the number of generators, S G ×n is n generators.

[0132]

[0133] Where ΔV q , ΔV d are the changes of the quadrature-axis component and the direct-axis component of the generator stator voltage, ΔI q , ΔI d They are the changes in the quadrature axis and direct axis components of the generator stator current, ΔV x , ΔV y are the changes in the x-axis component and y-axis component of all node voltages, ΔI Gx , ΔI Gy are the changes in the x-axis component and y-axis component of the generator current, ΔP e The change in electromagnetic power of the generator.

[0134]

[0135]

[0136] Where V q0 、V d0 are the initial values ​​of the quadrature-axis and direct-axis components of the generator stator voltage, I q0 ,I d0 are the initial values ​​of the quadrature-axis and direct-axis components of the generator stator current, V Gx0 、V Gy0 are the initial values ​​of the x-axis and y-axis components of the generator terminal current, I Gx0 ,I Gy0 are the initial values ​​of the x-axis and y-axis components of the generator current, the state variable Δx, the operating variable Δy, D, Tj are the damping coefficient and inertia time constant T of the generator respectively. j , R a is the stator resistance of the generator, and E is the unit matrix.

[0137]

[0138] According to formulas (19), (21), (23), (24) and (25), the state vector A is obtained.

[0139] Step 4023: Input the sample state data into a state matrix to calculate the damping ratio of the thermal power generation system.

[0140] The calculation formula of the eigenvalue is as follows:

[0141]

[0142] Where: λ is the eigenvalue, γ is the real part of the eigenvalue, is the imaginary part of the eigenvalue, and α is the imaginary unit.

[0143] The damping ratio is calculated as follows:

[0144]

[0145] Where: ξ is the damping ratio, γ is the real part of the eigenvalue, is the imaginary part of the eigenvalue.

[0146] The sample state data is input into the state matrix, the eigenvalue of the state matrix is ​​obtained, and the eigenvalue is transformed using formula (27) to obtain the damping ratio.

[0147] In another exemplary embodiment of the present application, step 203 specifically includes:

[0148] Step 2031: input the state data into the convolutional neural network for feature extraction to obtain local features.

[0149] Convolutional Neural Networks (CNN) consists of convolutional layers, pooling layers, and fully connected layers.

[0150] The convolution layer slides the convolution kernel on the feature map and performs convolution operation with the data in the receptive field to extract the structural features inside the data. The expression of the convolution operation is:

[0151]

[0152] Where: y l represents the output of the lth layer; represents the output of the i-th channel of the l-1th layer; c l-1 represents the cth channel of the l-1th layer; and denote weight and bias respectively.

[0153] The pooling layer performs feature selection after the convolution layer to reduce the number of features, reduce training parameters, and alleviate overfitting. The calculation expressions for maximum pooling and average pooling are:

[0154]

[0155] Where: x l(i,t) represents the value of the tth neuron in the ith channel of the lth layer; S represents the size of the pooling kernel; y l (i,j) The value of the jth neuron in the ith channel of the lth layer.

[0156] After convolution and pooling, the neurons in the fully connected layer are all connected to the neurons in the previous layer to integrate differentiated local feature information between different categories.

[0157] Step 2032: Input the local features into the long short-term memory network to extract dynamic features to obtain dynamic features.

[0158] Introducing memory units into the network structure of the Long Short-Term Memory (LSTM) network can effectively process sequence data.

[0159] Before information flows into the LSTM network cell, it first passes through the forget gate, whose main function is to selectively forget the information transmitted from the previous moment. The update calculation formula is:

[0160] f t =σ(W t ·[h t-1 ,x t ]+b f )(31);

[0161] Where: W t represents the weight matrix, b f represents the bias term, f t represents the forget gate; σ represents the Sigmoid activation function; h t-1 represents the output of the previous cell, x t Represents the input of the current cell.

[0162] After being filtered by the forget gate, the information is passed to the input gate. The LSTM network input signal is determined by the input gate to determine the information and content to be updated. The update calculation formula is:

[0163] i t =σ(W t ·[h t-1 ,x t ]+b i )(32);

[0164]

[0165] Where: W i and W c represents the weight matrix; b i and b c represents the bias term, Indicates that x t and h t-1 The state quantity that integrates the state information, c t represents the state at the tth time step, i t Represents the input gate.

[0166] The output gate uses the activation function σ to calculate the cell state that needs to be output. The input signal determines the useful information for output through the output gate and immediately updates the current LSTM neural network cell state. The update calculation formula is:

[0167] ο t =σ(W0·[h t-1 ,x t ]+b0)(35);

[0168] h t =ο t ·tanh(c t )(36);

[0169] Where: W0 is the weight matrix, b0 represents the bias term, h t represents the output value of the hidden layer at the tth time step, t Represents the output gate.

[0170] Step 2033: input the dynamic features into the attention mechanism module for weighted summation to obtain the damping ratio of the thermal power generation system.

[0171] The attention mechanism is a resource redistribution scheme that generally assigns greater weights to important objects and less or no weights to unimportant objects.

[0172] In the LSTM network, the attention mechanism can assign weights to the output at each moment and obtain the final output by summing up. The calculation formula is:

[0173]

[0174] Where: a irepresents the weight distribution of the attention mechanism; h i represents the output value of the hidden layer at the i-th time step, c i represents the weighted average sum of the outputs of each hidden layer, and i represents the i-th time step.

[0175] B4: Further, in step 2051, the sensitivity of each generator to the damping ratio is calculated using the damping ratio variation.

[0176] Specifically, the sensitivity of the generator to the damping ratio is obtained by perturbing the generator, wherein the perturbation is a small disturbance actively made to the generator. The sensitivity is composed of the perturbation value and the change in the damping ratio.

[0177] Step 2052: Input the sensitivity of each generator to the damping ratio into the power adjustment model to obtain the power adjustment amount of the thermal power generation system.

[0178] After calculating the sensitivity of each generator to the damping ratio, the sensitivity is brought into the power adjustment model and the power adjustment model is solved using the solver to obtain the power adjustment amount.

[0179] The expression of the power adjustment model is:

[0180]

[0181] The constraints are:

[0182]

[0183] in, and is the lower and upper power limits of the Jth generator, is the initial power of the Jth generator, is the power adjustment of the Jth generator, ξ0 is the initial damping ratio, Δξ is the change in damping ratio, ξ is the damping ratio, C J is the sensitivity of the Jth generator to the damping ratio, and n is the number of generators.

[0184] In another exemplary embodiment of the present application, step 206 specifically includes:

[0185] The power adjustment amount is input into a proportional-integral control correction adjustment amount model to obtain the correction adjustment amount. The expression of the proportional-integral control correction adjustment amount model is:

[0186] ΔP'=K p ΔP M +K I ΔP I (40);

[0187] Among them, ΔP' is the correction adjustment amount, ΔP M is the power adjustment, ΔP I is the deviation caused by the last regulation, K p is the proportionality coefficient, K I If ΔP'>0, the correction adjustment amount is adjusted upward, and if ΔP'<0, the correction adjustment amount is adjusted downward.

[0188] The deviation of the last regulation is composed of the difference between the power actually monitored by the power monitoring platform and the target power adjustment. For example, the target power adjustment issued last cycle is ΔP t- '1, and the power adjustment actually monitored by the power monitoring platform is ΔP t- ”1, then the deviation of the last regulation is ΔP I =ΔP t- '1-ΔP t- ”1.

[0189] In another exemplary embodiment of the present application, step 207 specifically includes:

[0190] For a thermal power generation system, there are multiple generators and energy storage. For each generator, the adjustable capacity is obtained according to its output constraint and ramp constraint. The calculation formula is as follows:

[0191]

[0192] Where: and To adjust the capacity down and up for the mth generator, and is the lower and upper limits of the output of the mth generator, PT m is the initial output of the mth generator at the current moment, and is the ramp-down rate and ramp-up rate of the mth generator. For energy storage, its down-regulation capacity and up-regulation capacity are its output lower limit and output upper limit respectively.

[0193] After calculating the correction adjustment ΔP' and the adjustable capacity of the generator, determine the down-regulation capacity and up-regulation capacity of the generator, and arrange them from large to small according to the adjustment capacity. Starting from the first generator, the adjustment amount is allocated in sequence. The allocation amount is:

[0194]

[0195] Then the remaining correction adjustment ΔP" is:

[0196] ΔP"=ΔP'-ΔPT m (43);

[0197] If ΔP" is zero, the allocation is terminated; if the adjustable capacity of all generators is insufficient to allocate the correction adjustment, that is,

[0198]

[0199] Then the remaining correction adjustment ΔP" is:

[0200]

[0201] This part of the adjustment is controlled by energy storage.

[0202] Table 2 - Generator adjustment

[0203] dynamo Adjustment amount Unit 1 12.2500 Unit 2 31.8500 Unit 3 30.9680 Unit 4 24.8920 Unit 5 31.8500 Unit 6 27.4400 Unit 7 26.4600 Unit 8 40.6700 Unit 9 49.0000

[0204] Embodiment 2, as Figure 5 As shown, an embodiment of the present invention provides a power control method for a thermal power generation system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0205] First, based on the same inventive concept, the embodiment of the present application also provides a power control device for implementing the thermal power generation system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the power control device for one or more thermal power generation systems provided below can refer to the limitations of the power control method for the thermal power generation system above, and will not be repeated here.

[0206] In an exemplary embodiment, Figure 5 As shown, a power control device of a thermal power generation system is provided, comprising:

[0207] The acquisition module 21 is used to acquire the real-time information of the thermal power generation system; the real-time information includes the real-time information before the generator is disturbed and the real-time information after the generator is disturbed.

[0208] The state data module 22 is used to calculate the state data of the thermal power generation system according to the real-time information; the state data includes the state data before the generator is disturbed and the state data after the generator is disturbed.

[0209] The damping ratio prediction module 23 is used to predict the damping ratio of the thermal power generation system by using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system; the damping ratio of the thermal power generation system includes the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance; wherein the thermal power generation system stability prediction model includes a convolutional neural network, a long short-term memory network and an attention mechanism module.

[0210] The damping ratio variation calculation module 24 is used to obtain the damping ratio variation according to the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance.

[0211] The first calculation module 25 is used to obtain the power adjustment amount of the thermal power generation system based on the damping ratio change amount and the power adjustment model; wherein the power adjustment model is constructed with the goal of minimizing the square of the generator power adjustment amount.

[0212] The second calculation module 26 is used to determine a correction adjustment amount according to the power adjustment amount.

[0213] The control module 27 is used to distribute the power adjustment amount by using the correction adjustment amount and the adjustable capacity of each generator to achieve power control of the thermal power generation system.

[0214] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0215] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0216] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0217] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present 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 may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0218] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0219] Embodiment 3 is an embodiment of the present invention, which provides a power control system for a thermal power generation system, including an acquisition module, a calculation module, and a prediction module;

[0220] The acquisition module is used to acquire real-time information of the thermal power generation system; the real-time information includes real-time information before the generator is disturbed and real-time information after the generator is disturbed;

[0221] A state data calculation module, used to calculate the state data of the thermal power generation system according to the real-time information; the state data includes the state data before the generator is disturbed and the state data after the generator is disturbed;

[0222] A damping ratio prediction module, used to predict the damping ratio of the thermal power generation system by using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system; the damping ratio of the thermal power generation system includes the sum of the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance; wherein the thermal power generation system stability prediction model includes a convolutional neural network, a long short-term memory network and an attention mechanism module;

[0223] A damping ratio variation calculation module, used for obtaining a damping ratio variation according to the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance;

[0224] A first calculation module is used to obtain a power adjustment amount of the thermal power generation system based on the damping ratio change amount and the power adjustment model; wherein the power adjustment model is constructed with the goal of minimizing the square of the power adjustment amount of the generator;

[0225] A second calculation module, used to determine a correction adjustment amount according to the power adjustment amount;

[0226] The control module is used to distribute the power adjustment amount by using the correction adjustment amount and the adjustable capacity of each generator to achieve power control of the thermal power generation system.

[0227] If the 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, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0228] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0229] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0230] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned 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, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0231] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power control method for a thermal power generation system, characterized in that: include: Collecting first characteristic data of the first object in the first state, and calculating first state data according to the first characteristic data; Obtaining first stable data through first state data to construct a first state prediction model for prediction; Obtaining first adjustment data through the first state data and the first state prediction model; A first correction amount is determined according to the first adjustment data so as to achieve a first target distribution.

2. The power control method of the thermal power generation system according to claim 1, characterized in that: The first characteristic data includes operating parameters of the first object in a first state; The first state data includes a first electrical parameter set of a first object in a first state.

3. The power control method of the thermal power generation system according to claim 2, characterized in that: The first stable data includes constructing a first stable model through the operating parameters of each sub-part of each first object during operation, and inputting the first state data into the first stable model to obtain the first stable data.

4. The power control method of the thermal power generation system according to claim 3, characterized in that: The first adjustment data includes a physical quantity that is the same as the first target effect data and that is exhibited by the adjusted object during operation.

5. The power control method of the thermal power generation system according to claim 4, characterized in that: The first correction amount includes: the correction amount of each sub-part when the first object is corrected according to the first adjustment data to achieve the first goal; The first target allocation includes: adjusting the amount of the first object in the first state according to the first correction amount and the first adjustment data to achieve the first target.

6. The power control method of the thermal power generation system according to claim 5, characterized in that: The constructing of the first stable model includes, specifically, constructing a convolutional neural network, a long short-term memory network and an attention mechanism.

7. The power control method of the thermal power generation system according to claim 6, characterized in that: The first adjustment data includes, specifically, inputting the sensitivity of each generator to the damping ratio into a power adjustment model to obtain the first adjustment data.

8. A power control system using the thermal power generation system according to any one of claims 1 to 7, characterized in that: Acquisition module, calculation module, prediction module; The acquisition module is used to collect real-time information of the thermal power generation system; the real-time information includes real-time information before the generator is disturbed and real-time information after the generator is disturbed; The calculation module is used to calculate the state data of the thermal power generation system according to the real-time information; the state data includes the state data before the generator is disturbed and the state data after the generator is disturbed; The prediction module is used to predict the damping ratio of the thermal power generation system using the state data and the trained thermal power generation system stability prediction model to obtain the damping ratio of the thermal power generation system; the damping ratio of the thermal power generation system includes the sum of the damping ratio of the thermal power generation system before the generator disturbance and the damping ratio of the thermal power generation system after the generator disturbance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images