Method, system and equipment for optimizing frequency modulation and peak regulation performance of thermal power generating unit and storage medium

Abstract

The invention discloses a thermal power generating unit frequency modulation and peak regulation performance optimization method, system and device and a storage medium, and relates to the technical field of thermal power generation control, and the method comprises the steps: obtaining historical working condition data of a thermal power generating unit, building a target prediction model based on the historical working condition data, inputting real-time working condition data to the target prediction model, the method comprises the following steps: determining prediction signals of future coal as fired quantity and pulverized coal flow velocity and load variation of a thermal power generating unit, determining delay information between a coal as fired quantity signal and a pulverized coal flow velocity signal according to the prediction signals and corresponding actual signals, compensating system response lag time difference based on the delay information, and determining the coal as fired quantity according to the load variation. Determining adjustment values of the coal as fired and the air volume, and adjusting the coal as fired and the air volume in real time based on the adjustment values; and on the basis of a cascade control strategy, the air powder flow speed and the air powder temperature of the boiler are adjusted in real time, rapid response to dynamic changes of a combustion system is achieved, and the adjusting capacity of a thermal power generating unit under frequent load fluctuation is improved.

Description

Technical Field

[0001] The present application relates to the field of thermal power generation control technology, and in particular to a method, system, device and storage medium for optimizing the frequency and peak regulation performance of a thermal power unit. Background Art

[0002] In the current power system, thermal power units, as important equipment for frequency and peak regulation of the power grid, play a key role in balancing power supply and demand. With the frequent fluctuations in power demand, the requirements for power grid dispatch are constantly increasing, making the frequency and peak regulation performance of thermal power units an important indicator for measuring their load response capabilities.

[0003] However, when dealing with these frequent load fluctuations, existing thermal power units often face the problems of response lag and insufficient regulation accuracy due to the limitations of the combustion control system. The combustion efficiency and stability of the boiler have a direct impact on the frequency regulation and peak regulation performance of the thermal power unit. As the core parameter of combustion control, the air-coal ratio is mainly relied on by the traditional combustion control method, that is, the combustion is maintained by adjusting the amount of air and coal powder entering the boiler. However, this fixed control method is difficult to ensure the optimal operating state of the boiler when facing rapidly changing loads, resulting in reduced combustion efficiency and delayed response, which further affects the regulation ability of the thermal power unit. Especially during periods of severe load fluctuations, the boiler takes a long time to stabilize, which increases the risk of grid frequency fluctuations and leads to system instability and power supply safety hazards. Summary of the invention

[0004] The present application aims to solve the problem in the prior art that when thermal power units cope with these frequent load fluctuations, it is difficult to ensure the optimal operating state of the boiler of the thermal power unit, resulting in reduced combustion efficiency and response delay, which further affects the regulation ability of the thermal power unit. Based on this, a method, system, equipment and storage medium for optimizing the frequency and peak regulation performance of thermal power units are proposed.

[0005] In order to achieve the above objectives, in a first aspect, the present application provides a method for optimizing frequency and peak regulation performance of a thermal power unit, comprising: Acquire historical operating condition data of the thermal power unit, wherein the historical operating condition data includes coal powder demand, air-coal ratio, power load parameters, environmental parameters and combustion efficiency parameters; Building a target prediction model based on the historical operating condition data, inputting real-time operating condition data into the target prediction model, and determining prediction signals of future furnace coal quantity and coal powder flow rate and load change of the thermal power unit; Determine the delay information between the coal quantity signal entering the furnace and the coal powder flow rate signal according to the predicted signal and the corresponding actual signal, and compensate for the system response lag time difference based on the delay information; Determine adjustment values ​​of the amount of coal and the amount of air entering the furnace according to the load change, and adjust the amount of coal and the amount of air entering the furnace in real time based on the adjustment values; and Based on the cascade control strategy, the air-powder flow rate and air-powder temperature of the boiler are adjusted in real time to achieve high efficiency and stability of the thermal power unit under various operating conditions.

[0006] In some possible embodiments, the target prediction model is constructed based on the historical operating condition data, real-time operating condition data is input into the target prediction model, and prediction signals of future coal quantity and pulverized coal flow rate as well as load change of the thermal power unit are determined, including: Construct an initial prediction model that introduces the local sensitive hashing self-attention mechanism; Dividing the historical operating condition data into a training set and a validation set, inputting the training set into the initial prediction model to complete model training, and inputting the trained model into the validation set for validation, and adjusting the training strategy according to the validation result to obtain the target prediction model; The real-time operating condition data is input into the target prediction model to determine the prediction signals of the actual future coal quantity entering the furnace and the coal powder flow rate and the load change of the thermal power unit.

[0007] In some possible embodiments, the method of determining the delay information between the coal quantity signal entering the furnace and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensating the system response lag time difference based on the delay information includes: The correlation between the coal quantity signal and the actual coal powder flow rate signal entering the furnace is analyzed based on the cross-correlation delay estimation algorithm, and the cross-correlation value under different lag times is determined; Determine a lag time for making the cross-correlation function reach a maximum value based on the cross-correlation value, wherein the lag time is used to characterize the delay relationship between the coal quantity signal entering the furnace and the coal powder flow rate signal; Delay information is generated based on the lag time and fed back to the control system to compensate for the system response time difference caused by the signal delay and optimize the overall control strategy.

[0008] In some possible embodiments, the cross-correlation delay estimation algorithm is used to analyze the correlation between the coal quantity signal and the actual coal powder flow rate signal entering the furnace, and determine the cross-correlation value under different lag times, including: The coal quantity signal and the actual coal powder flow rate signal entering the furnace are used as inputs, and multiple different lag step sizes are set to construct a cross-correlation function; Based on the cross-correlation function, the cross-correlation value between the coal quantity signal and the coal powder flow rate signal under different time delays is obtained.

[0009] In some possible embodiments, the coal quantity signal and the actual coal powder flow rate signal entering the furnace are used as inputs, and a plurality of different lag steps are set to construct a cross-correlation function, including: If it is a continuous time signal, the expression of the cross-correlation function is: , If it is a discrete time signal, the expression of the cross-correlation function is: , In the formula, x(t) is the coal quantity signal, y(t) is the actual coal powder flow rate signal entering the furnace, τ is the lag time step, N is the number of signal samples, and R xy (τ) is the correlation between signals x(t) and y(t) at a lag time of τ.

[0010] In some possible embodiments, determining adjustment values ​​of the amount of coal entering the furnace and the amount of air entering the furnace according to the load change, and adjusting the amount of coal entering the furnace and the amount of air entering the furnace in real time based on the adjustment values ​​includes: Based on the load change, the adjustment value of the amount of coal entering the furnace and the adjustment value of the air volume are determined, wherein: The adjustment value of coal quantity is expressed as: , The adjustment value of the air volume is expressed as: , Where ∆P(t) is the load change, k M is the proportional coefficient of coal quantity, k W is the proportional coefficient of air volume.

[0011] In some possible embodiments, the cascade control strategy is based on real-time adjustment of the air-powder flow rate and air-powder temperature of the boiler to achieve high efficiency and stability of the thermal power unit under various operating conditions, including: The inner loop control is based on the PID controller to adjust according to the deviation between the set target air-powder flow rate and the actual measured air-powder flow rate, where: The adjustment expression is: , In the formula, e(t) is the deviation between the set value and the actual value, K p , K i , K d are proportional, integral and derivative gains respectively; The outer loop control adjusts the target air-powder temperature in real time based on inputs including external load changes and combustion efficiency.

[0012] Compared with the prior art, the technical solution provided by the embodiment of the present application includes at least the following beneficial effects or advantages: 1) By constructing a target prediction model that introduces a local sensitive hashing self-attention mechanism, the target prediction model is used to predict the actual future coal quantity and coal powder flow rate signals entering the furnace, and the time delay between the predicted signal and the actual signal is calculated. The lag time is obtained through the cross-correlation delay estimation algorithm and fed back to the control system to optimize the real-time and accuracy of the thermal power unit control strategy, achieve rapid response to dynamic changes in the combustion system, improve the regulation ability of the thermal power unit under frequent load fluctuations, and reduce the response lag in traditional control methods. In addition, the cross-correlation delay estimation algorithm feeds back signal delay information to the control system, effectively compensating for the delay problem, ensuring that the boiler maintains the best combustion efficiency under various load conditions, and through continuous monitoring and adjustment, the system can maintain the operating efficiency of the boiler, thereby reducing frequency fluctuations while ensuring that the boiler is always in the best operating state, extending the service life of the equipment, and improving energy utilization efficiency.

[0013] 2) The model uses the local sensitive hashing algorithm, which effectively reduces the complexity of the self-attention mechanism calculation by hashing the features of the input sequence, so that the model can still maintain a high response speed when facing complex coal powder flow and coal input data; when performing precise control of the air-coal ratio, the local sensitive hashing self-attention mechanism can automatically focus on key features related to load changes and combustion efficiency, ensuring that the model can give priority to these important factors in dynamic adjustment, helping the control system to more accurately adjust the coal powder flow and air volume; and as the operating conditions change, the local sensitive hashing self-attention mechanism can adapt to different input modes and automatically adjust the attention weight, which enables the model to maintain a high prediction accuracy when facing different load demands and environmental changes, providing a reliable basis for dynamic feedforward compensation control.

[0014] 3) By using the load change output by the target prediction model, the load change trend can be predicted in advance through dynamic feedforward compensation control, and the pulverized coal flow rate into the furnace can be adjusted in time, thereby improving the system's adaptability to load changes, reducing combustion deviations, improving combustion stability and efficiency, and reducing energy consumption and emissions.

[0015] 4) By integrating the cascade control strategy, the inner loop of this control mechanism focuses on the real-time adjustment of the air-powder flow rate, and optimizes the combustion effect by accurately controlling the optimal ratio of fuel and air to ensure the efficient operation of the boiler. At the same time, the outer loop control is responsible for monitoring the air-powder temperature of the boiler and making timely adjustments to maintain its stability under various operating conditions. It can be flexibly adjusted according to different loads and operating conditions to ensure that the thermal power unit maintains high efficiency and stability under various operating conditions.

[0016] In a second aspect, the present application provides a system for optimizing frequency and peak regulation performance of a thermal power unit, comprising: An acquisition module is configured to acquire historical operating condition data of the thermal power unit, wherein the historical operating condition data includes coal powder demand, air-coal ratio, power load parameters, environmental parameters and combustion efficiency parameters; A model creation module is configured to construct an initial prediction model that introduces a local sensitive hashing self-attention mechanism, and train and verify the initial prediction model to obtain a target prediction model; A prediction module is configured to input the real-time operating condition data based on the target prediction model to determine the prediction signal of the future coal quantity and coal powder flow rate into the furnace and the load change of the thermal power unit; A delay compensation module is configured to determine the delay information between the coal quantity signal entering the furnace and the coal powder flow rate signal according to the predicted signal and the corresponding actual signal, and compensate the system response lag time difference based on the delay information; The air-coal quantity adjustment module is configured to determine the adjustment values ​​of the coal quantity and the air quantity according to the load change, and adjust the coal quantity and the air quantity in real time based on the adjustment values; The air-powder regulating module is configured to adjust the air-powder flow rate and air-powder temperature of the boiler in real time based on a cascade control strategy, so as to achieve high efficiency and stability of the thermal power unit under various operating conditions.

[0017] In a third aspect, the present application further provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the method for optimizing the frequency and peak regulation performance of a thermal power unit provided in the first aspect above.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the method for optimizing the frequency and peak regulation performance of a thermal power unit provided in the first aspect above.

[0019] It can be understood that the beneficial effects of the technical solutions provided in the second, third and fourth aspects can be found in the relevant description of the first aspect, and will not be repeated here.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a flow chart of a method for optimizing frequency and peak regulation performance of a thermal power unit according to an embodiment of the present application; Figure 2 It is a control principle flow chart of a method for optimizing frequency and peak regulation performance of a thermal power unit according to an embodiment of the present application; Figure 3 is a flow chart of the control principle related to the lag time according to an embodiment of the present application; Figure 4 is a flow chart of the control principle of the outer loop and inner loop feedback according to an embodiment of the present application; Figure 5 It is a block diagram of a frequency and peak regulation performance optimization system for a thermal power unit according to an embodiment of the present application; Figure 6 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The embodiments of the present application are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific implementations and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0025] See also Figures 1 to 4 This embodiment provides a method for optimizing frequency and peak regulation performance of a thermal power unit, the method comprising: Step S100: Acquire historical operating condition data of the thermal power unit, wherein the historical operating condition data includes coal powder demand, air-coal ratio, power load parameters, environmental parameters and combustion efficiency parameters; In this step, it is first necessary to conduct comprehensive data collection and processing on the thermal power units, mainly including the collection of historical operating data, which may include coal powder demand, air-coal ratio, combustion efficiency parameters, power load parameters, environmental parameters and other relevant operating conditions. Ensuring the comprehensiveness and accuracy of the data is crucial for subsequent analysis and modeling.

[0026] In addition, historical operating condition data can be sorted and preprocessed. For example, outliers can be removed, missing values ​​can be filled, and data can be standardized to ensure data quality and provide a reliable basis for model training. Data preprocessing can not only improve the learning effect of the model, but also reduce prediction errors and improve the overall performance of the system. The processed data can be sorted into a format suitable for model training to provide a reliable data basis for subsequent analysis and prediction. It can be understood that the specific preprocessing method can be selected according to actual needs. Data preprocessing is also a commonly used method in the prior art, and the specific process will not be described in detail here.

[0027] Step S200: constructing a target prediction model based on the historical operating condition data, inputting real-time operating condition data into the target prediction model, and determining prediction signals of future coal quantity and coal powder flow rate and load change of the thermal power unit; In this step, an initial prediction model that introduces a local sensitive hashing self-attention mechanism is constructed; the historical operating condition data is divided into a training set and a verification set, the training set is input into the initial prediction model to complete model training, and the trained model is input into the verification set for verification, and the training strategy is adjusted according to the verification result to obtain the target prediction model; the real-time operating condition data is input into the target prediction model to determine the prediction signals of the actual future coal input amount and coal powder flow rate and the load change of the thermal power unit.

[0028] Combination Figure 2 As shown, in some embodiments, the initial prediction model constructed can be a Reformer model. In the process of constructing the model, first, a reasonable network structure is designed, and hyperparameters that are consistent with the actual amount of coal entering the furnace and the prediction requirements of the coal powder flow rate signal are set. For example, the selection of the network structure can include a 6-layer encoder and a 6-layer decoder to effectively process complex time series data; in terms of hyperparameter setting, the hidden layer dimension is set to 256 to ensure that the model has sufficient expressive power; 8 self-attention heads are set to enhance the model's ability to capture input features; in addition, appropriate local sensitive hashing parameters are selected to effectively reduce the computational complexity while ensuring sensitivity to important features; the initial value of the learning rate is set to 0.001, and the learning rate decay strategy is combined to optimize the training process.

[0029] It should be noted that when processing long time series, the local sensitive hashing self-attention mechanism effectively improves the learning efficiency and prediction accuracy of the model by performing feature selection and accelerated calculation on the input sequence. This mechanism uses hashing technology to cluster similar features, thereby reducing computational complexity and accelerating attention calculations, ensuring that the model can quickly process and capture the dynamic changes of coal powder flow rate and the amount of coal entering the furnace. By minimizing the prediction error and optimizing the model parameters, it ensures that the model can effectively capture the timing characteristics of the coal quantity and coal powder flow rate signals. During the training process, the local sensitive hashing self-attention mechanism improves the model's ability to recognize historical data patterns by focusing on important time windows and features, thereby making the prediction results more accurate.

[0030] It can be understood that through the local sensitive hashing algorithm, the algorithm hashes the features of the input sequence and effectively reduces the complexity of the self-attention mechanism calculation, so that the model can still maintain a high response speed when facing complex coal powder flow and coal input data; at the same time, when performing precise control of the air-coal ratio, the local sensitive hashing self-attention mechanism can automatically focus on key features related to load changes and combustion efficiency, ensuring that the model can give priority to these important factors in dynamic adjustment; this feature is particularly important in the prediction of coal powder flow and coal input, helping the control system to adjust the coal powder flow and air volume more accurately; and, as the operating conditions change, the local sensitive hashing self-attention mechanism can adapt to different input modes and automatically adjust the attention weight, which enables the model to maintain a high prediction accuracy when facing different load demands and environmental changes, providing a reliable basis for dynamic feedforward compensation control.

[0031] Optionally, after the initial prediction model is constructed, the initial prediction model is trained using the historical operating data collected and processed in step S100. Exemplarily, the data set is first divided into a training set (80%) and a validation set (20%) to facilitate subsequent model evaluation; in terms of loss function, the mean square error (MSE) is used to quantify the difference between the predicted value and the actual value to ensure the effectiveness of model learning; in terms of optimizer, selecting the Adam optimizer can improve the convergence speed and training effect of the model; during the training process, 100 epochs of training are performed, and the performance of the model on the validation set is evaluated at the end of each epoch to monitor whether overfitting occurs, and the training strategy is adjusted according to the evaluation results to ultimately ensure the stability of the model and prediction accuracy.

[0032] Optionally, through this refined model construction and training process, the initial prediction model can provide high-precision prediction results, with a prediction success rate of up to 99%; next, the trained target prediction model will be used to predict the future coal volume and coal powder flow rate signals, and calculate the time delay between the predicted signal and the actual signal as well as the load change; then, through the cross-correlation delay estimation algorithm, the obtained delay information will be fed back to the control system to optimize the overall control strategy and improve the frequency and peak regulation performance of the thermal power unit.

[0033] Step S300: Determine the delay information between the coal quantity signal entering the furnace and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensate for the system response lag time difference based on the delay information; In this step, the correlation between the coal quantity signal and the actual coal powder flow rate signal entering the furnace is analyzed based on the cross-correlation delay estimation algorithm to determine the cross-correlation value under different lag times; the lag time that makes the cross-correlation function reach the maximum value is determined based on the cross-correlation value, and the lag time is used to characterize the delay relationship between the coal quantity signal entering the furnace and the coal powder flow rate signal; delay information is generated based on the lag time and fed back to the control system to compensate for the system response time difference caused by the signal delay and optimize the overall control strategy.

[0034] In some embodiments, a correlation between the coal quantity signal and the actual coal powder flow rate signal entering the furnace is calculated using a cross-correlation delay estimation algorithm, specifically including taking the coal quantity signal x(t) and the actual coal powder flow rate signal entering the furnace y(t) as inputs, analyzing them through a cross-correlation delay estimation algorithm, and setting a plurality of different lag step sizes τ to calculate the cross-correlation values ​​between the two signals under different time delays; the cross-correlation function R xy (τ) is used to quantify the correlation between signals x(t) and y(t) at a lag time τ, If it is a continuous time signal, the expression of the cross-correlation function is: Where τ is the lag time, R xy (τ) represents the correlation between the signals x(t) and y(t) at a lag time τ. The correlation at different time lags is calculated by taking the dot product of the sliding signals y(t) and x(t); If it is a discrete-time signal, the cross-correlation function can be calculated in the following discrete form: Among them, N is the number of samples of the signal, and τ is the discrete lag time. In this way, the lag time corresponding to the maximum correlation value is found, which is the delay between the signals; Combination Figure 2 and Figure 3 As shown, by calculating the cross-correlation values ​​corresponding to all lag times τ, we can find the value that makes Rxy (τ) Lag time T to reach the maximum value max , the maximum value represents the optimal time delay between the coal quantity signal and the coal powder flow rate signal, reflecting the dynamic relationship and influence mechanism between the two. Specifically, T max The value of will provide an important basis for subsequent dynamic adjustment. max The feedback is fed back to the coordinated control system for dynamic adjustment of the pulverized coal flow rate. This feedback mechanism is intended to compensate for the system response lag caused by signal delay and ensure the real-time and stability of the control strategy. By adjusting the pulverized coal flow rate in real time, it can effectively respond to combustion deviations caused by load fluctuations and improve the frequency and peak regulation performance of thermal power units.

[0035] Optionally, after the calculated delay information is fed back to the controller, the system can dynamically adjust the control strategy according to the load changes monitored in real time, respond in time and take corresponding measures. For example, when the load suddenly increases, the control system can adjust the amount of coal and air entering the furnace in advance to ensure the stability and efficiency of the combustion process. This feedback mechanism can not only effectively reduce the response error caused by signal delay, but also improve the system's adaptability to changes in external conditions, thereby ensuring that the boiler always remains in the best working state and reducing the risk of frequency fluctuations. In addition, through real-time delay compensation, the stability of the entire control system has been significantly enhanced, making the thermal power unit more flexible and efficient in responding to fluctuations in power demand, thereby better meeting the needs of the power market.

[0036] Specifically, when a load change is detected, the control system can quickly calculate the required pulverized coal flow rate and air volume adjustment values ​​based on the delayed information of real-time feedback. This feedback mechanism can not only reduce the response error caused by signal delay, but also enhance the boiler's ability to adapt to changes in external conditions and improve the overall regulation ability of the system. In addition, through continuous monitoring and adjustment, the system can maintain the operating efficiency of the boiler, thereby reducing frequency fluctuations while ensuring that the boiler is always in the best operating state, extending the service life of the equipment and improving energy efficiency.

[0037] Of course, dynamic time warping (DTW) can also be used for delay estimation, including (1) The coal quantity signal x(t) and the actual coal powder flow rate signal y(t) are taken as inputs, and the two signals x(t) and y(t) are standardized or normalized to ensure that they have the same dimension and scale, thereby reducing the error caused by amplitude differences; (2) By calculating the DTW distance of the two signals, the DTW algorithm automatically adjusts the time deviation between the coal quantity signal and the coal powder flow rate signal and calculates the optimal alignment path. First, the distance between the two signals at each time point is calculated (usually the Euclidean distance), and then the distance matrix D(i,j) is generated. , and then recursively calculate the cumulative distance of each point: C(i,j)=D(i,j)+min(C(i−1,j),C(i,j−1),C(i−1,j−1)). Finally, by calculating all possible paths, we find the path with the minimum cumulative distance from the starting point to the end point and obtain the optimal time-aligned path. (3) After calculating the optimal alignment path, the DTW algorithm will provide the optimal alignment time point for the two signals. The delay T between the two signals can be determined by the time difference of the alignment path. max， Delay T max This is the optimized time deviation, which reflects the optimal time alignment between signals; (4) The calculated delay time T max Feedback is given to the coordinated control system to compensate for the system response lag caused by signal delay. This feedback mechanism is designed to compensate for the system response lag caused by signal delay and ensure the real-time and stability of the control strategy. Based on this feedback mechanism, the control system can effectively respond to load fluctuations and adjust the pulverized coal flow rate to improve the frequency and peak regulation performance of the thermal power unit.

[0038] Step S400: determining adjustment values ​​of the amount of coal entering the furnace and the amount of air entering the furnace according to the load change, and adjusting the amount of coal entering the furnace and the amount of air entering the furnace in real time based on the adjustment values; In this step, based on the target prediction model, the load change ∆P(t) is predicted in real time, and the prediction result is input into the feedforward controller to respond to future load changes in advance. Specifically, the feedforward controller calculates the corresponding furnace coal adjustment value ∆M(t) and air volume adjustment value ∆W(t) according to the load change ∆P(t), where: The adjustment value of coal quantity is expressed as: , The adjustment value of the air volume is expressed as: , Where ∆P(t) is the load change, k M is the proportional coefficient of coal quantity, k W It is the proportional coefficient of air volume; it reflects the impact of load changes on the system. These coefficients are analyzed through historical data and optimized through models to ensure that the system can make adjustments quickly and effectively when the load fluctuates.

[0039] Optionally, the feedforward compensation signals ∆M(t) and ∆W(t) are input into the coordinated control system. The feedforward control signal and the feedback control signal work in parallel. The feedforward control is used to quickly respond to load changes to reduce combustion deviations, while the feedback control is used to correct the system steady-state deviations caused by external factors or model uncertainties in real time to ensure accurate dynamic regulation. Specifically, according to the results provided by the target prediction model, the amount of coal entering the furnace M(t) and the primary air volume W(t) are calculated and adjusted in advance. When an increase in load is predicted, the feedforward controller increases the amount of coal entering the furnace and the air volume in advance to maintain system stability; when a decrease in load is predicted, the amount of coal entering the furnace and the air volume are reduced in a timely manner, thereby reducing the impact of load changes on the system and ensuring the continuity and stability of the combustion process. It is understandable that although feedforward control can quickly respond to the deviation caused by load changes, there may still be certain prediction errors due to the uncertainty of the load prediction model. Therefore, feedback control is indispensable. The possible errors in feedforward control are corrected through the feedback channel to ensure the stable operation of the system under different working conditions. The combination of feedforward and feedback control forms a closed-loop control system, making the regulation of the combustion process more accurate and efficient.

[0040] Step S500: Based on the cascade control strategy, the air-powder flow rate and the air-powder temperature of the boiler are adjusted in real time to achieve high efficiency and stability of the thermal power unit under various operating conditions.

[0041] In this step, a cascade control strategy is introduced into the coordinated control system, aiming to achieve precise control of the air-powder flow rate by the inner loop and regulation of the air-powder temperature by the outer loop. The inner loop of this control mechanism focuses on the real-time regulation of the air-powder flow rate, and optimizes the combustion effect by precisely controlling the optimal ratio of fuel to air, thereby ensuring the efficient operation of the boiler. At the same time, the outer loop control is responsible for monitoring the air-powder temperature of the boiler and adjusting it in time to maintain its stability under various working conditions. This multi-level precise control strategy not only forms a complete set of coordinated control systems, but also can be flexibly adjusted according to different loads and operating conditions to ensure that the thermal power unit maintains high efficiency and stability under various operating conditions. Through such a comprehensive control method, the frequency regulation and peak regulation performance of the thermal power unit has been significantly improved, further ensuring the safety and reliability of power supply, providing solid technical support for coping with fluctuations in power demand, and promoting the effective use of energy and sustainable development of the environment.

[0042] Combination Figure 2 and Figure 4 As shown, the inner loop control uses a precise PID controller to adjust according to the deviation between the set target air-powder flow rate and the actual measured air-powder flow rate to ensure the precise control of the air-powder flow rate by the inner loop, where: The adjustment expression is: , In the formula, e(t) is the deviation between the set value and the actual value, K p , K i , K d are proportional, integral and derivative gains respectively; Optionally, the outer loop control is responsible for adjusting the target air-powder flow rate according to inputs such as external load changes and combustion efficiency, thereby ensuring that the inner loop control can be flexibly adjusted according to external conditions to achieve more precise control. Through cascade control, the inner and outer loops cooperate with each other, with the inner loop responsible for fine adjustments and the outer loop responsible for large-scale target adjustments, thereby forming a multi-level, comprehensive control system, which effectively improves the frequency and peak regulation capabilities of thermal power units.

[0043] By constructing a target prediction model that introduces a local sensitive hashing self-attention mechanism, the target prediction model is used to predict the actual future coal quantity and coal powder flow rate signals entering the furnace, and the time delay between the predicted signal and the actual signal is calculated. The lag time is obtained through the cross-correlation delay estimation algorithm and fed back to the control system to optimize the real-time and accuracy of the thermal power unit control strategy, achieve rapid response to dynamic changes in the combustion system, improve the regulation ability of the thermal power unit under frequent load fluctuations, and reduce the response lag in traditional control methods. In addition, the cross-correlation delay estimation algorithm feeds back signal delay information to the control system, effectively compensating for the delay problem, ensuring that the boiler maintains the best combustion efficiency under various load conditions, and through continuous monitoring and adjustment, the system can maintain the operating efficiency of the boiler, thereby reducing frequency fluctuations while ensuring that the boiler is always in the best operating state, extending the service life of the equipment, and improving energy utilization efficiency.

[0044] In the above method steps, by building a target prediction model that introduces the local sensitive hashing algorithm, the algorithm effectively reduces the complexity of the self-attention mechanism calculation by hashing the features of the input sequence, so that the model can still maintain a high response speed when facing complex coal powder flow and coal input data; when performing precise control of the air-coal ratio, the local sensitive hashing self-attention mechanism can automatically focus on key features related to load changes and combustion efficiency, ensuring that the model can give priority to these important factors in dynamic adjustment, helping the control system to more accurately adjust the coal powder flow and air volume; and as the operating conditions change, the local sensitive hashing self-attention mechanism can adapt to different input modes and automatically adjust the attention weight, which enables the model to maintain a high prediction accuracy when facing different load demands and environmental changes, and provides a reliable basis for dynamic feedforward compensation control.

[0045] At the same time, by using the load change output by the target prediction model, the load change trend can be predicted in advance through dynamic feedforward compensation control, and the pulverized coal flow into the furnace can be adjusted in time, thereby improving the system's adaptability to load changes, reducing combustion deviations, improving combustion stability and efficiency, and reducing energy consumption and emissions.

[0046] In addition, by integrating the cascade control strategy, the inner loop of this control mechanism focuses on the real-time adjustment of the air-powder flow rate, and optimizes the combustion effect by accurately controlling the optimal ratio of fuel and air to ensure the efficient operation of the boiler. At the same time, the outer loop control is responsible for monitoring the air-powder temperature of the boiler, forming a complete multi-level control system, which can be adjusted in time to maintain its stability under various operating conditions. It can be flexibly adjusted according to different loads and operating conditions to ensure that the thermal power unit maintains high efficiency and stability under various operating conditions.

[0047] See also Figure 5 , Figure 5 A block diagram of a thermal power unit frequency regulation and peak regulation performance optimization system 200 provided in this embodiment is shown. The thermal power unit frequency regulation and peak regulation performance optimization system 200 includes: The acquisition module 210 is configured to acquire historical operating condition data of the thermal power unit, wherein the historical operating condition data includes coal powder demand, air-coal ratio, power load parameters, environmental parameters and combustion efficiency parameters; The model creation module 220 is configured to construct an initial prediction model that introduces a local sensitive hashing self-attention mechanism, and train and verify the initial prediction model to obtain a target prediction model; The prediction module 230 is configured to input the real-time operating condition data based on the target prediction model to determine the prediction signal of the future coal quantity and coal powder flow rate into the furnace and the load change of the thermal power unit; The delay compensation module 240 is configured to determine the delay information between the coal quantity signal and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensate the system response lag time difference based on the delay information; The air-coal quantity adjustment module 250 is configured to determine the adjustment values ​​of the coal quantity and the air quantity according to the load variation, and adjust the coal quantity and the air quantity in real time based on the adjustment values; The air-powder regulating module 260 is configured to adjust the air-powder flow rate and air-powder temperature of the boiler in real time based on a cascade control strategy, so as to achieve high efficiency and stability of the thermal power unit under various operating conditions.

[0048] It can be understood that, when a thermal power unit frequency regulation and peak regulation performance optimization system 200 in this embodiment is implemented, each module runs the above Figures 1 to 4The steps of a method for optimizing the frequency and peak regulation performance of a thermal power unit in the corresponding embodiment, and the technical effects that can be achieved can refer to the above Figures 1 to 4 The description of the technical effects achieved in the corresponding embodiments will not be repeated here.

[0049] See also Figure 6 , Figure 6 5 is a block diagram of an electronic device provided in an embodiment of the present application. The server 500 of the electronic device includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501, such as a program of a method for optimizing the frequency and peak regulation performance of a thermal power unit. When the processor 501 executes the computer program 503, the steps of the method for optimizing the frequency and peak regulation performance of a thermal power unit in the above-mentioned embodiments are implemented, such as Figure 1 The corresponding embodiment of step S100 to step S500. Alternatively, the processor 501 executes the computer program 503 to implement the above Figure 5 The functions of each module in the corresponding embodiment are, for example, Figure 5 For details on the functions of the modules (eg, acquisition module 210), please refer to Figure 5 The relevant descriptions in the corresponding embodiments are not repeated here.

[0050] Exemplarily, the computer program 503 may be divided into one or more units, one or more units are stored in the memory 502, and are executed by the processor 501 to complete the technical solution provided in the above embodiment. One or more units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 503 in the server 500.

[0051] The electronic device may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 6 It is only an example of the server 500 in the electronic device and does not constitute a limitation of the server 500. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the turntable terminal device may also include an input and output terminal device, a network access terminal device, a bus, etc.

[0052] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0053] The memory 502 may be an internal storage unit of the server 500, such as a hard disk or memory of the server 500. The memory 502 may also be an external storage terminal device of the server 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 500. Further, the memory 502 may also include both an internal storage unit of the server 500 and an external storage terminal device. The memory 502 is used to store computer programs and other programs and data required by the turntable terminal device. The memory 502 may also be used to temporarily store data that has been output or is to be output.

[0054] In some embodiments, a computer-readable storage medium is also provided, which stores a computer program. When the computer program is executed by a processor, the steps of the method for optimizing the frequency and peak regulation performance of a thermal power unit as described in the above embodiment are implemented.

[0055] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0056] If the integrated unit 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. Among them, the computer-readable storage medium can be non-volatile or volatile. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0057] The terms "first", "second", "third", etc. in the specification and claims of the present application and the drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a series of steps or units are included, or optionally, steps or units not listed are included, or optionally, other steps or units inherent to these processes, methods, products or devices are included.

[0058] Only the part relevant to the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processing or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the process can be terminated, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0059] The terms "component", "module", "system", "unit", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or distributed between two or more computers. In addition, these units can be executed from various computer-readable media having various data structures stored thereon. Units can communicate through local and / or remote processes, for example, based on signals having one or more data packets (e.g., data from a second unit interacting with another unit in a local system, a distributed system, and / or a network. For example, the Internet interacts with other systems via signals).

[0060] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0061] Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present embodiment application. The appearance of this phrase in various positions in the specification is not necessarily the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It can be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0062] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0063] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the disclosure disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

Claims

1. A method for optimizing frequency and peak regulation performance of a thermal power unit, characterized in that: include: Acquiring historical operating condition data of the thermal power unit, wherein the historical operating condition data includes pulverized coal demand, air-to-coal ratio, power load parameters, environmental parameters, and combustion efficiency parameters; Building a target prediction model based on the historical operating condition data, inputting real-time operating condition data into the target prediction model, and determining prediction signals of future coal inflow and pulverized coal flow rate and load changes of the thermal power unit; Determining the delay information between the coal quantity signal and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensating for the system response lag time difference based on the delay information; Determining adjustment values ​​for the amount of coal fed into the furnace and the amount of air flow according to the load change, and adjusting the amount of coal fed into the furnace and the amount of air flow in real time based on the adjustment values; Based on the cascade control strategy, the air-powder flow rate and air-powder temperature of the boiler are adjusted in real time to achieve high efficiency and stability of the thermal power unit under various operating conditions.

2. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 1, characterized in that: The target prediction model is constructed based on the historical operating condition data, and real-time operating condition data is input into the target prediction model to determine prediction signals of future furnace coal quantity and pulverized coal flow rate and load change of the thermal power unit, including: Build an initial prediction model that introduces the local sensitive hashing self-attention mechanism; Dividing the historical operating condition data into a training set and a validation set, inputting the training set into the initial prediction model to complete model training, inputting the trained model into the validation set for validation, and adjusting the training strategy according to the validation results to obtain the target prediction model; The real-time operating condition data is input into the target prediction model to determine the prediction signals of the actual amount of coal fed into the furnace and the flow rate of pulverized coal and the load change of the thermal power unit in the future.

3. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 1, characterized in that: The method of determining delay information between the coal quantity signal and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensating for the system response lag time difference based on the delay information, includes: The correlation between the coal quantity signal and the actual pulverized coal flow rate signal is analyzed based on the cross-correlation delay estimation algorithm, and the cross-correlation value under different lag times is determined. Determining a lag time for the cross-correlation function to reach a maximum value based on the cross-correlation value, wherein the lag time is used to characterize a delay relationship between the coal amount signal and the pulverized coal flow rate signal; Delay information is generated based on the lag time and fed back to the control system to compensate for the system response time difference caused by the signal delay and optimize the overall control strategy.

4. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 3, characterized in that: The cross-correlation delay estimation algorithm is used to analyze the correlation between the coal quantity signal and the actual pulverized coal flow rate signal, and determine the cross-correlation value under different lag times, including: The coal quantity signal and the actual coal pulverized flow rate signal entering the furnace are used as inputs, and multiple hysteresis step sizes are set to construct a cross-correlation function. Based on the cross-correlation function, the cross-correlation value between the coal quantity signal and the pulverized coal flow rate signal at different time delays is obtained.

5. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 4, characterized in that: The coal quantity signal and the actual pulverized coal flow rate signal entering the furnace are used as inputs, and multiple different hysteresis step sizes are set to construct a cross-correlation function, including: If it is a continuous time signal, the expression of the cross-correlation function is: , If it is a discrete-time signal, the expression of the cross-correlation function is: , Where x(t) is the coal quantity signal, y(t) is the actual coal flow rate signal, τ is the lag time step, N is the number of signal samples, and R is the xy (τ) is the correlation between signals x(t) and y(t) at the lag time τ.

6. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 1, characterized in that: Determining adjustment values ​​of the amount of coal fed into the furnace and the amount of air flow according to the load change, and adjusting the amount of coal fed into the furnace and the amount of air flow in real time based on the adjustment values, includes: Based on the load change, the adjustment value of the amount of coal fed into the furnace and the adjustment value of the air volume are determined, wherein: The adjustment value expression of coal quantity is: , The adjustment value expression of air volume is: , Where ∆P(t) is the load change, k M is the proportional coefficient of coal quantity, k W is the proportional coefficient of air volume.

7. A method for optimizing frequency and peak regulation performance of a thermal power unit according to claim 1, characterized in that: The above-mentioned cascade control strategy is based on which the air-powder flow rate and air-powder temperature of the boiler are adjusted in real time to achieve high efficiency and stability of the thermal power unit under various operating conditions, including: The inner loop control is based on the PID controller to adjust according to the deviation between the set target air powder flow rate and the actual measured air powder flow rate, where: The adjustment expression is: , Where, e(t) is the deviation between the set value and the actual value, K p , K i , K d are proportional, integral and differential gains respectively; The outer loop control adjusts the target air-powder temperature in real time based on inputs including external load changes and combustion efficiency.

8. A frequency regulation and peak regulation performance optimization system for thermal power units, characterized in that: include: an acquisition module configured to acquire historical operating condition data of the thermal power unit, wherein the historical operating condition data includes pulverized coal demand, air-coal ratio, power load parameters, environmental parameters, and combustion efficiency parameters; A model creation module is configured to construct an initial prediction model that introduces a local sensitive hashing self-attention mechanism, and train and verify the initial prediction model to obtain a target prediction model; A prediction module is configured to input real-time operating condition data based on the target prediction model to determine prediction signals of future coal inflow and pulverized coal flow rate and load change of the thermal power unit; a delay compensation module configured to determine delay information between the coal quantity signal and the pulverized coal flow rate signal according to the predicted signal and the corresponding actual signal, and compensate for the system response lag time difference based on the delay information; an air-coal quantity adjustment module configured to determine adjustment values ​​of the coal quantity and the air quantity fed into the furnace according to the load variation, and to adjust the coal quantity and the air quantity fed into the furnace in real time based on the adjustment values; The air-powder adjustment module is configured to adjust the air-powder flow rate and air-powder temperature of the boiler in real time based on a cascade control strategy, so as to achieve high efficiency and stability of the thermal power unit under various operating conditions.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of a method for optimizing the frequency and peak regulation performance of a thermal power unit according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the steps of a method for optimizing the frequency and peak regulation performance of a thermal power unit according to any one of claims 1 to 7 are implemented.

Images