Intelligent coordination control system and method based on secondary reheating unit

Abstract

The invention discloses an intelligent coordination control system and method based on a secondary reheat unit, and belongs to the technical field of energy, and the method comprises the steps: collecting boiler and steam turbine operation data through a sensor, carrying out the preprocessing, combining a thermodynamic system physical mechanism with an ST-Attention-LSTM model, constructing a mechanism-data dual-drive thermodynamic system dynamic response prediction model, and carrying out the prediction of the dynamic response of the thermodynamic system. Multivariable prediction is achieved, and initial values of control parameters are set; using K-means clustering to classify system disturbance, calculating a weighted compensation amount, and obtaining a corrected control parameter through feedback correction; a rolling optimization algorithm is used for dynamically adjusting control parameters, and a working condition-rule mapping updating mechanism and a water quality prediction model are combined to adjust a water supply flow set value through self-adaptive fuzzy control; a coal yard is managed through unattended operation and real-time coal inventory, automatic repairing, starting, stopping and alarming mechanisms are set, carbon emission is monitored, and an optimization strategy is formulated; the unit operation efficiency can be improved, the energy consumption can be reduced, and the system stability and response speed can be enhanced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy, in particular to an intelligent coordination control system and method based on a double-reheat unit. BACKGROUND

[0002] Under the background of global energy transformation, coal-fired power generation is gradually changing from the main body of power supply to supporting and regulating power, and is more involved in the operation safety and peak regulation tasks of new power systems. As an advanced technology of coal-fired power generation, the double-reheat technology has complex heating surfaces and thermal inertia, making it difficult to accurately control the steam temperature, which not only affects the operation efficiency and safety of the unit, but also restricts the further development of coal-fired power generation technology. With the increasing demand for grid peak regulation, the optimization of coal-fired power generation thermal control technology has become an urgent need, and realizing rapid and accurate regulation and control of steam temperature is of great significance to ensure the stable operation of the power grid.

[0003] A double-reheat once-through boiler-turbine DBC coordination control system is disclosed in a patent with the authorized announcement number CN102566433B, which includes a two-way direct energy and mass balance coordination control system composed of an energy demand signal of the double-reheat steam turbine to the boiler energy and heat signals and fuel-water ratio signals representing the energy and mass balance of the double-reheat once-through boiler, realizing dynamic decoupling control of the unit. At the same time, considering the complex characteristics of the double-reheat unit, dynamic weighting compensation of the boiler characteristic point heat, steam turbine pressure correction, and asymmetric constraint adaptive correction compensation links are designed, effectively improving the regulation quality of the unit of the thermal power plant with double-reheat.

[0004] The above existing technology has the following problems: 1) The DBC coordination control system mainly relies on the pre-designed two-way direct energy and mass balance coordination control system, limiting its ability to adapt to complex and variable working conditions; 2) Lack of real-time learning and self-optimization ability; 3) The DBC system involves multiple complex compensation links and control logic, which increases the overall complexity of the system, thereby increasing the difficulty of maintenance, debugging, and troubleshooting. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides an intelligent coordinated control system and method based on a double-reheat unit, which collects and pre-processes the operation data of a boiler and a steam turbine through a sensor, combines the physical mechanism of a thermal system with an ST-Attention-LSTM model to construct a mechanism-data dual-driven dynamic response prediction model of the thermal system, realizes multivariate prediction and sets the initial value of a control parameter, classifies system disturbances using a K-means clustering method, calculates a weighted compensation amount, and obtains a corrected control parameter through feedback correction, dynamically adjusts the control parameter using a rolling optimization algorithm, combines a working condition-rule mapping update mechanism and a water quality prediction model to set the water flow set value through adaptive fuzzy control, manages a coal yard through unattended operation and real-time coal inventory, sets an automatic repair, start-stop and alarm mechanism, monitors carbon emissions and formulates an optimization strategy, and can improve the operation efficiency of the unit, reduce energy consumption, and enhance the stability and response speed of the system.

[0006] To achieve the above object, the present application provides the following technical scheme: An intelligent coordinated control system based on a double-reheat unit, comprising: an intelligent control module, a coordinated control module, and an auxiliary control module. The intelligent control module comprises a prediction control unit and an intelligent feedforward unit; the prediction control unit is configured with a multivariate prediction control strategy, which is used to predict the real-time operation state of the boiler and the steam turbine according to historical data, real-time operation data and the physical mechanism of the thermal system, using a pre-constructed mechanism-data dual-driven dynamic response prediction model of the thermal system; the mechanism-data dual-driven dynamic response prediction model of the thermal system is constructed based on an ST-Attention-LSTM model; the intelligent feedforward unit is configured with an intelligent feedforward control strategy; the intelligent feedforward control strategy is used to correct the prediction results through K-means clustering. The coordinated control module comprises a boiler main control unit and a steam turbine main control unit; the boiler main control unit dynamically adjusts the valve opening degree and the boiler combustion rate according to the received load instruction, optimizes the combustion process of the boiler, and matches the energy of the boiler with the output energy of the steam turbine; the steam turbine main control unit is used to receive the load instruction and adjust the steam admission amount, speed and power of the steam turbine according to the received load instruction. The auxiliary control module comprises a feedwater control unit; the feedwater control unit is configured with an adaptive fuzzy control strategy; the adaptive fuzzy control strategy is used to automatically call or modify the fuzzy control rule library according to the preset working condition-rule mapping update mechanism, combine the pre-constructed water quality prediction model to obtain the water quality trend in advance, convert the fuzzy set into a control amount through the barycentric method, and automatically adjust the set value of the feedwater flow; the water quality prediction model is configured based on a GRU network.

[0007] Specifically, the prediction control unit adopts a multivariable prediction control strategy, and the specific steps include: A1: Collect the operation data of the boiler and the steam turbine in real time through sensors , wherein the collected operation data is preprocessed, and the preprocessing includes: representing the first k operation data, k representing the number of collected operation data; the operation data includes secondary reheat steam temperature, pressure, fuel flow, feed water flow, steam turbine admission, and rotating speed; A2: Determine the input features of the ST-Attention-LSTM model in combination with the physical mechanism of the thermal system, initialize the weights and thresholds of the ST-Attention-LSTM model, train the ST-Attention-LSTM model using the preprocessed operation data, and obtain a mechanism-data dual-driven dynamic response prediction model of the thermal system; A3: Set a sampling time T, based on the mechanism-data dual-driven dynamic response prediction model of the thermal system, calculate the output layer of the mechanism-data dual-driven dynamic response prediction model of the thermal system according to the operation data at the current time, and obtain the prediction result of the operation state of the boiler and the steam turbine in the next sampling time T , wherein the prediction result includes: representing the first k predicted operation data; A4: Set the initial value of the control parameter of the boiler and the steam turbine, set the target function, the operation constraint condition, and the initial parameter of the rolling optimization algorithm, calculate the target function value according to the prediction result, check whether the target function value meets the operation constraint condition, if not, adjust the control parameter of the boiler and the steam turbine using the rolling optimization algorithm, and roll the time window forward by one sampling time, repeat the step A4, and obtain new control parameter .

[0008] Specifically, the training step of the ST-Attention-LSTM model includes: A2.1: Divide the preprocessed operation data into a training set, a validation set, and a test set according to a ratio of 7:2:1, and the operation data dimension includes a time series dimension and a feature dimension; A2.2: Initialize the attention layer weight, the LSTM layer weight, and the threshold of the model, and the input of the attention layer is the hidden state of the LSTM layer; A2.3: Use the mean square error of the model prediction value and the actual operation data as the loss function, and use the Adam optimizer to train the ST-Attention-LSTM model; A2.4: Evaluate the generalization ability of the ST-Attention-LSTM model using the test set, if the mean square error exceeds the set threshold, then adjust the network structure of the ST-Attention-LSTM model until the accuracy requirement is met.

[0009] Specifically, the logic of the objective function in A4 is that the objective function value comprehensively reflects the optimization goals of three dimensions of boiler fuel cost, matching degree of boiler output power and demand power, and system operation efficiency, and the importance of the three dimensions is adjusted by weight factors, wherein the boiler fuel cost is determined by the fuel flow, the matching degree of boiler output power and demand power is determined by the difference between the two, and the system operation efficiency is calculated from the real-time operation parameters of the unit.

[0010] Specifically, the intelligent feedforward unit adopts an intelligent feedforward control strategy, and the specific steps include: B1: Real-time monitoring of disturbance information of the system through sensors ; the disturbance information includes fuel heat value fluctuation, power grid load impact, water hardness change, and equipment fault early warning signal, wherein, l represents the number of disturbance information, represents the l th disturbance information; B2: Real-time classification of disturbance information using K-means clustering, and obtaining the prediction error of the original control parameter according to the classified disturbance information and the prediction result of the mechanism-data dual-driven thermal system dynamic response prediction model, and calculating the compensation amount of the prediction error using an intelligent feedforward control algorithm, the formula is: , wherein, represents the compensation amount of the prediction error , and represents the feedforward control function; B3: Set the error threshold to H, and add the obtained compensation amount to the original control parameter to obtain the control parameter error after adding the compensation amount ; If , adjust the output variable according to the prediction result; If , adjust the control parameter using a rolling optimization algorithm, and correct the prediction result using a feedback correction control algorithm based on real-time operation state data to obtain the corrected prediction value , wherein, represents the corrected prediction value of the t th output variable at time i ; B4: Re-adjust the control parameter based on the corrected prediction result; B5: Repeat B1 to B4 until the system reaches a steady state, and after feedback correction, obtain the corrected control parameters and use them to drive the operation of the boiler and the steam turbine.

[0011] Specifically, the logic of the feedback correction control algorithm in B3 is as follows: t The corrected predicted value of the output variable at time i is equal to the original predicted value of the output variable plus the sum of the product of the feedback correction coefficient of the output variable for each prediction error and the corresponding prediction error, plus an additional correction term determined according to the real-time operating conditions of the system, wherein the feedback correction coefficient is obtained by training historical prediction error and actual deviation data, and the additional correction term is used to compensate for the deviation not covered by the model under extreme operating conditions.

[0012] Specifically, the feedwater control unit adopts an adaptive fuzzy control strategy, and the specific steps include: C1: Set the feedwater flow domain, divide the low, moderate, and high fuzzy sets within the feedwater flow domain, and configure a triangular membership function for each fuzzy set, wherein the vertex position of the membership function is calibrated according to historical optimal feedwater flow data, and the feedwater flow domain is determined according to the rated evaporation capacity of the boiler; C2: Map the corrected predicted value to the configured triangular membership function, and calculate the membership values of the corrected predicted value belonging to each fuzzy set; C3: According to the system requirements, formulate a fuzzy control rule base, combine the membership values in C2, and according to the fuzzy control rules in the fuzzy control rule base, use the maximum and minimum reasoning method to calculate the output fuzzy set, i.e., determine the fuzzy interval to which the feedwater flow should belong; the system requirements include water quality standard, steam temperature stability range, and unit load response speed.

[0013] Specifically, the feedwater control unit adopts an adaptive fuzzy control strategy, and the specific steps further include: C4: Introduce a working condition-rule mapping update mechanism to identify the current working condition of the unit in real time, automatically call the corresponding fuzzy control rules from the fuzzy control rule base in C3 according to the working condition type, and if there is no matching fuzzy control rule for the current working condition, modify the existing fuzzy control rule parameters based on the control effect of similar historical working conditions; C5: Call the pre-built water quality prediction model to obtain the water quality trend in a preset time period; C6: Convert the output fuzzy set to a control variable using the barycentric method, and the conversion logic is: the control variable is equal to the sum of the product of each predicted value in the fuzzy set and its membership value, divided by the sum of all membership values, and then multiplied by a weight factor; the control variable is used to adjust the set value of the feedwater flow; the weight factor is dynamically adjusted according to the water quality trend output by the water quality prediction model; C7: applying the obtained control quantity to the water supply system, monitoring the response of the system to the control quantity, collecting actual water supply flow data in real time, comparing the actual water supply flow data with the corrected predicted value, calculating the error and error change rate of the two, and using the error and error change rate automatic membership function vertex position, fuzzy control rule base and weight factor.

[0014] The application also provides an intelligent coordinated control method based on a double-reheat unit, comprising: Step S1: collecting the operation data of the boiler and the steam turbine in real time through a sensor, pre-processing the collected operation data, combining the physical mechanism of the thermal system and the ST-Attention-LSTM model, constructing a mechanism-data double-driven dynamic response prediction model of the thermal system, and using the mechanism-data double-driven dynamic response prediction model of the thermal system to perform multivariate prediction on the operation state of the boiler and the steam turbine, and setting the initial value of the control parameter of the boiler and the steam turbine according to the multivariate prediction result; Step S2: setting the operation constraint condition of the boiler and the steam turbine, monitoring and classifying the system disturbance information in real time through K-means clustering, and calculating the weighted compensation amount of the prediction error based on the dynamic response prediction model of the thermal system and the disturbance influence factor, adding the compensation amount to the control parameter, correcting the prediction error through a feedback correction mechanism, and obtaining the corrected control parameter; Step S3: using a rolling optimization algorithm to perform real-time dynamic adjustment on the corrected control parameter of the boiler and the steam turbine, combining a working condition-rule mapping update mechanism and a water quality prediction model, and using an adaptive fuzzy control strategy to automatically adjust the set value of the water supply flow to obtain the best efficiency of the stable operation of the boiler; Step S4: updating the coal yard inventory through an unattended and real-time coal inventory method and visual monitoring, setting an automatic repair mechanism, an automatic start-stop mechanism and an alarm mechanism, triggering the alarm mechanism immediately if an abnormality or a fault is found, and automatically adjusting the start-stop state of the boiler and the steam turbine for repair; Step S5: monitoring the carbon emission of the boiler and the steam turbine in real time, formulating an optimization control strategy according to the carbon emission, evaluating the energy use of the boiler and the steam turbine at regular intervals, identifying the energy-saving potential according to the evaluation result, and formulating energy-saving measures.

[0015] The application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the intelligent coordinated control method based on a double-reheat unit when executing the computer program.

[0016] Compared with the prior art, the application has the following beneficial effects: 1.The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost.

[0017] 2.The application provides an intelligent coordination control method based on a double-reheat unit, through real-time data acquisition, prediction model and intelligent control, rolling optimization and adaptive control method, the stable operation of the system can be ensured, and the failure and downtime are reduced; through the adaptive fuzzy control strategy, the set value of the feed water flow can be automatically adjusted, the stable operation of the boiler can be ensured, the energy utilization efficiency can be optimized, and the energy consumption can be reduced; the carbon emission situation is monitored in real time, and the optimal control strategy is made, so that the environmental pollution is reduced; through unattended, real-time coal inventory and visual monitoring means, the coal yard inventory situation can be mastered in real time, and the management efficiency is improved; the application of the rolling optimization algorithm and the adaptive control strategy makes the system adapt to different working conditions and changes, and improves the adaptability and flexibility of the system. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost. Figure 2 The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost. Figure 3 The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost. Figure 4 The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost. Figure 5 The application provides an intelligent coordination control system based on a double-reheat unit, and optimization and improvement are made on the architecture, operation steps and processes, the system has the advantages of simple process, low investment and operation cost, and low production cost. DETAILED DESCRIPTION

[0019] Embodiment 1 Please refer to Figure 1 The application provides an embodiment: an intelligent coordination control system based on a double-reheat unit, which comprises an intelligent control module, a coordination control module and an auxiliary control module. The intelligent control module is used for real-time analysis of operation data of the boiler and the steam turbine, and real-time optimization control of operation processes of the boiler and the steam turbine; the intelligent control module comprises a predictive control unit and an intelligent feedforward unit; a multivariable predictive control strategy is configured in the predictive control unit, the multivariable predictive control strategy is used for predicting real-time operation states of the boiler and the steam turbine by using a pre-constructed mechanism-data double-driven thermal system dynamic response prediction model according to historical data, real-time operation data and a physical mechanism of the thermal system, and automatically adjusting control parameters by using a rolling optimization algorithm based on a prediction result; the mechanism-data double-driven thermal system dynamic response prediction model is constructed based on an ST-Attention-LSTM model; an intelligent feedforward control strategy is configured in the intelligent feedforward unit, and the intelligent feedforward control strategy is used for correcting the prediction result by K-means clustering. The operation data of the boiler and the steam turbine comprise temperature and pressure data, flow data, combustion data, emission data, speed and position data, electrical data, vibration and noise data, and thermal efficiency and efficiency data.

[0020] The control parameters comprise fuel flow, valve opening, temperature set point and pressure set point; adjusting the control parameters can affect the output of the system, such as energy consumption, output power and system efficiency.

[0021] The disturbance information comprises fuel flow, steam pressure, temperature change, equipment failure and parameter change.

[0022] The coordination control module is used for coordinating control of the boiler and the steam turbine by the multivariable predictive control strategy and the intelligent feedforward control strategy of the intelligent control module; the coordination control module comprises a boiler main control unit and a steam turbine main control unit; the boiler main control unit dynamically adjusts valve opening and boiler combustion rate by receiving a load instruction, optimizes a combustion process of the boiler, and matches energy of the boiler with output energy of the steam turbine; the steam turbine main control unit is used for receiving a load instruction and adjusting steam admission, speed and power of the steam turbine according to the received load instruction. The auxiliary control module is used for coal yard management and feedwater control; the auxiliary control module comprises a feedwater control unit; an adaptive fuzzy control strategy is configured in the feedwater control unit; the adaptive fuzzy control strategy is used for automatically calling or correcting a fuzzy control rule base according to a preset working condition-rule mapping update mechanism, combining a pre-constructed water quality prediction model to obtain a water quality change trend in advance, converting a fuzzy set into a control amount by a gravity center method, and automatically adjusting a set value of feedwater flow; the water quality prediction model is configured based on a GRU network.

[0023] The intelligent control module further comprises a neural network unit; the neural network unit models and controls a complex nonlinear system by simulating a working principle of a human brain neural network.

[0024] The coordinated control module further comprises a digital electro-hydraulic regulating unit, a feedback correction unit, a disturbance monitoring and compensation unit, and an energy balance unit. The digital electro-hydraulic regulating unit is responsible for the control of turbine governing valves, achieving rapid response of load and stability of steam pressure. The feedback correction unit compensates for prediction errors. The disturbance monitoring and compensation unit monitors system disturbances in real time and calculates compensation amounts through intelligent feedforward control algorithms. The energy balance unit monitors energy flow within the unit in real time, ensuring energy balance between the boiler and the steam turbine, and avoiding energy waste.

[0025] The auxiliary control module further comprises a smart coal yard unit and a fault diagnosis and repair unit. The smart coal yard unit realizes real-time updating and visual monitoring of coal yard inventory through unattended and real-time coal inventorying. The automatic fault diagnosis and repair unit diagnoses potential faults of the unit and repairs them through real-time monitoring and data analysis, improving the reliability of the unit. The APS automatic start-stop unit automatically controls the start and stop processes of the unit through pre-set programs and logic.

[0026] The intelligent coordinated control system based on a double-reheat unit further comprises a data processing module and an energy management module. The data processing module uses data processing methods to perform real-time processing, analysis, and monitoring of unit operation data. The data processing module includes a data acquisition unit, a data analysis unit, an automatic repair unit, an automatic start-stop unit, and a monitoring and alarm unit. The data acquisition unit uses sensors to collect real-time operation data of the boiler and the steam turbine. The data analysis unit preprocesses and analyzes the collected data and optimizes control strategies based on the analysis results. The automatic repair unit sets up an automatic repair mechanism to automatically diagnose and repair faults or abnormalities. The automatic start-stop unit automatically adjusts the start and stop states of the unit according to the unit's operation needs and energy market demands. The monitoring and alarm unit monitors the system's operation state in real time, alarms in a timely manner when abnormalities are found, and takes processing measures.

[0027] The energy management module is used to realize energy management and energy-saving optimization during the operation of the unit. The energy management module includes an energy efficiency evaluation unit, a carbon emission monitoring unit, and an energy-saving measure development unit. The energy efficiency evaluation unit evaluates and analyzes the energy usage of the unit. The carbon emission monitoring unit monitors the carbon emissions of the unit in real time and reduces carbon emissions through optimized control strategies. The energy-saving measure development unit develops energy-saving measures, such as optimizing combustion methods and improving thermal efficiency, based on evaluation results.

[0028] Example 2 Please refer to Figures 2-4 In this embodiment, a multivariable predictive control strategy is adopted in the predictive control unit, and the specific steps include: A1: Collecting real-time operation data of the boiler and the steam turbine through a sensor , wherein the collected operation data is preprocessed, and the preprocessing comprises: representing the i-th operation data, k representing the i-th operation data, k representing the number of the collected operation data; the operation data comprises secondary reheat steam temperature, pressure, fuel flow, feed water flow, steam turbine admission, and rotating speed; A2: determining input features of an ST-Attention-LSTM model in combination with a physical mechanism of the thermal system, initializing weights and thresholds of the ST-Attention-LSTM model, training the ST-Attention-LSTM model using the preprocessed operation data, and obtaining a mechanism-data dual-driven dynamic response prediction model of the thermal system; Further, the prediction control unit is configured with a mechanism-data dual-driven multivariable prediction control strategy, and the core is to construct an ST-Attention-LSTM, i.e., a thermal system dynamic response prediction model of a space-time attention-long short-term memory network, and the specific implementation logic is as follows: (1) in combination with the physical mechanism of the secondary reheat unit, such as the boiler heat balance equation, and historical operation data, determining input features and output targets of the model, wherein the input features comprise secondary reheat steam temperature, steam turbine admission pressure, fuel flow, and feed water flow; (2) the ST-Attention-LSTM model comprises an input layer, a space-time attention layer, an LSTM layer, and an output layer: the input layer receives the preprocessed operation data, which is processed by excluding abnormal values, normalization, and time sequence alignment; the space-time attention layer strengthens the time sequence correlation capture of key parameters by calculating the attention weights of each input feature; the LSTM layer memorizes long-term time sequence features through a gating unit to avoid the gradient disappearance problem of traditional RNN; and the output layer outputs the prediction result of the unit operation state to obtain the constructed ST-Attention-LSTM model, wherein the gating unit comprises an input gate, a forgetting gate, and an output gate; (3) training the constructed ST-Attention-LSTM model.

[0029] A3: setting a sampling time T, based on the mechanism-data dual-driven dynamic response prediction model of the thermal system, obtaining the prediction result of the operation state of the boiler and the steam turbine in the next sampling time T of the output layer through the hidden layer calculation of the mechanism-data dual-driven dynamic response prediction model of the thermal system according to the operation data at the current time , wherein the prediction result of the operation state of the boiler and the steam turbine in the next sampling time T of the output layer is represented as representing the i-th predicted operation data; k ​A4: Set the initial value of the control parameter of the boiler and the steam turbine, set the objective function, the initial parameter of the running constraint condition and the rolling optimization algorithm, calculate the objective function value according to the prediction result, and check whether the objective function value meets the running constraint condition, if not, adjust the control parameter of the boiler and the steam turbine using the rolling optimization algorithm, and roll the time window forward by one sampling time, repeat step A4 to obtain new control parameters .

[0030] The training steps of the ST-Attention-LSTM model in A2 include: A2.1: The preprocessed operation data is divided into training set, validation set and test set according to the proportion of 7:2:1, and the operation data dimension includes time series dimension and feature dimension; A2.2: Initialize the attention layer weight, LSTM layer weight and threshold value of the model, and the input of the attention layer is the hidden state of the LSTM layer; A2.3: The mean square error of the model prediction value and the actual operation data is used as the loss function, and the ST-Attention-LSTM model is trained using the Adam optimizer; A2.4: The generalization ability of the ST-Attention-LSTM model is evaluated using the test set, if the mean square error exceeds the set threshold, the network structure of the ST-Attention-LSTM model is adjusted again until the accuracy requirement is met.

[0031] The logic of the objective function in A3 is: the objective function value comprehensively reflects the optimization objectives of three dimensions of boiler fuel cost, matching degree of boiler output power and demand power, and system running efficiency, and the importance of the three dimensions is adjusted by weight factors, wherein the boiler fuel cost is determined by fuel flow, the matching degree of boiler output power and demand power is determined by the difference between the two, and the system running efficiency is calculated by real-time running parameters of the unit. Specifically, the objective function formula is: ; The running constraint condition includes: ; Wherein, J represents the objective function value, represents the fuel cost used by the boiler, represents the fuel flow function, represents the boiler output power function, represents the demand power when the boiler is working, represents the system efficiency function, t represents the current time, , , represents a weight factor, represents a control parameter of a boiler and a steam turbine, and represents a minimum value and a maximum value of a control parameter, and represents a minimum value and a maximum value of a temperature, represents a temperature function based on , and represents a minimum value and a maximum value of a pressure, represents a pressure function based on , and represents a minimum value and a maximum value of a flow rate, represents a flow rate function based on .

[0032] The intelligent feedforward unit adopts an intelligent feedforward control strategy, and the specific steps include: B1: Real-time monitoring of disturbance information of the system through a sensor ; the disturbance information includes fuel heat value fluctuation, power grid load impact, water quality hardness change, and equipment fault early warning signal, wherein, l represents the number of disturbance information, represents the l th disturbance information; B2: Real-time classification of the disturbance information using K-means clustering, and obtaining a prediction error of the original control parameter according to the classified disturbance information and a prediction result of a mechanism-data dual-driven thermal system dynamic response prediction model, and calculating a compensation amount of the prediction error using an intelligent feedforward control algorithm, the formula being: , wherein, represents a compensation amount of the prediction error , represents a feedforward control function, wherein the K-means clustering is a prior art content in the field and is not the inventive scheme of the present application, and is not described here; B3: Setting an error threshold value H, adding the obtained compensation amount to the original control parameter to obtain a control parameter error after adding the compensation amount ; if , adjusting an output variable according to the prediction result; if , adjusting the control parameter using a rolling optimization algorithm, and correcting the prediction result based on real-time running state data using a feedback correction control algorithm to obtain a corrected prediction value , wherein, represents the t thi Corrected predicted values ​​of each output variable; B4: Based on the corrected prediction results, readjust the control parameters; B5: Repeat B1 to B4 until the system reaches a steady state. After feedback correction, the corrected control parameters are obtained and used to drive the operation of the boiler and turbine.

[0033] The optimization problems solved by the rolling optimization algorithm in B3 include: ; in, Indicates the system in time t The running status, Indicates the system in time The running status, This represents a dynamic response prediction model for a thermal system. Indicates the system in time The constraint value, Describes the minimum value function. n Indicates the time step.

[0034] The logic of the feedback correction control algorithm in B3 is as follows: t The corrected predicted value of the i-th output variable at time i equals the original predicted value of that output variable plus the sum of the products of the feedback correction coefficients for each prediction error and the corresponding prediction errors, plus an additional correction term determined based on the real-time operating conditions of the system. The feedback correction coefficients are obtained through training with historical prediction error and actual deviation data, and the additional correction term is used to compensate for deviations not covered by the model under extreme conditions. Specifically, the formula for the feedback correction control algorithm is: ; in, express t Time of the first i The corrected predicted values ​​of each output variable. express t Time of the first i The original predicted values ​​of each output variable. express t Time of the first i The output variable for the first... j Feedback correction coefficient for each prediction error, express t Time of the first i The prediction error of each output variable. express t Time of the first i Additional correction terms for each output variable.

[0035] The water supply control unit adopts an adaptive fuzzy control strategy, and the specific steps include: C1: setting a water flow domain, dividing the low, moderate, and high three fuzzy sets within the water flow domain, and configuring a triangular membership function for each fuzzy set, wherein the vertex position of the membership function is calibrated according to historical optimal water flow data, and the water flow domain is determined according to the rated evaporation capacity of the boiler; Wherein, the boundaries of the fuzzy set are usually determined based on experience, system requirements or expert knowledge, the domain of the water flow is set to [0, 100], and the water flow range [0, 30) is defined as low, [30, 70] is defined as moderate, and (70, 100] is defined as high.

[0036] In the low flow fuzzy set, the triangular membership function is defined as the function value being 1 when the water flow is 0, i.e. completely belonging to the low set, the function value being 0 when the flow is 30, i.e. not belonging to the low set, and passing through an intermediate point in the process of linearly decreasing; In the moderate flow fuzzy set, the triangular membership function takes boundary values 0 and 1 at flow rates of 30 and 70 respectively, and passes through an intermediate point in the process of linearly changing; In the high flow fuzzy set, the triangular membership function takes boundary value 1 at flow rate 100, i.e. completely belongs to the high set, the function value is 0 at flow rate 70, i.e. not belonging to the high set, and passes through an intermediate point in the process of linearly changing.

[0037] C2: mapping the corrected predicted value to the configured triangular membership function, and calculating the membership value of the corrected predicted value belonging to each fuzzy set; Further, the specific steps of C2 include: (1) Set the three vertices of the triangular membership function as b , s , q , wherein, s is the center point; (2) According to the definition of the fuzzy control strategy, the boundaries of the low, moderate, and high three fuzzy sets are determined to be [0, 30), [30, 70], and (70, 100) respectively; (3) Receive the corrected predicted value, and determine whether the corrected predicted value falls within the water flow domain; If it is not within the water flow domain, the triangular membership value of the predicted value is 0; If it is within the water flow domain, determine which fuzzy set range the predicted value belongs to; If it is not within the fuzzy set range, the triangular membership value of the predicted value is 0; If in the fuzzy set range, according to the fuzzy set range to which it belongs, the membership degree thereof is calculated using a corresponding triangular membership function, wherein the triangular membership function calculation formula is a prior art content in the field and is not the creative scheme of the present application, and thus will not be described here in detail.

[0038] C3: According to system requirements, a fuzzy control rule library is formulated, the membership value in C2 is combined, the fuzzy set of the output is calculated using the maximum-minimum reasoning method according to the fuzzy control rules in the fuzzy control rule library, that is, the fuzzy interval to which the feedwater flow should belong is determined; the system requirements include water quality standard, steam temperature stable range, unit load response speed, wherein the maximum-minimum reasoning method is a prior art content in the field and is not the creative scheme of the present application, and thus will not be described here in detail; Further, the process of formulating the fuzzy control rule library mainly adopts if-else logic, traverses all fuzzy set combinations of input variables, formulates the output rules corresponding to each combination in combination with system requirement constraints, and ensures that the rules are not missed and not in conflict, wherein the if-else logic is a prior art content in the field and is not the creative scheme of the present application, and thus will not be described here in detail.

[0039] C4: An operating condition-rule mapping update mechanism is introduced, the current operating condition of the unit is identified in real time, the corresponding fuzzy control rules are automatically called from the fuzzy control rule library in C3 according to the operating condition type, and if there is no matching fuzzy control rule for the current operating condition, the existing fuzzy control rule parameters are corrected based on the control effect of the historical similar operating condition; Further, the operating condition-rule mapping update mechanism refers to a closed-loop optimization mechanism for establishing the dynamic association between the operating condition type and the fuzzy control rule library by identifying the current operating condition of the unit in real time, and automatically correcting the rule parameters based on the historical similar operating condition when there is no matching rule, and the core purpose is to solve the problem that the traditional fuzzy control relies on fixed rules and is difficult to adapt to the complex and variable operating conditions of the secondary reheat unit, such as load fluctuation, fuel switching and water quality change, to ensure that the control rules are always synchronized with the real-time running state of the unit and to improve the control accuracy of the key parameters such as the feedwater flow.

[0040] C5: A pre-constructed water quality prediction model is called to obtain the water quality change trend in a preset time period; Further, the construction process of the water quality prediction model includes: (1) determining the prediction target and accuracy requirement, wherein the core target of the model is to predict the future change trend of the key water quality parameters of the feedwater system to provide an advance for the feedwater flow adjustment; (2) defining the input and output variable dimensions, wherein the input variables include historical water quality parameters, operation parameters, raw water characteristic parameters and environmental interference parameters; the output variable is the prediction value of the water hardness, silicon content and conductivity every 10 minutes in the next 1 hour; (3) Deploy online water quality analyzers at the feedwater pump inlet and boiler inlet, read operating parameters from the unit DCS system, obtain raw water data from the water plant interface, obtain environmental data from the plant meteorological station, and perform preprocessing and dataset division. (4) Load the GRU network architecture and train the GRU network architecture using the partitioned training set to obtain a trained water quality prediction model. The GRU network architecture is existing technology in this field and is not an inventive solution of this application. It will not be described in detail here.

[0041] C6: The centroid method is used to convert the output fuzzy set into a control quantity. The conversion logic is as follows: the control quantity is equal to the sum of the products of each predicted value and its membership value in the fuzzy set, divided by the sum of all membership values, and then multiplied by a weighting factor. The control quantity is used to adjust the setpoint of the water supply flow rate. The weighting factor is dynamically adjusted according to the water quality change trend output by the water quality prediction model. Specifically, the conversion formula is: ; in, This represents the converted control quantity. Represents the first in the fuzzy set i One predicted value, This represents the membership degree in the fuzzy set A. Represents the membership function. Indicates the weighting factor; C7: Apply the obtained control quantity to the water supply system, monitor the system's response to the control quantity, collect actual water supply flow data in real time, compare the actual water supply flow data with the corrected predicted value, calculate the error and error change rate between the two, and use the error and error change rate to automatically determine the vertex position of the membership function, the fuzzy control rule base, and the weight factor.

[0042] Example 3 Please see Figure 5 Another embodiment of the present invention provides: an intelligent coordinated control method based on a double reheat unit, comprising: Step S1: Real-time acquisition of boiler and turbine operating data through sensors, preprocessing of the acquired operating data, construction of a mechanism-data dual-driven dynamic response prediction model of the thermal system by combining the physical mechanism of the thermal system and the ST-Attention-LSTM model, and multivariate prediction of the operating status of the boiler and turbine by using the mechanism-data dual-driven dynamic response prediction model of the thermal system. Based on the multivariate prediction results, initial values ​​of control parameters of the boiler and turbine are set. Step S2: setting the operation constraints of the boiler and the steam turbine, monitoring and classifying the system disturbance information in real time through K-means clustering, calculating the weighted compensation amount of the prediction error based on the thermal system dynamic response prediction model and the disturbance influence factor, adding the compensation amount to the control parameter, correcting the prediction error through the feedback correction mechanism, and obtaining the corrected control parameter; Step S3: using a rolling optimization algorithm to dynamically adjust the corrected control parameters of the boiler and the steam turbine in real time, combining a working condition-rule mapping update mechanism and a water quality prediction model self-adaptive fuzzy control strategy to automatically adjust the set value of the feedwater flow, and obtaining the best efficiency of the stable operation of the boiler; Step S4: updating the coal yard inventory through unattended and real-time coal inventory updating and visual monitoring, setting an automatic repair mechanism, an automatic start-stop mechanism and an alarm mechanism, triggering the alarm mechanism immediately if an abnormality or failure is found, and automatically adjusting the start-stop state of the boiler and the steam turbine for repair; Step S5: monitoring the carbon emission of the boiler and the steam turbine in real time, formulating an optimal control strategy according to the carbon emission, evaluating the energy use of the boiler and the steam turbine regularly, identifying the energy saving potential according to the evaluation results, and formulating energy saving measures.

[0043] Embodiment 4 An electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the intelligent coordinated control method based on the double-reheat unit when executing the computer program.

[0044] The embodiments of the present application are described above with reference to the drawings, but the present application is not limited to the specific embodiments described above, and the specific embodiments described above are only illustrative, not limiting, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments without departing from the purpose of the present application and the scope protected by the claims, which are all within the protection of the present application.

Claims

1. An intelligent coordinated control system for a double-reheat unit, comprising: The intelligent control module, the coordination control module and the auxiliary control module; The intelligent control module comprises a predictive control unit and an intelligent feedforward unit; the predictive control unit is configured with a multivariable predictive control strategy, which is used to predict the real-time operation state of the boiler and the steam turbine by using a pre-constructed mechanism-data dual-driven thermal system dynamic response prediction model according to historical data, real-time operation data and physical mechanism of the thermal system; the mechanism-data dual-driven thermal system dynamic response prediction model is constructed based on an ST-Attention-LSTM model; the intelligent feedforward unit is configured with an intelligent feedforward control strategy; The intelligent feedforward control strategy is used to correct the prediction results by K-means clustering; The coordination control module comprises a boiler main control unit and a steam turbine main control unit; the boiler main control unit dynamically adjusts the valve opening degree and the boiler combustion rate to match the energy of the boiler with the output energy of the steam turbine by receiving the load instruction; and the steam turbine main control unit is used to receive the load instruction and adjust the steam admission amount, the rotating speed and the power of the steam turbine according to the received load instruction; The auxiliary control module comprises a feedwater control unit; the feedwater control unit is configured with an adaptive fuzzy control strategy; the adaptive fuzzy control strategy is used to automatically call or correct the fuzzy control rule base according to a preset working condition-rule mapping update mechanism, combine a pre-constructed water quality prediction model to obtain the water quality change trend in advance, convert the fuzzy set into a control amount by the barycentric method, and automatically adjust the set value of the feedwater flow; and the water quality prediction model is configured based on a GRU network.

2. The intelligent coordinated control system based on double-reheat unit as claimed in claim 1, wherein, The predictive control unit adopts the multivariable predictive control strategy, and the specific steps comprise: A1: Collecting the operation data of the boiler and the steam turbine in real time through sensors , pre-processing the collected operation data, wherein, represents the k th operation data, k represents the number of the collected operation data; the operation data includes the secondary reheat steam temperature, the pressure, the fuel flow, the feed water flow, the steam turbine admission, and the rotating speed; A2: combined with the physical mechanism of the thermal system, the input features of the ST-Attention-LSTM model are determined, the weights and thresholds of the ST-Attention-LSTM model are initialized, the ST-Attention-LSTM model is trained by using the preprocessed operation data, and the mechanism-data dual-driven thermal system dynamic response prediction model is obtained; A3: set a sampling time T, based on a mechanism-data double-driven dynamic response prediction model of a thermal system, according to the running data at the current time, through the implicit layer calculation of the mechanism-data double-driven dynamic response prediction model of the thermal system, the predicted results of the running states of the boiler and the steam turbine in the next sampling time T of the output layer are obtained wherein, represents the k th predicted running data; A4: set the initial values of the control parameters of the boiler and the steam turbine, set the objective function, the operation constraint condition and the initial parameters of the rolling optimization algorithm, calculate the objective function value according to the prediction result, and check whether the objective function value meets the operation constraint condition, if not, adjust the control parameters of the boiler and the steam turbine using the rolling optimization algorithm, and roll the time window forward by one sampling time, repeat step A4 to obtain new control parameters .

3. The intelligent coordinated control system based on double-reheat unit as claimed in claim 2, wherein, The training steps of the ST-Attention-LSTM model comprise: A2.1: the preprocessed operation data is divided into a training set, a validation set and a test set according to a ratio of 7:2:1, and the operation data dimensions include a time series dimension and a feature dimension; A2.2: the attention layer weight, the LSTM layer weight and the threshold of the model are initialized, and the input of the attention layer is the hidden state of the LSTM layer; A2.3: the mean square error of the model prediction value and the actual operation data is used as the loss function, and the ST-Attention-LSTM model is trained by using the Adam optimizer; A2.4: the generalization ability of the ST-Attention-LSTM model is evaluated by using the test set, if the mean square error exceeds the set threshold, the network structure of the ST-Attention-LSTM model is adjusted again until the accuracy requirement is met.

4. The intelligent coordinated control system for a double reheat based unit as claimed in claim 3 wherein, The logic of the target function in A4 is: the target function value comprehensively reflects the optimization goals of three dimensions of boiler fuel cost, matching degree of boiler output power and demand power, and system operation efficiency, and the importance of the three dimensions is adjusted by weight factors, wherein the boiler fuel cost is determined by the fuel flow, the matching degree of the boiler output power and the demand power is determined by the difference between the two, and the system operation efficiency is calculated from the real-time operation parameters of the unit.

5. The intelligent coordinated control system based on double-reheat unit as claimed in claim 4, wherein, The intelligent feedforward unit adopts an intelligent feedforward control strategy, and the specific steps include: B1: Real-time monitoring of disturbance information of the system through sensors ; the disturbance information includes fuel heat value fluctuation, power grid load impact, water quality hardness change, equipment fault early warning signal, wherein, l represents the number of disturbance information, represents the first l disturbance information; B2: using K-means clustering to classify the disturbance information in real time, and according to the classified disturbance information and the prediction result of the mechanism-data double-driven thermal system dynamic response prediction model, the prediction error of the original control parameter is obtained, and the compensation amount of the prediction error is calculated using the intelligent feedforward control algorithm, the formula is: wherein, represents the prediction error of the compensation amount, represents the feedforward control function; B3: set the error threshold to H, and the resulting compensation amount is added to the original control parameter to obtain the control parameter with the added compensation amount ; If then adjust the output variable according to the prediction result; If , the control parameters are adjusted using a rolling optimization algorithm, and the prediction results are corrected using a feedback correction control algorithm based on real-time operating state data to obtain corrected prediction values , wherein represents t the corrected prediction value of the i th output variable at the t th moment i . B4: based on the corrected prediction result, the control parameters are re-adjusted; B5: repeat B1 to B4 until the system reaches a stable state, and after feedback correction, the corrected control parameters are obtained and used to drive the operation of the boiler and the steam turbine.

6. The intelligent coordinated control system based on double reheat unit as claimed in claim 5 wherein, The logic of the feedback correction control algorithm in B3 is: t The corrected predicted value of the i th output variable at time t is equal to the original predicted value of the output variable plus the sum of the product of the feedback correction coefficient of the output variable and the corresponding prediction error, and the additional correction term determined according to the real-time working condition of the system, wherein the feedback correction coefficient is obtained by training the historical prediction error and actual deviation data, and the additional correction term is used to compensate for the deviation not covered by the model under extreme working conditions.

7. The intelligent coordinated control system based on double reheat unit as claimed in claim 6 wherein, The feedwater control unit adopts an adaptive fuzzy control strategy, and the specific steps include: C1: set the feedwater flow domain, divide the low, moderate and high fuzzy sets in the feedwater flow domain, and configure a triangular membership function for each fuzzy set, wherein the vertex position of the membership function is calibrated according to the historical optimal feedwater flow data, and the feedwater flow domain is determined according to the rated evaporation capacity of the boiler; C2: Corrected predicted values Mapping onto the configured triangular membership function, calculate the membership value of the corrected predicted value belonging to each fuzzy set; C3: according to the system requirements, a fuzzy control rule library is formulated, the membership value in C2 is combined, the fuzzy control rule in the fuzzy control rule library is used to calculate the output fuzzy set, i.e. to determine the fuzzy interval to which the feedwater flow should belong; the system requirements include water quality standard, steam temperature stable range and unit load response speed.

8. The intelligent coordinated control system for a double reheat based unit as claimed in claim 7 wherein, The feedwater control unit adopts an adaptive fuzzy control strategy, and the specific steps further include: C4: introduce a working condition-rule mapping update mechanism to identify the current working condition of the unit in real time, automatically call the corresponding fuzzy control rule from the fuzzy control rule library in C3 according to the working condition type, and if there is no matching fuzzy control rule for the current working condition, correct the existing fuzzy control rule parameters based on the control effect of the similar historical working condition; C5: call the pre-constructed water quality prediction model to obtain the water quality change trend in a preset time period; C6: the barycentric method is used to convert the output fuzzy set into a control quantity, and the conversion logic is: the control quantity is equal to the sum of the product of each predicted value in the fuzzy set and its membership value, divided by the sum of all membership values, and then multiplied by a weight factor; the control quantity is used to adjust the set value of the feedwater flow; the weight factor is dynamically adjusted according to the water quality change trend output by the water quality prediction model; C7: apply the obtained control quantity to the feedwater system, monitor the response of the system to the control quantity, collect the actual feedwater flow data in real time, compare the actual feedwater flow data with the corrected predicted value, calculate the error and error change rate, and use the error and error change rate to automatically adjust the vertex position of the membership function, the fuzzy control rule library and the weight factor.

9. An intelligent coordinated control method based on a double-reheat unit, which is implemented based on the intelligent coordinated control system based on a double-reheat unit in any one of claims 1-8, characterized in that, ​ Step S1: Collect the operation data of the boiler and the steam turbine in real time through the sensor, pretreat the collected operation data, combine the physical mechanism of the thermal system and the ST-Attention-LSTM model, construct a mechanism-data double-driven dynamic response prediction model of the thermal system, and use the mechanism-data double-driven dynamic response prediction model of the thermal system to perform multivariate prediction on the operation state of the boiler and the steam turbine, set the initial value of the control parameter of the boiler and the steam turbine according to the multivariate prediction result; Step S2: Set the operation constraint condition of the boiler and the steam turbine, monitor and classify the system disturbance information in real time through K-means clustering, calculate the weighted compensation amount of the prediction error based on the dynamic response prediction model of the thermal system and the disturbance influence factor, add the compensation amount to the control parameter, correct the prediction error through the feedback correction mechanism, and obtain the corrected control parameter; Step S3: Use a rolling optimization algorithm to dynamically adjust the control parameter of the boiler and the steam turbine in real time, combine the working condition-rule mapping update mechanism and the water quality prediction model, use an adaptive fuzzy control strategy to automatically adjust the set value of the feed water flow, and obtain the best efficiency of the stable operation of the boiler; Step S4: Update the coal yard inventory through unattended and real-time coal inventory methods and visually monitor, set an automatic repair mechanism, an automatic start-stop mechanism and an alarm mechanism, if an abnormality or a fault is found, immediately trigger the alarm mechanism and automatically adjust the start-stop state of the boiler and the steam turbine for repair; Step S5: Real-time monitor the carbon emission of the boiler and the steam turbine, and develop an optimal control strategy according to the carbon emission, evaluate the energy use of the boiler and the steam turbine regularly, identify the energy saving potential according to the evaluation result, and develop energy saving measures.

10. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the steps of the intelligent coordination control method of the double-reheat unit in claim 9.

Images