Integrated thermoelectric enterprise safety management system and method

Abstract

The invention discloses a thermoelectric enterprise safety management system and method based on integration, and relates to the technical field of thermoelectric production safety control. The system performs quantification processing on the collected real-time disturbance data set through a preset coupling algorithm to generate a risk pre-coupling factor representing a multi-source disturbance coupling risk; generating a predicted operation state of a future time node in combination with a current operation state set representing the operation condition of the equipment; the prediction operation state is compared with a preset operation safety threshold value, the safety and stability margin is calculated, an original control target of the unit is dynamically adjusted, and the system generates a prediction error by comparing the prediction operation state with a subsequently collected actual operation state; and the prediction model correction parameters of the prediction model are corrected by using the prediction error, and online adaptive adjustment of the prediction model is realized, so that quantitative evaluation of multiple disturbance coupling effects is realized, and a decision basis is provided for predictive risk prevention and control.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power production safety control, and in particular to an integrated thermal power enterprise safety management system and method. Background Art

[0002] As a key link in energy supply, thermal power companies place paramount importance on the safety and stability of their units. Traditional safety management systems typically rely on threshold monitoring of key operating parameters, often viewing various disturbance sources in isolation. Response mechanisms are often passive, triggering alarms or protective actions only after parameters actually exceed preset safety limits. This lacks foresight and fails to provide operators with sufficient response time, increasing the risk of unplanned downtime. Control strategies are generally rigid. When faced with safety risks, control systems often rigidly switch between ensuring unit safety and meeting grid dispatch instructions, lacking flexible adjustment mechanisms. Control and prediction models are mostly static. Over long-term operation, their dynamic characteristics may drift due to factors such as wear and scaling of unit equipment. Static models struggle to adapt to these changes, resulting in a gradual decline in the accuracy of their predictions and control. Therefore, how to overcome the problems of delayed response, one-sided risk assessment, rigid control strategy and static model of traditional safety management systems, and develop an integrated safety management system that can proactively assess coupling risks, flexibly adjust control objectives and have adaptive capabilities, is a technical challenge that needs to be urgently solved in this field. Summary of the Invention

[0003] The purpose of the present invention is to provide an integrated thermal power enterprise safety management system to solve the problems raised in the above background technology.

[0004] The technical solution of the present invention is: an integrated thermal power enterprise safety management system, comprising: A risk quantification module is configured to collect a real-time disturbance data set, quantify the real-time disturbance data set according to a preset coupling algorithm, and generate a risk pre-coupling factor representing the multi-source disturbance coupling risk; wherein the real-time disturbance data set includes load disturbance data representing changes in grid load and fuel disturbance data representing changes in fuel quality; A horizon prediction module is used to generate a predicted operating state at a future time node based on the risk pre-coupling factor and the current operating state set that currently characterizes the operating status of the equipment according to a prediction model; and to calculate a safety and stability margin based on the comparison of the predicted operating state with a preset operating safety threshold; a dynamic optimization module, configured to dynamically adjust the original control target of the unit according to the safety and stability margin to generate a safety-corrected control target, wherein the safety-corrected control target is used to guide the operation of the equipment under the condition that safety constraints are met; The adaptive correction module is used to generate a prediction error by comparing the predicted operating state with the actual operating state collected subsequently; based on the prediction error, a prediction model correction parameter is generated for correcting the prediction model to achieve online adaptive adjustment of the prediction model.

[0005] Preferably, the risk quantification module is further used to collect a combustion stability index characterizing the furnace combustion condition; and the risk quantification module includes: Determining the load disturbance data as a power grid load dispatch rate; By performing differential calculation on the moisture data of the fuel entering the furnace, the fuel disturbance data representing the change rate of the fuel moisture is generated; The grid load dispatch rate and the fuel moisture change rate are weighted and summed, and normalized according to the combustion stability index to generate the risk pre-coupling factor.

[0006] Preferably, the weight coefficient used for weighting the grid load dispatch rate and the fuel moisture change rate in the coupling algorithm is obtained by performing a multivariate linear regression analysis on historical non-shutdown operation data.

[0007] Preferably, the current operating state set includes the current turbine vibration severity; and the horizon prediction module includes: By using the prediction model, the current steam turbine vibration severity and the risk pre-coupling factor are used as input to generate a predicted vibration severity as the predicted operating state; The predicted vibration severity is subtracted from the turbine vibration interlock protection value serving as the operation safety threshold to calculate the safety stability margin.

[0008] Preferably, the dynamic optimization module includes: Based on the safety and stability margin, a boost rate suppression coefficient is calculated and generated by a preset nonlinear function, wherein when the safety and stability margin is greater than a high threshold, the boost rate suppression coefficient approaches 1; when the safety and stability margin is between the low threshold and the high threshold, the boost rate suppression coefficient continuously changes between 0 and 1; when the safety and stability margin is lower than the low threshold, the boost rate suppression coefficient approaches 0; The original control target is multiplied by the pressure increase rate suppression coefficient to generate the safety-corrected control target.

[0009] Preferably, the original control target is the original dispatching boost target of the power grid, and the safety-corrected control target is the safe boost rate; the dynamic optimization module is also used to generate a dynamic main steam pressure set value for sending to the coordinated control system based on the safe boost rate.

[0010] Preferably, the adaptive correction module includes: subtracting the predicted operating state from the actual operating state to generate the prediction error; Multiplying the prediction error by a preset feedback gain coefficient to generate an adjustment amount for the correction parameter of the prediction model; Online adaptive adjustment is achieved by iteratively updating the correction parameters of the prediction model.

[0011] Preferably, an integrated thermal power enterprise safety management method comprises the following steps: Collecting a real-time disturbance data set, quantifying the real-time disturbance data set according to a preset coupling algorithm, and generating a risk pre-coupling factor representing the multi-source disturbance coupling risk; Based on the risk pre-coupling factor and the current operating state set that currently characterizes the operating status of the equipment, a predicted operating state at a future time node is generated according to a prediction model; based on the predicted operating state and a preset operating safety threshold, a safety and stability margin is calculated; According to the safety and stability margin, the original control target of the unit is dynamically adjusted to generate a safety-corrected control target; By comparing the predicted operating state with the actual operating state collected subsequently, a prediction error is generated; based on the prediction error, a prediction model correction parameter for correcting the prediction model is generated to achieve online adaptive adjustment of the prediction model.

[0012] The present invention provides an integrated thermal power enterprise safety management system and method, which has the following beneficial effects: (1) The system integrates the real-time disturbance data of grid load changes and fuel quality fluctuations from multiple sources, generates risk pre-coupling factors based on the coupling algorithm, and realizes the quantitative evaluation of the coupling effects of multiple disturbances. It shifts the starting point of safety management from post-response to pre-assessment, and provides a decision-making basis for predictive risk prevention and control.

[0013] (2) Based on the risk pre-coupling factor and the current operating status set, the system predicts key parameters such as the turbine vibration intensity at future time nodes, compares them with the operating safety threshold, and calculates the safety stability margin, enabling the system to proactively identify potential risks, quantify the distance between the unit and the safety boundary, and achieve a transition from passive triggering protection to active avoidance.

[0014] (3) Based on the safety and stability margin, the system generates a boost rate suppression coefficient through a nonlinear function, flexibly and smoothly adjusts the original control target, and generates a safety-corrected control target. This can maximize the satisfaction of grid dispatching requirements while ensuring safety constraints, thereby enhancing the unit's operational flexibility and control flexibility under complex working conditions.

[0015] (4) The system continuously compares the predicted operating status with the actual operating status and uses the prediction error to perform online adaptive adjustment on the correction parameters of the prediction model, thus solving the problem that the traditional static model gradually becomes ineffective due to its inability to adapt to unit changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the system of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0018] Example 1 This embodiment provides an integrated thermal power enterprise safety management system. This system, through the synergy of a risk quantification module and a horizon prediction module, enables real-time perception and forward-looking warning of thermal power enterprise operation risks, thereby effectively improving the safety and stability of unit operation. In practical applications, the risk quantification module is used to calculate the load dispatch rate of the power grid. and online data of fuel moisture entering the furnace Real-time collection, combined with the furnace combustion stability index Perform quantitative processing to generate the risk pre-coupling factor F, the calculation formula is: ; in, is the grid load dispatch rate weight coefficient, is the grid load dispatch rate, is the weight coefficient of the fuel moisture change rate, is the moisture change rate of fuel entering the furnace, is the furnace combustion stability index; and It is a weight coefficient obtained by performing a multivariate linear regression analysis on historical non-shutdown operation data, reflecting the relative importance of the impact of grid load disturbance and fuel disturbance on system vibration. It is a dimensionless index that characterizes the stability of the combustion process. The closer its value is to 1, the more stable the combustion state is. When it decreases, the risk brought by fuel moisture changes will be amplified, which is highly consistent with the thermal shock and thermal stress coupling risks caused by unstable combustion in the actual operation of thermal power companies; For example, in scenarios where grid load fluctuates rapidly or fuel quality suddenly drops, the risk quantification module can quickly capture these disturbances and quantify them into a single risk pre-coupling factor, providing a unified risk assessment basis for subsequent prediction and control. This proactive risk assessment enables the system to switch from a reactive post-alarm mode to a proactive pre-assessment mode, reserving valuable time for the crew's response and adjustments. The horizon prediction module receives the risk pre-coupling factor and current turbine vibration intensity Taking the current operating state set as input, the predicted vibration intensity within the future short time horizon is generated according to the preset prediction model. . Predicted vibration intensity The calculation formula is: ; in, is the current turbine vibration intensity, is the prediction time step, is the increment function, is the current main steam pressure, Modify parameters for the prediction model. It is an incremental function fitted by historical data, and its internal key coefficients are modified by the forecast model parameters Perform online dynamic adjustments to reflect real-time changes in unit characteristics and ensure prediction accuracy; The horizon prediction module will predict the vibration intensity Interlock protection value with preset turbine vibration Compare and calculate the safety and stability margin , the calculation formula is: ( is the turbine vibration interlock protection value, To predict the vibration intensity), safety and stability margin Directly quantify the safety distance between the current operation and the triggering of emergency shutdown protection. For example, when the safety stability margin is small, it indicates that the unit's operating status is close to the safety threshold. The system can issue an early warning and trigger the dynamic optimization module to implement intervention; This active avoidance logic based on predictive safety margins allows the system to no longer passively wait for vibration values ​​to approach the interlocking protection boundary. Instead, it proactively predicts future vibration trends and calculates the gap between them and the safety boundary, thus achieving a transition from passive protection response to predictive active protection.

[0019] Example 2 This embodiment further refines the functions of the risk quantification module so that it can generate risk pre-coupling factors more accurately.

[0020] The risk quantification module directly determines the load disturbance data as the grid load dispatch rate , can directly reflect the rapid changes of the power grid's load instructions to the unit. At the same time, by analyzing the moisture data of the fuel entering the furnace Perform differential calculation to generate fuel moisture change rate , which can better characterize the thermal shock intensity of the combustion process caused by the rapid fluctuation of fuel quality than the simple fuel moisture value. For example, when the fuel moisture increases rapidly in a short period of time, The risk quantification module can immediately identify this potential combustion instability risk; The risk quantification module also collects the combustion stability index that characterizes the furnace combustion conditions. , the index is determined by the furnace temperature , furnace pressure and flue gas oxygen content Several key parameters are calculated through weighted models, such as: ( are the weight coefficients corresponding to furnace temperature, furnace pressure and flue gas oxygen content, is the normalization function, is the furnace temperature, is the furnace pressure, is the oxygen content of flue gas, combustion stability index The closer it is to 1, the closer the combustion state is to the ideal stable state); The risk quantification module calculates the grid load dispatch rate and fuel moisture change rate Perform weighted summation according to the combustion stability index Perform normalization to generate risk pre-coupling factors ; This precise risk pre-coupling factor calculation enables the system to more sensitively capture potential thermal shock and thermal stress coupling risks, providing more reliable input for subsequent prediction and control, and effectively avoiding the limitation that a single disturbance indicator is not sufficient to fully reflect the risks under complex working conditions.

[0021] Example 3 This embodiment further describes a method for determining a weight coefficient for weighting the grid load dispatch rate and the fuel moisture change rate in the coupling algorithm.

[0022] The weight coefficient in the coupling algorithm is determined by collecting historical data of the quasi-steady-state operation of the unit in the past 1 to 2 years, including the grid load dispatch rate , online data of fuel moisture entering the furnace , furnace combustion stability index and the actual vibration intensity of the turbine During the data screening process, data segments related to abnormal operating conditions such as the unit's start-up and shutdown processes, load rejection, overhaul, and major equipment defects are strictly excluded to ensure that the data used for analysis can truly reflect the dynamic response characteristics of the unit within the normal operating boundaries. The data synchronization sampling frequency is usually set to 1 minute / time to capture the effective dynamic process of load and fuel changes; After normalization, the grid load dispatch rate L and the combustion stability index S are used as key factors influencing the fuel moisture change rate. These two parameters (primary independent variables) are fitted with the turbine vibration change (dependent variable). The weight coefficients and calibration process use the statistical method of multivariate linear regression. The goal is to minimize the sum of squared errors between the actual vibration intensity and the model prediction value. The mathematical expression is: ; in, is the power grid load dispatch rate weight coefficient; is the weight coefficient of the moisture change rate of the fuel entering the furnace; is the actual vibration intensity change of the steam turbine caused by the disturbance at the i-th data point; is the grid load dispatch rate of the i-th data point; is the change rate of fuel moisture entering the furnace at the i-th data point; is the furnace combustion stability index of the i-th data point; is the total number of data points; Through this regression analysis, the best fitting coefficient can be obtained and For this particular unit, these two coefficients accurately quantify the contributions of grid load disturbances and fuel moisture disturbances to vibration risk, respectively. This historical data-based calibration method enables the risk quantification module to more accurately assess the risk of multi-source disturbance coupling, avoiding biases caused by subjective experience.

[0023] Example 4 This embodiment further clarifies the input and output of the horizon prediction module and elaborates on the calculation process of the predicted vibration intensity and safety stability margin; The horizon prediction module uses the current turbine vibration intensity and risk pre-coupling factors As the core input, combined with the current main steam pressure and the prediction model correction parameters from the adaptive correction module , through the preset prediction model, predict the vibration intensity in the next 3-5 minutes , the calculation formula is: ; in, is the current turbine vibration intensity; is the prediction time step; is the increment function; is the current main steam pressure; Correcting parameters for prediction models; Increment function is a multivariate nonlinear function, for example it can take the form of a second-order polynomial: ; in, is the incremental function coefficient; the correction parameter of the prediction model is a matrix containing all coefficients The parameter vector of Fine-tuning is performed through the online correction process to ensure the accuracy of the prediction. For example, when the unit operating characteristics drift slightly, the prediction model corrects the parameters Able to automatically adjust to predict vibration intensity Always keep a high degree of consistency with the actual situation; The horizon prediction module calculates the predicted vibration intensity Interlock protection value with turbine vibration Compare and calculate the safety and stability margin , the calculation formula is: ( is the turbine vibration interlock protection value, the turbine vibration interlock protection value; It is a mandatory safety critical value clearly defined in the unit design specifications; To predict the vibration intensity), safety and stability margin Directly quantified as the safety distance between the current operation and the triggering of emergency shutdown protection. For example, when the safety stability margin When the safety margin is high, it indicates that the unit is running smoothly and has sufficient safety redundancy. When it gradually decreases, it indicates potential risks and the system can take timely intervention measures.

[0024] This precise calculation of predicted vibration intensity and safety stability margin enables thermal power companies to proactively assess unit operating risks and provide a decision-making basis for the dynamic optimization module, thereby achieving precise control of the unit's operating status and proactive safety management.

[0025] Example 5 This embodiment describes in detail how the dynamic optimization module dynamically adjusts the original control target of the unit according to the safety and stability margin.

[0026] The dynamic optimization module is used to calculate and generate a boost rate suppression coefficient based on the safety and stability margin through a preset nonlinear function, wherein when the safety and stability margin is greater than the upper threshold, the boost rate suppression coefficient approaches 1; when the safety and stability margin is between the lower threshold and the upper threshold, the boost rate suppression coefficient continuously changes between 0 and 1; when the safety and stability margin is lower than the lower threshold, the boost rate suppression coefficient approaches 0; the original control target is multiplied by the boost rate suppression coefficient to generate a safety-corrected control target; Dynamic optimization module receives safety and stability margin As input, the preset Sigmoid nonlinear function is used to calculate the boost rate suppression coefficient , the calculation formula is: ; in, is the pressure rise rate suppression coefficient; is the parameter for the steepness of the suppression curve; is the safety and stability margin; is the response threshold, parameter and Determining the steepness and response threshold of the suppression curve has clear engineering significance and is easy to adjust online. Its initial value can be statistically analyzed based on the safety margin distribution before the protection action is triggered in the unit's historical operating data to ensure that the suppression curve takes effect smoothly within a reasonable safety margin range. For example, when the safety margin When it is larger, the boost rate suppression coefficient When it approaches 1, it indicates that the unit is operating safely and the voltage can be increased according to the original control target. Decrease and fall below the threshold When the boost rate suppression coefficient It quickly approaches 0, thus strongly suppressing the boost rate; when the safety and stability margin M is between the high threshold and the low threshold, the boost rate suppression coefficient I smoothly transitions between 0 and 1. This middle ground is the key to achieving flexible control, which ensures that the control adjustment is a continuous and smooth process rather than an abrupt step. Specifically, the response threshold It can be regarded as the center point of the transition area. The system is most sensitive to changes in the safety margin near this point. The high and low thresholds can be understood as defining the main change range of the Sigmoid curve from "basic no inhibition" (I≈1) to "strong inhibition" (I≈0). At the same time, an alarm threshold can be set in the system, which can be set to the same as the response threshold. Equal or set according to safety regulations, when the safety stability margin When the value falls below this alarm threshold, the system will trigger an audible and visual alarm to alert operators; This nonlinear characteristic, through the construction of a risk-level adaptive adjustment mechanism, enables continuous and smooth adjustment of control silence in risk-free states, fine-tuning intervention in low-risk scenarios, and strong suppression control in high-risk conditions. This avoids secondary oscillations that may be caused by traditional rule-based step-type control adjustments, ensuring control flexibility and stability. The dynamic optimization module then converts the original control objective and the calculated pressure rise rate suppression coefficient Multiply them together to generate the safe pressure increase rate as the control target after safety correction , ( To control the target after safety correction, is the original control target; is the boost rate suppression coefficient), the control target after safety correction Used to guide equipment operation under the condition of meeting safety constraints, for example, when the safety stability margin is low, the control target after safety correction will be significantly reduced, thus effectively preventing the unit from entering the dangerous area due to blind pursuit of high load; This nonlinear dynamic flexible control enables thermal power companies to maximize the grid dispatching needs while ensuring the safety of the units, and generate a flexible boost curve that can maximize the grid dispatching needs while ensuring the safety of the units.

[0027] Example 6 This embodiment further clarifies the specific application of the control target after safety correction, and clarifies the safe boost rate. Applied to subsequent control steps.

[0028] In order to achieve refined control of the unit, the dynamic optimization module further optimizes the safety boost rate based on the , generating the dynamic main steam pressure setpoint for sending to the coordinated control system. The calculation formula is: ; in, for Dynamic main steam pressure set value at the moment; for Dynamic main steam pressure set value at the moment; is the safe pressure increase rate; is the time step; Dynamic main steam pressure setpoint The main steam pressure can be adjusted in real time to meet the unit's operating requirements under different safety margins. For example, when the unit vibration risk increases, the dynamic main steam pressure setpoint will be adjusted to slow down the pressure increase rate and effectively suppress vibration deterioration. This mechanism of generating a dynamic main steam pressure set value based on the safe boost rate makes the control of the unit more refined and intelligent, realizes flexible control of the unit operation, and improves the operating efficiency and safety of thermal power enterprises.

[0029] Example 7 This embodiment describes in detail how the adaptive correction module implements online adaptive adjustment of the prediction model by comparing the predicted operating state with the actual operating state acquired subsequently; After each control cycle, the adaptive correction module calculates the predicted vibration intensity output by the horizon prediction module Actual vibration intensity collected in real time by the sensor The prediction error , the formula is: ( is the prediction error; is the actual vibration intensity; To predict vibration intensity); Prediction error Directly reflects the accuracy of the prediction model. For example, when the unit's dynamic characteristics drift due to wear, scaling, etc., the prediction error will gradually increase, indicating that the prediction model needs to be revised; The adaptive correction module is based on the prediction error With learning rate , generate the adjustment amount of the correction parameters of the prediction model, to this end, first define the incremental function The corresponding input feature vector: ; Subsequently, the least mean square algorithm is used to update the correction parameters of the prediction model. The update formula is: ; in, for The prediction model correction parameter vector at the moment; for The prediction model correction parameter vector at the moment; is the learning rate, which is used to control the speed and amplitude of adjustment; for The prediction error at the moment; for The input feature vector at time t; Prediction model correction parameters is the increment function The parameter vector of the model coefficients in , whose initial values It is obtained through offline historical data regression analysis, and the parameters of the prediction model are corrected Iterative updates enable online adaptive adjustment of the prediction model. For example, when the unit's operating environment slowly changes, the adaptive correction module can continuously learn and correct the parameters of its own prediction model to ensure that the prediction model accurately reflects the unit's actual operating status. This adaptive correction closed loop driven by prediction errors can solve the problem of traditional static models gradually becoming ineffective due to their inability to adapt to the drift of unit operating characteristics, and achieve continuous self-update of the entire safety management system.

[0030] Example 8 This embodiment provides an integrated thermal power enterprise safety management method, which includes the following steps: Collect real-time disturbance data sets, quantify them according to a preset coupling algorithm, and generate risk pre-coupling factors that characterize the coupling risk of multi-source disturbances; Based on the risk pre-coupling factor and the current operating status set that characterizes the current equipment operation status, the prediction model is used to generate the predicted operating status at future time nodes. The predicted operating status is compared with the preset operating safety threshold to calculate the safety and stability margin. According to the safety and stability margin, the original control target of the unit is dynamically adjusted to generate the safety-corrected control target; By comparing the predicted operating state with the actual operating state collected subsequently, a prediction error is generated; based on the prediction error, a prediction model correction parameter is generated for correcting the prediction model, thereby realizing online adaptive adjustment of the prediction model.

[0031] This method uses a risk quantification module to collect real-time disturbance data sets and generates risk pre-coupling factors based on a preset coupling algorithm. This step enables the system to proactively identify and quantify the risks of multi-source disturbance coupling, providing a basis for subsequent decision-making. For example, when grid load changes dramatically or fuel quality fluctuates, the system can quickly perceive and quantify these risks, avoiding the one-sided focus on a single disturbance source in traditional methods. The Vision Prediction module uses the risk pre-coupling factor and the current operating state set to generate a predicted vibration severity for future time points using a prediction model. This prediction is then compared with the turbine vibration interlock protection value to calculate the safety and stability margin. This step enables the prediction of the unit's future operating state and the assessment of the safety margin, enabling the system to proactively mitigate potential risks. For example, if the safety and stability margin decreases, the system can provide an early warning, buying time for intervention measures and avoiding downtime caused by excessive vibration. The dynamic optimization module calculates the boost rate suppression coefficient based on the safety and stability margin through a nonlinear function, dynamically adjusts the unit's original control target, and generates a safe boost rate. This step enables flexible adjustment of the unit's control target, balancing safety and economy. For example, when the risk is high, the system will reduce the safe boost rate to ensure the unit's safe operation; when the risk is low, the unit can quickly respond to grid dispatch requirements and improve operating efficiency. The adaptive correction module compares the predicted vibration severity with the actual vibration severity subsequently collected to generate a prediction error. Combined with the feedback gain coefficient, it generates prediction model correction parameters used to revise the prediction model, enabling online adaptive adjustment of the prediction model. This step ensures the long-term accuracy of the prediction model and its adaptability to changes in unit characteristics. For example, when unit operating characteristics drift, the adaptive correction module can automatically correct the prediction model, ensuring that the system continues to provide accurate risk assessments and control instructions. Through the coordinated execution of the above steps, the integrated thermal power enterprise safety management method realizes comprehensive, intelligent and proactive management of the operational risks of thermal power enterprises.

[0032] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An integrated thermal power enterprise safety management system, characterized in that: include: A risk quantification module is configured to collect a real-time disturbance data set, quantify the real-time disturbance data set according to a preset coupling algorithm, and generate a risk pre-coupling factor representing the multi-source disturbance coupling risk; wherein the real-time disturbance data set includes load disturbance data representing changes in grid load and fuel disturbance data representing changes in fuel quality; A horizon prediction module is used to generate a predicted operating state at a future time node based on the risk pre-coupling factor and the current operating state set that currently characterizes the operating status of the equipment according to a prediction model; and to calculate a safety and stability margin based on the comparison of the predicted operating state with a preset operating safety threshold; a dynamic optimization module, configured to dynamically adjust the original control target of the unit according to the safety and stability margin to generate a safety-corrected control target, wherein the safety-corrected control target is used to guide the operation of the equipment under the condition that safety constraints are met; The adaptive correction module is used to generate a prediction error by comparing the predicted operating state with the actual operating state collected subsequently; based on the prediction error, a prediction model correction parameter is generated for correcting the prediction model to achieve online adaptive adjustment of the prediction model.

2. The integrated thermal power enterprise safety management system according to claim 1 is characterized in that: The risk quantification module is also used to collect a combustion stability index that characterizes the furnace combustion condition; Furthermore, the risk quantification module includes: Determining the load disturbance data as a power grid load dispatch rate; By performing differential calculation on the moisture data of the fuel entering the furnace, the fuel disturbance data representing the change rate of the fuel moisture is generated; The grid load dispatch rate and the fuel moisture change rate are weighted and summed, and normalized according to the combustion stability index to generate the risk pre-coupling factor.

3. The integrated thermal power enterprise safety management system according to claim 2 is characterized in that: The weight coefficient used for weighting the grid load dispatch rate and the fuel moisture change rate in the coupling algorithm is obtained by performing a multivariate linear regression analysis on historical non-shutdown operation data.

4. The integrated thermal power enterprise safety management system according to claim 1 is characterized in that: The current operating state set includes the current turbine vibration severity; the horizon prediction module includes: By using the prediction model, the current steam turbine vibration severity and the risk pre-coupling factor are used as input to generate a predicted vibration severity as the predicted operating state; The predicted vibration severity is subtracted from the turbine vibration interlock protection value serving as the operation safety threshold to calculate the safety stability margin.

5. The integrated thermal power enterprise safety management system according to claim 1 is characterized in that: The dynamic optimization module includes: Based on the safety and stability margin, a boost rate suppression coefficient is calculated and generated by a preset nonlinear function, wherein when the safety and stability margin is greater than a high threshold, the boost rate suppression coefficient approaches 1; when the safety and stability margin is between the low threshold and the high threshold, the boost rate suppression coefficient continuously changes between 0 and 1; when the safety and stability margin is lower than the low threshold, the boost rate suppression coefficient approaches 0; The original control target is multiplied by the pressure increase rate suppression coefficient to generate the safety-corrected control target.

6. The integrated thermal power enterprise safety management system according to claim 5 is characterized in that: The original control target is the original dispatching boost target of the power grid, and the safety-corrected control target is the safe boost rate; the dynamic optimization module is also used to generate a dynamic main steam pressure set value for sending to the coordinated control system based on the safe boost rate.

7. The integrated thermal power enterprise safety management system according to claim 1 is characterized in that: The adaptive correction module includes: subtracting the predicted operating state from the actual operating state to generate the prediction error; Multiplying the prediction error by a preset feedback gain coefficient to generate an adjustment amount for the correction parameter of the prediction model; Online adaptive adjustment is achieved by iteratively updating the correction parameters of the prediction model.

8. An integrated thermal power enterprise safety management method, characterized in that: The method is performed by a system according to any one of claims 1 to 7, comprising the following steps: Collecting a real-time disturbance data set, quantifying the real-time disturbance data set according to a preset coupling algorithm, and generating a risk pre-coupling factor representing the multi-source disturbance coupling risk; Based on the risk pre-coupling factor and the current operating state set that currently characterizes the operating status of the equipment, a predicted operating state at a future time node is generated according to a prediction model; based on the predicted operating state and a preset operating safety threshold, a safety and stability margin is calculated; According to the safety and stability margin, the original control target of the unit is dynamically adjusted to generate a safety-corrected control target; By comparing the predicted operating state with the actual operating state collected subsequently, a prediction error is generated; based on the prediction error, a prediction model correction parameter for correcting the prediction model is generated to achieve online adaptive adjustment of the prediction model.

Images