Real-time optimization method and system for sliding pressure operation of turboset

Abstract

The invention belongs to the technical field of turboset operation management, and particularly relates to a turboset sliding pressure operation real-time optimization method and system, and the system comprises a sensor integration module, a heat rate prediction module, an optimization algorithm module, a dynamic optimization module and a supervision control end. The heat rate prediction module calculates and predicts the heat rate of the turboset based on the operation data of the turboset, the optimization algorithm module searches the optimal main steam pressure by using the GSA algorithm, and the dynamic optimization module dynamically optimizes the sliding pressure operation of the turboset based on the optimal main steam pressure. Real-time optimization of sliding pressure operation of the steam turbine set is achieved, all sensors on the steam turbine set are monitored through the collecting, monitoring and evaluating module so as to judge the collecting operation performance of the sensor integration module, and when a collecting qualified signal is generated, the parameter maintaining performance of the steam turbine set is evaluated and analyzed; and the operation effect of the turboset is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of operation management of steam turbine units, and specifically to a real-time optimization method and system for sliding pressure operation of steam turbine units. Background Art

[0002] A steam turbine unit refers to a rotary power machine that efficiently converts steam thermal energy into mechanical energy, and is known as the heart of a power plant. Its core function is to drive a generator to generate electricity or directly drive mechanical equipment such as pumps, fans, compressors, and ship propellers through the expansion work of steam in the steam turbine. At the same time, the exhaust steam or intermediate extraction steam can be used to meet the heating demand;

[0003] In a Chinese invention patent with the publication number CN110765627A, an intelligent operation optimization system and method for steam turbine units of thermal power enterprises based on big data are disclosed. The technical solution of this invention solves the general intelligent optimization model of steam turbine units through a queuing competition algorithm, obtains the optimized values of the steam inlet volume, power generation volume, extraction steam volume, and exhaust steam volume of the steam turbine unit, and then regulates the system to achieve the operation optimization of the thermal power load distribution of the steam turbine unit, achieving the effect of system energy conservation, and there is no need to transform equipment to reduce costs;

[0004] However, in the actual application process of the above invention technical solution, it is impossible to accurately judge the risk status of data collection on the basis of realizing the comprehensive monitoring and reasonable optimization of the steam turbine unit, and it is difficult to accurately evaluate the parameter maintenance control performance of the steam turbine unit when judging that the data collection performance is poor, which is not conducive to ensuring the safe, stable and energy-saving operation of the steam turbine unit, and increases the operation supervision difficulty of the steam turbine unit;

[0005] In view of the above technical defects, a solution is proposed now. Summary of the Invention

[0006] The purpose of the present invention is to provide a real-time optimization method and system for sliding pressure operation of steam turbine units, which solves the problems that the prior art cannot accurately judge the risk status of data collection on the basis of realizing the comprehensive monitoring and reasonable optimization of the steam turbine unit, and it is difficult to accurately evaluate the parameter maintenance control performance of the steam turbine unit when judging that the data collection performance is poor, which is not conducive to ensuring the safe, stable and energy-saving operation of the steam turbine unit, and the operation supervision of the steam turbine unit is difficult and the intelligent level is low.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A real-time optimization system for sliding pressure operation of a steam turbine unit, including a sensor integration module, a heat rate prediction module, an optimization algorithm module, a dynamic optimization module, and a supervision and control terminal; the sensor integration module collects various operation data of the steam turbine unit in real time through several high-precision sensors installed at key parts of the steam turbine unit, including main steam pressure, temperature, flow rate, rotational speed, back pressure, and extraction steam volume, sets the data collection frequency to ten times per second, and performs filtering, noise reduction, and outlier processing on the collected data, and sends the processed operation data to the heat rate prediction module;

[0009] The heat rate prediction module calculates the heat rate of the steam turbine unit based on the operation data of the steam turbine unit and through the heat rate calculation formula, predicts the heat rate using the LS-SVM algorithm, and sends the predicted heat rate to the optimization algorithm module; the optimization algorithm module takes the predicted heat rate as the objective function within the feasible main steam pressure range, uses the GSA algorithm to search for the optimal main steam pressure, and sends the optimal main steam pressure to the dynamic optimization module and the supervision and control terminal; the dynamic optimization module performs dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure, and sends the optimization information to the supervision and control terminal.

[0010] Furthermore, the heat rate calculation formula is as follows:

[0011] ;

[0012] In the formula, HRt represents the predicted heat rate; Fthr represents the main steam flow rate; Hthr represents the main steam enthalpy value; Fhrh represents the hot reheat steam flow rate; Hhrh represents the enthalpy value of the reheat hot section steam; Fffw represents the feed water flow rate; Hffw represents the boiler feed water enthalpy value; Fcrh represents the cold reheat steam flow rate; Hcrh represents the enthalpy value of the reheat cold section; Frhs represents the reheat desuperheating water flow rate; Hrhs represents the enthalpy value of the reheat desuperheating water; Wc represents the generator power corrected for the secondary pressure drop.

[0013] Furthermore, the sensor integration module is communicatively connected to the acquisition monitoring and evaluation module. The acquisition monitoring and evaluation module monitors all the sensors on the steam turbine unit, marks the corresponding sensors as monitoring object i, and i is a natural number greater than 1; through acquisition anomaly evaluation and analysis, monitoring object i is marked as an obstacle object or a normal object. If there is an obstacle object within a unit time, an acquisition alarm signal is generated;

[0014] If there is no obstacle object within a unit time, an acquisition alarm signal or an acquisition qualified signal is generated through sensor cooperation decision analysis, and the acquisition alarm signal or the acquisition qualified signal is sent to the supervision and control terminal. When the supervision and control terminal receives the acquisition alarm signal, it issues a warning.

[0015] Furthermore, the specific analysis process of the acquisition anomaly evaluation and analysis is as follows:

[0016] Obtain the operation data collected by the monitoring object i. If the corresponding operation data is not within the normal collection value range of the monitoring object i, then define the corresponding operation data as error data; count the number of times of collection of error data corresponding to the monitoring object i within a unit time and mark it as the miscollection detection value. Compare the miscollection detection value with the preset miscollection detection threshold. If the miscollection detection value exceeds the preset miscollection detection threshold, then mark the monitoring object i as an obstacle object.

[0017] Furthermore, if the miscollection detection value does not exceed the preset miscollection detection threshold, then obtain the time when the monitoring object i performs data collection and mark it as the actual collection time. Mark the deviation duration of the actual collection time compared to the corresponding standard collection time as the obstruction measurement duration; obtain all the obstruction measurement durations corresponding to the monitoring object i within a unit time and calculate their average value. Based on this, obtain the obstruction measurement time table value, and compare the obstruction measurement duration with the preset obstruction measurement duration threshold, and mark the number of obstruction measurement durations exceeding the preset obstruction measurement duration threshold within a unit time as the obstruction measurement time anomaly value;

[0018] Calculate the weighted sum of the miscollection detection value, the obstruction measurement time table value, and the obstruction measurement time anomaly value of the monitoring object i to obtain the collection anomaly evaluation value. Compare the collection anomaly evaluation value with the preset collection anomaly evaluation threshold. If the collection anomaly evaluation value exceeds the preset collection anomaly evaluation threshold, then mark the monitoring object i as an obstacle object; if the collection anomaly evaluation value does not exceed the preset collection anomaly evaluation threshold, then mark the monitoring object i as a normal object.

[0019] Furthermore, the specific analysis process of the sensor cooperating with decision analysis is as follows:

[0020] Obtain the collection anomaly evaluation values of all sensors. Mark the average value of all collection anomaly evaluation values as the cooperation preliminary evaluation value. Compare the cooperation preliminary evaluation value with the preset cooperation preliminary evaluation threshold. If the cooperation preliminary evaluation value exceeds the preset cooperation preliminary evaluation threshold, then generate a collection alarm signal;

[0021] If the cooperation preliminary evaluation value does not exceed the preset cooperation preliminary evaluation threshold, then define the corresponding standard collection time as the target time. If the operation data collected by the monitoring object i at the corresponding target time is error data or the obstruction measurement duration exceeds the preset obstruction measurement duration threshold, then assign the collection judgment symbol TX-1 to the monitoring object i;

[0022] If there is a sensor assigned the collection judgment symbol TX-1 at the corresponding target time, then mark the corresponding target time as the alarm time, and mark the ratio of the number of alarm times within a unit time as the collection alarm value. Compare the collection alarm value with the preset collection alarm threshold. If the collection alarm value exceeds the preset collection alarm threshold, then generate a collection alarm signal; if the collection alarm value does not exceed the preset collection alarm threshold, then generate a collection qualified signal.

[0023] Further, the acquisition monitoring and evaluation module is communicatively connected to the maintenance detection and evaluation module. The acquisition monitoring and evaluation module sends a qualified acquisition signal to the maintenance detection and evaluation module. When the maintenance detection and evaluation module receives the qualified acquisition signal, it conducts a turbine unit maintenance performance evaluation and analysis to generate a qualified maintenance signal or a maintenance anomaly signal, and sends the qualified maintenance signal or the maintenance anomaly signal to the supervision and control terminal. When the supervision and control terminal receives the maintenance anomaly signal, it issues a warning.

[0024] Further, the specific analysis process of the turbine unit maintenance performance evaluation and analysis includes:

[0025] Obtain the operating parameters that need to be monitored during the operation of the turbine unit, mark the corresponding operating parameters as matching parameter k, and k is a natural number greater than 1; obtain the real-time data of the matching parameter k. When the deviation value of the real-time data from the corresponding data standard value exceeds the corresponding preset deviation threshold, it is determined that the matching parameter k is in a maintenance risk state;

[0026] Obtain the occurrence times and the occurrence duration each time of the matching parameter k being in the maintenance risk state within a unit time, and define them as the maintenance risk frequency value and the maintenance risk time value respectively. Compare the maintenance risk frequency value and the maintenance risk time value with the corresponding preset maintenance risk frequency threshold and preset maintenance risk time threshold respectively. If the maintenance risk frequency value or the maintenance risk time value exceeds the corresponding preset threshold, mark the matching parameter k as a maintenance damage parameter;

[0027] If both the maintenance risk frequency value and the maintenance risk time value do not exceed the corresponding preset thresholds, mark the maximum deviation value of the real-time data of the matching parameter k from the corresponding data standard value within a unit time as the maintenance deviation amplitude value. Calculate the weighted sum of the maintenance deviation amplitude value, the maintenance risk frequency value, and the maintenance risk time value of the matching parameter k to obtain the maintenance anomaly characteristic value. Compare the maintenance anomaly characteristic value with the preset maintenance anomaly characteristic threshold. If the maintenance anomaly characteristic value exceeds the preset maintenance anomaly characteristic threshold, mark the matching parameter k as a maintenance damage parameter; If there is a maintenance damage parameter within a unit time, generate a maintenance anomaly signal.

[0028] Further, if there is no maintenance damage parameter within a unit time, retrieve the preset maintenance importance weight value of the matching parameter k. Mark the ratio of the maintenance anomaly characteristic value of the matching parameter k to the corresponding preset maintenance anomaly characteristic threshold as the maintenance anomaly detection ratio value. Multiply the maintenance anomaly detection ratio value of the matching parameter k by the corresponding preset maintenance importance weight value, and mark the product result as the maintenance risk judgment value;

[0029] Obtain the maintenance risk judgment values of all operating parameters to be monitored, sum up all the maintenance risk judgment values, and accordingly obtain the maintenance risk assessment value. Compare the maintenance risk assessment value with the preset maintenance risk assessment threshold. If the maintenance risk assessment value exceeds the preset maintenance risk assessment threshold, generate a maintenance anomaly signal; if the maintenance risk assessment value does not exceed the preset maintenance risk assessment threshold, generate a maintenance qualified signal.

[0030] Furthermore, the present invention also proposes a real-time optimization method for the sliding pressure operation of a steam turbine unit, including the following steps:

[0031] Step 1: Collect various operating data of the steam turbine unit, and perform filtering, noise reduction, and outlier processing on the collected data.

[0032] Step 2: Predict the heat rate of the steam turbine unit based on the operating data of the steam turbine unit.

[0033] Step 3: Take the predicted heat rate as the objective function, and use the GSA algorithm to search for the optimal main steam pressure within the feasible main steam pressure range.

[0034] Step 4: Perform dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] 1. In the present invention, through the sensor integration module, various operating data of the steam turbine unit are collected in real time and data processing is performed. The heat rate prediction module calculates and predicts the heat rate of the steam turbine unit based on the operating data of the steam turbine unit. The optimization algorithm module takes the predicted heat rate as the objective function within the feasible main steam pressure range and uses the GSA algorithm to search for the optimal main steam pressure. The dynamic optimization module performs dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure, significantly improving the efficiency of the steam turbine unit, reducing energy consumption, enhancing adaptability, and improving economy and safety.

[0037] 2. In the present invention, the acquisition monitoring and evaluation module monitors all sensors on the steam turbine unit to judge the acquisition operation performance of the sensor integration module. When a collection alarm signal is generated, the operation of the steam turbine unit is paused and the relevant sensors are inspected and repaired. When a collection qualified signal is generated, the maintenance detection and evaluation module evaluates and analyzes the parameter maintenance performance of the steam turbine unit. When a maintenance anomaly signal is generated, the operation of the steam turbine unit is paused and the cause is investigated, which is beneficial to ensuring the operation effect of the steam turbine unit, significantly reducing the management difficulty of the steam turbine unit, and having a high level of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0039] Figure 1 System block diagram of Embodiment 1 in the present invention;

[0040] Figure 2 System block diagrams of Embodiments 2 and 3 in the present invention;

[0041] Figure 3 Method flowchart of Embodiment 4 in the present invention. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Embodiment 1: As Figure 1 shown, a real-time optimization system for sliding pressure operation of a steam turbine unit proposed by the present invention includes a sensor integration module, a heat rate prediction module, an optimization algorithm module, a dynamic optimization module, and a supervision and control terminal;

[0044] The sensor integration module collects various operation data of the steam turbine unit in real time through several high-precision sensors installed at key parts of the steam turbine unit, including main steam pressure, temperature, flow rate, rotational speed, back pressure, extraction steam volume, etc. Preferably, the data collection frequency is set to ten times per second; and the collected data is filtered, denoised, and processed for outliers to improve the data quality, and the processed operation data is sent to the heat rate prediction module;

[0045] The heat rate prediction module calculates the heat rate of the steam turbine unit based on the operation data of the steam turbine unit and through the heat rate calculation formula, provides a theoretical basis for the algorithm, ensures the physical rationality of the prediction result, and uses the LS-SVM algorithm to predict the heat rate, and sends the predicted heat rate to the optimization algorithm module, thereby providing information support for the analysis process of the optimization algorithm module; the heat rate calculation formula is as follows:

[0046] ;

[0047] In the formula, HRt represents the predicted heat rate; Fthr represents the main steam flow rate; Hthr represents the main steam enthalpy value; Fhrh represents the hot reheat steam flow rate; Hhrh represents the enthalpy value of the hot reheat section steam; Fffw represents the feed water flow rate; Hffw represents the boiler feed water enthalpy value; Fcrh represents the cold reheat steam flow rate; Hcrh represents the enthalpy value of the cold reheat section; Frhs represents the reheat attemperating water flow rate; Hrhs represents the enthalpy value of the reheat attemperating water; Wc represents the generator power corrected for the secondary pressure drop.

[0048] Within the feasible main steam pressure range, the optimization algorithm module uses the predicted heat rate as the objective function, searches for the optimal main steam pressure using the GSA algorithm, and sends the optimal main steam pressure to the dynamic optimization module and the supervision and control terminal; the dynamic optimization module performs dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure, and sends the optimization information to the supervision and control terminal.

[0049] Through the collaborative work of each module, the present invention can achieve real-time optimization of the sliding pressure operation of the steam turbine unit, improve the efficiency of the steam turbine unit, reduce energy consumption, enhance adaptability, and improve economy and safety.

[0050] Embodiment 2: As Figure 2 shown, the difference between this embodiment and Embodiment 1 is that the sensor integration module is communicatively connected to the acquisition, monitoring and evaluation module. The acquisition, monitoring and evaluation module monitors all the sensors on the steam turbine unit, marks the corresponding sensors as monitoring object i, and i is a natural number greater than 1; through acquisition anomaly evaluation and analysis, monitoring object i is marked as an obstacle object or a normal object. If there is an obstacle object within a unit time, an acquisition alarm signal is generated;

[0051] If there is no obstacle object within a unit time, an acquisition alarm signal or an acquisition qualified signal is generated through the cooperation of the sensors and decision analysis, and the acquisition alarm signal or the acquisition qualified signal is sent to the supervision and control terminal. When the supervision and control terminal receives the acquisition alarm signal, a warning is issued to remind the supervisor to suspend the operation of the steam turbine unit and check and repair the relevant sensors on the steam turbine unit as needed, ensuring the timeliness and accuracy of data acquisition, avoiding affecting the monitoring effect of the steam turbine unit, and being beneficial to ensuring the safe, stable and energy-saving operation of the steam turbine unit; the specific analysis process of the acquisition anomaly evaluation and analysis is as follows:

[0052] Obtain the operation data collected by monitoring object i. If the corresponding operation data is not within the normal acquisition value range of monitoring object i, the corresponding operation data is defined as error data; count the number of times of the error data corresponding to monitoring object i within a unit time and mark it as the wrong acquisition detection value. Compare the wrong acquisition detection value with the preset wrong acquisition detection threshold. If the wrong acquisition detection value exceeds the preset wrong acquisition detection threshold, indicating that the acquisition operation performance of monitoring object i is poor, then monitoring object i is marked as an obstacle object;

[0053] If the sampling error detection value does not exceed the preset sampling error detection threshold, the moment of data collection for the monitored object i is obtained and marked as the actual sampling moment, and the deviation duration of the actual sampling moment from the corresponding standard sampling moment is marked as the blocking measurement duration; all the blocking measurement durations corresponding to the monitored object i within a unit time are obtained and their mean value is calculated, thereby obtaining the blocking measurement table value, and the blocking measurement duration is numerically compared with the preset blocking measurement duration threshold, and the number of blocking measurement durations exceeding the preset blocking measurement duration threshold within a unit time is marked as the blocking measurement anomaly value;

[0054] The collection anomaly evaluation value is obtained by performing a weighted sum calculation on the sampling error detection value, the blocking measurement table value, and the blocking measurement anomaly value of the monitored object i; that is, corresponding preset weight coefficients are assigned to the sampling error detection value, the blocking measurement table value, and the blocking measurement anomaly value respectively, the sampling error detection value, the blocking measurement table value, and the blocking measurement anomaly value are respectively multiplied by the corresponding preset weight coefficients, and the three groups of product results are summed up, thereby obtaining the collection anomaly evaluation value; moreover, the larger the value of the collection anomaly evaluation value, the worse the comprehensive collection operation performance of the monitored object i;

[0055] The collection anomaly evaluation value is numerically compared with the preset collection anomaly evaluation threshold. If the collection anomaly evaluation value exceeds the preset collection anomaly evaluation threshold, indicating that the comprehensive collection operation performance of the monitored object i is poor, then the monitored object i is marked as an obstacle object; if the collection anomaly evaluation value does not exceed the preset collection anomaly evaluation threshold, indicating that the comprehensive collection operation performance of the monitored object i is good, then the monitored object i is marked as a normal object.

[0056] Furthermore, the specific analysis process of the sensor cooperation decision analysis is as follows: the collection anomaly evaluation values of all sensors are obtained, the average value of all the collection anomaly evaluation values is marked as the cooperation initial evaluation value, and the cooperation initial evaluation value is numerically compared with the preset cooperation initial evaluation threshold. If the cooperation initial evaluation value exceeds the preset cooperation initial evaluation threshold, indicating that the operation status of the sensor integration module is not good, then a collection alarm signal is generated;

[0057] If the cooperation initial evaluation value does not exceed the preset cooperation initial evaluation threshold, then the corresponding standard sampling moment is defined as the target moment. If the operation data collected by the monitored object i at the corresponding target moment is incorrect data or the blocking measurement duration exceeds the preset blocking measurement duration threshold, then the sampling judgment symbol TX-1 is assigned to the monitored object i;

[0058] If there is a sensor assigned with the acquisition judgment symbol TX-1 at the corresponding target time, mark the corresponding target time as the alarm time, and mark the ratio of the number of alarm times within the unit time as the acquisition alarm value. Compare the acquisition alarm value with the preset acquisition alarm threshold. If the acquisition alarm value exceeds the preset acquisition alarm threshold, it indicates that the operating condition of the sensor integration module is poor, and then generate an acquisition alarm signal; if the acquisition alarm value does not exceed the preset acquisition alarm threshold, it indicates that the operating condition of the sensor integration module is good, and then generate an acquisition qualified signal.

[0059] Embodiment 3: As Figure 2 shown, the difference between this embodiment and Embodiment 1 and Embodiment 2 is that the acquisition monitoring and evaluation module is communicatively connected to the maintenance detection and evaluation module. The acquisition monitoring and evaluation module sends the acquisition qualified signal to the maintenance detection and evaluation module. When the maintenance detection and evaluation module receives the acquisition qualified signal, it generates a maintenance qualified signal or a maintenance abnormal signal through the performance evaluation and analysis of the steam turbine unit maintenance;

[0060] And send the maintenance qualified signal or the maintenance abnormal signal to the supervision and control terminal. When the supervision and control terminal receives the maintenance abnormal signal, it issues a warning to remind the supervision personnel to suspend the operation of the steam turbine unit and conduct a cause investigation, and make reasonable countermeasures as needed to ensure the control effect of the operating parameters of the steam turbine unit, which is beneficial to the continuous stability of various operating parameters, further improves the operating effect of the steam turbine unit, and has a high level of intelligence. The specific analysis process of the performance evaluation and analysis of the steam turbine unit maintenance is as follows:

[0061] Obtain the operating parameters that need to be monitored during the operation of the steam turbine unit, mark the corresponding operating parameters as the matching parameter k, and k is a natural number greater than 1; obtain the real-time data of the matching parameter k. When the deviation value of the real-time data from the current corresponding data standard value exceeds the corresponding preset deviation threshold, it is determined that the matching parameter k is in a maintenance risk state;

[0062] Obtain the occurrence times of the matching parameter k in the maintenance risk state within the unit time and the occurrence duration each time, and define them as the maintenance risk frequency value and the maintenance risk time value respectively. Compare the maintenance risk frequency value and the maintenance risk time value with the corresponding preset maintenance risk frequency threshold and preset maintenance risk time threshold respectively. If the maintenance risk frequency value or the maintenance risk time value exceeds the corresponding preset threshold, it indicates that the maintenance performance of the matching parameter k within the unit time is poor, and then mark the matching parameter k as a maintenance damage parameter;

[0063] If both the maintenance risk frequency value and the maintenance risk time value do not exceed the corresponding preset threshold, then mark the maximum deviation value of the real-time data of the matching parameter k from the corresponding data standard value within the unit time as the maintenance deviation amplitude;

[0064] The maintenance deviation amplitude value, maintenance risk frequency value, and maintenance risk time value of the matching parameter k are weighted and summed to calculate the deviation feature value. That is, corresponding preset weight coefficients are assigned to the maintenance deviation amplitude value, maintenance risk frequency value, and maintenance risk time value respectively. The maintenance deviation amplitude value, maintenance risk frequency value, and maintenance risk time value are multiplied by the corresponding preset weight coefficients respectively, and the three groups of product results are summed to obtain the deviation feature value accordingly. Moreover, the larger the value of the deviation feature value, the worse the control condition for the matching parameter k, and the worse the comprehensive maintenance performance of the matching parameter k per unit time.

[0065] The deviation feature value is numerically compared with the preset deviation feature threshold. If the deviation feature value exceeds the preset deviation feature threshold, it indicates that the control condition for the matching parameter k is poor, and the comprehensive maintenance performance of the matching parameter k per unit time is poor. Then, the matching parameter k is marked as a maintenance damage-causing parameter. If there is a maintenance damage-causing parameter within a unit time, it indicates that the parameter maintenance risk of the steam turbine unit is relatively high, and the operation control condition of the steam turbine unit is poor. Then, a maintenance anomaly signal is generated.

[0066] Furthermore, if there is no maintenance damage-causing parameter within a unit time, the preset maintenance importance weight value of the matching parameter k is retrieved. Among them, the values of the preset maintenance importance weight values are all positive numbers, and the more important the stable maintenance of the corresponding operating parameter is, the larger the value of the corresponding preset maintenance importance weight value is. The ratio of the deviation feature value of the matching parameter k to the corresponding preset deviation feature threshold is marked as the deviation detection ratio, and the deviation detection ratio of the matching parameter k is multiplied by the corresponding preset maintenance importance weight value, and the product result is marked as the maintenance risk judgment value.

[0067] The maintenance risk judgment values of all operating parameters to be monitored are obtained, and the sum of all maintenance risk judgment values is calculated to obtain the maintenance risk assessment value. The maintenance risk assessment value is numerically compared with the preset maintenance risk assessment threshold. If the maintenance risk assessment value exceeds the preset maintenance risk assessment threshold, it indicates that the parameter maintenance risk of the steam turbine unit is relatively high comprehensively. Then, a maintenance anomaly signal is generated. If the maintenance risk assessment value does not exceed the preset maintenance risk assessment threshold, it indicates that the parameter maintenance risk of the steam turbine unit is relatively low comprehensively, and the operation control condition of the steam turbine unit is better. Then, a maintenance qualified signal is generated.

[0068] Embodiment 4: As Figure 3 shown, the difference between this embodiment and Embodiment 1, Embodiment 2, and Embodiment 3 is that a real-time optimization method for sliding pressure operation of a steam turbine unit proposed by the present invention includes the following steps:

[0069] Step 1: Collect various operating data of the steam turbine unit, and perform filtering, denoising, and outlier processing on the collected data.

[0070] Step 2: Predict the heat rate of the steam turbine unit based on the operation data of the steam turbine unit;

[0071] Step 3: Take the predicted heat rate as the objective function and use the GSA algorithm to search for the optimal main steam pressure;

[0072] Step 4: Conduct dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure.

[0073] The working principle of the present invention: When in use, various operation data of the steam turbine unit are collected in real time through the sensor integration module and data processing is carried out. The heat rate prediction module calculates and predicts the heat rate of the steam turbine unit based on the operation data of the steam turbine unit. The optimization algorithm module takes the predicted heat rate as the objective function within the feasible main steam pressure range and uses the GSA algorithm to search for the optimal main steam pressure. The dynamic optimization module conducts dynamic optimization of the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure, realizing real-time optimization of the sliding pressure operation of the steam turbine unit, improving the efficiency of the steam turbine unit, reducing energy consumption, enhancing adaptability, promoting economy and safety. Moreover, all sensors on the steam turbine unit are monitored through the acquisition monitoring and evaluation module to judge the acquisition operation performance of the sensor integration module. When an acquisition alarm signal is generated, the operation of the steam turbine unit is paused and the relevant sensors are inspected and repaired. When an acquisition qualified signal is generated, the parameter maintenance performance of the steam turbine unit is evaluated and analyzed through the maintenance detection and evaluation module. When a maintenance abnormal signal is generated, the operation of the steam turbine unit is paused and the cause is investigated, which is beneficial to ensuring the operation effect of the steam turbine unit and has a high level of intelligence.

[0074] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, according to the content of this specification, many modifications and changes can be made. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the relevant technical field can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A real-time optimization system for sliding pressure operation of a steam turbine unit, characterized in that: It includes a sensor integration module, a heat rate prediction module, an optimization algorithm module, a dynamic optimization module and a supervision control terminal; the sensor integration module collects various operating data of the steam turbine unit in real time, and performs filtering, denoising and outlier processing on the collected data, and sends the processed operating data to the heat rate prediction module; The heat rate prediction module calculates the heat rate of the steam turbine unit based on the operating data of the steam turbine unit through the heat rate calculation formula, and uses the LS-SVM algorithm to predict the heat rate, and sends the predicted heat rate to the optimization algorithm module; the optimization algorithm module uses the GSA algorithm to search for the optimal main steam pressure within the feasible main steam pressure range with the predicted heat rate as the objective function; the dynamic optimization module dynamically optimizes the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure, and sends the optimization information to the supervision and control end.

2. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 1, characterized in that: The heat rate calculation formula is as follows: ; In the formula, HRt represents the predicted heat rate; Fthr represents the main steam flow rate; Hthr represents the main steam enthalpy; Fhrh represents the hot reheat steam flow rate; Hhrh represents the reheat hot section steam enthalpy; Fffw represents the feed water flow rate; Hffw represents the boiler feed water enthalpy; Fcrh represents the cold reheat steam flow rate; Hcrh represents the reheat cold section enthalpy; Frhs represents the reheat desuperheating water flow rate; Hrhs represents the reheat desuperheating water enthalpy; Wc represents the generator power after the secondary pressure drop correction.

3. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 1, characterized in that: The sensor integration module is connected to the data acquisition monitoring and evaluation module through communication. The data acquisition monitoring and evaluation module monitors all sensors on the steam turbine unit and marks the corresponding sensor as a monitoring object i, where i is a natural number greater than 1. The monitored object i is marked as an obstacle object or a normal object through acquisition anomaly assessment and analysis. If an obstacle object exists within a unit time, an acquisition alarm signal is generated; If there is no obstacle object within a unit time, the sensor is used in conjunction with decision analysis to generate a collection alarm signal or a collection qualified signal, and the collection alarm signal or the collection qualified signal is sent to the supervision and control end.

4. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 3, characterized in that: The specific analysis process of the collection anomaly assessment analysis is as follows: the number of erroneous data collections corresponding to the monitoring object i in unit time is counted and marked as the error detection value; if the error detection value exceeds the preset error detection threshold, the monitoring object i is marked as an obstacle object.

5. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 4, characterized in that: If the sampling error detection value does not exceed the preset sampling error detection threshold, the sampling error detection value, the resistance measurement time table value and the resistance measurement time difference value of the monitoring object i are weighted and calculated to obtain the collection difference evaluation value. If the collection difference evaluation value exceeds the preset collection difference evaluation threshold, the monitoring object i is marked as an obstacle object. If the collection abnormal evaluation value does not exceed the preset collection abnormal evaluation threshold, the monitored object i is marked as a normal object.

6. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 3, characterized in that: The specific analysis process of sensor coordination decision analysis is as follows: obtain the collection abnormal evaluation values ​​of all sensors, mark the average value of all collection abnormal evaluation values ​​as the coordination initial evaluation value, and generate a collection alarm signal if the coordination initial evaluation value exceeds the preset coordination initial evaluation threshold; if the coordination initial evaluation value does not exceed the preset coordination initial evaluation threshold, compare the collection alarm value with the preset collection alarm threshold, and generate a collection alarm signal if the collection alarm value exceeds the preset collection alarm threshold; Otherwise, a collection qualified signal is generated.

7. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 3, characterized in that: The acquisition monitoring and evaluation module is communicatively connected to the maintenance detection and evaluation module. The acquisition monitoring and evaluation module sends the acquisition qualified signal to the maintenance detection and evaluation module. When the maintenance detection and evaluation module receives the acquisition qualified signal, it performs maintenance performance evaluation and analysis of the steam turbine unit to generate a maintenance qualified signal or a maintenance abnormality signal, and sends the maintenance qualified signal or the maintenance abnormality signal to the supervision and control end.

8. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 7, characterized in that: The specific analysis process of the steam turbine unit maintenance performance evaluation and analysis includes: The operating parameters that need to be monitored during the operation of the steam turbine unit are obtained, and the corresponding operating parameters are marked as matching parameters k, where k is a natural number greater than 1; if the maintenance risk frequency value or the maintenance risk time value exceeds the corresponding preset threshold, the matching parameter k is marked as the maintenance damage parameter; If the maintenance risk frequency value and the maintenance risk time value do not exceed the corresponding preset threshold value, the maintenance bias value, maintenance risk frequency value and maintenance risk time value of the matching parameter k are weighted and summed to obtain the dimensional anomaly feature value. If the dimensional anomaly feature value exceeds the preset dimensional anomaly feature threshold, the matching parameter k is marked as a maintenance damage parameter; if there is a maintenance damage parameter within a unit time, a maintenance abnormality signal is generated.

9. A real-time optimization system for sliding pressure operation of a steam turbine unit according to claim 8, characterized in that: If there is no maintenance damage parameter within a unit time, all maintenance risk judgment values ​​are summed up and calculated to obtain a maintenance risk assessment value. If the maintenance risk assessment value exceeds a preset maintenance risk assessment threshold, a maintenance abnormality signal is generated; Otherwise a maintain qualified signal is generated.

10. A real-time optimization method for sliding pressure operation of a steam turbine unit, characterized in that: The following steps are involved: Step 1: Collect and process various operating data of the steam turbine unit; Step 2: predict the heat rate of the steam turbine unit; Step 3: Taking the predicted heat rate as the objective function, the GSA algorithm is used to search for the optimal main steam pressure; Step 4: Dynamically optimize the sliding pressure operation of the steam turbine unit based on the optimal main steam pressure.

Images