A control system and method for increasing boiler feed water temperature by using superheated steam

Abstract

The present invention provides a control system and method for increasing boiler feed water temperature by using superheated steam. Through multiple technical units, including a data acquisition unit, a feature extraction unit, an algorithm knowledge base construction unit, a data grouping unit, a model matching unit, an algorithm model application unit, a model deployment unit and a construction monitoring unit, the real-time monitoring and automatic adjustment of the control system for increasing boiler feed water temperature by using superheated steam, adjusting steam pressure, and optimizing boiler operation are performed. The steam inlet pressure of the high-pressure heater is increased by real-time monitoring and automatic adjustment, thereby increasing the feed water temperature at the outlet of the high-pressure heater. The present invention increases the feed water temperature entering the boiler, thereby increasing the flue gas temperature at the inlet of the SCR, which is beneficial to the unit to perform full-load denitration and deep peak regulation.

Description

Technical Field

[0001] The invention relates to the technical field of energy-saving operation control systems for coal-fired boilers, and in particular to a control system and method for increasing boiler feed water temperature by utilizing superheated steam. Background Art

[0002] The control system that uses superheated steam to increase the boiler feed water temperature mainly ensures that the superheated steam temperature generated by the boiler is stable within a certain range through a series of automatic control measures. This can not only improve the operating efficiency of the boiler, but also effectively protect the boiler equipment and prevent equipment damage caused by overheating.

[0003] At present, industrial boiler superheated steam temperature control mostly adopts cascade control. This control system has a high operating frequency and anti-interference ability, and can adaptively meet the requirements of superheated steam temperature control.

[0004] With the development of computer technology and control theory, boiler control systems have achieved a transition from traditional manual operation to microcomputer automatic control. Microcomputer control systems can automatically adjust fuel supply, air volume, water level and other parameters according to preset control strategies to keep the boiler running in the best condition.

[0005] In the process of using superheated steam to increase the boiler feed water temperature, there is a problem that the superheated steam temperature is difficult to control. The superheated steam temperature has the characteristics of large inertia, large delay, time-varying and nonlinearity, making it difficult for the control system to quickly and accurately adjust the steam temperature. Especially in large units, this difficulty is more significant, and conventional control methods often have poor effects. For this reason, a control system and method for increasing the boiler feed water temperature using superheated steam is developed. Summary of the invention

[0006] The purpose of the present invention is to provide a control system and method for increasing the boiler feed water temperature by using superheated steam, so as to solve the problem that the superheated steam temperature has the characteristics of large inertia, large delay, time variation and nonlinearity, making it difficult for the control system to adjust the steam temperature quickly and accurately.

[0007] In a first aspect, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, comprising a device end, a server end, and a background control end;

[0008] The equipment end includes a boiler, a superheater, a desuperheater, a regulating valve, a water supply device, a sensor matrix and an equipment end control device, and the server end establishes a communication connection with the equipment end and the background control end;

[0009] The server receives the control command of the background control end and the actual data of the device end, performs data analysis and processing according to the control command of the background control end and the actual data of the device end, outputs the device end execution command, and transmits the feedback information of the device end execution command to the background control end, and the server includes:

[0010] An acquisition unit is used to acquire historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of the control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of the control system for increasing boiler feed water temperature by using superheated steam includes operation data of boiler, superheater, desuperheater, regulating valve, water supply equipment and sensor matrix;

[0011] A data feature extraction unit performs data preprocessing on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, performs data feature extraction on the preprocessed data, and obtains a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam;

[0012] The algorithm knowledge base construction unit uses a feature selection algorithm to perform data screening on the data feature extraction results of the control system for increasing boiler feed water temperature by using superheated steam, performs weighted processing on the screening results, obtains weighted results of feature data, obtains multiple artificial intelligence algorithm models, constructs an algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, establishes attribute labels for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, and establishes a matching relationship between the weighted results of feature data and the attribute labels;

[0013] A data grouping unit, extracting time information of real-time data of a control system for increasing boiler feed water temperature by using superheated steam, dividing the time information into time periods, obtaining a real-time time period division result, extracting real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result, and obtaining real-time time period grouped hot steam and boiler feed water temperature data;

[0014] The model matching unit performs weighted evaluation on the hot steam and boiler feed water temperature data of the real-time period grouping to obtain the weighted evaluation result of the real-time period grouping data, and matches the feature data in the weighted evaluation result of the real-time period grouping data with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the real-time period data;

[0015] The algorithm model application unit substitutes the real-time period data into the corresponding artificial intelligence algorithm model, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the trained artificial intelligence algorithm model;

[0016] The model deployment unit integrates the trained artificial intelligence algorithm model into a real-time control system for increasing boiler feed water temperature by using superheated steam, and uses the trained artificial intelligence algorithm model to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time predicted values ​​of steam temperature and boiler feed water temperature;

[0017] A monitoring unit is constructed to monitor the operating status information and operating parameters of the steam temperature control system in real time. If the operating status information and operating parameters do not match the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

[0018] In view of the large inertia, large delay, time-varying and nonlinear characteristics of superheated steam temperature, the real-time monitoring and automatic adjustment of the boiler feed water temperature control system are improved by utilizing superheated steam, the steam pressure is adjusted, and the boiler operation is optimized, so as to effectively solve the problems of large inertia, large delay, time-varying and nonlinearity in superheated steam temperature control, thereby achieving the goal of quickly and accurately adjusting the steam temperature.

[0019] Furthermore, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, further comprising: a heating execution unit, the heating execution unit comprising a collection unit and a first data processing unit;

[0020] The data collection unit collects the steam temperature, pressure and flow rate during the operation of the unit. When the steam temperature during the operation of the unit is higher than the preset standard value, the boiler feed water temperature is detected. If the boiler feed water temperature is lower than the preset standard value, the superheated steam is started to increase the boiler feed water temperature control system to heat the water in the boiler.

[0021] The first data processing unit obtains the user's boiler water temperature demand information, and predicts the use of superheated steam to increase the boiler feed water temperature based on the steam temperature during the operation of the unit. If the boiler feed water temperature prediction value is consistent with the user's boiler water temperature demand information, a control command for increasing the boiler feed water temperature by using superheated steam is generated. After receiving the control command for increasing the boiler feed water temperature by using superheated steam, the device executes the control command to heat the water in the boiler by using superheated steam.

[0022] Furthermore, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the algorithm model application unit comprises:

[0023] A time period construction unit is used to establish a data collection time period, and collect the boiler feed water temperature and superheated steam temperature of each time period according to the time information of the data collection time period;

[0024] The information comparison unit compares the collected boiler feed water temperature and superheated steam temperature in each period with the steam temperature and boiler feed water temperature prediction values ​​obtained by the trained artificial intelligence algorithm model in the algorithm optimization unit;

[0025] The first algorithm optimization unit, if the compared numerical error is within the preset error value range, the artificial intelligence algorithm model in the algorithm optimization unit continues to be used; if the compared numerical error is outside the preset error value range, the data of this time period and the corresponding artificial intelligence algorithm are optimized to obtain the optimized artificial intelligence algorithm model.

[0026] Furthermore, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the first algorithm optimization unit further includes:

[0027] The data time segmentation unit divides the steam temperature and boiler feed water temperature prediction curves into sections based on the generation time of the real-time steam temperature and boiler feed water temperature prediction values, and establishes a section sequence of the prediction value curves;

[0028] The second data analysis unit defines the values ​​of two adjacent serial numbers in the segmented sequence of the prediction value curve as a prediction value segment, retrieves the prediction values ​​corresponding to the two adjacent serial numbers in the segmented sequence of the prediction value curve, and generates a segmented prediction value curve by placing the prediction values ​​corresponding to the two adjacent serial numbers in the segmented sequence of the prediction value curve in the model deployment unit, and combines each prediction value segment of the segmented sequence of the prediction value curve to establish a prediction curve for steam temperature and boiler feed water temperature;

[0029] Furthermore, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the second data analysis unit further includes:

[0030] A data retrieval unit retrieves time information of each predicted value in the segmented sequence of the predicted value curve, retrieves corresponding data in real-time data of a control system for increasing boiler feed water temperature by using superheated steam according to the time information of each predicted value in the segmented sequence of the predicted value curve, and obtains real-time data corresponding to the predicted value curve;

[0031] The third data analysis unit generates a real-time segmented curve in the model deployment unit corresponding to the real-time data of the predicted value curve, generates an image of the real-time segmented curve and the steam temperature and boiler feed water temperature predicted curves on a grid under the same coordinate system, and records the coordinates of the connection points between the image and the grid, to obtain the grid coordinates of the real-time segmented curve and the coordinates of the segmented predicted value curve;

[0032] The prediction error warning unit compares the real-time segmented curve grid coordinates with the segmented prediction value curve coordinates. If the coordinate information is inconsistent, a prediction error warning information is generated.

[0033] Furthermore, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the algorithm model application unit comprises:

[0034] The model training unit performs weighted evaluation on the data in the prediction error warning information to obtain the weighted evaluation result of the prediction error warning information, screens out the characteristic data in the weighted evaluation result of the prediction error warning information, and matches it with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the prediction error warning information, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the artificial intelligence algorithm model after the prediction error training;

[0035] The model output unit integrates the artificial intelligence algorithm model after prediction error training into the model deployment unit for use.

[0036] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the heating execution unit comprises:

[0037] After receiving the control command of increasing the boiler feed water temperature by using superheated steam, the equipment end executes the control command and applies it to the following devices. The water in the boiler is heated by using superheated steam, including: main steam, bypass superheated steam, pressure reducing regulating valve, desuperheater, desuperheating water, desuperheating water regulating valve, first stage extraction steam, No. 1 high pressure heater, etc.

[0038] The method comprises extracting part of the steam from the outlet of the medium-temperature superheater arranged in the boiler as bypass superheated steam;

[0039] The bypass superheated steam is reduced in pressure by the pressure reducing regulating valve to become the bypass superheated steam after pressure reduction, and then is reduced in temperature by the desuperheater to finally become the desuperheated and reduced pressure superheated steam;

[0040] When the system is running, the first stage extraction steam isolation valve is closed, and the superheated steam with reduced temperature and pressure replaces the first stage extraction steam to enter the No. 1 high-pressure heater to heat the low-temperature feed water; the low-temperature feed water is heated by the No. 1 high-pressure heater and becomes high-temperature feed water, and is finally sent to the economizer in the boiler.

[0041] In a second aspect, a control method for increasing boiler feed water temperature by using superheated steam, comprising: obtaining historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of the control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of the control system for increasing boiler feed water temperature by using superheated steam includes operating data of a boiler, a superheater, a desuperheater, a regulating valve, a water supply device and a sensor matrix;

[0042] Performing data preprocessing on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, performing data feature extraction on the preprocessed data, and obtaining a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam;

[0043] The data feature extraction results of the control system for increasing the boiler feed water temperature by using superheated steam are screened through a feature selection algorithm, and the screening results are weighted to obtain weighted results of feature data, and a variety of artificial intelligence algorithm models are obtained to build an algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and attribute labels are established for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and a matching relationship is established between the weighted results of feature data and the attribute labels;

[0044] Extract the time information of the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, divide the time information into time periods, obtain the real-time time period division result, extract the real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result, and obtain the real-time time period grouped hot steam and boiler feed water temperature data;

[0045] Perform weighted evaluation on the hot steam and boiler feed water temperature data of the real-time period grouping to obtain the weighted evaluation result of the real-time period grouping data, match the feature data in the weighted evaluation result of the real-time period grouping data with the artificial intelligence algorithm model in the algorithm knowledge base, and obtain the artificial intelligence algorithm model corresponding to the real-time period data;

[0046] Substitute the real-time time period data into the corresponding artificial intelligence algorithm model, simulate the dynamic change law of steam temperature through the artificial intelligence algorithm model, complete the artificial intelligence algorithm model training, and obtain the trained artificial intelligence algorithm model;

[0047] Integrate the trained artificial intelligence algorithm model into a real-time control system that uses superheated steam to increase boiler feed water temperature, and use the trained artificial intelligence algorithm model to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time steam temperature and boiler feed water temperature prediction values;

[0048] The operating status information and operating parameters of the steam temperature control system are monitored in real time. If the operating status information and operating parameters do not match the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

[0049] The beneficial effects of the present invention are as follows: The present invention provides a control system and method for increasing boiler feed water temperature by using superheated steam, aiming to solve the problems of large inertia, large delay, time variability and nonlinearity in superheated steam temperature control. Through multiple technical units, including a data acquisition unit, a feature extraction unit, an algorithm knowledge base construction unit, a data grouping unit, a model matching unit, an algorithm model application unit, a model deployment unit and a construction monitoring unit, accurate prediction and control of steam temperature and boiler feed water temperature are achieved. The control system for increasing boiler feed water temperature by using superheated steam continuously captures and analyzes the historical and real-time data of the boiler control system, dynamically matches the most suitable artificial intelligence model through artificial intelligence technology, and monitors the operating status of the system in real time. By using the real-time monitoring and automatic adjustment of the control system for increasing boiler feed water temperature by using superheated steam, adjusting steam pressure, and optimizing boiler operation, the problems of large inertia, large delay, time variability and nonlinearity in superheated steam temperature control are effectively solved, thereby achieving the goal of quickly and accurately adjusting the steam temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A schematic diagram of a method flow chart provided by an embodiment of the present invention.

[0052] Figure 2 A prior art system diagram provided for an embodiment of the present invention.

[0053] Figure 3 A system diagram of an embodiment of the present invention under actual use conditions.

[0054] Figure numerals: 1. boiler; 2. turbine high-pressure cylinder; 3. No. 1 high-pressure heater; 4. first-stage extraction steam isolation valve; 5. low-temperature feed water; 6. high-temperature feed water; 7. main steam; 8. first-stage extraction steam; 9. bypass superheated steam; 10. bypass superheated steam after pressure reduction; 11. bypass superheated steam isolation valve; 12. pressure reducing regulating valve; 13. cooling water isolation valve; 14. cooling water regulating valve; 15. desuperheater; 16. cooling and pressure reducing superheated steam; 17. cooling water; 18. economizer; 19. low-temperature superheater; 20. medium-temperature superheater; 21. high-temperature superheater. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0056] In a first aspect, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, comprising a device end, a server end, and a background control end;

[0057] The equipment end includes a boiler, a superheater, a desuperheater, a regulating valve, a water supply device, a sensor matrix and an equipment end control device, and the server end establishes a communication connection with the equipment end and the background control end;

[0058] The server receives the control command of the background control end and the actual data of the device end, performs data analysis and processing according to the control command of the background control end and the actual data of the device end, outputs the device end execution command, and transmits the feedback information of the device end execution command to the background control end, and the server includes:

[0059] An acquisition unit is used to acquire historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of the control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of the control system for increasing boiler feed water temperature by using superheated steam includes operation data of boiler, superheater, desuperheater, regulating valve, water supply equipment and sensor matrix;

[0060] The acquisition unit is mainly connected to the data interface of the boiler control system to continuously capture historical data and real-time data from the system. Historical data includes but is not limited to historical temperature records of steam, pressure change records, flow statistics, and past boiler feed water temperature control parameter settings. These data are crucial to understanding the working status and performance of the boiler. Real-time data reflects the current working status of the boiler and its related equipment, such as the boiler's combustion efficiency, the heat exchange efficiency of the superheater, the operating status of the desuperheater, the opening of the regulating valve, the flow and pressure of the feed water equipment, and various environmental parameters monitored by the sensor matrix.

[0061] A data feature extraction unit performs data preprocessing on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, performs data feature extraction on the preprocessed data, and obtains a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam;

[0062] In the data feature extraction unit, the system uses a series of data preprocessing techniques, such as missing value filling, outlier detection and processing, and data smoothing, to improve data quality. Next, feature engineering techniques are used to extract meaningful features from the preprocessed data. These features include the peak value, fluctuation range, and periodic changes of steam temperature, as well as the correlation between boiler feed water temperature and other parameters. These features will provide strong support for subsequent model training and prediction.

[0063] The algorithm knowledge base construction unit uses a feature selection algorithm to perform data screening on the data feature extraction results of the control system for increasing boiler feed water temperature by using superheated steam, performs weighted processing on the screening results, obtains weighted results of feature data, obtains multiple artificial intelligence algorithm models, constructs an algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, establishes attribute labels for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, and establishes a matching relationship between the weighted results of feature data and the attribute labels;

[0064] The algorithm knowledge base construction unit first uses the feature selection algorithm to screen the extracted features to remove redundant and irrelevant features, and emphasizes the influence of certain important features through weighted processing. Subsequently, the system will obtain and integrate a variety of artificial intelligence algorithm models, such as linear regression, support vector machine, neural network, etc., to build a rich algorithm knowledge base. In order to facilitate management and selection of suitable models, the system will establish attribute labels for each algorithm model and establish a matching relationship between these labels and the weighted results of feature data.

[0065] A data grouping unit, extracting time information of real-time data of a control system for increasing boiler feed water temperature by using superheated steam, dividing the time information into time periods, obtaining a real-time time period division result, extracting real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result, and obtaining real-time time period grouped hot steam and boiler feed water temperature data;

[0066] The data grouping unit divides the data into time periods according to the time information in the real-time data, such as "peak period" and "valley period". This division helps to understand the working characteristics and load changes of the boiler in different time periods. Then, the system extracts the real-time steam and boiler feed water temperature data corresponding to each time period for more refined analysis and prediction.

[0067] The model matching unit performs weighted evaluation on the hot steam and boiler feed water temperature data of the real-time period grouping to obtain the weighted evaluation result of the real-time period grouping data, and matches the feature data in the weighted evaluation result of the real-time period grouping data with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the real-time period data;

[0068] In the model matching unit, the system performs a weighted evaluation of the real-time time period grouping data to determine which features are more important in the current period. Then, based on the importance of these features and the attribute labels in the algorithm knowledge base, the system matches the AI ​​algorithm model that best suits the current data characteristics. This dynamic matching mechanism ensures the accuracy and adaptability of the prediction model.

[0069] The algorithm model application unit substitutes the real-time period data into the corresponding artificial intelligence algorithm model, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the trained artificial intelligence algorithm model;

[0070] After determining the appropriate algorithm model, the algorithm model application unit will substitute the real-time period data into the model for training. By simulating the dynamic change of steam temperature, the system can continuously adjust the parameters and structure of the model to achieve the best prediction effect. After the training is completed, the system will obtain an optimized artificial intelligence algorithm model, which is used to predict the future steam temperature and boiler feed water temperature.

[0071] The model deployment unit integrates the trained artificial intelligence algorithm model into a real-time control system for increasing boiler feed water temperature by using superheated steam, and uses the trained artificial intelligence algorithm model to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time predicted values ​​of steam temperature and boiler feed water temperature;

[0072] The model deployment unit is responsible for integrating the trained artificial intelligence algorithm model into the real-time boiler feed water temperature control system. By continuously receiving new real-time data and inputting it into the model, the system predicts the changing trends of steam temperature and boiler feed water temperature in real time. These predicted values ​​will provide valuable reference information for boiler operators, helping them to better adjust and control the working status of the boiler.

[0073] A monitoring unit is constructed to monitor the operating status information and operating parameters of the steam temperature control system in real time. If the operating status information and operating parameters do not match the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

[0074] The monitoring unit will monitor the operating status information and operating parameters of the steam temperature control system in real time, such as the combustion efficiency of the boiler, the quality of the steam, etc. When these status information and parameters deviate significantly from the real-time steam temperature and the predicted value of the boiler feed water temperature, the monitoring system will immediately issue an alarm message to remind the operator to pay attention and take corresponding countermeasures. At the same time, the system will automatically optimize and adjust the artificial intelligence algorithm model used to adapt to the current working environment and data characteristics. This self-learning and adjustment ability enables the system to maintain efficient and accurate prediction performance.

[0075] The technical solution of this application continuously captures historical data and real-time data from the boiler control system through the acquisition unit. Clean and format the data to ensure data quality. Use the data feature extraction unit to preprocess the data, including missing value filling, outlier detection and processing, etc. Extract meaningful features, such as the peak value and fluctuation range of steam temperature. Through the algorithm knowledge base construction unit, filter and weight the extracted features. Integrate multiple artificial intelligence algorithm models, establish an algorithm knowledge base, and set attribute labels for each model. The data grouping unit divides the data into time periods according to time information. The model matching unit matches the most suitable artificial intelligence algorithm model according to the time period data and feature importance. Substitute the real-time time period data into the matched algorithm model for training. Adjust the model parameters and structure to achieve the best prediction effect. Through the model deployment unit, integrate the trained model into the boiler feed water temperature control system. Construct a monitoring unit to monitor the operating status and parameters of the system in real time and compare them with the predicted values.

[0076] The technical solution of this application uses artificial intelligence technology, and the system can accurately predict the steam temperature and boiler feed water temperature, providing valuable reference information for operators. The optimized control system can help operators better adjust and control the working state of the boiler, thereby improving the operating efficiency of the boiler. The monitoring system can monitor the operating status information and parameters in real time, detect abnormal conditions in time and issue alarms, and improve the safety of boiler operation.

[0077] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, further comprising: a heating execution unit, the heating execution unit comprising a collection unit and a first data processing unit;

[0078] The data collection unit collects the steam temperature, pressure and flow rate during the operation of the unit. When the steam temperature during the operation of the unit is higher than the preset standard value, the boiler feed water temperature is detected. If the boiler feed water temperature is lower than the preset standard value, the superheated steam is started to increase the boiler feed water temperature control system to heat the water in the boiler.

[0079] The first data processing unit obtains the user's boiler water temperature demand information, and predicts the use of superheated steam to increase the boiler feed water temperature based on the steam temperature during the operation of the unit. If the boiler feed water temperature prediction value is consistent with the user's boiler water temperature demand information, a control command for increasing the boiler feed water temperature by using superheated steam is generated. After receiving the control command for increasing the boiler feed water temperature by using superheated steam, the device executes the control command to heat the water in the boiler by using superheated steam.

[0080] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the algorithm model application unit comprises:

[0081] A time period construction unit is used to establish a data collection time period, and collect the boiler feed water temperature and superheated steam temperature of each time period according to the time information of the data collection time period;

[0082] The information comparison unit compares the collected boiler feed water temperature and superheated steam temperature in each period with the steam temperature and boiler feed water temperature prediction values ​​obtained by the trained artificial intelligence algorithm model in the algorithm optimization unit;

[0083] The first algorithm optimization unit, if the compared numerical error is within the preset error value range, the artificial intelligence algorithm model in the algorithm optimization unit continues to be used; if the compared numerical error is outside the preset error value range, the data of this time period and the corresponding artificial intelligence algorithm are optimized to obtain the optimized artificial intelligence algorithm model.

[0084] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the first algorithm optimization unit further includes:

[0085] The data time segmentation unit divides the steam temperature and boiler feed water temperature prediction curves into sections based on the generation time of the real-time steam temperature and boiler feed water temperature prediction values, and establishes a section sequence of the prediction value curves;

[0086] The second data analysis unit defines the values ​​of two adjacent serial numbers in the segmented sequence of the prediction value curve as a prediction value segment, retrieves the prediction values ​​corresponding to the two adjacent serial numbers in the segmented sequence of the prediction value curve, and generates a segmented prediction value curve by placing the prediction values ​​corresponding to the two adjacent serial numbers in the segmented sequence of the prediction value curve in the model deployment unit, and combines each prediction value segment of the segmented sequence of the prediction value curve to establish a prediction curve for steam temperature and boiler feed water temperature;

[0087] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the second data analysis unit further includes:

[0088] A data retrieval unit retrieves time information of each predicted value in the segmented sequence of the predicted value curve, retrieves corresponding data in real-time data of a control system for increasing boiler feed water temperature by using superheated steam according to the time information of each predicted value in the segmented sequence of the predicted value curve, and obtains real-time data corresponding to the predicted value curve;

[0089] The third data analysis unit generates a real-time segmented curve in the model deployment unit corresponding to the real-time data of the predicted value curve, generates an image of the real-time segmented curve and the steam temperature and boiler feed water temperature predicted curves on a grid under the same coordinate system, and records the coordinates of the connection points between the image and the grid, to obtain the grid coordinates of the real-time segmented curve and the coordinates of the segmented predicted value curve;

[0090] The prediction error warning unit compares the real-time segmented curve grid coordinates with the segmented prediction value curve coordinates. If the coordinate information is inconsistent, a prediction error warning information is generated.

[0091] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the algorithm model application unit comprises:

[0092] The model training unit performs weighted evaluation on the data in the prediction error warning information to obtain the weighted evaluation result of the prediction error warning information, screens out the characteristic data in the weighted evaluation result of the prediction error warning information, and matches it with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the prediction error warning information, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the artificial intelligence algorithm model after the prediction error training;

[0093] The model output unit integrates the artificial intelligence algorithm model after prediction error training into the model deployment unit for use.

[0094] Specifically, the present invention provides a control system for increasing boiler feed water temperature by using superheated steam, wherein the heating execution unit comprises:

[0095] After receiving the control command of increasing the boiler feed water temperature by using superheated steam, the equipment end executes the control command and applies it to the following devices, which use superheated steam to heat the water in the boiler, including: main steam 7, bypass superheated steam 9, pressure reducing regulating valve 12, desuperheater 15, desuperheating water 17, desuperheating water regulating valve 14, first stage extraction steam 8, No. 1 high pressure heater 3, etc.;

[0096] The method comprises extracting part of the steam from the outlet of the medium-temperature superheater 20 arranged in the boiler 1 as the bypass superheated steam 9;

[0097] The bypass superheated steam 9 is reduced in pressure by the pressure reducing regulating valve 12 to become the reduced pressure bypass superheated steam 10, and then is reduced in temperature by the desuperheater 15 to finally become the reduced temperature and pressure reduced superheated steam 16;

[0098] When the system is running, the first stage extraction steam isolation valve 4 is closed, and the superheated steam 16 with reduced temperature and pressure replaces the first stage extraction steam 8 to enter the No. 1 high-pressure heater 3 to heat the low-temperature feed water 5; the low-temperature feed water 5 is heated by the No. 1 high-pressure heater 3 and becomes high-temperature feed water 6, and is finally sent to the economizer 18 in the boiler 1.

[0099] In a second aspect, a method for controlling boiler feed water temperature by using superheated steam is provided, comprising: in step S101, obtaining historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of the control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of the control system for increasing boiler feed water temperature by using superheated steam includes operating data of a boiler, a superheater, a desuperheater, a regulating valve, a water supply device and a sensor matrix;

[0100] Boiler: This is the main equipment for producing superheated steam, which includes key parts such as combustion system, steam-water system and control system. The boiler generates heat by burning fuel, heating water into steam, and further superheating it into superheated steam.

[0101] Superheater: Its function is to further heat saturated steam into superheated steam, thereby increasing the temperature and enthalpy of the steam.

[0102] Desuperheater: Desuperheater is used to adjust the temperature of superheated steam. By injecting an appropriate amount of water into the superheated steam, the temperature of the steam can be reduced to meet the control requirements.

[0103] Regulating valve: There are usually multiple regulating valves in the system to control parameters such as feed water volume and desuperheating water flow. For example, the boiler main feed water valve (V1), desuperheating water valve (V2) and drum feed water branch valve (V3), etc. These valves control the corresponding flow by adjusting the opening.

[0104] Sensor Matrix: The sensor matrix includes multiple sensors for real-time monitoring of the temperature of superheated steam and feeding back the temperature signal to the control system that uses superheated steam to increase the boiler feed water temperature.

[0105] In step S102, data preprocessing is performed on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, and data feature extraction is performed on the preprocessed data to obtain a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam;

[0106] In step S103, the feature extraction results of the control system for increasing the boiler feed water temperature by using superheated steam are screened by a feature selection algorithm, and the screening results are weighted to obtain feature data weighted results, and multiple artificial intelligence algorithm models are obtained to construct an algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and attribute labels are established for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and a matching relationship is established between the weighted feature data results and the attribute labels;

[0107] In step S104, the time information of the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam is extracted, the time information is divided into time periods to obtain a real-time time period division result, and the real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result are extracted to obtain the real-time time period grouped hot steam and boiler feed water temperature data;

[0108] In step S105, the hot steam and boiler feed water temperature data of the real-time period grouping are weighted evaluated to obtain the weighted evaluation result of the real-time period grouping data, and the feature data in the weighted evaluation result of the real-time period grouping data is matched with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the real-time period data;

[0109] In step S106, the real-time time period data is substituted into the corresponding artificial intelligence algorithm model, and the dynamic change law of the steam temperature is simulated by the artificial intelligence algorithm model to complete the artificial intelligence algorithm model training and obtain the trained artificial intelligence algorithm model;

[0110] In step S107, the trained artificial intelligence algorithm model is integrated into a real-time control system for increasing boiler feed water temperature by using superheated steam, and the trained artificial intelligence algorithm model is used to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time steam temperature and boiler feed water temperature prediction values;

[0111] In step S108, the operating status information and operating parameters of the steam temperature control system are monitored in real time. If the operating status information and operating parameters are inconsistent with the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

[0112] From the above embodiments, it can be seen that the present invention provides a control system and method for increasing boiler feed water temperature by using superheated steam, which realizes an intelligent and efficient boiler feed water temperature control solution by integrating the device side, the server side and the background control side. The following is a detailed description of each part of the system:

[0113] The control system for increasing boiler feed water temperature by using superheated steam includes the equipment side, server side and background control side. The equipment side includes boilers, superheaters, desuperheaters, regulating valves, feed water equipment, sensor matrix and equipment side control devices. These components work together to maintain the normal operation of the boiler and the precise control of feed water temperature.

[0114] The server establishes a communication connection with the device and the backend control end, and receives control commands from the backend control end and actual data from the device. The server conducts in-depth analysis and processing of these data and outputs execution commands to the device to ensure stable control of the water supply temperature. At the same time, the server also transmits the feedback information of the device execution command to the backend control end in a timely manner for real-time monitoring and adjustment by the operator.

[0115] The server side further includes multiple functional units to achieve tasks such as data acquisition, processing, model building, model application and monitoring.

[0116] Specifically, the acquisition unit is responsible for collecting historical data and real-time data, which are the basis for subsequent data processing and model building.

[0117] The data feature extraction unit preprocesses and extracts features from the collected data in order to mine useful information for subsequent analysis.

[0118] The algorithm knowledge base construction unit uses the extracted feature data and a variety of artificial intelligence algorithm models to build a comprehensive algorithm knowledge base, providing rich choices for subsequent model matching.

[0119] The data grouping unit selects appropriate algorithm models for processing data in different time periods by dividing the time periods and grouping the data.

[0120] The model matching unit matches the most suitable artificial intelligence algorithm model from the algorithm knowledge base according to the characteristics of real-time data.

[0121] The algorithm model application unit substitutes real-time data into the matched model, completes the model training by simulating the dynamic change of steam temperature, and obtains the trained artificial intelligence algorithm model.

[0122] The model deployment unit integrates the trained model into the real-time control system to achieve real-time prediction and control of steam temperature and boiler feed water temperature.

[0123] In addition, the control system for increasing boiler feed water temperature by using superheated steam also includes a heating execution unit, which can start the control system to heat the water in the boiler when the steam temperature is higher than the preset standard and the boiler feed water temperature is lower than the preset standard. This function ensures the stability of the boiler feed water temperature and the timely response of the control system.

[0124] In order to further improve the accuracy and adaptability of the model, the control system for increasing boiler feed water temperature using superheated steam also continuously optimizes and adjusts the model by comparing real-time data with model predictions. When there is a large error between the predicted value and the real-time data, the system will trigger the optimization process and make necessary adjustments to the model to improve its prediction accuracy.

[0125] In the present invention, under low load conditions, the principle of using superheated steam to heat the water in the boiler is that the temperature of the secondary air entering the boiler is increased through the heating of the hot air heat exchanger, which increases the heat in the boiler and is conducive to stable combustion in the boiler; at the same time, due to the increase in the temperature of the hot air entering the boiler, the flow rate of the hot air can be appropriately reduced, thereby improving the boiler efficiency of the unit under low load conditions and generating considerable economic benefits. In addition, the No. 1 high-pressure heater is a condensing heat exchanger, and the level of its outlet feed water temperature depends on the feed water end difference of the No. 1 high-pressure heater, and the feed water end difference refers to the difference between the saturation temperature at the inlet steam pressure of the No. 1 high-pressure heater and the outlet feed water temperature. Since the superheated steam pressure after cooling and pressure reduction is higher than the first stage steam extraction pressure, the steam inlet pressure of the No. 1 high-pressure heater is increased, and then the feed water temperature at the outlet of the No. 1 high-pressure heater is increased. The increase in feed water temperature is one of the important means to achieve SCR full-load denitrification.

[0126] The system operation of the prior art is as follows Figure 1 As shown:

[0127] After entering the boiler 1, the high-temperature feed water 6 is heated by the economizer 18, the low-temperature superheater 19, the medium-temperature superheater 20, and the high-temperature superheater 21 respectively and becomes the main steam 7. The main steam 7 at the outlet of the boiler 1 enters the high-pressure cylinder 2 of the steam turbine to perform work; the first extraction steam 8 extracted from the high-pressure cylinder 2 of the steam turbine passes through the first extraction steam isolation valve 4 and enters the No. 1 high-pressure heater 3. The low-temperature feed water 5 is heated by the No. 1 high-pressure heater 3 and becomes the high-temperature feed water 6. The high-temperature feed water 6 is sent to the economizer 18 in the boiler 1.

[0128] The system and method disclosed in the present invention are as follows in actual use: Figure 2 As shown:

[0129] Under low load conditions, after receiving the control command for increasing the boiler feed water temperature by using superheated steam, the equipment end executes the control command and uses the superheated steam to heat the water in the boiler. The control command includes the operation steps of each component in the system and the parameter adjustment of each component. The specific steps are as follows: a portion of the superheated steam is taken from the outlet of the medium-temperature superheater 20 arranged in the boiler 1 as the bypass superheated steam 9, the original first-stage extraction steam isolation valve 4 is closed, the first-stage extraction steam 8 is isolated, and the first-stage extraction steam 8 is no longer extracted from the high-pressure cylinder 2 of the steam turbine;

[0130] The bypass superheated steam 9 passes through the bypass superheated steam isolation valve 11 and is decompressed by the pressure reducing regulating valve 12, and becomes the decompressed bypass superheated steam 10;

[0131] The desuperheated water 17 passes through the desuperheated water isolation valve 13, and the desuperheated water regulating valve 14 is used to adjust the flow rate. After the decompression, the bypass superheated steam 10 passes through the desuperheater 15 and is decompressed by the desuperheated water 17, and finally the bypass superheated steam 9 is converted into the desuperheated and decompressed superheated steam 16.

[0132] The superheated steam 16 with reduced temperature and pressure is sent to the No. 1 high-pressure heater 3, thereby replacing the original first-stage extraction steam 8 to heat the low-temperature feed water 5. The low-temperature feed water 5 is heated by the No. 1 high-pressure heater 3 and becomes high-temperature feed water 6. The high-temperature feed water 6 is finally sent to the economizer 18 in the boiler 1.

[0133] When the system is operating normally, the pressure of the first extraction steam 8 changes with the change of the unit load. Taking a 350MW supercritical unit as an example, the pressure of the first extraction steam 8 is 11MPa at 10%THA load, and the pressure of the first extraction steam 8 is about 3MPa at 30%THA load. Since the No. 1 high-pressure heater 3 is a condensing heat exchanger, the temperature of its outlet high-temperature feed water 6 depends on the feed water end difference of the No. 1 high-pressure heater 3, and the feed water end difference refers to the difference between the saturated temperature at the inlet steam pressure of the No. 1 high-pressure heater 3 and the outlet high-temperature feed water 6 temperature. Therefore, the temperature of the high-temperature feed water 6 at the outlet of the No. 1 high-pressure heater 3 continues to decrease with the decrease of the load.

[0134] The system and method disclosed in the present invention adopts the bypass superheated steam 10 extracted from the outlet of the medium-temperature superheater 20 and reduced in temperature and pressure as the steam source of the No. 1 high-pressure heater 3. The temperature and pressure of the reduced-temperature and reduced-pressure superheated steam 16 entering the No. 1 high-pressure heater 3 can be adjusted by the cooling water regulating valve 14 and the pressure reducing regulating valve 12.

[0135] Since the pressure of the bypass superheated steam 9 extracted from the outlet of the medium-temperature superheater 20 is much higher than the pressure of the first-stage extraction steam 8, the pressure can still reach about 11 MPa even at a 30% THA load. Therefore, the system and method disclosed in the present invention can achieve that the pressure of the cooled and reduced-pressure superheated steam 16 entering the No. 1 high-pressure heater 3 under low-load conditions of the unit is higher than the pressure of the first-stage extraction steam 8 under this condition, thereby greatly increasing the temperature of the high-temperature feed water 6 at the outlet of the No. 1 high-pressure heater 3. After calculation, it can be increased by more than 40°C.

[0136] The present invention discloses a control system and method for increasing the temperature of boiler feed water by using superheated steam. The use steps are as follows: first, through data analysis, a control command for increasing the temperature of boiler feed water by using superheated steam is obtained and then the control command is executed. After receiving the control command for increasing the temperature of boiler feed water by using superheated steam, the device end executes the control command and is applied to the following device. Using superheated steam to heat the water in the boiler includes extracting a part of superheated steam from the outlet of the medium-temperature superheater in the boiler, and the part of superheated steam enters the No. 1 high-pressure heater after being reduced in pressure by a pressure reducing valve and reduced in temperature by cooling water, and the original first-stage steam extraction is isolated. The inlet steam of the No. 1 high-pressure heater is changed from the original first-stage steam extraction to superheated steam after pressure reduction and temperature reduction. The No. 1 high-pressure heater is a condensing heat exchanger, and the outlet feed water temperature of the No. 1 high-pressure heater depends on the feed water end difference of the No. 1 high-pressure heater, and the feed water end difference refers to the difference between the saturated temperature at the inlet steam pressure of the No. 1 high-pressure heater and the outlet feed water temperature. Since the pressure of the superheated steam after temperature reduction and pressure reduction is higher than the first-stage steam extraction pressure, the inlet steam pressure of the No. 1 high-pressure heater is increased, and then the outlet feed water temperature of the No. 1 high-pressure heater is increased. The increase of feed water temperature is one of the important means to achieve SCR full load denitration. The present invention increases the feed water temperature entering the boiler, thereby increasing the flue gas temperature at the SCR inlet, which is beneficial to the unit to perform full load denitration and deep peak regulation.

[0137] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0138] The above-described embodiments of the present invention do not limit the protection scope of the present invention.

Claims

1. A control system for increasing boiler feed water temperature by using superheated steam, characterized in that: Including device side, server side and background control side; The equipment end includes a boiler, a superheater, a desuperheater, a regulating valve, a water supply device, a sensor matrix and an equipment end control device, and the server end establishes a communication connection with the equipment end and the background control end; The server receives the control command of the background control end and the actual data of the device end, performs data analysis and processing according to the control command of the background control end and the actual data of the device end, outputs the device end execution command, and transmits the feedback information of the device end execution command to the background control end, and the server includes: An acquisition unit is used to acquire historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of the control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of the control system for increasing boiler feed water temperature by using superheated steam includes operation data of boiler, superheater, desuperheater, regulating valve, water supply equipment and sensor matrix; A data feature extraction unit performs data preprocessing on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, performs data feature extraction on the preprocessed data, and obtains a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam; The algorithm knowledge base construction unit uses a feature selection algorithm to perform data screening on the data feature extraction results of the control system for increasing boiler feed water temperature by using superheated steam, performs weighted processing on the screening results, obtains weighted results of feature data, obtains multiple artificial intelligence algorithm models, constructs an algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, establishes attribute labels for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing boiler feed water temperature by using superheated steam, and establishes a matching relationship between the weighted results of feature data and the attribute labels; A data grouping unit, extracting time information of real-time data of a control system for increasing boiler feed water temperature by using superheated steam, dividing the time information into time periods, obtaining a real-time time period division result, extracting real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result, and obtaining real-time time period grouped hot steam and boiler feed water temperature data; The model matching unit performs weighted evaluation on the hot steam and boiler feed water temperature data of the real-time period grouping to obtain the weighted evaluation result of the real-time period grouping data, and matches the feature data in the weighted evaluation result of the real-time period grouping data with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the real-time period data; The algorithm model application unit substitutes the real-time period data into the corresponding artificial intelligence algorithm model, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the trained artificial intelligence algorithm model; The model deployment unit integrates the trained artificial intelligence algorithm model into a real-time control system for increasing boiler feed water temperature by using superheated steam, and uses the trained artificial intelligence algorithm model to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time predicted values ​​of steam temperature and boiler feed water temperature; A monitoring unit is constructed to monitor the operating status information and operating parameters of the steam temperature control system in real time. If the operating status information and operating parameters do not match the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

2. The system according to claim 1, characterized in that Also includes: A heating execution unit, wherein the heating execution unit comprises a collection unit and a first data processing unit; The data collection unit collects the steam temperature, pressure and flow rate during the operation of the unit. When the steam temperature during the operation of the unit is higher than the preset standard value, the boiler feed water temperature is detected. If the boiler feed water temperature is lower than the preset standard value, the superheated steam is started to increase the boiler feed water temperature control system to heat the water in the boiler. The first data processing unit obtains the user's boiler water temperature demand information, and predicts the use of superheated steam to increase the boiler feed water temperature based on the steam temperature during the operation of the unit. If the boiler feed water temperature prediction value is consistent with the user's boiler water temperature demand information, a control command for increasing the boiler feed water temperature by using superheated steam is generated. After receiving the control command for increasing the boiler feed water temperature by using superheated steam, the device executes the control command to heat the water in the boiler by using superheated steam.

3. The system according to claim 1, characterized in that The algorithm model application unit includes: A time period construction unit is used to establish a data collection time period, and collect the boiler feed water temperature and superheated steam temperature of each time period according to the time information of the data collection time period; The information comparison unit compares the collected boiler feed water temperature and superheated steam temperature in each period with the steam temperature and boiler feed water temperature prediction values ​​obtained by the trained artificial intelligence algorithm model in the algorithm optimization unit; The first algorithm optimization unit, if the compared numerical error is within the preset error value range, the artificial intelligence algorithm model in the algorithm optimization unit continues to be used; if the compared numerical error is outside the preset error value range, the data of this time period and the corresponding artificial intelligence algorithm are optimized to obtain the optimized artificial intelligence algorithm model.

4. The system according to claim 3, characterized in that The first algorithm optimization unit also includes: The data time segmentation unit divides the steam temperature and boiler feed water temperature prediction curves into sections based on the generation time of the real-time steam temperature and boiler feed water temperature prediction values, and establishes a section sequence of the prediction value curves; The second data analysis unit defines the values ​​of two adjacent serial numbers in the prediction value curve segment sequence as a prediction value segment, retrieves the prediction values ​​corresponding to the two adjacent serial numbers in the prediction value curve segment sequence, and generates a segmented prediction value curve by placing the prediction values ​​corresponding to the two adjacent serial numbers in the prediction value curve segment sequence in the model deployment unit, combines each prediction value segment of the prediction value curve segment sequence, and establishes steam temperature and boiler feed water temperature prediction curves.

5. The system according to claim 4, characterized in that The second data analysis unit further includes: A data retrieval unit retrieves time information of each predicted value in the segmented sequence of the predicted value curve, retrieves corresponding data in real-time data of a control system for increasing boiler feed water temperature by using superheated steam according to the time information of each predicted value in the segmented sequence of the predicted value curve, and obtains real-time data corresponding to the predicted value curve; The third data analysis unit generates a real-time segmented curve in the model deployment unit corresponding to the real-time data of the predicted value curve, generates an image of the real-time segmented curve and the steam temperature and boiler feed water temperature predicted curves on a grid under the same coordinate system, and records the coordinates of the connection points between the image and the grid, to obtain the grid coordinates of the real-time segmented curve and the coordinates of the segmented predicted value curve; The prediction error warning unit compares the real-time segmented curve grid coordinates with the segmented prediction value curve coordinates. If the coordinate information is inconsistent, a prediction error warning information is generated.

6. The system according to claim 1, characterized in that The algorithm model application unit includes: The model training unit performs weighted evaluation on the data in the prediction error warning information to obtain the weighted evaluation result of the prediction error warning information, screens out the characteristic data in the weighted evaluation result of the prediction error warning information, and matches it with the artificial intelligence algorithm model in the algorithm knowledge base to obtain the artificial intelligence algorithm model corresponding to the prediction error warning information, simulates the dynamic change law of steam temperature through the artificial intelligence algorithm model, completes the artificial intelligence algorithm model training, and obtains the artificial intelligence algorithm model after the prediction error training; The model output unit integrates the artificial intelligence algorithm model after prediction error training into the model deployment unit for use.

7. The system according to claim 2, characterized in that The heating execution unit comprises: After receiving the control command of increasing the boiler feed water temperature by using superheated steam, the equipment end executes the control command and applies it to the following device, wherein the water in the boiler is heated by using superheated steam, including: main steam (7), bypass superheated steam (9), pressure reducing regulating valve (12), desuperheater (15), desuperheating water (17), desuperheating water regulating valve (14), first stage extraction steam (8), and No. 1 high pressure heater (3); extracting part of the steam from the outlet of the medium-temperature superheater (20) arranged in the boiler (1) as bypass superheated steam (9); The bypass superheated steam (9) is reduced in pressure by the pressure reducing regulating valve (12) to become reduced pressure bypass superheated steam (10), and then is reduced in temperature by the desuperheater (15) to finally become reduced temperature and pressure reduced superheated steam (16); When the system is in operation, the first stage extraction steam isolation valve (4) is closed, and the superheated steam (16) with reduced temperature and pressure replaces the first stage extraction steam (8) and enters the No. 1 high-pressure heater (3) to heat the low-temperature feed water (5); the low-temperature feed water (5) is heated by the No. 1 high-pressure heater (3) and becomes high-temperature feed water (6), and is finally sent to the economizer (18) in the boiler (1).

8. A method for controlling boiler feed water temperature by using superheated steam, characterized in that: Including, obtaining historical data of a control system for increasing boiler feed water temperature by using superheated steam and real-time data of a control system for increasing boiler feed water temperature by using superheated steam, wherein the historical data of a control system for increasing boiler feed water temperature by using superheated steam includes historical steam temperature, historical steam pressure, historical steam flow rate and historical boiler feed water temperature control parameters, and the real-time data of a control system for increasing boiler feed water temperature by using superheated steam includes operating data of boiler, superheater, desuperheater, regulating valve, feed water equipment and sensor matrix; Performing data preprocessing on the historical data of the control system for increasing the boiler feed water temperature by using superheated steam and the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, performing data feature extraction on the preprocessed data, and obtaining a data feature extraction result of the control system for increasing the boiler feed water temperature by using superheated steam; The data feature extraction results of the control system for increasing the boiler feed water temperature by using superheated steam are screened through a feature selection algorithm, and the screening results are weighted to obtain weighted results of feature data, and a variety of artificial intelligence algorithm models are obtained to build an algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and attribute labels are established for the artificial intelligence algorithm models in the algorithm knowledge base for the control system for increasing the boiler feed water temperature by using superheated steam, and a matching relationship is established between the weighted results of feature data and the attribute labels; Extract the time information of the real-time data of the control system for increasing the boiler feed water temperature by using superheated steam, divide the time information into time periods, obtain the real-time time period division result, extract the real-time hot steam and boiler feed water temperature real-time data corresponding to each time period information in the time period division result, and obtain the real-time time period grouped hot steam and boiler feed water temperature data; Perform weighted evaluation on the hot steam and boiler feed water temperature data of the real-time period grouping to obtain the weighted evaluation result of the real-time period grouping data, match the feature data in the weighted evaluation result of the real-time period grouping data with the artificial intelligence algorithm model in the algorithm knowledge base, and obtain the artificial intelligence algorithm model corresponding to the real-time period data; Substitute the real-time time period data into the corresponding artificial intelligence algorithm model, simulate the dynamic change law of steam temperature through the artificial intelligence algorithm model, complete the artificial intelligence algorithm model training, and obtain the trained artificial intelligence algorithm model; Integrate the trained artificial intelligence algorithm model into a real-time control system that uses superheated steam to increase boiler feed water temperature, and use the trained artificial intelligence algorithm model to predict the real-time steam temperature and boiler feed water temperature to obtain the real-time steam temperature and boiler feed water temperature prediction values; The operating status information and operating parameters of the steam temperature control system are monitored in real time. If the operating status information and operating parameters do not match the real-time steam temperature and boiler feed water temperature predicted values, the monitoring system will issue an alarm message and optimize the artificial intelligence algorithm model.

Images