Thermal power generating unit transition peak load cruise control method based on intelligent control algorithm

Abstract

The invention discloses a thermal power generating unit transition peak regulation load cruise control method based on an intelligent control algorithm, and relates to the technical field of load coordination control. According to the thermal power generating unit transition peak regulation load cruise control method based on the intelligent control algorithm, data are classified, the load demand change condition is determined firstly, internal coordination of a thermal power generating unit is achieved based on the load demand change condition, and control operation of various factors in a boiler is achieved; then analysis is carried out in combination with the time from instruction generation to implementation and set early warning of a threshold value in the boiler, compensation and optimization of a coordination strategy are completed through a compensation algorithm, prediction operation during load change is completed, analysis of the safety condition is achieved through historical big data, the expected prediction time is obtained, and the prediction efficiency is improved. And the corresponding load demand is traced according to the prediction time, so that enough time is given to complete the coordination operation in the load supply process, and the operation safety of the thermal power generating unit is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of load coordination control, and in particular to a load cruise control method for transient peak-shaving of a thermal power unit based on an intelligent control algorithm. Background Art

[0002] With the widespread access to new energy and the continuous changes in the load characteristics of the power system, thermal power units need to take on more peak-shaving tasks. Traditional control methods often have problems such as slow response speed and low control accuracy when facing rapidly changing load demands, making it difficult to meet the needs of modern power systems.

[0003] The reference patent name is: A method for intelligent control of flexibility and deep peak regulation of thermal power units (patent publication number: CN115327910A, patent publication date: 2022-11-11), including: conducting disturbance tests at typical operating points, and establishing a gain scheduling model of the coordination system through fitting, identification and other methods; establishing a fuzzy rule base, and inferring the dynamic mathematical model of the coordination system corresponding to the grid load instructions in real time, and using it as a prediction model; the predictive controller predicts the output trajectory according to the prediction equation, the Kalman filter estimates the system state, and the performance index calculates the optimal control quantity. It is suitable for the coordinated control system of thermal power units with frequently changing operating conditions. It is simple, reliable, easy to implement, and can be configured and implemented through the power plant DCS system. It has broad engineering application value.

[0004] Based on the description in the above-mentioned document, in the process of undertaking peak-shaving tasks, the existing thermal power units have a problem that the changes in load demand do not mean an increase in stability. As a result, during the response process of the thermal power units, by the time personnel notice data abnormalities, the actual coordinated operation of the thermal power units is difficult to meet the demand, resulting in increased boiler pressure or equipment damage safety issues, resulting in failure to carry out timely coordination and failure to predict subsequent load demand conditions. To this end, the present invention provides a load cruise control method for transient peak-shaving of thermal power units based on an intelligent control algorithm. Summary of the Invention

[0005] In response to the deficiencies in the prior art, the present invention provides a load cruise control method for transient peak-shaving of thermal power units based on an intelligent control algorithm. This method solves the problem that, during the peak-shaving task of existing thermal power units, changes in load demand do not mean an increase in stability. As a result, during the response of the thermal power units, by the time personnel notice data anomalies, the actual coordinated operation of the thermal power units is difficult to meet the demand, resulting in increased boiler pressure or equipment damage, safety issues, and failure to carry out timely coordination and processing, and failure to predict subsequent load demand conditions.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for controlling peak load cruise of a thermal power unit based on an intelligent control algorithm, specifically comprising the following steps:

[0007] S1. Collect real-time and historical operating data of thermal power units, and collect historical load demand data;

[0008] S2. Classify and process the data, first determining changes in load demand. Based on these changes, internal coordination of the thermal power units is achieved, and control operations on various factors within the boiler are implemented. The time from command generation to execution, as well as the setting of early warning thresholds within the boiler, are then analyzed. Compensation algorithms are used to compensate and optimize the coordination strategy, completing prediction operations when load changes occur.

[0009] S3. Introduce the current real-time operating data, complete the prediction of subsequent load changes, generate corresponding control strategies, and display them on a visual interface.

[0010] Preferably, the operation of classifying the data in S2 is:

[0011] s21. Initially classify the collected data according to real-time data and historical data, and set the classification template to implement the filling operation of the collected data;

[0012] s22. The classification template uses the search criteria to complete the screening of real-time data and historical data, and repairs abnormal data in the filled data;

[0013] s23. After the search is completed, the classification template is retained and classified in chronological order to form a data set for each individual category.

[0014] Preferably, the operation in s22 is:

[0015] The search criteria for the classification template are unit type as the first criterion, data category corresponding to the unit type as the second criterion, and data collection time as the third criterion;

[0016] And according to the condition content and the collected data, a traversal operation is performed, and the numerical results of the data content that meets the condition content are filled into the classification template;

[0017] Traverse the numerical result columns of the classification template to verify the blank result columns, and delete and repair the result columns with garbled characters.

[0018] Preferably, the operation of determining the load demand change in S2 is:

[0019] A1. After extracting the load demand data, determine the period with the largest total load demand based on date changes, and extract the load demand data for the current period;

[0020] A2. Establish a load change curve according to the time sequence and the corresponding load demand values, and calculate the average load demand value based on the load demand value at each time, and mark the nodes with higher load demand than the average load demand;

[0021] The calculation formula for the average load demand value is:

[0022] P 平 =(P1+P2+…+P n ) / n;

[0023] P 平 is the average load demand value, and P n is the load demand value at the nth time node;

[0024] A3. Determine the specific coordination operations of the corresponding thermal power units based on the marked nodes.

[0025] Preferably, the internal coordination operation of the thermal power unit based on the load demand change in S2 is:

[0026] B1. Based on the increase in load demand, a command is transmitted to the thermal power unit to implement coordinated control of the steam turbine and boiler. The steam turbine master control responds and generates a command that is transmitted to the boiler master control for coordinated control operations.

[0027] B2. After recording the load demand changes, an instruction is generated and transmitted to the boiler master control to complete the coordinated operation. The transmission time is T1. Then, according to the instruction, the fuel amount and water supply amount of the boiler are controlled to complete the regulation of the thermal power unit and generate the corresponding load supply.

[0028] Preferably, the specific operation of the compensation algorithm in S2 is:

[0029] C1. When extracting the corresponding marked node part, the total fuel amount of the boiler at the cycle node is marked as G x , x represents the number of cycle nodes, and x∈{1, 2, 3, ...} the time intervals between adjacent cycle nodes are the same. When extracting the corresponding marked node part, the real-time pressure value of the boiler corresponding to the cycle node is marked as U x , and the total water supply at the corresponding cycle node is the total H x ;

[0030] C2. Set the boiler pressure safety threshold interval to [W1, W2] and the boiler water-coal ratio safety threshold interval to [K1, K2]. Extract multiple processing times after exceeding the safety threshold interval during the operation of the thermal power unit. After removing outliers, select the maximum value as the human response time and label it as T2.

[0031] C3. Establish curves for fuel quantity and boiler pressure at cycle nodes, as well as curves for cycle nodes and water-coal ratio. By analyzing the curves, obtain corresponding optimized values that can provide early warning.

[0032] Preferably, the curve analysis operation of the fuel quantity and boiler pressure at the periodic node in C3 is:

[0033] d01. Establish a curvilinear coordinate system, forming the horizontal axis in the order of the periodic nodes, starting from the starting point of the horizontal axis, and using the fuel quantity and boiler pressure as the vertical axis;

[0034] d02. Then, the fuel quantity and boiler pressure values at the corresponding period nodes are filled into the curve coordinate system, and the fuel quantity and boiler pressure curves are established using smooth curves. The segmentation operation is performed according to the rise and fall of the fuel quantity and boiler pressure curves;

[0035] d03. The pressure safety threshold interval is introduced as a pressure threshold constant function, and the first hidden danger node is determined by the intersection of the pressure threshold maximum constant function and the rising curve of the fuel quantity and boiler pressure curve. The second hidden danger node is then determined based on the intersection of the pressure threshold minimum constant function and the falling curve of the fuel quantity and boiler pressure curve. The reaction time T2 of the personnel processing and the time T1 for completing the coordinated operation transmission are then compensated to determine the corresponding fuel quantity safety node before the hidden danger node.

[0036] Preferably, the curve analysis operation of the water-coal ratio and boiler pressure at the periodic node in C3 is:

[0037] d11. Establish a curvilinear coordinate system, forming the horizontal axis in the order of periodic nodes, starting from the starting point of the horizontal axis and using the water-coal ratio as the vertical axis;

[0038] d12. Then, the corresponding periodic nodes and water-coal ratio values are filled into the curve coordinate system, and the periodic nodes and water-coal ratio curves are established with smooth curves. The segmentation operation is performed according to the rise and fall of the periodic nodes and the water-coal ratio curves.

[0039] d13. The water-coal ratio safety threshold interval is introduced as the water-coal ratio threshold constant function, and the third hidden danger node is determined by the intersection of the water-coal ratio threshold maximum constant function with the periodic node and the rising curve in the water-coal ratio curve. The fourth hidden danger node is determined according to the intersection of the water-coal ratio threshold minimum constant function with the periodic node and the falling curve in the water-coal ratio curve. Then, the personnel processing reaction time T2 and the time T1 for completing the coordinated operation transmission are compensated to the hidden danger node to determine the corresponding water-coal ratio safety node.

[0040] Preferably, the formula for determining the safety node in the operations of d03 and d13 is:

[0041] The formula for determining the fuel quantity safety node: G Z1 =F(Z1-T1-T2), when U x =W1 or U x =W2, and the corresponding cycle node at this time is Z1, (Z1-T1-T2) represents the time node after the corresponding cycle node compensation time, F(Z1-T1-T2) represents the fuel quantity value at the corresponding time node, G Z1 is the fuel quantity value when the cycle node is Z1, that is, the fuel quantity safety node;

[0042] The formula for determining the safety node of water-coal ratio is: (H x / G x ) Z2 =f(Z2-T1-T2), when (H x / G x )=K1or(H x / G x )=K2, and the corresponding periodic node at this time is Z2, (Z2-T1-T2) represents the time node after the corresponding periodic node compensation time, f(Z1-T1-T2) represents the water-coal ratio value at the corresponding time node, (H x / G x ) Z2 It is the water-coal ratio value when the cycle node is Z2, that is, the water-coal ratio safety node.

[0043] Preferably, the operation of introducing real-time running data for prediction in S3 is:

[0044] s31. By collecting real-time operating data and tracing back to the fuel quantity safety node and the water-coal ratio safety node, determine the historical load demand;

[0045] s32. Compare the load demand corresponding to the safety node with the load demand in the real-time data. When the load demand in the real-time data reaches the load demand corresponding to the safety node, a control instruction is generated and transmitted to the thermal power unit for coordinated control.

[0046] The present invention provides a method for controlling peak load during transition of thermal power units based on an intelligent control algorithm. Compared with the prior art, it has the following advantages:

[0047] 1. This method of load cruise control for transient peak-shaving of thermal power units based on an intelligent control algorithm classifies and processes data to first determine the load demand changes, then implements internal coordination of the thermal power units based on the load demand changes and controls various factors in the boiler. It then analyzes the time taken from command generation to implementation and the threshold setting warnings in the boiler, uses a compensation algorithm to compensate and optimize the coordination strategy, and completes the prediction operation when the load changes. This method uses historical big data to analyze safety situations, derives the desired prediction time, and traces the corresponding load demand based on the prediction time, thereby providing sufficient time to complete the coordination operation during the load supply process and ensure the safe operation of the thermal power units.

[0048] 2. This method of load cruise control for transient peak-shaving of thermal power units based on an intelligent control algorithm establishes a load change curve according to the time sequence and the corresponding load demand values, and derives the average load demand value based on the load demand value at each time. The nodes with higher than the average load demand are marked to extract high-demand data nodes in the historical data, thereby achieving faster search for target data during data analysis, making the data more representative during subsequent coordinated control of thermal power units, thereby maximizing time compensation and better ensuring the safety of thermal power unit control.

[0049] 3. This method of load cruise control for transient peak-shaving of thermal power units based on an intelligent control algorithm establishes curves for fuel quantity and boiler pressure at cycle nodes, as well as curves for cycle nodes and water-coal ratio. By analyzing the curves, the method obtains the corresponding optimized values that can provide early warnings. When the load demand in the real-time data meets the corresponding load demand at any safety node, it is necessary to determine whether it corresponds to a specific safety hazard. The load cruise control operation is completed while maintaining the fault tolerance rate, so that the thermal power unit can better achieve load supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is an operational flow chart of the load cruise control method of the present invention;

[0051] Figure 2 This is an operational flow chart of the compensation algorithm of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying 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 making creative efforts are within the scope of protection of the present invention.

[0053] See also Figure 1-Figure 2 , the present invention provides two technical solutions:

[0054] Example 1: A method for controlling peak load cruise during transition of a thermal power unit based on an intelligent control algorithm, specifically comprising the following steps:

[0055] S1. Collect real-time and historical operating data of thermal power units, and collect historical load demand data;

[0056] S2. Classify and process the data, first determining changes in load demand. Based on these changes, internal coordination of the thermal power units is achieved, and control operations on various factors within the boiler are implemented. The time from command generation to execution, as well as the setting of early warning thresholds within the boiler, are then analyzed. Compensation algorithms are used to compensate and optimize the coordination strategy, completing prediction operations when load changes occur.

[0057] S3. Introduce the current real-time operating data, complete the prediction of subsequent load changes, generate corresponding control strategies, and display them on a visual interface.

[0058] By classifying and processing the data, we first determine the changes in load demand, realize internal coordination of thermal power units based on the changes in load demand, and realize control operations of various factors in the boiler. Then, we analyze the time from instruction generation to implementation and the setting warning of thresholds in the boiler, and complete compensation and optimization of the coordination strategy through compensation algorithms, and complete prediction operations when load changes. In this way, we can use historical big data to analyze safety situations, obtain the desired prediction time, and trace the corresponding load demand based on the prediction time, so as to give enough time to complete the coordination operations in the load supply process and ensure the safe operation of thermal power units.

[0059] In the embodiment of the present invention, the operation of classifying the data in S2 is:

[0060] s21. Initially classify the collected data according to real-time data and historical data, and set the classification template to implement the filling operation of the collected data;

[0061] s22. The classification template uses the search criteria to complete the screening of real-time data and historical data, and repairs abnormal data in the filled data;

[0062] s23. After the search is completed, the classification template is retained and classified in chronological order to form a data set for each individual category.

[0063] In the embodiment of the present invention, the operation in s22 is:

[0064] The search criteria for the classification template are unit type as the first criterion, data category corresponding to the unit type as the second criterion, and data collection time as the third criterion;

[0065] And according to the condition content and the collected data, a traversal operation is performed, and the numerical results of the data content that meets the condition content are filled into the classification template;

[0066] Traverse the numerical result columns of the classification template to verify the blank result columns, and delete and repair the result columns with garbled characters.

[0067] In the embodiment of the present invention, the operation of determining the load demand change in S2 is:

[0068] A1. After extracting the load demand data, determine the period with the largest total load demand based on date changes, and extract the load demand data for the current period;

[0069] A2. Establish a load change curve according to the time sequence and the corresponding load demand values, and calculate the average load demand value based on the load demand value at each time, and mark the nodes with higher load demand than the average load demand;

[0070] The calculation formula for the average load demand value is:

[0071] P 平 =(P1+P2+…+P n ) / n;

[0072] P 平 is the average load demand value, and P n is the load demand value at the nth time node;

[0073] A3. Determine the specific coordination operations of the corresponding thermal power units based on the marked nodes.

[0074] In the embodiment of the present invention, the internal coordination operation of the thermal power generation unit based on the load demand change in S2 is as follows:

[0075] B1. Based on the increase in load demand, a command is transmitted to the thermal power unit to implement coordinated control of the steam turbine and boiler. The steam turbine master control responds and generates a command that is transmitted to the boiler master control for coordinated control operations.

[0076] B2. After recording the load demand changes, an instruction is generated and transmitted to the boiler master control to complete the coordinated operation. The transmission time is T1. Then, according to the instruction, the fuel amount and water supply amount of the boiler are controlled to complete the regulation of the thermal power unit and generate the corresponding load supply.

[0077] By establishing a load change curve according to the time sequence and the corresponding load demand values, and deriving the average load demand value based on the load demand value at each time, the node parts with higher than the average load demand are marked, so as to extract the high-demand data nodes in the historical data, thereby achieving faster search for target data during the data analysis process, so that the data in the subsequent coordinated control of thermal power units is more representative, thereby maximizing the compensation of time and better ensuring the safety of thermal power unit control.

[0078] In the embodiment of the present invention, the specific operations of the compensation algorithm in S2 are:

[0079] C1. When extracting the corresponding marked node part, the total fuel amount of the boiler at the cycle node is marked as G x , x represents the number of cycle nodes, and x∈{1, 2, 3, ...} the time intervals between adjacent cycle nodes are the same. When extracting the corresponding marked node part, the real-time pressure value of the boiler corresponding to the cycle node is marked as U x , and the total water supply at the corresponding cycle node is the total H x ;

[0080] C2. Set the boiler pressure safety threshold interval to [W1, W2] and the boiler water-coal ratio safety threshold interval to [K1, K2]. Extract multiple processing times after exceeding the safety threshold interval during the operation of the thermal power unit. After removing outliers, select the maximum value as the human response time and label it as T2.

[0081] C3. Establish curves for fuel quantity and boiler pressure at cycle nodes, as well as curves for cycle nodes and water-coal ratio. By analyzing the curves, obtain corresponding optimized values that can provide early warning.

[0082] In the embodiment of the present invention, the curve analysis operation of the fuel quantity and boiler pressure at the period node C3 is as follows:

[0083] d01. Establish a curvilinear coordinate system, forming the horizontal axis in the order of the periodic nodes, starting from the starting point of the horizontal axis, and using the fuel quantity and boiler pressure as the vertical axis;

[0084] d02. Then, the fuel quantity and boiler pressure values at the corresponding period nodes are filled into the curve coordinate system, and the fuel quantity and boiler pressure curves are established using smooth curves. The segmentation operation is performed according to the rise and fall of the fuel quantity and boiler pressure curves;

[0085] d03. The pressure safety threshold interval is introduced as a pressure threshold constant function, and the first hidden danger node is determined by the intersection of the pressure threshold maximum constant function and the rising curve of the fuel quantity and boiler pressure curve. The second hidden danger node is then determined based on the intersection of the pressure threshold minimum constant function and the falling curve of the fuel quantity and boiler pressure curve. The reaction time T2 of the personnel processing and the time T1 for completing the coordinated operation transmission are then compensated to determine the corresponding fuel quantity safety node before the hidden danger node.

[0086] In the embodiment of the present invention, the curve analysis operation of the water-coal ratio and the boiler pressure at the periodic node C3 is as follows:

[0087] d11. Establish a curvilinear coordinate system, forming the horizontal axis in the order of periodic nodes, starting from the starting point of the horizontal axis and using the water-coal ratio as the vertical axis;

[0088] d12. Then, the corresponding periodic nodes and water-coal ratio values are filled into the curve coordinate system, and the periodic nodes and water-coal ratio curves are established with smooth curves. The segmentation operation is performed according to the rise and fall of the periodic nodes and the water-coal ratio curves.

[0089] d13. The water-coal ratio safety threshold interval is introduced as the water-coal ratio threshold constant function, and the third hidden danger node is determined by the intersection of the water-coal ratio threshold maximum constant function with the periodic node and the rising curve in the water-coal ratio curve. The fourth hidden danger node is determined according to the intersection of the water-coal ratio threshold minimum constant function with the periodic node and the falling curve in the water-coal ratio curve. Then, the personnel processing reaction time T2 and the time T1 for completing the coordinated operation transmission are compensated to the hidden danger node to determine the corresponding water-coal ratio safety node.

[0090] In the embodiment of the present invention, the formula for determining the safety node in the operations of d03 and d13 is:

[0091] The formula for determining the fuel quantity safety node: G Z1 =F(Z1-T1-T2), when U x =W1 or U x =W2, and the corresponding cycle node at this time is Z1, (Z1-T1-T2) represents the time node after the corresponding cycle node compensation time, F(Z1-T1-T2) represents the fuel quantity value at the corresponding time node, G Z1 is the fuel quantity value when the cycle node is Z1, that is, the fuel quantity safety node;

[0092] The formula for determining the safety node of water-coal ratio is: (H x / G x ) Z2 =f(Z2-T1-T2), when (H x / G x )=K1or(H x / Gx )=K2, and the corresponding periodic node at this time is Z2, (Z2-T1-T2) represents the time node after the corresponding periodic node compensation time, f(Z1-T1-T2) represents the water-coal ratio value at the corresponding time node, (H x / G x ) Z2 It is the water-coal ratio value when the cycle node is Z2, that is, the water-coal ratio safety node.

[0093] In the embodiment of the present invention, the operation of introducing real-time operation data for prediction in S3 is:

[0094] s31. By collecting real-time operating data and tracing back to the fuel quantity safety node and the water-coal ratio safety node, determine the historical load demand;

[0095] s32. Compare the load demand corresponding to the safety node with the load demand in the real-time data. When the load demand in the real-time data reaches the load demand corresponding to the safety node, a control instruction is generated and transmitted to the thermal power unit for coordinated control.

[0096] By establishing curves for fuel quantity and boiler pressure at cycle nodes, as well as curves for cycle nodes and water-coal ratio, and analyzing the curves, we can obtain corresponding optimized values that can provide early warnings. When the load demand in real-time data meets the corresponding load demand at any safety node, it is necessary to determine whether it corresponds to a specific safety hazard situation, complete the load cruise control operation while maintaining the fault tolerance rate, and enable the thermal power unit to better achieve load supply.

[0097] The difference between Example 2 and Example 1 is that the present invention also uses the existing load control method and the load cruise control method of the present invention to control the simulated thermal power unit with problems, and records the number of problems predicted in advance and the time for completing the supply. The specific results are shown in Table 1:

[0098] Table 1 Control results

[0099] Problem prediction rate Supply processing time Existing load control methods 76％ 6h Load control method of the present invention 98％ 4.5h

[0100] To sum up, the load cruise control method of the present invention can predict problems in advance and complete the search for most existing problems in the control operation when the load demand changes. At the same time, after the load cruise control, the completion time of the supply can be greatly shortened, so it can be better implemented in actual application.

[0101] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0102] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0103] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for controlling peak load during transition of thermal power units based on an intelligent control algorithm, characterized by: The specific steps include: S1. Collect real-time and historical operating data of thermal power units, and collect historical load demand data; S2. Classify and process the data, first determining changes in load demand. Based on these changes, internal coordination of the thermal power units is achieved, and control operations on various factors within the boiler are implemented. The time from command generation to execution, as well as the setting of early warning thresholds within the boiler, are then analyzed. Compensation algorithms are used to compensate and optimize the coordination strategy, completing prediction operations when load changes occur. S3. Introduce the current real-time operating data, complete the prediction of subsequent load changes, generate corresponding control strategies, and display them on a visual interface.

2. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 1 is characterized in that: The operation of classifying the data in S2 is: s21. Initially classify the collected data according to real-time data and historical data, and set the classification template to implement the filling operation of the collected data; s22. The classification template uses the search criteria to complete the screening of real-time data and historical data, and repairs abnormal data in the filled data; s23. After the search is completed, the classification template is retained and classified in chronological order to form a data set for each individual category.

3. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 2, characterized in that: The operations in s22 are: The search criteria for the classification template are unit type as the first criterion, data category corresponding to the unit type as the second criterion, and data collection time as the third criterion; And according to the condition content and the collected data, a traversal operation is performed, and the numerical results of the data content that meets the condition content are filled into the classification template; Traverse the numerical result columns of the classification template to verify the blank result columns, and delete and repair the result columns with garbled characters.

4. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 1 is characterized in that: The operation of determining the load demand change in S2 is: A1. After extracting the load demand data, determine the period with the largest total load demand based on date changes, and extract the load demand data for the current period; A2. Establish a load change curve according to the time sequence and the corresponding load demand values, and calculate the average load demand value based on the load demand value at each time, and mark the nodes with higher load demand than the average load demand; The calculation formula for the average load demand value is: P 平 =(P1+P2+…+P n ) / n; P 平 is the average load demand value, and P n is the load demand value at the nth time node; A3. Determine the specific coordination operations of the corresponding thermal power units based on the marked nodes.

5. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 1 is characterized in that: The internal coordination operation of the thermal power generation units based on the load demand change in S2 is: B1. Based on the increase in load demand, a command is transmitted to the thermal power unit to implement coordinated control of the steam turbine and boiler. The steam turbine master control responds and generates a command that is transmitted to the boiler master control for coordinated control operations. B2. After recording the load demand changes, an instruction is generated and transmitted to the boiler master control to complete the coordinated operation. The transmission time is T1. Then, according to the instruction, the fuel amount and water supply amount of the boiler are controlled to complete the regulation of the thermal power unit and generate the corresponding load supply.

6. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 1, characterized in that: The specific operation of the compensation algorithm in S2 is: C1. When extracting the corresponding marked node part, the total fuel amount of the boiler at the cycle node is marked as G x , x represents the number of cycle nodes, and x∈{1, 2, 3, ...} the time intervals between adjacent cycle nodes are the same. When extracting the corresponding marked node part, the real-time pressure value of the boiler corresponding to the cycle node is marked as U x , and the total water supply at the corresponding cycle node is the total H x ; C2. Set the boiler pressure safety threshold interval to [W1, W2] and the boiler water-coal ratio safety threshold interval to [K1, K2]. Extract multiple processing times after exceeding the safety threshold interval during the operation of the thermal power unit. After removing outliers, select the maximum value as the human response time and label it as T2. C3. Establish curves for fuel quantity and boiler pressure at cycle nodes, as well as curves for cycle nodes and water-coal ratio. By analyzing the curves, obtain corresponding optimized values that can provide early warning.

7. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 6 is characterized in that: The curve analysis operation of the fuel quantity and boiler pressure at the period node in C3 is: d01. Establish a curvilinear coordinate system, forming the horizontal axis in the order of the periodic nodes, starting from the starting point of the horizontal axis, and using the fuel quantity and boiler pressure as the vertical axis; d02. Then, the fuel quantity and boiler pressure values at the corresponding period nodes are filled into the curve coordinate system, and the fuel quantity and boiler pressure curves are established using smooth curves. The segmentation operation is performed according to the rise and fall of the fuel quantity and boiler pressure curves; d03. The pressure safety threshold interval is introduced as a pressure threshold constant function, and the first hidden danger node is determined by the intersection of the pressure threshold maximum constant function and the rising curve of the fuel quantity and boiler pressure curve. The second hidden danger node is then determined based on the intersection of the pressure threshold minimum constant function and the falling curve of the fuel quantity and boiler pressure curve. The reaction time T2 of the personnel processing and the time T1 for completing the coordinated operation transmission are then compensated to determine the corresponding fuel quantity safety node before the hidden danger node.

8. The method for controlling peak load during transition of a thermal power plant based on an intelligent control algorithm according to claim 7 is characterized in that: The curve analysis operation of the water-coal ratio and boiler pressure at the periodic node C3 is as follows: d11. Establish a curvilinear coordinate system, forming the horizontal axis in the order of periodic nodes, starting from the starting point of the horizontal axis and using the water-coal ratio as the vertical axis; d12. Then, the corresponding periodic nodes and water-coal ratio values are filled into the curve coordinate system, and the periodic nodes and water-coal ratio curves are established with smooth curves. The segmentation operation is performed according to the rise and fall of the periodic nodes and the water-coal ratio curves. d13. The water-coal ratio safety threshold interval is introduced as the water-coal ratio threshold constant function, and the third hidden danger node is determined by the intersection of the water-coal ratio threshold maximum constant function with the periodic node and the rising curve in the water-coal ratio curve. The fourth hidden danger node is determined according to the intersection of the water-coal ratio threshold minimum constant function with the periodic node and the falling curve in the water-coal ratio curve. Then, the personnel processing reaction time T2 and the time T1 for completing the coordinated operation transmission are compensated to the hidden danger node to determine the corresponding water-coal ratio safety node.

9. The method for controlling peak load cruise during transition of a thermal power plant based on an intelligent control algorithm according to claim 8, characterized in that: The formula for determining the safety node in the operations of d03 and d13 is: The formula for determining the fuel quantity safety node: G Z1 =F(Z1-T1-T2), when U x =W1 or U x =W2, and the corresponding cycle node at this time is Z1, (Z1-T1-T2) represents the time node after the corresponding cycle node compensation time, F(Z1-T1-T2) represents the fuel quantity value at the corresponding time node, G Z1 is the fuel quantity value when the cycle node is Z1, that is, the fuel quantity safety node; The formula for determining the safety node of water-coal ratio is: (H x / G x ) Z2 =f(Z2-T1-T2), when (H x / G x )=K1or(H x / G x )=K2, and the corresponding periodic node at this time is Z2, (Z2-T1-T2) represents the time node after the corresponding periodic node compensation time, f(Z1-T1-T2) represents the water-coal ratio value at the corresponding time node, (H x / G x ) Z2 It is the water-coal ratio value when the cycle node is Z2, that is, the water-coal ratio safety node.

10. The method for controlling peak load during transition of thermal power generation units based on an intelligent control algorithm according to claim 9, characterized in that: The operations of introducing real-time running data into S3 for prediction are as follows: s31. By collecting real-time operating data and tracing back to the fuel quantity safety node and the water-coal ratio safety node, determine the historical load demand; s32. Compare the load demand corresponding to the safety node with the load demand in the real-time data. When the load demand in the real-time data reaches the load demand corresponding to the safety node, a control instruction is generated and transmitted to the thermal power unit for coordinated control.

Images