A boiler denitrification intelligent control method and system

Abstract

The present invention relates to the field of intelligent control technology, including a method and system for intelligent control of boiler denitrification, comprising the following steps: obtaining the calculated difference between the current and previous cycle NOx concentrations, generating a jump concentration determination result, screening the response area based on the determination result in combination with the disturbance ratio, calculating the response delay to generate delay data, fitting the lag and residual to generate a correlation coefficient, extracting the positive relationship micro-area calculation and correcting the ammonia injection parameters, and generating a control adjustment record. In the present invention, the accuracy of local anomaly identification is enhanced by analyzing the ratio of concentration jump to disturbance deviation, optimizing the stability of response area identification by combining point set statistics, tracking the timing of ammonia injection startup and NOx response to clarify the reaction dynamics, improving the regulation time control power, linearly fitting the residual and lag to establish an error correlation path, analyzing the source of transmission distortion, and implementing a joint correction of proportion and concentration in combination with the lag relationship to achieve precise ammonia dosing and enhance the efficiency and dynamic stability of boiler flue gas denitrification.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a boiler denitration intelligent control method and system. Background Art

[0002] The field of intelligent control technology involves the dynamic regulation and control of various production processes through the perception and analysis of the operating status of industrial systems. Its core content is the use of computer technology, control theory, and sensor detection methods to collect information, make decisions, and execute control on target systems. Covering multiple areas such as industrial automation, process control, and energy management, it is characterized by systematicity, multivariable coupling, and dynamic characteristics. In particular, in the operational control of energy equipment, intelligent control places special emphasis on adaptive regulation of complex operating conditions and optimized control of operating efficiency. It is commonly used in power plant boilers, combustion devices, chemical reaction processes, and other fields.

[0003] The intelligent boiler denitrification control method is a process control method based on real-time monitoring of nitrogen oxide emission characteristics during boiler combustion, using set rule parameters to control the operation of the denitrification system. This method involves real-time collection of boiler combustion conditions and flue gas composition, and uses a set program flow to logically determine and proportionally adjust the amount and location of ammonia injection to regulate the selective catalytic reduction reaction process. Specifically, it uses flue gas nitrogen oxide concentration data and furnace load conditions as the basis for judgment, and uses control parameters to adjust the system's actuators to achieve regulation and control of the denitrification agent dosage.

[0004] In the existing boiler denitrification process, the single variable control path based on concentration or load is generally used, which lacks the ability to identify the dynamic linkage of emission behavior. The point identification process mainly relies on fixed threshold rules, resulting in weak ability to identify local anomalies and easy misjudgment of response areas under complex disturbance backgrounds. The ammonia injection reaction lag mainly relies on empirical parameter estimation, which fails to reflect the time matching between the ammonia injection action and the actual emission response, resulting in accumulated control delays and affecting the effectiveness of real-time regulation. Residual control tends to correct static errors, lacks a structural analysis and tracing mechanism for the source of errors, and cannot identify regulation imbalances caused by uneven system responses. Ammonia injection regulation generally adopts a single proportional control method, ignoring the coupling relationship between dynamic response and local residuals, resulting in local over- or under-dosing under multi-variable changes, restricting the efficient operation of the denitrification process. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent control method for boiler denitrification.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a boiler denitrification intelligent control method, comprising the following steps:

[0007] S1: Obtain the current NOx concentration value of the boiler furnace NOx detection point and the NOx concentration value at the corresponding time of the previous sampling cycle, calculate the concentration difference and compare it with the jump recognition threshold to generate the jump concentration judgment result;

[0008] S2: Based on the jump concentration determination result, the disturbance deviation is calculated by combining the airflow velocity value and the standard flow velocity reference value, and whether the deviation value exceeds the reference is determined. The concentration difference value and the disturbance deviation ratio are simultaneously calculated, and the area where the ratio exceeds the limit is screened to generate the ammonia injection response area identification result;

[0009] S3: Based on the ammonia injection response area identification result, extract the ammonia injection start time and the time point when the NOx concentration first decreases, calculate the response delay value, and generate NOx response delay data;

[0010] S4: Based on the NOx response delay data, the difference between the response delay value and the theoretical response time is calculated as a hysteresis value, the real-time NOx residual value of the corresponding point is collected, a linear fit is performed between the hysteresis value and the real-time residual value, and a relationship of the same direction of change is determined to generate residual hysteresis correlation data;

[0011] S5: Determine the residual lag correlation data, extract the ammonia injection amount and liquid supply concentration values in the positive correlation micro-area, calculate the ammonia injection amount adjustment ratio and concentration adjustment ratio in combination with the NOx real-time residual value, perform correction actions, and generate an ammonia injection control adjustment record.

[0012] As a further solution of the present invention, the jump concentration judgment result includes the jump point position identifier, jump amplitude level, and jump trend direction; the ammonia injection response area identification result includes the high response area position, response intensity level, and response influence range; the NOx response delay data includes the response time difference sequence, the response start time set, and the response end time set; the residual lag correlation data includes the linear fitting slope value, the change direction consistency index, and the lag and residual fitting degree; the ammonia injection control adjustment record includes the ammonia injection adjustment ratio, the liquid supply concentration adjustment ratio, and the adjustment applicable area.

[0013] As a further solution of the present invention, the step of obtaining the jump concentration determination result includes:

[0014] S111: Calculate the difference between the current NOx concentration value at the boiler furnace NOx flue gas detection point and the NOx concentration value at the corresponding moment of the previous sampling period. Calculate the difference using the absolute difference between the current NOx concentration value and the NOx concentration value of the previous period to obtain a concentration change difference.

[0015] S112: Compare the concentration change difference with the jump recognition threshold item by item, identify the concentration change difference item that is greater than the jump recognition threshold, and use the formula:

[0016] ;

[0017] Calculate the multi-cycle composite concentration fluctuation value , obtain the jump concentration judgment index value, where, Represents the NOx concentration value of the current cycle, Represents the NOx concentration value of the previous cycle, represents the average value of the transition recognition threshold;

[0018] S113: According to the magnitude relationship between the jump concentration judgment index value and the jump identification threshold, mark all time points where the jump concentration judgment index value is greater than the jump identification threshold and the corresponding detection point sequence number to generate a jump concentration judgment result.

[0019] As a further embodiment of the present invention, the step of obtaining the identification result of the ammonia injection response area includes:

[0020] S211: Based on the jump concentration determination result, the difference between the airflow velocity value at each detection point and the corresponding standard flow velocity reference value is calculated, and the absolute value is taken to obtain the flow velocity disturbance value at each detection point. The degree of disturbance is calculated by the ratio of the disturbance value to the reference value to obtain the disturbance deviation ratio;

[0021] S212: Perform joint processing based on the disturbance deviation ratio and the concentration change difference of the corresponding detection point, using the formula:

[0022] ;

[0023] Calculate the concentration perturbation composite ratio ,in, represents the NOx concentration value at the i-th moment, Indicates the NOx concentration value at the previous moment, represents the airflow velocity value at point i, Indicates the standard flow rate reference value at point i;

[0024] S213: Based on the concentration disturbance composite ratio, compare with a preset concentration disturbance identification threshold, screen all spatial areas where the ratio exceeds the threshold, and record the corresponding detection point position information and time information to establish an ammonia injection response area identification result.

[0025] As a further solution of the present invention, the step of acquiring NOx response delay data includes:

[0026] S311: Based on the set of points in the ammonia injection response area identification result, continuous time series values of NOx concentration corresponding to each point after the ammonia injection action are collected. According to the changing trend of the NOx concentration values in the collection sequence of each point, the direction of the value fluctuation between each time series point is determined, and the time when the NOx concentration first changes from a non-decreasing state to a decreasing state is identified, and the time point of the first decrease in NOx concentration is obtained;

[0027] S312: Calculate the time difference between the first drop time of the NOx concentration and the trigger time of the ammonia injection action at each point, record the time interval data corresponding to each point, and obtain the point response delay value;

[0028] S313: Based on the point response delay value, the response time of each point after the ammonia injection action is triggered is arranged in sequence according to the point number and time sequence to form a cross-point response time set and establish NOx response delay data.

[0029] As a further solution of the present invention, the step of obtaining the residual lag correlation data includes:

[0030] S411: Calculating the theoretical response time of each point under the current liquid supply conditions based on the response delay value of each point in the NOx response delay data and the current liquid supply conditions, and subtracting the response delay value of each point from the theoretical response time to obtain a response lag value for each point;

[0031] S412: Based on the response hysteresis value of each point, the difference between the real-time NOx concentration of each point after the end of the current cycle and the corresponding reference concentration before ammonia injection is collected to construct a set of real-time NOx residual values corresponding to each point, using the formula:

[0032] ;

[0033] Calculate the residual lagged slope value ,in, represents the response lag value of point i, represents the real-time residual value of NOx at point i, represents the average value of all point response lag values, Represents the average value of the real-time residual value of NOx at all points, Indicates the number of points;

[0034] S413: Arrange the point slope values and the isotropic judgment results according to the residual lag slope values, output the correlation strength between the lag and the residual at each point in time sequence, and establish residual lag correlation data.

[0035] As a further embodiment of the present invention, the step of obtaining the ammonia injection control adjustment record includes:

[0036] S511: Based on the residual lag correlation data, screen the point area with a positive slope value, identify the micro-area with a positive residual lag relationship in the current cycle, extract the ammonia injection amount data and the liquid supply concentration value of the point corresponding to the micro-area, and obtain the positive micro-area ammonia injection and liquid supply data;

[0037] S512: Based on the forward micro-area ammonia injection liquid supply data and the real-time residual value of NOx at the corresponding point, the offset degree of the current liquid supply parameter to the residual response is calculated, and the adjustment ratio of the ammonia injection amount and the adjustment ratio of the liquid supply concentration are calculated to generate ammonia injection control offset ratio data;

[0038] S513: According to the ammonia injection control offset ratio data, a correction operation of the ammonia injection amount and the liquid supply concentration at the corresponding point is performed, the corresponding parameter change values and correction directions before and after the adjustment are recorded, and an ammonia injection control adjustment record is established.

[0039] A boiler denitrification intelligent control system, comprising:

[0040] The jump recognition module obtains the NOx concentration value of the current detection point and the previous cycle, calculates the difference and compares it with the jump recognition threshold, selects the jump point, and generates the concentration jump judgment result;

[0041] The response identification module obtains the airflow velocity value and the flow velocity reference value according to the concentration jump determination result, calculates the disturbance deviation ratio, determines the response point, and generates an ammonia injection response area identification result;

[0042] The time delay determination module extracts the time between the start of ammonia injection and the decrease of NOx concentration based on the ammonia injection response area identification result, calculates and determines the response delay value, and generates NOx response delay data;

[0043] The residual correlation module obtains the response hysteresis value and the NOx residual value based on the NOx response delay data, performs linear fitting, extracts the slope to determine the same-direction change relationship, and generates residual hysteresis correlation data;

[0044] The control and adjustment module extracts the ammonia injection amount and the liquid supply concentration according to the residual lag correlation data, calculates the adjustment data in combination with the residual value, performs the correction action, and generates an ammonia injection control and adjustment record.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, by real-time identification of the trend of flue gas NOx concentration changes and combining the response ratio relationship between the concentration mutation amplitude and the airflow disturbance intensity, high-sensitivity identification of emission status is achieved, and local response capability under unstable working conditions is enhanced. A statistical mechanism of continuous point sets is introduced in the comparison of concentration changes and disturbance differences, so that the identification of response areas is more collective and structured, avoiding interference caused by isolated point misjudgment. By time-series tracking the delayed relationship between the start of ammonia injection and the decrease in NOx concentration, a stable reaction dynamic evaluation system is formed, providing clear time limit support for subsequent adjustment actions. The linear fitting of residuals and theoretical lags further reveals the potential lag source of control deviation. The changes in slope and directionality map the transmission distortion in the control chain, and the evaluation method of the error correlation structure is optimized. After determining the NOx concentration residual influence area, a linkage mechanism of proportional adjustment and concentration correction is introduced to achieve real-time differentiated regulation based on response lag, effectively control the resource input redundancy in non-target areas, improve the overall reaction efficiency, form high adaptability and strong coupling response capability, and improve the stability and energy saving of the denitrification process. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of the main steps of the present invention;

[0048] Figure 2 This is a flow chart for obtaining the jump concentration determination result of the present invention;

[0049] Figure 3 A flowchart for obtaining the identification result of the ammonia injection response area of the present invention;

[0050] Figure 4 This is a flow chart for obtaining NOx response delay data of the present invention;

[0051] Figure 5 This is a flow chart for obtaining residual lag correlation data of the present invention;

[0052] Figure 6 A flow chart for obtaining ammonia injection control and adjustment records according to the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0055] See also Figure 1 , a boiler denitrification intelligent control method, comprising the following steps:

[0056] S1: Obtain the current NOx concentration value of the boiler furnace NOx flue gas detection point and the NOx concentration value at the corresponding time of the previous sampling cycle, calculate the concentration difference, and compare it with the jump recognition threshold one by one. When the concentration difference is greater than the jump recognition threshold, it is marked as a concentration jump point and the jump concentration judgment result is generated;

[0057] S2: Based on the jump concentration determination result, the current airflow velocity value at the concentration jump point is recorded. Combined with the standard flow velocity reference value under the current boiler load state, the absolute difference between the airflow velocity value and the reference value is calculated to obtain a disturbance deviation value. The ratio between the concentration difference value and the disturbance deviation value is calculated and compared with the ammonia injection response ratio threshold. The set of points with a value higher than the ammonia injection response ratio threshold is counted to generate the ammonia injection response area identification result.

[0058] S3: Based on the point set in the ammonia injection response area identification results, collect the continuous time series values of the NOx concentration corresponding to the point after the ammonia injection action, extract the time when the ammonia injection starts and the time when the NOx concentration first drops, calculate the time difference between the two and define it as the response delay value, and generate NOx response delay data;

[0059] S4: Based on the response delay value of each point in the NOx response delay data, the theoretical response time of the current liquid supply reaction is obtained, the difference between each response delay value and the theoretical response time is calculated as the hysteresis value, the real-time NOx residual value of the corresponding point after the end of the current cycle is collected, and a linear fit judgment is performed between the hysteresis value and the real-time residual value. The slope value is extracted and the relationship of the same direction change is judged to generate residual hysteresis correlation data;

[0060] S5: Determine the micro-area with a positive relationship in the residual lag correlation data, extract the ammonia injection amount and the liquid supply concentration value in the current cycle, calculate the ammonia injection amount adjustment ratio and the concentration adjustment ratio in combination with the NOx real-time residual value, and perform correction actions to generate an ammonia injection control adjustment record.

[0061] The jump concentration determination results include the jump point location identification, jump amplitude level, and jump trend direction; the ammonia injection response area identification results include the high response area location, response intensity level, and response influence range; the NOx response delay data include the response time difference sequence, the response start time set, and the response end time set; the residual lag correlation data include the linear fitting slope value, the change direction consistency index, and the lag and residual fitting degree; the ammonia injection control adjustment record includes the ammonia injection adjustment ratio, the liquid supply concentration adjustment ratio, and the adjustment applicable area.

[0062] See also Figure 2 , S1 step is:

[0063] S111: Calculate the difference between the current NOx concentration value at the boiler furnace NOx flue gas detection point and the NOx concentration value at the corresponding moment of the previous sampling period. Calculate the difference using the absolute difference between the current NOx concentration value and the NOx concentration value of the previous period to obtain a concentration change difference.

[0064] Based on the current NOx concentration value of the boiler furnace NOx flue gas detection point and the NOx concentration value at the corresponding moment of the previous sampling cycle, the corresponding values of each detection point in the two cycles are obtained, and the difference calculation operation is performed on each pair of data, and the absolute value is taken as the concentration change difference of this round of sampling cycle. When performing the specific execution, taking the detection point numbered A1 as an example, the current cycle concentration value is 165mg / m³, and the previous cycle concentration value is 160mg / m³, then the difference is calculated as Similarly, the current value of detection point A2 is 172mg / m³, and the value in the previous cycle was 170mg / m³. The calculated difference is , follow this operation to complete the difference acquisition of all monitoring points, and obtain a set of concentration change difference data. The results are shown in the following table:

[0065] Table 1 NOx concentration change difference table at monitoring points

[0066]

[0067] As shown in Table 1, after comparing the current NOx concentration value of each detection point with that of the previous cycle, a clear change difference is formed. This difference is the core indicator in the subsequent jump identification operation to obtain the concentration change difference.

[0068] S112: Compare the concentration change difference with the jump recognition threshold item by item, and identify the concentration change difference item that is greater than the jump recognition threshold, using the formula:

[0069] ;

[0070] Calculate the multi-cycle composite concentration fluctuation value , obtain the jump concentration judgment index value, where, Represents the NOx concentration value of the current cycle, Represents the NOx concentration value of the previous cycle, represents the average value of the transition recognition threshold;

[0071] According to the concentration change difference, the data of each point is analyzed and processed jointly with the set jump recognition threshold. In the judgment process, the recognition of concentration mutation is enhanced by adding a square root of square difference. Taking point A1 as an example, the current value is 165 and the value of the previous cycle is 160. The calculation is performed to obtain , , the total is For point A3, the current value is 169, and the previous period is 165. The calculation result is , applying the above operation to all detection points, we get the following results:

[0072] Table 2 Calculation table of jump concentration judgment index

[0073]

[0074] As shown in Table 2, for the judgment values of each point, when the result is greater than 3.5mg / m³, it is determined to be a jump item. The setting of the threshold of 3.5mg / m³ is based on the NOx emission fluctuation range of different load stages under the actual boiler operation state. Specifically, it refers to the fluctuation range of the average difference in NOx concentration between two adjacent time periods within the load change cycle. This range is usually concentrated between 2.8 and 3.2mg / m³. In order to improve the sensitivity of recognition and eliminate the interference of small disturbances in some stable operation periods, this system adjusts the threshold upward to 3.5mg / m³ to ensure that transient fluctuations of 5mg / m³ and above can be detected. For response, in actual operation, the threshold value will be dynamically fine-tuned with the change of boiler load. When the load increases, the NOx emission range will increase. When setting, the threshold value will be slightly increased with the increase of main steam flow, and vice versa. The final selected value is a medium-high setting of the average difference monitored under typical high-load conditions, which is representative and robust. During the judgment process, all parameters are directly collected and calculated through data without manual setting. The benefit of the formula is that the fluctuation sensitivity of the numerical level is enhanced by superimposing the square root of the difference, thereby providing a clear judgment boundary for the threshold exceeding behavior and obtaining the jump concentration judgment index value.

[0075] S113: Based on the magnitude relationship between the jump concentration determination index value and the jump identification threshold, mark all time points where the jump concentration determination index value is greater than the jump identification threshold and the corresponding detection point sequence number, and generate a jump concentration determination result;

[0076] Based on the jump concentration judgment index value and the set jump identification threshold of 3.5mg / m³, each judgment is performed item by item. For monitoring points with judgment values higher than the threshold, jump mark identification is performed. When performing the judgment operation, the points with comparison values greater than the threshold are directly recorded with their sampling cycle time and point number. The judgment values of A1, A3 and A4 are 6.5, 4.5 and 6.5 respectively, all greater than the threshold, and therefore are identified as jump points. The value of A2 is 0.5, which is lower than the threshold and is not marked. In the result record, the time series and point number need to be organized to form the judgment result item, and finally a structured jump concentration result set is output to generate the jump concentration judgment result.

[0077] See also Figure 3 , step S2 is:

[0078] S211: Based on the jump concentration determination result, the airflow velocity value at each detection point is combined with the corresponding standard flow velocity reference value to calculate the difference between the two, and the absolute value is taken to obtain the flow velocity disturbance value at each detection point. The degree of disturbance is calculated by the ratio of the disturbance value to the reference value to obtain the disturbance deviation ratio;

[0079] Based on the jump concentration judgment result, it is necessary to clarify the difference between the airflow velocity associated with each monitoring point and the standard flow velocity reference value. In practice, the airflow velocity can be collected through the wind speed measurement points arranged in the boiler furnace. For example, if the airflow velocity collected at a certain measurement point during the sampling period is 12.4m / s, and the standard flow velocity reference value of this point under steady-state operation is 10.0m / s, then the flow velocity disturbance value of this measurement point is 12.4-10.0=2.4m / s. In order to obtain the degree of disturbance, it is necessary to construct a disturbance deviation ratio, which can be obtained by comparing the disturbance amount with the standard flow velocity reference value, that is: 2.4 / 10.0=0.24. If the disturbance deviation reference value set by the system is 0.2, then the ratio is judged to be out of limit state, which is specific. The judgment standard is divided into the following intervals: the disturbance deviation ratio is less than or equal to 0.1 and is considered a stable interval; 0.1 to 0.2 is a critical fluctuation interval; and more than 0.2 is an abnormal disturbance interval. This type of interval needs to be included in the subsequent joint identification. If the collection point is marked as a jump point in the jump concentration judgment result at the same time point, the concentration change difference is the current concentration minus the concentration at the previous moment. Assuming that the current NOx concentration is 105mg / m³ and the previous cycle is 95mg / m³, the difference is 10mg / m³, which can be directly incorporated into the subsequent calculation to form a cross data pair. This data pair is the corresponding result pair of disturbance deviation and concentration change, which can form a dual-parameter input item corresponding to multiple detection points and establish a disturbance deviation ratio.

[0080] S212: Combined processing is performed based on the disturbance deviation ratio and the concentration change difference of the corresponding detection point, using the formula:

[0081] ;

[0082] Calculate the concentration perturbation composite ratio ,in, represents the NOx concentration value at the i-th moment, Indicates the NOx concentration value at the previous moment, represents the airflow velocity value at point i, Indicates the standard flow rate reference value at point i;

[0083] According to the coordinated change trend between the disturbance deviation ratio and the concentration change difference, it is necessary to establish a cross-parameter coupling relationship measurement index. Here, the method of constructing a concentration disturbance composite ratio is adopted. During the implementation process, for each detection point, it is necessary to obtain the absolute difference between the current NOx concentration value and the previous NOx concentration value. At the same time, it is also necessary to obtain the current airflow velocity value and the standard flow velocity reference value of the corresponding point. Then, the actual calculation is performed based on the formula. Assume that the corresponding parameters of a certain monitoring point are:

[0084] , , , , then the calculation process is as follows:

[0085] Calculate the molecular part:

[0086] ;

[0087] Calculate the denominator:

[0088] ;

[0089] Calculate the composite ratio:

[0090] ;

[0091] The results show that the concentration disturbance composite ratio of the detection point in the current cycle is 0.117. The results can be further summarized to determine whether it is in the scope of the linkage ammonia injection response. The operating data of the monitoring point is listed as follows:

[0092] Table 3 Ammonia injection area detection point operating parameters

[0093]

[0094] Table 3 lists the experimental data. The above data are all collected from actual tests. Based on this data, a composite ratio group of multiple detection points can be further formed as the input basis for judging whether the ratio exceeds the limit.

[0095] S213: Based on the concentration disturbance composite ratio, the preset concentration disturbance identification threshold is compared, all spatial regions where the ratio exceeds the threshold are screened, and the position information and time information of the corresponding detection points are recorded to establish the ammonia injection response area identification result;

[0096] According to the composite ratio of concentration disturbance, positioning and screening operations are performed in the time dimension and the spatial detection point dimension. In the specific implementation, the composite ratio judgment result of each detection point can be called, and the recognition threshold is set to 0.10 to determine whether it is greater than the threshold. If the conditions are met, the corresponding point number and the detection time point information are extracted to form a data marking structure, which can be used for response area mapping. For example, for the detection point A1 in Table 1, because its composite ratio is 0.117>0.10, it is marked as a response area point, and its sampling period is recorded as "t4" and the spatial position is labeled "A1". In this way, the screening operation of the ammonia injection interval data is completed and the ammonia injection response area recognition result is established. The setting of the above recognition threshold is based on the airflow disturbance and Based on the coordinated fluctuations between NOx concentration mutations, the composite ratio value ranges of the stable and disturbed sections under multiple representative operating cycles in actual operating conditions were extracted respectively, and their cross-fluctuation boundary intervals were calculated. Finally, the average value at the intersection of the two value ranges was selected as the standard line of the identification threshold. Specifically, the composite ratio is minimum at 0.102 in the disturbance interval and maximum at 0.098 in the stable interval. The critical value is set at 0.10 at the intersection of the two. The threshold fluctuates with the changes in boiler load level, airflow density and sampling frequency within the detection period. The fine-tuning interval can be set separately under different load levels to cover the numerical variation range under different operating conditions, so that the identification limit is always kept within the state interval with high distinguishability.

[0097] See also Figure 4 , S3 steps are:

[0098] S311: Based on the set of points in the ammonia injection response area identification results, collect continuous time series values of NOx concentration corresponding to each point after the ammonia injection action. Based on the changing trend of the NOx concentration values in the collection sequence of each point, determine the direction of value fluctuation between each time series point, identify the time when the NOx concentration first changes from a non-decreasing state to a decreasing state, and obtain the time point when the NOx concentration first decreases.

[0099] Based on the point set in the ammonia injection response area identification result, each identified point is marked and associated with the concentration value time series channel in the monitoring database according to the number. NOx concentration data within 30 minutes after the ammonia injection action is continuously collected from each channel. The sampling frequency is set to 1 time per minute, that is, 30 groups of NOx concentration time series values are obtained for each point. For example, the sequence collected at point A001 within 30 minutes after the ammonia injection is {129, 127, 128, 124, 122, 121...}. This sequence is used as the basis for subsequent analysis of this point. Next, the actual start time of the ammonia injection action at each point needs to be determined. The start time data comes from the control system execution signal record. For example, the start time of the ammonia injection action at point A001 is 13:02. This information is accurately recorded in seconds. At the same time, the NOx concentration time series value is timestamped. The first drop is judged by matching rows and then performing a "first drop" judgment in the NOx concentration sequence corresponding to each point. During the judgment process, the difference between the first set of data after the ammonia injection action is started and the previous one is compared backward. If the current value shows a downward trend of less than or equal to negative 2ppm compared with the previous value, it is judged to be the first drop. For example, in the A001 point sequence, the value at 13:03 minutes is 127, and the value at 13:04 minutes is 124, so the first drop time is considered to be 13:04. This judgment rule sets the drop amplitude threshold to 2ppm, which is the system default setting value. According to the historical equipment response range setting, the reasonable range is 1.5ppm to 3ppm. In this embodiment, the value is uniformly set to 2ppm. Through this rule, the time point of the first NOx concentration drop at all ammonia injection response points can be obtained. Some sample data are shown in the following table:

[0100] Table 4 Example of concentration change time series at ammonia injection response points

[0101]

[0102] As shown in Table 4, the first drop time of point A001 occurs in the second minute after the ammonia injection. Compared with other points, it can establish a basis for subsequent analysis.

[0103] S312: Calculate the time difference between the first drop time of NOx concentration and the trigger time of ammonia injection at each location, record the time interval data corresponding to each location, and obtain the location response delay value;

[0104] According to the time point of the first drop in NOx concentration obtained above, combined with the trigger time of the ammonia injection action corresponding to the point, the time interval between the two is calculated point by point as the basic data of the point response delay. For example, point A001 starts ammonia injection at 13:02, and the concentration drops for the first time at 13:04, then the response delay is 2 minutes. In this process, an "absolute time difference" operation needs to be performed on each pair of time values. The conversion unit is seconds. The execution method is to take the difference between the two timestamps and convert them into seconds. The time difference is the point response delay. For example, for A001, the time difference is 13:04-13:02=2 minutes=120 seconds. The NOx concentration change intensity factor is further introduced, and the 1 / 2 average weight term of the total concentration change amplitude is superimposed on the response time difference. The concentration change value is obtained by taking the absolute value of each item in the continuous time series value sequence and then summing them up. For example, A001 The 30-minute sampling sequence at point A001 is {129, 127, 128, 124…}, so the difference sequence is {2, 1, 4,…}. After summing, assume the total difference is 48 ppm. Take half of this, 24, and add it to the time difference. The corrected response delay for this point is 120 + 24 = 144 seconds. Then introduce the reference fluctuations M and N for mean square root correction. Assuming that the average concentration difference at point A001 3 minutes before ammonia injection is M = 5 ppm and 3 minutes after ammonia injection is N = 12 ppm, the correction term is √(5² + 12²) = 13.0 ppm. The final response delay is 144 ÷ 13.0 ≈ 11.08 seconds. This value is used to represent the actual effective delay time of the ammonia injection response. For unified management purposes, retain two decimal places to form a unified data format output, recorded as 11.08. After processing all points in this way, a set of point response delay values can be formed.

[0105] S313: Based on the point response delay value, the response time of each point after the ammonia injection action is triggered is arranged in order of point number and time to form a cross-point response time set and establish NOx response delay data;

[0106] Based on the point response delay values obtained in the previous section, each point is sorted in ascending order by number and, combined with the response time values, a dual index is established to form a traceable response process time series. The response time required for each point after ammonia injection is then recorded in a unified table structure. For example, the response delays for points A001 and A002 are 11.08 seconds and 12.75 seconds, respectively. This data is recorded in the system database field to enable unified analysis of the response behavior trends of each point. All point response time data can also be categorized into three intervals: less than 30 seconds, 30 to 60 seconds, and more than 60 seconds. For example, less than 30 seconds is designated as "fast response," 30 to 60 seconds as "medium response," and more than 60 seconds as "slow response." Combined with the field attributes, these data are recorded in a unified output table, enabling the system to track and quickly locate high-latency points. For example, the response delay of point A001, 11.08 seconds, falls into the fast response category, and the field recorded in the subsequent output data structure is "fast response."

[0107] See also Figure 5 , step S4 is:

[0108] S411: Based on the response delay value of each point in the NOx response delay data and the current liquid supply conditions, the theoretical response time of each point under the current liquid supply conditions is calculated, and the response delay value of each point is subtracted from the theoretical response time to obtain the response lag value of each point;

[0109] Based on the response delay value of each point in the NOx response delay data, the acquisition of the response delay value needs to be further refined. First, for the point set indicated by the data source, the number of corresponding points and their spatial positions are clarified. For example, a total of 9 points are sampled in the upper, middle and lower layers of the boiler furnace, and their NOx response delay values are recorded in different operating cycles. This value is obtained by the difference between the ammonia injection trigger time and the first NOx drop time defined in the previous paragraph. For example, the ammonia injection action of point A occurs at the 350th second, and the corresponding NOx first drop is recorded at the 362nd second. Its response delay value is 12 seconds. The remaining points are calculated in this way. For the theoretical response time of the reaction under the liquid supply condition, it is necessary to first collect parameters such as the current ammonia injection flow rate, ammonia diffusion rate, and spatial distribution. For example, the current liquid supply flow rate is 80L / h. According to the historical operation records and experimental fitting relationship, it can be known that the theoretical diffusion reaction time under this condition is 10 seconds. The reaction time is determined by the distance from the ammonia injection inlet to the target point, the ambient temperature, the mixing state, etc. For example, the lower point is within 3 meters from the ammonia injection inlet, and the diffusion rate is 0.3m / s at a temperature of 60°C. The obtained time is seconds, the theoretical response time is recorded as 10 seconds. For example, if the response delay of the above point is 12 seconds, the hysteresis value is 2 seconds. If the response delay of point B is 9 seconds, the hysteresis value is -1 second. In actual operation, the response delay of each point and the theoretical time are recorded in the data table, see Table 5:

[0110] Table 5 Hysteresis value calculation data table

[0111]

[0112] As shown in Table 5, the acquisition of hysteresis values requires the joint execution of the difference calculation process in combination with the timing response and the theoretical time of the working condition estimation. The obtained hysteresis value of the response at each point is the core data required for the next step of analysis.

[0113] S412: Based on the response hysteresis value of each point, the difference between the real-time NOx concentration of each point after the end of the current cycle and the corresponding reference concentration before ammonia injection is collected to construct a set of real-time NOx residual values corresponding to each point, using the formula:

[0114] ;

[0115] Calculate the residual lagged slope value ,in, represents the response lag value of point i, represents the real-time residual value of NOx at point i, represents the average value of all point response lag values, Represents the average value of the real-time residual value of NOx at all points, Indicates the number of points;

[0116] According to the response hysteresis value of each point mentioned above, it is necessary to further collect NOx concentration data after the end of the current working cycle. This data comes from the actual NOx emission value recorded at the detection point. For example, the NOx concentration at the end of the current cycle at point A is 85mg / m³, while the corresponding baseline concentration at this point before ammonia injection is 90mg / m³, and the real-time residual value is -5mg / m³. Perform this operation on all points to obtain the residual value of each point. , and the response lag value of the point is recorded as . Then, two sets of sequence data were constructed and , perform linear fitting operation and obtain the total number of points , respectively, into the hysteresis values in the above table : 2, -1, 5, corresponding to the residual value :-5,-2,-10, calculate the average value of each group , . Further calculation of the molecular part:

[0117] ;

[0118] ;

[0119] The denominator is:

[0120] ;

[0121] Therefore, the slope The result is a negative value of -1.33, which means that the later the response is, the more negative the residual tends to be, and the two show a downward trend in the same direction.

[0122] S413: Based on the residual lag slope value, the point slope value and the isotropic judgment result are sorted, and the correlation strength between the lag and the residual of each point is output in time sequence to establish the residual lag correlation data;

[0123] Based on the residual lag slope values obtained above, data collation operations are continued. First, a one-to-one correspondence is established between the slope results of all points and the corresponding lag values and residual values. For example, the lag value of point A is 2 seconds, the residual is -5 mg / m³, and the fitted slope is -1.33. The lag value of point B is -1 second, -2 mg / m³, and -1.33. The lag value of point C is 5 seconds, -10 mg / m³, and -1.33, forming three data sets. Subsequently, the data are sorted by time according to the order of collection, and a sequence identifier is generated according to the point number. Finally, this data is organized into a structured record table containing the point number, response delay, lag value, NOx residual, and slope value. This is used to track the long-term trend and regional consistency of the lag effect, and to obtain residual lag correlation data. This result provides a supporting data foundation for identifying the NOx injection ammonia adjustment deviation effect and can be used for subsequent regional ammonia injection rhythm control judgment.

[0124] See also Figure 6 , step S5 is:

[0125] S511: Based on the residual lag correlation data, the point area with a positive slope value is screened, and the micro-area with a positive residual lag relationship in the current cycle is identified. The ammonia injection amount data and the liquid supply concentration value of the corresponding point in the micro-area are extracted to obtain the positive micro-area ammonia injection and liquid supply data;

[0126] When screening positive relationship micro-areas based on residual lag correlation data, it is necessary to call the residual and lag paired data of all points in the previous cycle. First, extract the data points with residual lag correlation coefficient greater than 0 from the point response data collected in the whole cycle. For example, suppose that among points A, B, and C, the residual of point A is 5ppm and the lag is 6s, the residual of point B is -2ppm and the lag is 3s, and the residual of point C is 3ppm and the lag is 5s. The slope value is determined by linear regression. If the slopes of points A and C are both greater than 0, they are determined to be positive micro-area point sets, and then the ammonia injection point set is selected. The total amount of ammonia sprayed and the liquid supply concentration values of points A and C in the current cycle are extracted from the recording system. For example, the ammonia spray amount at point A is 3.5 L / min, corresponding to a concentration of 28%, and the ammonia spray amount at point C is 4.2 L / min, with a concentration of 31%. The above extraction results are constructed into a data set to form the forward micro-area ammonia spray and liquid supply data. This data can be used as the basic data set for all adjustment ratio calculations and subsequent correction actions. It is used for superposition and comparison with the NOx residual trend to determine whether it constitutes a basis for adjustment and perform parameter correction processing, ultimately obtaining the forward micro-area ammonia spray and liquid supply data.

[0127] S512: Based on the forward micro-area ammonia injection liquid supply data and the real-time residual value of NOx at the corresponding point, the offset degree of the current liquid supply parameter to the residual response is calculated, and the adjustment ratio of the ammonia injection amount and the adjustment ratio of the liquid supply concentration are calculated to generate ammonia injection control offset ratio data;

[0128] After obtaining the forward micro-area ammonia injection supply data, it is necessary to combine the ammonia injection parameters of each point in the current cycle with the NOx residual. The calculation of the ammonia injection adjustment ratio is based on the ammonia injection amount change amplitude corresponding to each unit residual change. For example, the ammonia injection amount of point A is 3.5L / min, the NOx residual is 5ppm, the ammonia injection amount of point C is 4.2L / min, and the residual is 3ppm. The corresponding ammonia injection increment under unit residual is 0.7 and 1.4L / min / ppm. Combined with the current liquid supply concentration of 28% and 31% respectively, the concentration adjustment amplitude is calculated proportionally to obtain the composite offset degree between concentration and ammonia injection amount. In order to further reflect the above adjustment The numerical basis of the adjustment operation is set as 0.6L / min / ppm for the baseline ammonia injection amount and 2% for the concentration adjustment. By comparing with the above calculated values, it is found that the ammonia injection deviation of point A exceeds the threshold but the concentration adjustment does not exceed the limit, while point C exceeds the limit at the same time. Therefore, point C is included in the control target list, and it is recorded that it needs to perform a dual-parameter adjustment operation. The process relies on the participating items in the data set, compares the gap between the deviation degree and the threshold point by point, completes the classification labeling and outputs the result data table as a reference for the correction execution operation. Through the above analysis process, the ammonia injection and concentration correction parameters can be linked and organized into structured records to generate ammonia injection control deviation ratio data.

[0129] S513: Based on the ammonia injection control offset ratio data, the ammonia injection amount and the liquid supply concentration at the corresponding point are corrected, the parameter change values and correction directions before and after the adjustment are recorded, and an ammonia injection control adjustment record is established;

[0130] According to the ammonia injection control offset ratio data, the current ammonia injection set value will be called in the point data recording module and merged with the adjustment ratio result to form a parameter update instruction. In actual operation, the corresponding point, such as point C, has an original ammonia injection volume of 4.2L / min, which needs to be increased by 1.4L / min. After adjustment, it is set to 5.6L / min, and the liquid supply concentration is adjusted from the original 31% to 33%; the above adjustment operations are simultaneously recorded in the control record table, and the field content covers the value before adjustment, the value after adjustment, the adjustment direction and the adjustment amplitude. For example, the adjustment direction of the ammonia injection volume at point C is "increase", the amplitude is 33.3%, and the concentration adjustment direction is also "increase", the amplitude is 6.45%; this record structure is used to construct cross-cycle comparison and ammonia injection control strategy traceability. By saving the point, cycle, parameter value and direction identification, the ammonia injection control action management and full process tracking are realized, and finally the ammonia injection control adjustment record is established.

[0131] A boiler denitrification intelligent control system, comprising:

[0132] The jump recognition module obtains the NOx concentration value of the current detection point and the previous cycle, calculates the difference and compares it with the jump recognition threshold, selects the jump point, and generates the concentration jump judgment result;

[0133] The response identification module obtains the airflow velocity value and the flow velocity reference value according to the concentration jump judgment result, calculates the disturbance deviation ratio, determines the response point, and generates the ammonia injection response area identification result;

[0134] The time delay determination module extracts the time between the start of ammonia injection and the decrease of NOx concentration based on the ammonia injection response area identification results, calculates and determines the response delay value, and generates NOx response delay data;

[0135] The residual correlation module obtains the response lag value and NOx residual value based on the NOx response delay data, performs linear fitting, extracts the slope to determine the same-direction change relationship, and generates residual lag correlation data;

[0136] The control and adjustment module extracts the ammonia injection amount and the liquid supply concentration based on the residual lag correlation data, calculates the adjustment data based on the residual value, performs the correction action, and generates the ammonia injection control and adjustment record.

[0137] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A boiler denitrification intelligent control method, characterized in that: The following steps are involved: S1: Obtain the current NOx concentration value of the boiler furnace NOx detection point and the NOx concentration value at the corresponding time of the previous sampling cycle, calculate the concentration difference and compare it with the jump recognition threshold to generate the jump concentration judgment result; S2: Based on the jump concentration determination result, the disturbance deviation is calculated by combining the airflow velocity value and the standard flow velocity reference value, and whether the deviation value exceeds the reference is determined. The concentration difference value and the disturbance deviation ratio are simultaneously calculated, and the area where the ratio exceeds the limit is screened to generate the ammonia injection response area identification result; S3: Based on the ammonia injection response area identification result, extract the ammonia injection start time and the time point when the NOx concentration first decreases, calculate the response delay value, and generate NOx response delay data; S4: Based on the NOx response delay data, the difference between the response delay value and the theoretical response time is calculated as a hysteresis value, the real-time NOx residual value of the corresponding point is collected, a linear fit is performed between the hysteresis value and the real-time residual value, and a relationship of the same direction of change is determined to generate residual hysteresis correlation data; S5: Determine the residual lag correlation data, extract the ammonia injection amount and liquid supply concentration values in the positive correlation micro-area, calculate the ammonia injection amount adjustment ratio and concentration adjustment ratio in combination with the NOx real-time residual value, perform correction actions, and generate an ammonia injection control adjustment record.

2. The boiler denitrification intelligent control method according to claim 1, characterized in that: The jump concentration determination result includes the jump point position identifier, jump amplitude level, and jump trend direction; the ammonia injection response area identification result includes the high response area position, response intensity level, and response influence range; the NOx response delay data includes the response time difference sequence, the response start time set, and the response end time set; the residual lag correlation data includes the linear fitting slope value, the change direction consistency index, and the lag and residual fitting degree; the ammonia injection control adjustment record includes the ammonia injection adjustment ratio, the liquid supply concentration adjustment ratio, and the adjustment applicable area.

3. The intelligent control method for boiler denitrification according to claim 1, characterized in that: The steps for obtaining the jump concentration determination result include: S111: Calculate the difference between the current NOx concentration value at the boiler furnace NOx flue gas detection point and the NOx concentration value at the corresponding moment of the previous sampling period. Calculate the difference using the absolute difference between the current NOx concentration value and the NOx concentration value of the previous period to obtain a concentration change difference. S112: Compare the concentration change difference with the jump recognition threshold item by item, identify the concentration change difference item that is greater than the jump recognition threshold, and use the formula: ； Calculate the multi-cycle composite concentration fluctuation value , obtain the jump concentration judgment index value, where, Represents the NOx concentration value of the current cycle, Represents the NOx concentration value of the previous cycle, represents the average value of the transition recognition threshold; S113: According to the magnitude relationship between the jump concentration judgment index value and the jump identification threshold, mark all time points where the jump concentration judgment index value is greater than the jump identification threshold and the corresponding detection point sequence number to generate a jump concentration judgment result.

4. The intelligent control method for boiler denitrification according to claim 1, characterized in that: The steps for obtaining the identification results of the ammonia injection response area include: S211: Based on the jump concentration determination result, the difference between the airflow velocity value at each detection point and the corresponding standard flow velocity reference value is calculated, and the absolute value is taken to obtain the flow velocity disturbance value at each detection point. The degree of disturbance is calculated by the ratio of the disturbance value to the reference value to obtain the disturbance deviation ratio; S212: Perform joint processing based on the disturbance deviation ratio and the concentration change difference of the corresponding detection point, using the formula: ； Calculate the concentration perturbation composite ratio ,in, represents the NOx concentration value at the i-th moment, Indicates the NOx concentration value at the previous moment, represents the airflow velocity value at point i, Indicates the standard flow rate reference value at point i; S213: Based on the concentration disturbance composite ratio, compare with a preset concentration disturbance identification threshold, screen all spatial areas where the ratio exceeds the threshold, and record the corresponding detection point position information and time information to establish an ammonia injection response area identification result.

5. The boiler denitrification intelligent control method according to claim 1, characterized in that: The steps for obtaining NOx response delay data include: S311: Based on the set of points in the ammonia injection response area identification result, continuous time series values of NOx concentration corresponding to each point after the ammonia injection action are collected. According to the changing trend of the NOx concentration values in the collection sequence of each point, the direction of the value fluctuation between each time series point is determined, and the time when the NOx concentration first changes from a non-decreasing state to a decreasing state is identified, and the time point of the first decrease in NOx concentration is obtained; S312: Calculate the time difference between the first drop time of the NOx concentration and the trigger time of the ammonia injection action at each point, record the time interval data corresponding to each point, and obtain the point response delay value; S313: Based on the point response delay value, the response time of each point after the ammonia injection action is triggered is arranged in sequence according to the point number and time sequence to form a cross-point response time set and establish NOx response delay data.

6. The intelligent control method for boiler denitrification according to claim 1, characterized in that: The steps for obtaining residual lag correlation data include: S411: Calculating the theoretical response time of each point under the current liquid supply conditions based on the response delay value of each point in the NOx response delay data and the current liquid supply conditions, and subtracting the response delay value of each point from the theoretical response time to obtain a response lag value for each point; S412: Based on the response hysteresis value of each point, the difference between the real-time NOx concentration of each point after the end of the current cycle and the corresponding reference concentration before ammonia injection is collected to construct a set of real-time NOx residual values corresponding to each point, using the formula: ； Calculate the residual lagged slope value ,in, represents the response lag value of point i, represents the real-time residual value of NOx at point i, represents the average value of all point response lag values, Represents the average value of the real-time residual value of NOx at all points, Indicates the number of points; S413: Arrange the point slope values and the isotropic judgment results according to the residual lag slope values, output the correlation strength between the lag and the residual at each point in time sequence, and establish residual lag correlation data.

7. The intelligent control method for boiler denitrification according to claim 1, characterized in that: The steps for obtaining ammonia injection control and adjustment records include: S511: Based on the residual lag correlation data, screen the point area with a positive slope value, identify the micro-area with a positive residual lag relationship in the current cycle, extract the ammonia injection amount data and the liquid supply concentration value of the point corresponding to the micro-area, and obtain the positive micro-area ammonia injection and liquid supply data; S512: Based on the forward micro-area ammonia injection liquid supply data and the real-time residual value of NOx at the corresponding point, the offset degree of the current liquid supply parameter to the residual response is calculated, and the adjustment ratio of the ammonia injection amount and the adjustment ratio of the liquid supply concentration are calculated to generate ammonia injection control offset ratio data; S513: According to the ammonia injection control offset ratio data, a correction operation of the ammonia injection amount and the liquid supply concentration at the corresponding point is performed, the corresponding parameter change values and correction directions before and after the adjustment are recorded, and an ammonia injection control adjustment record is established.

8. A boiler denitrification intelligent control system, characterized in that: The system is used to perform the method according to any one of claims 1 to 7, comprising: The jump recognition module obtains the NOx concentration value of the current detection point and the previous cycle, calculates the difference and compares it with the jump recognition threshold, selects the jump point, and generates the concentration jump judgment result; The response identification module obtains the airflow velocity value and the flow velocity reference value according to the concentration jump determination result, calculates the disturbance deviation ratio, determines the response point, and generates an ammonia injection response area identification result; The time delay determination module extracts the time between the start of ammonia injection and the decrease of NOx concentration based on the ammonia injection response area identification result, calculates and determines the response delay value, and generates NOx response delay data; The residual correlation module obtains the response hysteresis value and the NOx residual value based on the NOx response delay data, performs linear fitting, extracts the slope to determine the same-direction change relationship, and generates residual hysteresis correlation data; The control and adjustment module extracts the ammonia injection amount and the liquid supply concentration according to the residual lag correlation data, calculates the adjustment data in combination with the residual value, performs the correction action, and generates an ammonia injection control and adjustment record.

Images