Ammonia gas content monitoring method and system of flue gas denitration system

Abstract

The invention relates to the technical field of gas detection, in particular to an ammonia gas content monitoring method and system.The method comprises the steps that firstly, the ammonia consumption amount of each monitoring point is determined on the basis of the similar characteristics of the ammonia content and consumption amount between the monitoring points in a flue of the flue gas denitration system; then determining an ammonia consumption fitting difference based on the periodic characteristics of the ammonia content after the filter bag is cleaned and replaced and the similar characteristics of the ammonia content of the adjacent monitoring points; therefore, the periodic similar characteristics and the adjacent similar characteristics are combined, the more accurate fitting ammonia consumption of each monitoring point at the current sampling moment is determined, and the accuracy of monitoring the ammonia content of the flue gas denitrification system according to the fitting ammonia consumption is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of gas detection, and in particular to a method and system for monitoring the ammonia content of a flue gas denitration system. Background Art

[0002] The requirements for industrial flue gas treatment are gradually increasing, making the catalytic filter bag denitrification system widely used. As an efficient flue gas treatment technology, its core lies in the use of catalysts to promote the reduction reaction of ammonia and nitrogen oxides, converting nitrogen oxides into nitrogen and water. In order to better control the progress of denitrification and adjust the ammonia content as little as possible after the conversion, it is necessary to control the ammonia content at all times, so the monitoring of ammonia content is a key link in the operation of the catalytic filter bag denitrification system. It not only helps to accurately control the amount of ammonia injection to ensure the optimal efficiency of the denitrification reaction, but also effectively prevents secondary pollution caused by ammonia escape. It can monitor the ammonia concentration in various places in the flue gas in real time and provide accurate data support for the denitrification process.

[0003] At present, Tunable Diode Laser Absorption Spectroscopy (TDLAS) technology has become the mainstream choice for real-time monitoring of ammonia content. Its main measurement methods are laser in-situ method and extraction method. Among them, because the analysis system of the extraction method is far away from the sampling system, resulting in a certain lag in measurement, it is rarely used when real-time monitoring is required. The commonly used method is the laser in-situ method. This technology first emits a beam of laser, and then compares the difference between the laser intensity received by the receiver and the original laser intensity. In this process, ammonia will absorb the laser signal to reduce the laser intensity. Based on this feature, relevant data in the flue gas is directly collected at each monitoring point, and then data processing is performed to finally obtain the ammonia content of each monitoring point. The laser in-situ method is measured directly in the flue, and in order to accurately monitor the ammonia content in the flue, multiple sets of sensors need to be set up. The environment inside the flue is relatively complex, and some smoke dust occasionally gathers on the probe, causing the laser signal monitored by the probe to be scattered and reduced, resulting in a deviation in the monitoring value. Then, as the flue gas flows, the smoke dust is carried away by the airflow, causing the probe monitoring to be relatively accurate. The light signal monitored by the receiving probe is sometimes accurate and sometimes inaccurate, and the measurement accuracy is seriously affected by the smoke dust. That is, the accuracy of the prior art using the laser in-situ method to measure the final ammonia content in the flue of the flue gas denitrification system is low. Summary of the invention

[0004] In order to solve the technical problem that the accuracy of the final ammonia content in the flue of the flue gas denitrification system measured by the laser in-situ method in the prior art is low, the purpose of this application is to provide a method and system for monitoring the ammonia content in the flue gas denitrification system. The technical solution adopted is as follows: The first aspect of the present application provides a method for monitoring ammonia content in a flue gas denitrification system, comprising: In the flue of the flue gas denitrification system, the unpurified ammonia content before purification and the initial ammonia content after purification are collected at each monitoring point at each sampling time; and neighboring points distributed adjacent to each monitoring point are obtained from all monitoring points; At each sampling time, the ammonia consumption of each monitoring point is determined according to the initial ammonia content of each monitoring point, the unpurified ammonia content of each adjacent point and the relative distance; at least two periodic time periods in all sampling times are determined according to the periodic fluctuation of the time series difference change of the ammonia consumption of each monitoring point; Calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling time in each periodic time period; determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current periodic time period based on the overall similarity of the ammonia consumption deviation values ​​between the current periodic time period and other periodic time periods, and the ammonia consumption deviation values ​​corresponding to each sampling time in the current periodic time period; According to the periodic changes in the historical ammonia consumption of each monitoring point and the overall value of ammonia consumption in the current period, the reference ammonia consumption of each monitoring point at the current sampling time is determined; according to the reference ammonia consumption of each monitoring point at the current sampling time and the corresponding ammonia consumption fitting differences, the fitted ammonia consumption of each monitoring point at the current sampling time is determined; The ammonia content of the flue gas denitrification system is monitored according to the fitted ammonia consumption.

[0005] Furthermore, the process of obtaining the ammonia consumption includes: Take each monitoring point as the target point in turn; obtain all neighboring monitoring points within the preset neighborhood of the target point; At each sampling time, the distance from each neighboring monitoring point to the target point is negatively normalized to determine the distance weight of each neighboring monitoring point; the unpurified ammonia weighted value of each neighboring monitoring point is determined according to the product of the unpurified ammonia content of each neighboring monitoring point and the distance weight; the average unpurified ammonia content of the target point is determined according to the cumulative value of the unpurified ammonia weighted values ​​of all neighboring monitoring points; The difference between the average content of raw ammonia and the initial ammonia content of the target point is taken as the ammonia consumption of the target point.

[0006] Furthermore, the process of obtaining the periodic time period includes: Arrange the ammonia consumption of each monitoring point in chronological order to obtain an ammonia consumption time series; perform differential calculation on the ammonia consumption time series to obtain an ammonia consumption differential series; use the moment corresponding to the maximum point in the ammonia consumption differential series as the periodic interval moment; and divide all sampling moments into at least two periodic time periods with the periodic interval moment as the interval.

[0007] Furthermore, the process of obtaining the ammonia consumption fitting difference includes: For each monitoring point and each adjacent point, the difference confidence at each sampling moment in the current cycle time period is determined according to the ammonia consumption deviation value deviation and the ammonia consumption deviation value change rate deviation between each sampling moment in the current cycle time period and the sampling moment of the corresponding cycle position in each historical cycle time period; According to the product of the normalized value of the difference confidence and the ammonia consumption deviation value at each sampling moment in the current cycle time period, the weighted ammonia consumption difference at each sampling moment in the current cycle time period is determined; according to the accumulated value of the weighted ammonia consumption differences at all sampling moments in the current cycle time period, the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current cycle time period is determined.

[0008] Furthermore, the process of obtaining the difference confidence includes: For each monitoring point and each adjacent point, the ammonia consumption cycle difference value corresponding to the current cycle time period and each historical cycle time period at each sampling time is determined according to the absolute value of the difference between the ammonia consumption deviation value at each sampling time in the current cycle time period and the ammonia consumption deviation value at the sampling time of the same cycle position in each historical cycle time period; Determine the overall cycle difference between the current cycle time period and each historical cycle time period according to the overall deviation in the change rate of the ammonia consumption deviation value at each sampling moment between the current cycle time period and each historical cycle time period; The product of the normalized value of the overall cycle difference and the ammonia consumption cycle difference value is used as the weighted cycle difference value between the current cycle time period and each historical cycle time period at each sampling moment; the accumulated values ​​of all weighted cycle difference values ​​corresponding to each sampling moment in the current cycle time period are negatively correlated and mapped to determine the difference confidence at each sampling moment in the current cycle time period.

[0009] Furthermore, the process of obtaining the overall period difference includes: The difference between the ammonia consumption deviation value at the next sampling moment corresponding to each sampling moment and the ammonia consumption deviation value corresponding to the previous sampling moment is taken as the ammonia consumption difference change rate; after arranging the ammonia consumption change rates of all sampling moments in each cycle time period in chronological order, the ammonia consumption change rate sequence of each cycle time period is determined; the DTW distance between the two ammonia consumption change rate sequences corresponding to the current cycle time period and each historical cycle time period is taken as the corresponding overall cycle difference.

[0010] Furthermore, the process of obtaining the reference ammonia consumption includes: The ammonia consumption in each historical period corresponding to each monitoring point is predicted by the SARIMA model algorithm to determine the predicted ammonia consumption of each monitoring point at the current moment; The sampling time corresponding to the same period position of the current sampling time in each historical period time period is used as the comparison sampling time; the overall ammonia consumption of each monitoring point at the current sampling time is determined according to the average of all ammonia consumptions corresponding to each monitoring point at the current sampling time and all comparison sampling times; According to the average of the predicted ammonia consumption and the overall ammonia consumption, a reference ammonia consumption of each monitoring point at the current sampling moment is determined.

[0011] Furthermore, the process of obtaining the fitted ammonia consumption includes: The sum of the reference ammonia consumption of each neighboring point corresponding to each monitoring point at the current sampling moment and the fitted difference in ammonia consumption is taken as the relative ammonia consumption of each neighboring point corresponding to each monitoring point; based on the mean of the relative ammonia consumption of all neighboring points corresponding to each monitoring point, the fitted ammonia consumption of each monitoring point at the current sampling moment is determined.

[0012] Furthermore, the process of monitoring the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption includes: The final ammonia content at each monitoring point is determined by taking the difference between the average raw ammonia content and the fitted ammonia consumption.

[0013] In a second aspect, the present application provides an ammonia content monitoring system for a flue gas denitrification system, the system comprising: The data acquisition preprocessing module is used to collect the unpurified ammonia content before purification and the initial ammonia content after purification at each monitoring point at each sampling time in the flue of the flue gas denitrification system; and obtain the neighboring points distributed adjacent to each monitoring point among all monitoring points; The first determination module is used to determine the ammonia consumption of each monitoring point at each sampling time according to the initial ammonia content of each monitoring point and the unpurified ammonia content of each adjacent point and the relative distance; and determine at least two periodic time periods in all sampling times according to the periodic fluctuation of the time series difference change of the ammonia consumption of each monitoring point; The second determination module is used to calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling time in each periodic time period; according to the overall similarity of the ammonia consumption deviation values ​​between the current periodic time period and other periodic time periods, and the ammonia consumption deviation values ​​corresponding to each sampling time in the current periodic time period, determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current periodic time period; The third determination module is used to determine the reference ammonia consumption of each monitoring point at the current sampling time according to the periodic changes in the historical ammonia consumption of each monitoring point and the overall value of the ammonia consumption in the current periodic time period; according to the reference ammonia consumption of each monitoring point at the current sampling time and the corresponding ammonia consumption fitting differences, determine the fitted ammonia consumption of each monitoring point at the current sampling time; The ammonia content monitoring module is used to monitor the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption.

[0014] In a third aspect, the present application provides a computer device, comprising a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method of the first aspect or any embodiment of the first aspect of the present application.

[0015] In a fourth aspect, the present application provides a computer program product, comprising a computer program code, which, when executed, performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0016] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is performed.

[0017] This application has the following beneficial effects: In the existing technology, when monitoring ammonia content, various monitoring sensors are directly installed in the flue and are easily affected by smoke dust, resulting in unstable optical signals detected by the receiving probe, which seriously affects the measurement accuracy. In addition, due to the influence of smoke dust, when the laser in-situ method measures the final ammonia content, the accuracy of the optical signal fluctuates, sometimes accurate and sometimes inaccurate, which limits its reliability in practical applications.

[0018] First, the unpurified ammonia content of each point is fuzzily described by the ammonia content monitored in the unpurified flue gas in the nearby area. Then, the ammonia content of the same monitoring point before and after purification is compared and analyzed to calculate its purification consumption; at the same time, a single monitoring point is analyzed to examine the periodic variation law of its purification consumption in the historical time series. After that, the difference in ammonia consumption between the target monitoring point and its surrounding monitoring points in the past time series is analyzed; at the same time, according to the uniformity of the difference in ammonia consumption between the neighboring monitoring points and the target monitoring points in the past time series, its confidence is constructed; then, according to the difference in ammonia consumption between adjacent monitoring points, combined with the corresponding confidence, the fitting difference of ammonia consumption between many neighboring monitoring points and the target monitoring point at the target time is constructed. Finally, based on the periodic law of each monitoring point, the predicted ammonia consumption at the target time is preliminarily predicted, and combined with the corresponding monitored ammonia consumption, the reference ammonia consumption at the target time is obtained; then, the reference ammonia consumption of each neighboring monitoring point is combined with the corresponding fitting difference to construct the fitted ammonia consumption of the target monitoring point; then, based on the unpurified ammonia content of the target monitoring point at the target time and the corresponding fitted ammonia consumption, the final ammonia content corresponding to the target time is obtained. Based on this, the ammonia content monitoring error caused by the interference of smoke in the flue gas can be avoided. At the same time, it can effectively improve the stability and accuracy of ammonia monitoring in the flue, and at the same time help to optimize the ammonia supply process in the denitrification process and improve the working efficiency of the denitrification system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a method for monitoring ammonia content in a flue gas denitration system provided by one embodiment of the present invention; Figure 2 A structural diagram of an ammonia content monitoring system for a flue gas denitration system provided by one embodiment of the present invention; Figure 3 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of the ammonia content monitoring method and system of a flue gas denitrification system proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0022] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0023] The following is a detailed description of a method and system for monitoring ammonia content in a flue gas denitrification system provided by the present invention in conjunction with the accompanying drawings.

[0024] The present application provides a method for monitoring the ammonia content in a flue gas denitrification system. Figure 1 , which shows a flow chart of a method for monitoring ammonia content in a flue gas denitrification system provided by an embodiment of the present invention, the method comprising: Step S101: In the flue of the flue gas denitrification system, the unpurified ammonia content before purification and the initial ammonia content after purification are collected at each monitoring point at each sampling time; and neighboring points distributed adjacent to each monitoring point are obtained from all monitoring points.

[0025] A quantum cascade laser is installed as a light source at each monitoring point in the flue of the flue gas denitrification system, and the wavelength modulation spectrum technology is used as a monitoring unit to monitor and receive the laser signal at each sampling moment in real time. In a specific implementation of the embodiment of the present invention, the flue gas denitrification system uses Topsoe catalytic denitrification filter bags, the monitoring frequency is set to monitor once per second, and the corresponding time interval between adjacent sampling moments is 1 second; and the time range of the sampling moment is set to the current moment and the previous six months, which can be adjusted according to the specific implementation environment.

[0026] In addition, the wavelength of the laser beam emitted by the quantum cascade laser is a laser with a wavelength corresponding to the characteristic absorption peak of ammonia, which is used to monitor the content of each gas in the flue gas at the corresponding position; after the corresponding laser signal is collected, it is processed by least squares fitting or neural network algorithms to obtain the corresponding gas content; it should be noted that the specific process of monitoring the ammonia content with the help of the laser signal of the quantum cascade laser refers to the performance test research technology of the high-precision online flue gas ammonia analyzer based on quantum cascade laser, which belongs to the technical means in the prior art and will not be further elaborated here.

[0027] In a specific implementation of an embodiment of the present invention, a monitoring point is set every 0.1 meters in the flue of the flue gas denitrification system, and the ammonia content inside and outside the filter membrane of the Topsoe catalytic denitrification filter bag is monitored through the monitoring point. The corresponding ammonia content inside is the initial ammonia content after purification, and the ammonia content outside is the unpurified ammonia content. It should be noted that the embodiment of the present invention is not limited to the measurement of the final ammonia content, and the type of gas, such as nitrogen and nitrogen oxides, can be adjusted by adjusting the wavelength of the laser beam emitted by the quantum cascade laser, which will not be further elaborated here.

[0028] In a specific implementation of an embodiment of the present invention, other monitoring points with a Euclidean distance less than 1 meter from each monitoring point are used as neighboring points of each monitoring point. The range size can be adjusted according to the specific implementation environment, which will not be further elaborated here.

[0029] Step S102: At each sampling moment, the ammonia consumption of each monitoring point is determined according to the initial ammonia content of each monitoring point, the unpurified ammonia content of each adjacent point, and the relative distance; at least two periodic time periods in all sampling moments are determined according to the periodic fluctuation of the time series differential change of the ammonia consumption of each monitoring point.

[0030] In the catalytic filter bag denitrification system, the main method is to filter the smoke through the filter bag and catalyze the reaction of ammonia and nitrogen oxides. However, as the filtering and denitrification proceeds, the filter will be affected by the smoke left by the filtration, resulting in a decrease in its purification and denitrification efficiency. In order to ensure the smooth progress of the entire catalytic denitrification process, the filter bag will be cleaned or replaced regularly. This results in the consumption of ammonia at each monitoring point when passing through the filter (including the catalyst) changing periodically. In addition, since the flue gas is not diverted in the pipeline before entering the dust removal and denitrification filter bag, it is mixed and diffused arbitrarily. Therefore, before these flue gases are purified, the contents of each component in the flue gas in some adjacent areas are similar or even the same; this results in similar ammonia content before purification in this area; at the same time, it can also be concluded that the loss degree of the filter in this area is similar, and its dust removal and denitrification effect on the flue gas is also similar. Based on this, the difference in ammonia content inside and outside the filter at each monitoring point can be obtained. Combined with the ammonia content before dust removal and purification, the ammonia content monitoring at the corresponding position can be completed.

[0031] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the ammonia consumption includes: Take each monitoring point as the target point in turn; obtain all neighboring monitoring points within the preset neighborhood of the target point; At each sampling time, the distance from each neighboring monitoring point to the target point is normalized by negative correlation to determine the distance weight of each neighboring monitoring point; the unpurified ammonia weighted value of each neighboring monitoring point is determined according to the product of the unpurified ammonia content and the distance weight of each neighboring monitoring point; the average unpurified ammonia content of the target point is determined according to the cumulative value of the unpurified ammonia weighted values ​​of all neighboring monitoring points; the difference between the average unpurified ammonia content and the initial ammonia content of the target point is taken as the ammonia consumption of the target point.

[0032] Because ammonia flows in the flue, it passes through the flue and the filter bag filter relatively slowly, causing the various components in it to diffuse slowly, so that in a smaller area, the content of each component in the flue gas is relatively close. In this way, the ammonia content at several monitoring points near each monitoring point is relatively the same; therefore, the unpurified ammonia content of the monitoring point at a certain moment can be approximately described based on the unpurified ammonia content corresponding to the monitoring points adjacent to each monitoring point; further, based on the described unpurified ammonia content combined with the initial ammonia content after purification, the corresponding ammonia consumption can be determined. For each neighboring point, the closer it is to the target point, the higher the credibility of the ammonia content of the neighboring point, so the negative correlation normalized value of the distance is used as the weight for weighting to obtain a more accurate average unpurified ammonia content.

[0033] In a specific implementation of the embodiment of the present invention, the process of obtaining the ammonia consumption is expressed by the formula: ;in, For the The monitoring point is Ammonia consumption at each sampling time; For the The number of neighboring points of each monitoring point; For the The monitoring point and the corresponding The Euclidean distance between neighboring points; For the The monitoring point The neighboring point is The unpurified ammonia content at each sampling time; For the The monitoring point is The initial ammonia content at the sampling time; It is the softmax normalization function. Its unique normalization method can make the sum of all normalized values ​​1, making the subsequent accumulation operation more suitable for the scene. For the The monitoring point The distance weight of each neighboring point; For the At the sampling time The monitoring point The weighted value of raw ammonia at each neighboring point; For the At the sampling time The average content of raw ammonia at each monitoring point.

[0034] When denitrifying and dusting lime kiln flue gas, over time, dust will continue to accumulate on the filter screen, causing the subsequent flue gas purification efficiency through the filter bag to gradually decrease. In order to ensure the normal operation of the filter bag, the filter screen and filter bag need to be replaced and cleaned regularly. After replacement, the purification efficiency of the corresponding position will return to the initial efficiency. This leads to a periodic change in the purification efficiency of each monitoring point.

[0035] Preferably, in some possible implementations of the embodiments of the present invention, the process of acquiring the periodic time period includes: Arrange the ammonia consumption of each monitoring point in chronological order to obtain the ammonia consumption time series; perform differential calculation on the ammonia consumption time series to obtain the ammonia consumption differential series; use the time corresponding to the maximum point in the ammonia consumption differential series as the periodic interval time; divide all sampling times into at least two periodic time periods with the periodic interval time as the interval. Because the purification efficiency will increase suddenly every time the filter is replaced, the maximum point in the ammonia consumption differential series is used as the dividing point. Specifically, the next moment after the periodic interval moment is used as the starting moment of the new periodic time period, and the periodic interval moment is used as the ending moment of the old periodic time period; it can also be adjusted by itself.

[0036] Step S103: Calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling moment in each cycle time period; determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current cycle time period based on the overall similarity of the ammonia consumption deviation values ​​between the current cycle time period and other cycle time periods, and the ammonia consumption deviation values ​​corresponding to each sampling moment in the current cycle time period.

[0037] Although the flue gas components at each monitoring point, i.e., the neighborhood point, are similar before denitrification, the filters at different monitoring points are different in production and cleaning, resulting in different purification efficiencies. This difference is difficult to change during the flue gas denitrification and dust removal process. Therefore, within the same cycle, this difference will be retained. Therefore, the ammonia consumption deviation value between each monitoring point and each neighboring point at each sampling moment in each cycle time period is first calculated. In a specific implementation of an embodiment of the present invention, the process of obtaining the ammonia consumption deviation value is expressed by the formula: ;in, For the In the period of the cycle At the sampling time The monitoring point and the corresponding The ammonia consumption deviation between adjacent points; For the In the period of the cycle At the sampling time Ammonia consumption at each monitoring point; For the In the period of the cycle At the sampling time The monitoring point corresponds to The ammonia consumption of each neighboring point is calculated; and the ammonia consumption deviation value between each monitoring point and its corresponding neighboring points at each sampling time in each cycle time period is further calculated.

[0038] When the filter is in use, smoke will be left behind as it filters the flue gas; at the same time, the filter will be replaced and cleaned at regular intervals, so the purification efficiency of the filter is the same in each cycle throughout the entire sequence. From the above analysis, the filter will gradually become clogged at each monitoring point as it is used. Since the smoke components at two adjacent monitoring points are always close, the clogging speeds at the two monitoring points are similar, so the changes in the purification efficiency at the two monitoring points are consistent at every moment, resulting in similar differences in purification efficiency between two adjacent monitoring points in the same cycle. Similarly, the purification efficiency at the same moment in the past cycle should also be consistent. If the deviation is too large, it means that it is unreliable. Therefore, the confidence level can be measured based on this feature.

[0039] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the ammonia consumption fitting difference includes: For each monitoring point and each adjacent point, the difference confidence at each sampling moment in the current cycle time period is determined according to the ammonia consumption deviation value deviation and the ammonia consumption deviation value change rate deviation between each sampling moment in the current cycle time period and the sampling moment of the corresponding cycle position in each historical cycle time period. In a specific implementation of the embodiment of the present invention, the process of obtaining the difference confidence includes: For each monitoring point and each adjacent point, the ammonia consumption cycle difference value corresponding to the current cycle time period and each historical cycle time period at each sampling time is determined according to the absolute value of the difference between the ammonia consumption deviation value at each sampling moment in the current cycle time period and the ammonia consumption deviation value at the sampling moment of the same cycle position in each historical cycle time period. The cycle position refers to the index value of the corresponding sampling moment in the corresponding cycle time period, and the same cycle position means the same index value; when the corresponding cycle position does not exist in the corresponding historical cycle time period, the corresponding ammonia consumption cycle difference value is set to 0 to ensure the completeness of the embodiment; the smaller the ammonia consumption cycle difference value, the more similar the ammonia consumption characteristics at the corresponding sampling moments, and the greater the corresponding confidence.

[0040] The ammonia consumption cycle difference value is the corresponding confidence level analyzed in the local numerical dimension, and each ammonia consumption cycle difference value corresponds to only one cycle, so it is necessary to further analyze it in the overall dimension; based on this, the embodiment of the present invention further determines the overall cycle difference between the current cycle time period and each historical cycle time period according to the overall deviation of the ammonia consumption deviation value at each sampling time in the change rate between the current cycle time period and each historical cycle time period; in some possible implementation methods of the embodiment of the present invention, the acquisition process of the overall cycle difference includes: The difference between the ammonia consumption deviation value at the next sampling moment corresponding to each sampling moment and the ammonia consumption deviation value corresponding to the previous sampling moment is taken as the ammonia consumption difference change rate; after arranging the ammonia consumption change rates of all sampling moments in each periodic time period in chronological order, the ammonia consumption change rate sequence of each periodic time period is determined; the DTW distance between the two ammonia consumption change rate sequences corresponding to the current periodic time period and each historical periodic time period is taken as the corresponding overall periodic difference. Based on the characteristic that the changes in the purification efficiency of adjacent monitoring points usually tend to be consistent, the ammonia consumption change rate between periodic time periods should maintain the same trend. Therefore, the larger the DTW distance of the ammonia consumption change rate sequence of the two periodic time periods calculated by the dynamic time warping algorithm, that is, the smaller the overall periodic difference, the less it conforms to the periodic characteristics, and the smaller the corresponding confidence should be. It should be noted that the dynamic time warping algorithm is a technical means well known to those skilled in the art and will not be further elaborated here.

[0041] Therefore, the local and overall characterizations of confidence are further integrated, and the product of the normalized value of the overall cycle difference and the cycle difference value of ammonia consumption is further used as the weighted cycle difference value between the current cycle time period and each historical cycle time period at each sampling moment; the accumulated values ​​of all the weighted cycle difference values ​​corresponding to each sampling moment of the current cycle time period are negatively correlated to determine the difference confidence at each sampling moment in the current cycle time period. The confidence is characterized locally and overall by multiplication, and the weighted cycle difference values ​​of each historical cycle time period are integrated based on the obtained weighted cycle difference value, and considering that the greater the difference between the cycles, the less it conforms to the periodic characteristics, and the smaller the corresponding confidence should be, all the weighted cycle difference values ​​are accumulated and then negatively correlated to determine the confidence required by the embodiment of the present invention.

[0042] In a specific implementation of the embodiment of the present invention, the process of obtaining the difference confidence is expressed by the formula: ;in, For the Monitoring point and The neighboring point is the first in the current cycle time period The confidence level of the difference at each sampling moment; is the number of historical periodic time periods, that is, the number of periodic time periods other than the current periodic time period, and the current periodic time period is the periodic time period at the current time; For the Monitoring point and The overall cycle difference between the current cycle time period and each historical cycle time period corresponding to the neighboring points, that is, the DTW distance between the two ammonia consumption change rate sequences corresponding to the current cycle time period and each historical cycle time period; For the Monitoring point and The neighboring point is the first in the current cycle time period Deviation value of ammonia consumption at each sampling moment; For the Monitoring point and The neighboring point is In the historical period The ammonia consumption deviation value at each sampling moment is guaranteed to be in the same period position by the same index value c; is the softmax normalization function, which has the same purpose as the above softmax normalization function, and is used to cooperate with the accumulation to make it more suitable for the scene; is the absolute value symbol; It is an exponential function with a natural constant as the base, and other negative correlation mapping methods can be selected according to the specific implementation environment.

[0043] After obtaining the difference confidence, considering that the confidence of the ammonia consumption difference between two monitoring points at different times is different, the confidence is weighted to the ammonia consumption deviation, and further the weighted ammonia consumption difference at each sampling moment in the current cycle time period is determined according to the product of the normalized value of the difference confidence and the ammonia consumption deviation value at each sampling moment in the current cycle time period; according to the cumulative value of the weighted ammonia consumption difference at all sampling moments in the current cycle time period, the ammonia consumption fitting difference between each monitoring point and each neighboring point in the current cycle time period is determined; thereby comprehensively representing the ammonia consumption fitting difference between each monitoring point and each neighboring point in the dimension of the entire cycle, making the analysis result more robust.

[0044] In a specific implementation of the embodiment of the present invention, the process of obtaining the ammonia consumption fitting difference is expressed by the formula: ;in, The first Monitoring point and The difference in ammonia consumption fits between adjacent points; is the number of sampling moments in the current period; For the Monitoring point and The neighboring point is the first in the current cycle time period The confidence level of the difference at each sampling moment; For the Monitoring point and The neighboring point is the first in the current cycle time period Deviation value of ammonia consumption at each sampling moment; For the Monitoring point and The neighboring point is the first in the current cycle time period The weighted ammonia consumption difference at each sampling time; is the softmax normalization function.

[0045] Step S104: Determine the reference ammonia consumption of each monitoring point at the current sampling moment according to the historical periodic changes in ammonia consumption of each monitoring point and the overall numerical value of ammonia consumption in the current periodic time period; determine the fitted ammonia consumption of each monitoring point at the current sampling moment according to the reference ammonia consumption of each monitoring point at the current sampling moment and the corresponding fitting differences of each ammonia consumption.

[0046] During the use of the filter bag, smoke and dust are gradually deposited, which makes the dust removal and denitrification efficiency at the corresponding position gradually decrease. Then, due to regular cleaning, the corresponding denitrification efficiency shows periodic recovery, which causes the ammonia consumption at each monitoring point to show periodic changes. Based on this feature, the ammonia consumption of each past cycle can be predicted, so as to make a more accurate reference ammonia consumption characterization based on the predicted ammonia consumption value combined with the previously calculated ammonia consumption.

[0047] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the reference ammonia consumption includes: According to the ammonia consumption in each historical period time period corresponding to each monitoring point, the SARIMA model algorithm is used to predict and determine the predicted ammonia consumption of each monitoring point; the sampling time corresponding to the same period position in each historical period time period at the current sampling time is used as the comparison sampling time; according to the average of all ammonia consumption corresponding to each monitoring point at the current sampling time and all comparison sampling times, the overall ammonia consumption of each monitoring point at the current sampling time is determined; according to the average of the predicted ammonia consumption and the overall ammonia consumption, the reference ammonia consumption of each monitoring point at the current sampling time is determined. By combining the predicted ammonia consumption that can characterize the similar characteristics of the cycle and the overall ammonia consumption that characterizes the similar characteristics of the neighbors to comprehensively characterize the ammonia consumption of each monitoring point at the current moment, the obtained reference ammonia consumption can be made more accurate; it should be noted that the SARIMA model algorithm is a technical means well known to those skilled in the art, and will not be further limited or elaborated here.

[0048] In a specific implementation of the embodiment of the present invention, the process of obtaining the reference ammonia consumption is expressed by the formula: ;in, The current sampling time Reference ammonia consumption at each monitoring point; The current sampling time Predicted ammonia consumption at each monitoring point; The current sampling time The overall ammonia consumption of each monitoring point, i.e. The average of all ammonia consumption corresponding to each monitoring point at the current sampling time and all comparison sampling times.

[0049] By calculating the reference ammonia consumption, a preliminary prediction correction of the ammonia consumption of each monitoring point at the current sampling time is completed. At the same time, based on the previous results, the ammonia consumption fitting difference between each monitoring point and each adjacent point is obtained. The calculated reference ammonia consumption can be further corrected according to the ammonia consumption fitting difference, so that the obtained fitting ammonia consumption is more accurate.

[0050] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the fitted ammonia consumption includes: The sum of the reference ammonia consumption of each neighboring point corresponding to each monitoring point at the current sampling moment and the fitted difference in ammonia consumption is used as the relative ammonia consumption of each neighboring point corresponding to each monitoring point; the fitted ammonia consumption of each monitoring point at the current sampling moment is determined according to the mean of the relative ammonia consumption of all neighboring points corresponding to each monitoring point. Since each monitoring point corresponds to multiple neighboring points, after combining the corresponding reference ammonia consumption and the fitted difference in ammonia consumption, the fitted ammonia consumption is made more accurate by taking the average. In a specific implementation of an embodiment of the present invention, the process of obtaining the fitted ammonia consumption is expressed by the formula: ;in, The current sampling time Fitted ammonia consumption of each monitoring point; For the The number of neighboring points of each monitoring point; The current sampling time The monitoring point corresponds to Reference ammonia consumption of neighboring points; The first Monitoring point and The difference in ammonia consumption fits between adjacent points; The current sampling time The monitoring point corresponds to Relative ammonia consumption at adjacent points.

[0051] Step S105: monitoring the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption.

[0052] The fitted ammonia consumption is to characterize the ammonia consumption. Therefore, in order to monitor the final ammonia content more accurately, it is necessary to characterize the final ammonia content after purification based on the unpurified ammonia content. In some possible implementations of the embodiments of the present invention, the process of monitoring the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption includes: The final ammonia content at each monitoring point is determined by the difference between the average unpurified ammonia content and the fitted ammonia consumption. The ammonia consumption is obtained by calculating the difference between the unpurified ammonia content and the purified ammonia content. Therefore, in order to determine the final ammonia content after purification, the average unpurified ammonia content is further subtracted from the fitted ammonia consumption, thereby obtaining a more accurate final ammonia content after correction combined with the adjacent similarity and periodic similarity features; wherein, the formula corresponding to the process of obtaining the final ammonia content is: ;in, The current sampling time Final ammonia content at each monitoring point; The current sampling time Average content of unpurified ammonia at each monitoring point; The current sampling time Fitted ammonia consumption at each monitoring point.

[0053] In summary, a method for monitoring the ammonia content of a flue gas denitrification system first determines the ammonia consumption of each monitoring point based on the similar characteristics of the ammonia content and consumption between the monitoring points in the flue of the flue gas denitrification system; and then determines the ammonia consumption fitting difference based on the periodic characteristics of the ammonia content after the filter bag is cleaned and replaced and the similar characteristics of the ammonia content of the adjacent monitoring points; thereby combining the periodic similarity characteristics and the adjacent similarity characteristics to determine a more accurate fitting ammonia consumption of each monitoring point at the current sampling time, so that the ammonia content monitoring of the flue gas denitrification system based on the fitted ammonia consumption is more accurate.

[0054] This application also provides a system for monitoring the ammonia content of a flue gas denitrification system. Figure 2 , which shows a structural diagram of an ammonia content monitoring system for a flue gas denitrification system provided by an embodiment of the present invention, the system includes: a data acquisition preprocessing module 201, a first determination module 202, a second determination module 203, a third determination module 204 and an ammonia content monitoring module 205.

[0055] The data collection preprocessing module 201 is used to collect the unpurified ammonia content before purification and the initial ammonia content after purification at each monitoring point at each sampling time in the flue of the flue gas denitrification system; and obtain neighboring points distributed adjacent to each monitoring point among all monitoring points; The first determination module 202 is used to determine the ammonia consumption of each monitoring point at each sampling time according to the initial ammonia content of each monitoring point and the unpurified ammonia content of each adjacent point and the relative distance; determine at least two periodic time periods in all sampling times according to the periodic fluctuation of the time series difference change of the ammonia consumption of each monitoring point; The second determination module 203 is used to calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling time in each periodic time period; according to the overall similarity of the ammonia consumption deviation values ​​between the current periodic time period and other periodic time periods, and the ammonia consumption deviation values ​​corresponding to each sampling time in the current periodic time period, determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current periodic time period; The third determination module 204 is used to determine the reference ammonia consumption of each monitoring point at the current sampling time according to the periodic changes of the historical ammonia consumption of each monitoring point and the overall value of the ammonia consumption in the current periodic time period; determine the fitted ammonia consumption of each monitoring point at the current sampling time according to the reference ammonia consumption of each monitoring point at the current sampling time and the corresponding ammonia consumption fitting differences; The ammonia content monitoring module 205 is used to monitor the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption.

[0056] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the ammonia content monitoring system of a flue gas denitrification system provided in the above embodiment and the ammonia content monitoring method embodiment of a flue gas denitrification system belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0057] The present application also provides a computer device. Figure 3 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any of the ammonia content monitoring methods for flue gas denitrification systems introduced above.

[0058] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the ammonia content monitoring methods for a flue gas denitrification system introduced above.

[0059] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any of the ammonia content monitoring methods for a flue gas denitrification system introduced above.

[0060] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0061] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring ammonia content in a flue gas denitrification system, characterized in that: The method comprises: In the flue of the flue gas denitrification system, the unpurified ammonia content before purification and the initial ammonia content after purification are collected at each monitoring point at each sampling time; and neighboring points distributed adjacent to each monitoring point are obtained from all monitoring points; At each sampling time, the ammonia consumption of each monitoring point is determined according to the initial ammonia content of each monitoring point, the unpurified ammonia content of each adjacent point and the relative distance; at least two periodic time periods in all sampling times are determined according to the periodic fluctuation of the time series difference change of the ammonia consumption of each monitoring point; Calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling time in each periodic time period; determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current periodic time period based on the overall similarity of the ammonia consumption deviation values ​​between the current periodic time period and other periodic time periods, and the ammonia consumption deviation values ​​corresponding to each sampling time in the current periodic time period; According to the periodic changes in the historical ammonia consumption of each monitoring point and the overall value of ammonia consumption in the current period, the reference ammonia consumption of each monitoring point at the current sampling time is determined; according to the reference ammonia consumption of each monitoring point at the current sampling time and the corresponding ammonia consumption fitting differences, the fitted ammonia consumption of each monitoring point at the current sampling time is determined; The ammonia content of the flue gas denitrification system is monitored according to the fitted ammonia consumption.

2. The method for monitoring ammonia content in a flue gas denitration system according to claim 1, characterized in that: The process of obtaining the ammonia consumption includes: Take each monitoring point as the target point in turn; obtain all neighboring monitoring points within the preset neighborhood of the target point; At each sampling time, the distance from each neighboring monitoring point to the target point is negatively normalized to determine the distance weight of each neighboring monitoring point; the unpurified ammonia weighted value of each neighboring monitoring point is determined according to the product of the unpurified ammonia content of each neighboring monitoring point and the distance weight; the average unpurified ammonia content of the target point is determined according to the cumulative value of the unpurified ammonia weighted values ​​of all neighboring monitoring points; The difference between the average content of raw ammonia and the initial ammonia content of the target point is taken as the ammonia consumption of the target point.

3. The method for monitoring ammonia content in a flue gas denitration system according to claim 1, characterized in that: The process of obtaining the periodic time period includes: Arrange the ammonia consumption of each monitoring point in chronological order to obtain an ammonia consumption time series; perform differential calculation on the ammonia consumption time series to obtain an ammonia consumption differential series; use the moment corresponding to the maximum point in the ammonia consumption differential series as the periodic interval moment; and divide all sampling moments into at least two periodic time periods with the periodic interval moment as the interval.

4. The method for monitoring ammonia content in a flue gas denitration system according to claim 1, characterized in that: The process of obtaining the ammonia consumption fitting difference includes: For each monitoring point and each adjacent point, the difference confidence at each sampling moment in the current cycle time period is determined according to the ammonia consumption deviation value deviation and the ammonia consumption deviation value change rate deviation between each sampling moment in the current cycle time period and the sampling moment of the corresponding cycle position in each historical cycle time period; According to the product of the normalized value of the difference confidence and the ammonia consumption deviation value at each sampling moment in the current cycle time period, the weighted ammonia consumption difference at each sampling moment in the current cycle time period is determined; according to the accumulated value of the weighted ammonia consumption differences at all sampling moments in the current cycle time period, the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current cycle time period is determined.

5. The method for monitoring ammonia content in a flue gas denitration system according to claim 4, characterized in that: The process of obtaining the difference confidence includes: For each monitoring point and each adjacent point, the ammonia consumption cycle difference value corresponding to the current cycle time period and each historical cycle time period at each sampling time is determined according to the absolute value of the difference between the ammonia consumption deviation value at each sampling time in the current cycle time period and the ammonia consumption deviation value at the sampling time of the same cycle position in each historical cycle time period; Determine the overall cycle difference between the current cycle time period and each historical cycle time period according to the overall deviation in the change rate of the ammonia consumption deviation value at each sampling moment between the current cycle time period and each historical cycle time period; The product of the normalized value of the overall cycle difference and the ammonia consumption cycle difference value is used as the weighted cycle difference value between the current cycle time period and each historical cycle time period at each sampling moment; the accumulated values ​​of all weighted cycle difference values ​​corresponding to each sampling moment in the current cycle time period are negatively correlated and mapped to determine the difference confidence at each sampling moment in the current cycle time period.

6. The method for monitoring ammonia content in a flue gas denitration system according to claim 5, characterized in that: The process of obtaining the overall period difference includes: The difference between the ammonia consumption deviation value at the next sampling moment corresponding to each sampling moment and the ammonia consumption deviation value corresponding to the previous sampling moment is taken as the ammonia consumption difference change rate; after arranging the ammonia consumption change rates of all sampling moments in each cycle time period in chronological order, the ammonia consumption change rate sequence of each cycle time period is determined; the DTW distance between the two ammonia consumption change rate sequences corresponding to the current cycle time period and each historical cycle time period is taken as the corresponding overall cycle difference.

7. The method for monitoring ammonia content in a flue gas denitration system according to claim 1, characterized in that: The process of obtaining the reference ammonia consumption includes: The ammonia consumption in each historical period corresponding to each monitoring point is predicted by the SARIMA model algorithm to determine the predicted ammonia consumption of each monitoring point at the current moment; The sampling time corresponding to the same period position of the current sampling time in each historical period time period is used as the comparison sampling time; the overall ammonia consumption of each monitoring point at the current sampling time is determined according to the average of all ammonia consumptions corresponding to each monitoring point at the current sampling time and all comparison sampling times; According to the average of the predicted ammonia consumption and the overall ammonia consumption, a reference ammonia consumption of each monitoring point at the current sampling moment is determined.

8. The method for monitoring ammonia content in a flue gas denitration system according to claim 1, characterized in that: The process of obtaining the fitted ammonia consumption includes: The sum of the reference ammonia consumption of each neighboring point corresponding to each monitoring point at the current sampling moment and the fitted difference in ammonia consumption is taken as the relative ammonia consumption of each neighboring point corresponding to each monitoring point; based on the mean of the relative ammonia consumption of all neighboring points corresponding to each monitoring point, the fitted ammonia consumption of each monitoring point at the current sampling moment is determined.

9. The method for monitoring ammonia content in a flue gas denitration system according to claim 2, characterized in that: The process of monitoring the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption includes: The final ammonia content at each monitoring point is determined by taking the difference between the average raw ammonia content and the fitted ammonia consumption.

10. An ammonia content monitoring system for a flue gas denitrification system, characterized in that: The system comprises: The data acquisition preprocessing module is used to collect the unpurified ammonia content before purification and the initial ammonia content after purification at each monitoring point at each sampling time in the flue of the flue gas denitrification system; and obtain the neighboring points distributed adjacent to each monitoring point among all monitoring points; The first determination module is used to determine the ammonia consumption of each monitoring point at each sampling time according to the initial ammonia content of each monitoring point and the unpurified ammonia content of each adjacent point and the relative distance; and determine at least two periodic time periods in all sampling times according to the periodic fluctuation of the time series difference change of the ammonia consumption of each monitoring point; The second determination module is used to calculate the ammonia consumption deviation value between each monitoring point and each adjacent point at each sampling time in each periodic time period; according to the overall similarity of the ammonia consumption deviation values ​​between the current periodic time period and other periodic time periods, and the ammonia consumption deviation values ​​corresponding to each sampling time in the current periodic time period, determine the ammonia consumption fitting difference between each monitoring point and each adjacent point in the current periodic time period; The third determination module is used to determine the reference ammonia consumption of each monitoring point at the current sampling time according to the periodic changes in the historical ammonia consumption of each monitoring point and the overall value of the ammonia consumption in the current periodic time period; according to the reference ammonia consumption of each monitoring point at the current sampling time and the corresponding ammonia consumption fitting differences, determine the fitted ammonia consumption of each monitoring point at the current sampling time; The ammonia content monitoring module is used to monitor the ammonia content of the flue gas denitrification system according to the fitted ammonia consumption.

Images