CN117180952B - Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof - Google Patents
Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof Download PDFInfo
- Publication number
- CN117180952B CN117180952B CN202311465508.4A CN202311465508A CN117180952B CN 117180952 B CN117180952 B CN 117180952B CN 202311465508 A CN202311465508 A CN 202311465508A CN 117180952 B CN117180952 B CN 117180952B
- Authority
- CN
- China
- Prior art keywords
- flue gas
- time sequence
- water spray
- gas temperature
- correlation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 title claims abstract description 224
- 239000003546 flue gas Substances 0.000 title claims abstract description 224
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 79
- 230000023556 desulfurization Effects 0.000 title claims abstract description 79
- 239000000463 material Substances 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 27
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 238
- 238000005507 spraying Methods 0.000 claims abstract description 82
- 238000006243 chemical reaction Methods 0.000 claims abstract description 47
- 238000009826 distribution Methods 0.000 claims abstract description 35
- 230000003009 desulfurizing effect Effects 0.000 claims abstract description 34
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 33
- 239000000428 dust Substances 0.000 claims abstract description 25
- 238000003860 storage Methods 0.000 claims abstract description 10
- 239000007921 spray Substances 0.000 claims description 155
- 239000013598 vector Substances 0.000 claims description 82
- 238000010586 diagram Methods 0.000 claims description 66
- 239000000779 smoke Substances 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 29
- 239000007789 gas Substances 0.000 claims description 26
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 22
- 238000005728 strengthening Methods 0.000 claims description 20
- 239000002245 particle Substances 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 239000007787 solid Substances 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000011217 control strategy Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 239000007791 liquid phase Substances 0.000 claims description 4
- 238000006386 neutralization reaction Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000000746 purification Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 108010001267 Protein Subunits Proteins 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000002787 reinforcement Effects 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims 1
- 230000001105 regulatory effect Effects 0.000 claims 1
- 239000010410 layer Substances 0.000 description 53
- 230000000694 effects Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000005243 fluidization Methods 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000005514 two-phase flow Effects 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 239000002250 absorbent Substances 0.000 description 1
- 230000002745 absorbent Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000003916 acid precipitation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000000889 atomisation Methods 0.000 description 1
- JGIATAMCQXIDNZ-UHFFFAOYSA-N calcium sulfide Chemical compound [Ca]=S JGIATAMCQXIDNZ-UHFFFAOYSA-N 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000009751 slip forming Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004781 supercooling Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Landscapes
- Treating Waste Gases (AREA)
Abstract
Discloses a multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and a method thereof. The system comprises a desulfurizing agent storage and conveying device, a reaction tower, a water spraying and humidifying device, a dust removing system, a return material adjusting device, a desulfurized ash conveying system and an instrument control system, wherein an air inlet of the reaction tower is provided with an adjustable air flow distribution device, and the adjustable air flow distribution device is used for enabling the distribution of uplink flue gas in the reaction tower to be uniform; the bottom of the reaction tower is provided with a low-resistance Venturi device, a plurality of small Venturi devices are arranged in the low-resistance Venturi device, and the small Venturi devices are used for enabling the flue gas to circulate in a multidirectional airflow material layer; the water spraying and humidifying device is arranged at the outlet of the low-resistance Venturi device and is used for spraying atomized water so that the temperature of the flue gas is reduced. In this way, the temperature of the flue gas can be controlled.
Description
Technical Field
The application relates to the field of semi-dry flue gas desulfurization, and more particularly, to a multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and a method thereof.
Background
The industries of coal-fired power plants, steel and coking, cement, chemical industry, glass and the like in China can generate a large amount of dust and sulfur dioxide (SO) in the production process 2 ) Nitrogen Oxides (NO) x ) And pollutants such as heavy metal elements, in particular SO in flue gas 2 A series of environmental problems such as acid rain, photochemical smog, ozone layer damage, greenhouse effect and the like caused by emission are important points and difficulties to be solved.
Aiming at the current new policy requirements of environmental protection and the needs of water resource shortage and saving, the semi-dry desulfurization is compared with the wet desulfurization, so that the problems of waste water, white smoke and the like are avoided, and the investment and the operation cost of enterprises are greatly reduced. Therefore, the new research of the application of the semi-dry desulfurization device has very strong practical significance, the semi-dry desulfurization device based on the new desulfurization process is further developed, the desulfurization efficiency of the semi-dry desulfurization technology is improved, the most conforming desulfurization technology selected by enterprises can obtain the largest economic benefit, and the ultra-low emission requirement of pollutants can be realized by the combustion flue gas. Therefore, the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system is provided, and the safe and stable operation of the desulfurization system can be realized.
Disclosure of Invention
In view of this, the application provides a multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and a method thereof, which can comprehensively utilize flue gas temperature information and water spray flow information of a water spray humidifying device to realize self-adaptive control of water spray flow of the water spray humidifying device.
According to one aspect of the application, a multi-directional airflow material layer circulation semi-dry flue gas desulfurization system is provided, which comprises a desulfurizing agent storage and conveying device, a reaction tower, a water spraying and humidifying device, a dust removing system and a return material adjusting device, wherein,
an air inlet of the reaction tower is provided with an adjustable air flow distribution device, and the adjustable air flow distribution device is used for enabling the uplink flue gas in the reaction tower to be uniformly distributed;
the bottom of the reaction tower is provided with a low-resistance Venturi device, a plurality of small Venturi devices are arranged in the low-resistance Venturi device, and the small Venturi devices are used for enabling the flue gas to circulate in a multidirectional airflow material layer;
the water spraying and humidifying device is arranged at the outlet of the low-resistance Venturi device and is used for spraying atomized water so that the temperature of the flue gas is reduced;
in the operation process of the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system, flue gas is sprayed from the lower part of the reaction tower after passing through the desulfurizing agent storage and conveying device; the desulfurizing agent is mixed with the flue gas, sulfur dioxide in the flue gas is subjected to a rapid neutralization reaction on the particle liquid phase surface of the desulfurizing agent to obtain dust-containing flue gas after sulfur dioxide purification, the dust-containing flue gas is discharged from the reaction tower and enters the dust removal system, and the dust removal system is used for capturing solid particles in the dust-containing flue gas; and (3) passing the solid particles through the feed back adjusting device to return to the reaction tower for continuous reaction.
According to another aspect of the present application, there is provided a multi-directional gas stream bed circulation semi-dry flue gas desulfurization method, comprising:
acquiring flue gas temperature values at a plurality of preset time points in a preset time period acquired by a temperature sensor;
acquiring water spray flow values of the water spray humidifying device at a plurality of preset time points;
carrying out data structuring processing on the flue gas temperature values at a plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at a plurality of preset time points to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector;
extracting time sequence correlation characteristics between the flue gas temperature time sequence input vector and the water spraying flow time sequence input vector; and
based on the time sequence correlation characteristic, a control strategy of the water spray flow rate of the water spray humidifying device is determined.
According to the embodiment of the application, the system comprises a desulfurizing agent storage and conveying device, a reaction tower, a water spraying and humidifying device, a dust removing system and a return material adjusting device, wherein an air inlet of the reaction tower is provided with an adjustable air flow distribution device, and the adjustable air flow distribution device is used for enabling uplink flue gas in the reaction tower to be uniformly distributed; the bottom of the reaction tower is provided with a low-resistance Venturi device, a plurality of small Venturi devices are arranged in the low-resistance Venturi device, and the small Venturi devices are used for enabling the flue gas to circulate in a multidirectional airflow material layer; the water spraying and humidifying device is arranged at the outlet of the low-resistance Venturi device and is used for spraying atomized water so that the temperature of the flue gas is reduced. In this way, the temperature of the flue gas can be controlled.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present application and together with the description, serve to explain the principles of the present application.
Fig. 1 shows a block diagram of a multi-directional gas stream bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application.
FIG. 2 shows a block diagram of the water spray flow regulation module in a multi-directional gas stream bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application.
Fig. 3 shows a block diagram of the time-series-associated feature extraction unit in the multi-directional gas stream bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application.
Fig. 4 shows a block diagram of the water spray flow control unit in the multi-directional gas stream bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application.
Fig. 5 shows a flow chart of a multi-directional gas stream bed cycle semi-dry flue gas desulfurization method according to an embodiment of the present application.
Fig. 6 shows a schematic architecture diagram of a multi-directional gas stream bed cycle semi-dry flue gas desulfurization process according to an embodiment of the present application.
Fig. 7 shows an application scenario diagram of a multi-directional airflow bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application.
Wherein, 1, a reaction tower; 2. a water spray humidifying device; 3. a dust removal system; 4. a feed-back adjusting device; 11. a low resistance venturi device.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits have not been described in detail as not to unnecessarily obscure the present application.
The application provides a multidirectional air flow material layer circulation semi-dry flue gas desulfurization system, which comprises a desulfurizing agent storage and conveying device, a reaction tower 1, a water spraying and humidifying device 2, a dust removing system 3 and a return material adjusting device 4. As shown in fig. 1, in particular, the air inlet of the reaction tower 1 is provided with an adjustable air flow distribution device, and the adjustable air flow distribution device is used for making the distribution of the uplink flue gas in the reaction tower 1 uniform; the bottom of the reaction tower 1 is provided with a low-resistance Venturi device 11, a plurality of small Venturi devices are arranged in the low-resistance Venturi device 11, and the small Venturi devices are used for enabling the multi-directional airflow material layer of the flue gas to circulate; the water spraying and humidifying device 2 is arranged at the outlet of the low-resistance venturi device 11, and the water spraying and humidifying device 2 is used for spraying atomized water so that the temperature of the flue gas is reduced.
In the operation process of the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system, flue gas is sprayed from the lower part of the reaction tower 1 after passing through the desulfurizing agent storage and conveying device; the desulfurizing agent is mixed with the flue gas, sulfur dioxide in the flue gas is subjected to a rapid neutralization reaction on the particle liquid phase surface of the desulfurizing agent to obtain dust-containing flue gas after sulfur dioxide purification, the dust-containing flue gas enters the dust removal system 3 after being discharged from the reaction tower 1, and the dust removal system 3 is used for capturing solid particles in the dust-containing flue gas; the solid particles pass through the feed back adjusting device 4 to return to the reaction tower 1 for continuous reaction.
In the process that the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system actually carries out flue gas desulfurization, the water spraying and humidifying device 2 has the function of reducing the temperature of flue gas by spraying atomized water, thereby improving the desulfurization efficiency and reducing the consumption of desulfurizing agents. In general, it is necessary to control the water spray humidifying device 2, because if the water spray amount is too large, flue gas is supercooled, which affects the operation of the reaction tower 1; if the amount of water sprayed is too small, it may cause overheating of the flue gas, decrease the desulfurization efficiency and increase the consumption of the desulfurizing agent.
The existing method for controlling the water spraying and humidifying device mainly judges whether the water spraying amount needs to be adjusted or not and how to adjust the water spraying amount based on experience by manpower. However, this method is subjectively affected and there may be a problem in that the control results are inconsistent.
In this regard, the technical concept of the present application is to design a water spray flow rate regulation module in the water spray humidification device, and in the water spray flow rate regulation module, a deep learning algorithm is combined to comprehensively utilize flue gas temperature information and water spray flow rate information of the water spray humidification device to realize adaptive control of water spray flow rate of the water spray humidification device.
Based on this, fig. 2 shows a schematic block diagram of the water spray flow regulation module in the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system according to an embodiment of the present application. The water spray humidification device further includes a water spray flow regulation module 100, as shown in fig. 2, a multi-directional airflow material layer circulation semi-dry flue gas desulfurization system according to an embodiment of the application, the water spray flow regulation module 100 includes: a flue gas temperature acquisition unit 110 for acquiring flue gas temperature values at a plurality of predetermined time points within a predetermined period of time acquired by a temperature sensor; a water spray flow rate acquisition unit 120 for acquiring water spray flow rate values of the water spray humidification device at the plurality of predetermined time points; a data structuring unit 130, configured to perform data structuring processing on the flue gas temperature values at the plurality of predetermined time points and the water spraying flow rate values of the water spraying and humidifying device at the plurality of predetermined time points to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector; a time-series correlation feature extraction unit 140, configured to extract a time-series correlation feature between the flue gas temperature time-series input vector and the water spray flow time-series input vector; and a water spray flow control unit 150 for determining a control strategy for water spray flow of the water spray humidification device based on the time-series correlation characteristics.
Specifically, in the technical scheme of the application, firstly, flue gas temperature values of a plurality of preset time points in a preset time period acquired by a temperature sensor are acquired; and acquiring the water spray flow values of the water spray humidifying device at a plurality of preset time points. And then, arranging the flue gas temperature values at the plurality of preset time points and the water spraying flow values of the water spraying and humidifying device at the plurality of preset time points into a flue gas temperature time sequence input vector and a water spraying flow time sequence input vector according to the time dimension respectively so as to convert the flue gas temperature in time sequence discrete distribution and the water spraying flow in time sequence discrete distribution into structured vector representation.
Accordingly, the data structuring unit 130 is configured to: and arranging the flue gas temperature values at the plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at the plurality of preset time points into the flue gas temperature time sequence input vector and the water spraying flow rate time sequence input vector according to time dimensions respectively.
It should be understood that there is a reverse correlation between the flue gas temperature and the water spray flow of the water spray humidifying device, i.e. when the flue gas temperature value is higher than the predetermined temperature, the water spray flow value of the water spray humidifying device should be increased to reduce the flue gas temperature; when the flue gas temperature value is lower than the preset temperature, the water spraying flow value of the water spraying and humidifying device should be reduced so as to avoid supercooling of the flue gas. The related information reflects the regulation effect of the water spraying and humidifying device on the flue gas temperature. That is, the water spray flow value of the water spray humidifying device can influence the flue gas temperature value, and the flue gas temperature value can be fed back to the water spray humidifying device, so that a closed-loop control link is formed. In order to capture such a correlation, in the technical solution of the present application, it is expected to extract the time-series correlation feature between the flue gas temperature time-series input vector and the water-jet flow time-series input vector, and provide an important data source for judging how the water-jet flow value of the water-jet humidifying device should be adjusted.
In a specific example of the application, the implementation manner of extracting the time sequence correlation feature between the smoke temperature time sequence input vector and the water spray flow time sequence input vector is to code the smoke temperature time sequence input vector and the water spray flow time sequence input vector into a smoke temperature-water spray flow time sequence correlation matrix in a correlation manner, and then obtain a smoke temperature-water spray flow time sequence correlation feature map through a time sequence correlation feature extractor based on a convolutional neural network model. And taking the flue gas temperature-water spray flow time sequence correlation characteristic diagram as the time sequence correlation characteristic.
And then, the smoke temperature-water spray flow time sequence correlation characteristic diagram is subjected to characteristic autocorrelation correlation strengthening module to obtain an autocorrelation strengthening smoke temperature-water spray flow time sequence correlation characteristic diagram. That is, the autocorrelation in the flue gas temperature-water spray flow time sequence correlation characteristic diagram, namely the degree of interaction between the flue gas temperature and the water spray flow, is enhanced.
More specifically, in an embodiment of the present application, the encoding process of the flue gas temperature-water spray flow time sequence correlation characteristic map by a characteristic autocorrelation correlation strengthening module to obtain an autocorrelation strengthening flue gas temperature-water spray flow time sequence correlation characteristic map includes: firstly, passing a smoke temperature-water spray flow time sequence correlation characteristic diagram through a first convolution layer to obtain a dimension reduction characteristic diagram; then, the dimension reduction feature map passes through a second convolution layer to obtain an efficient association structure map; then, calculating a relation matrix of the efficient association structure diagram by cosine similarity operation; then, normalizing the relation matrix by using a Softmax function to obtain a normalized relation matrix; then, modeling the relation between any two feature values in the dimension reduction feature map by using the normalized relation matrix through element-by-element multiplication operation so as to obtain a correlation feature map; further, deconvolution operation is carried out on the correlation feature map so as to obtain a deconvoluted correlation feature map; then, the deconvoluted association feature map and the dimension reduction feature map are added element by element to obtain a preliminary result feature map; and then, after the preliminary result feature map is subjected to channel expansion to obtain an expanded preliminary result feature map, connecting the expanded preliminary result feature map with the flue gas temperature-water spray flow time sequence correlation feature map in a residual way to obtain the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map.
Accordingly, as shown in fig. 3, the timing-related feature extraction unit 140 includes: the convolutional encoding subunit 141 is configured to encode the flue gas temperature time sequence input vector and the water spray flow time sequence input vector into a flue gas temperature-water spray flow time sequence correlation matrix in a correlation manner, and obtain a flue gas temperature-water spray flow time sequence correlation feature map through a time sequence correlation feature extractor based on a convolutional neural network model; the strengthening subunit 142 is configured to pass the flue gas temperature-water spray flow time sequence correlation feature map through a feature autocorrelation correlation strengthening module to obtain an autocorrelation strengthening flue gas temperature-water spray flow time sequence correlation feature map; and a time sequence correlation characteristic obtaining subunit 143, configured to take the time sequence correlation characteristic diagram of the self-correlation enhanced flue gas temperature-water spray flow as the time sequence correlation characteristic.
Wherein, in the convolutional encoding subunit 141, the time-series correlation feature extractor based on the convolutional neural network model includes an input layer, a convolutional layer, an activation layer, a pooling layer, and an output layer. It is worth mentioning that convolutional neural networks (Convolutional Neural Network, CNN) are a deep learning model, particularly suitable for processing tasks with grid structure data, such as images and sequence data. Convolutional neural networks extract local features of input data by using convolutional layers and reduce the size and parameter amounts of feature maps by pooling layers. The convolution operation in the convolution layer may capture spatial local correlations in the input data, thereby reducing the number of parameters that need to be learned while retaining important information. The activation layer introduces nonlinear transformation to increase the expressive power of the model. The pooling layer is used for reducing the space dimension of the feature map, reducing the calculated amount and extracting more remarkable features. The convolutional neural network's application in time-series correlated feature extraction is based on its local feature extraction capability for time-series data. By sliding window operation of the convolutional layer, the convolutional neural network can capture time correlation and local patterns in the time series data, thereby extracting useful time series correlation features. These features can be used to analyze and predict patterns, trends, and associations in the time series data. In the convolutional coding subunit 141, a time sequence correlation feature extractor based on a convolutional neural network model extracts correlation features of smoke temperature and water spray flow time sequence data by using components such as a convolutional layer, an activation layer, a pooling layer and the like. These features may capture patterns and associations in the time series data by performing convolution and pooling operations on the input data to provide useful information for subsequent autocorrelation enhancement and feature acquisition steps.
More specifically, the reinforcement subunit 142 includes: the first convolution secondary subunit is used for enabling the smoke temperature-water spray flow time sequence correlation characteristic diagram to pass through the first convolution layer to obtain a dimension reduction characteristic diagram; the second convolution secondary subunit is used for enabling the dimension reduction feature map to pass through a second convolution layer to obtain an efficient association structure map; a relationship matrix calculation secondary subunit, configured to calculate a relationship matrix of the efficient association structure diagram by using cosine similarity operation; the normalization secondary subunit is used for performing normalization processing on the relation matrix by using a Softmax function to obtain a normalized relation matrix; the element-by-element multiplication secondary subunit is used for completing modeling of the relation between any two feature values in the dimension reduction feature map by the normalized relation matrix by utilizing element-by-element multiplication operation so as to obtain a correlation feature map; deconvolution secondary sub-unit, which is used for deconvoluting the correlation characteristic diagram to obtain deconvoluted correlation characteristic diagram; element-by-element addition secondary subunit, configured to add the deconvoluted association feature map and the dimension-reduction feature map element-by-element to obtain a preliminary result feature map; and the residual error is connected with a secondary subunit, and is used for carrying out channel expansion on the preliminary result characteristic diagram to obtain an expanded preliminary result characteristic diagram, and then connecting the expanded preliminary result characteristic diagram with the flue gas temperature-water spray flow time sequence correlation characteristic diagram residual error to obtain the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram.
And then, the self-correlation enhanced flue gas temperature-water spray flow time sequence correlation characteristic diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the water spray flow value of the water spray humidifying device should be increased, maintained or decreased.
Accordingly, as shown in fig. 4, the water spray flow control unit 150 includes: a feature distribution optimizing subunit 151, configured to perform feature distribution optimization on the autocorrelation enhanced flue gas temperature-water spray flow time sequence correlation feature map to obtain an optimized autocorrelation enhanced flue gas temperature-water spray flow time sequence correlation feature map; a classification subunit 152, configured to pass the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map through a classifier to obtain a classification result, where the classification result is used to indicate that the water spray flow value of the water spray humidifying device should be increased, should be kept or should be decreased; and a control strategy acquisition subunit 153 for using the classification result for a control strategy representing the water spray flow rate of the water spray humidification device.
In the technical scheme of the application, when the smoke temperature-water spray flow time sequence correlation characteristic diagram is obtained through a characteristic autocorrelation correlation strengthening module, each characteristic matrix of the smoke temperature-water spray flow time sequence correlation characteristic diagram expresses high-order correlation characteristics of full time domain correlation of the smoke temperature value and the water spray flow value, and channel distribution of the convolutional neural network model is followed among the characteristic matrixes, the characteristic autocorrelation strengthening module takes the channel vector of the smoke temperature-water spray flow time sequence correlation characteristic diagram as a unit, and characteristic autocorrelation strengthening under the characteristic matrix distribution dimension can be carried out based on the full time domain high-order correlation characteristic distribution of the characteristic matrix, so that the channel distribution of the autocorrelation strengthening smoke temperature-water spray flow time sequence correlation characteristic diagram is led to deviate from the channel distribution expression of the smoke temperature-water spray flow time sequence correlation characteristic diagram while the overall expression consistency of the autocorrelation strengthening smoke temperature-water spray flow time sequence correlation characteristic diagram is improved, the target distribution expression consistency of the classification result is influenced, and the smoke temperature-water spray flow correlation time sequence correlation characteristic diagram is accurately classified by the classifier.
Thus, it is preferred that the global average of each feature matrix of the flue gas temperature-water spray flow time series correlation feature map is first calculated to obtain flue gas temperature-water spray flow time series correlation feature vectors, e.g. denoted asCalculating the global average value of each characteristic matrix of the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram to obtain an autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic vector, for example, marked as +.>Then the smoke temperature-water spraying flow time sequence related characteristic vector is used for->For the time sequence correlation characteristic vector of the self-correlation enhanced flue gas temperature and water spraying flow>Optimizing to obtain optimized autocorrelation reinforced smoke temperature-water spraying flow time sequence correlation characteristic vector, for example, marked as +.>。
Accordingly, in one example, the feature distribution optimization subunit 151 is further configured to: carrying out feature distribution optimization on the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map by using the following optimization formula to obtain the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map; wherein, the optimization formula is:
wherein,representing a flue gas temperature-water spray flow time sequence correlation feature vector obtained by calculating the global average value of each feature matrix of the flue gas temperature-water spray flow time sequence correlation feature map, +. >Representing an autocorrelation enhanced flue gas temperature-water spray flow time sequence correlation feature vector obtained by calculating the global average value of each feature matrix of the autocorrelation enhanced flue gas temperature-water spray flow time sequence correlation feature map,/a>And->Respectively represent the time sequence correlation characteristic vector of the flue gas temperature and the water spraying flow>And the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic vector +.>Inverse of the global mean value of (2), and +.>Is a unit vector, +.>Representing multiplication by location +.>Representing vector subtraction +.>Representing vector addition, ++>And representing the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic vector obtained after the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic map is unfolded.
That is, if the self-correlation enhanced flue gas temperature-water spray flow time sequence correlation feature vector is taken into consideration in expressing consistency of channel dimension distributionRegarding as the smoke temperature-water spray flow time sequence correlation characteristic vector +.>The characteristic distribution enhancement input of (2) taking into account the flue gas temperature-water spray flow time sequence associated characteristic vector +.>The target distribution information loss of the target features in the class space possibly causes the class regression target loss, so that the self-supervision balance of feature enhancement and regression robustness can be realized through feature interpolation fusion by means of cross penalty to the outlier distribution (outlier distribution) of the feature distribution relative to each other so as to promote the flue gas temperature-water spray flow time sequence correlation feature vector- >And the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic vector +.>In this way, the optimized autocorrelation is used for strengthening the smoke temperature-water spraying flow time sequence correlation characteristic vector +.>And weighting the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram along the channel, so that the accuracy of a classification result obtained by the classifier of the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram can be improved.
Further, the classifying subunit 152 includes: the feature map expansion secondary subunit is used for expanding the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map into an optimized classification feature vector according to a row vector or a column vector; the full-connection coding secondary subunit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and a coding classification secondary subunit, configured to input the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
In summary, the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system based on the embodiment of the application is illustrated, and can realize the self-adaptive control of the water spray flow of the water spray humidifying device by comprehensively utilizing the flue gas temperature information and the water spray flow information of the water spray humidifying device.
As described above, the multi-directional gas stream layer cycle semi-dry flue gas desulfurization system according to the embodiments of the present application may be implemented in various terminal devices, for example, a server or the like having a multi-directional gas stream layer cycle semi-dry flue gas desulfurization algorithm. In one example, the multi-directional gas stream bed cycle semi-dry flue gas desulfurization system may be integrated into the terminal device as a software module and/or hardware module. For example, the multi-directional gas stream bed cycle semi-dry flue gas desulfurization system may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system can be one of a plurality of hardware modules of the terminal equipment.
Alternatively, in another example, the multi-directional gas stream layer cycle semi-dry flue gas desulfurization system and the terminal device may be separate devices, and the multi-directional gas stream layer cycle semi-dry flue gas desulfurization system may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 5 shows a flow chart of a multi-directional gas stream bed cycle semi-dry flue gas desulfurization method according to an embodiment of the present application. Fig. 6 shows a schematic diagram of a system architecture of a multi-directional gas stream bed cycle semi-dry flue gas desulfurization process according to an embodiment of the present application. As shown in fig. 5 and 6, the multi-directional airflow material layer circulation semi-dry flue gas desulfurization method according to the embodiment of the application comprises the following steps: s110, acquiring flue gas temperature values of a plurality of preset time points in a preset time period acquired by a temperature sensor; s120, acquiring water spray flow values of the water spray humidifying device at a plurality of preset time points; s130, carrying out data structuring processing on the flue gas temperature values at a plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at a plurality of preset time points to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector; s140, extracting time sequence correlation characteristics between the flue gas temperature time sequence input vector and the water spray flow time sequence input vector; and S150, determining a control strategy of the water spray flow rate of the water spray humidifying device based on the time sequence correlation characteristic.
In one possible implementation manner, performing data structuring processing on the flue gas temperature values at the plurality of preset time points and the water spraying flow rate values of the water spraying humidifying device at the plurality of preset time points to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector, including: and arranging the flue gas temperature values at the plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at the plurality of preset time points into the flue gas temperature time sequence input vector and the water spraying flow rate time sequence input vector according to time dimensions respectively.
Here, it will be understood by those skilled in the art that the specific operation of each step in the above-described multi-directional gas stream layer cycle semi-dry flue gas desulfurization method has been described in detail in the above description of the multi-directional gas stream layer cycle semi-dry flue gas desulfurization system with reference to fig. 2 to 4, and thus, repetitive descriptions thereof will be omitted.
Fig. 7 shows an application scenario diagram of a multi-directional airflow bed cycle semi-dry flue gas desulfurization system according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, flue gas temperature values at a plurality of predetermined time points (for example, D1 illustrated in fig. 7) within a predetermined period of time acquired by a temperature sensor are acquired, and water spray flow rate values of the water spray humidifying device at the plurality of predetermined time points (for example, D2 illustrated in fig. 7) are then input to a server (for example, S illustrated in fig. 7) where a multi-directional gas stream layer cycle semi-dry flue gas desulfurization algorithm is deployed, wherein the server is capable of processing the flue gas temperature values at the plurality of predetermined time points and the water spray flow rate values of the water spray humidifying device at the plurality of predetermined time points using the multi-directional gas stream layer cycle semi-dry flue gas desulfurization algorithm to obtain a classification result indicating that the water spray humidifying device should be increased, should be maintained or should be decreased.
Further, the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system is described in more detail. The adjustable airflow distribution device is arranged at the air inlet of the reaction tower of the multidirectional airflow material layer circulation semi-dry flue gas desulfurization system, so that the uplink flue gas in the reaction tower is uniformly distributed, the flue gas resistance is reduced, and the impact of the flue gas on the tower body is reduced. Meanwhile, the bottom of the tower is designed into a low-resistance Venturi device, a plurality of small Venturi devices are arranged in the low-resistance Venturi device, and the flue gas acceleration is effectively promoted through innovative design of small Venturi sizes, directions and distributionThe stability enables the multi-directional airflow material layer of the flue gas to circulate, and the desulfurization efficiency is greatly improved. After the flue gas enters the circulating fluidized bed body at a high speed, fresh desulfurizing agent is sprayed from the lower part of the reaction tower through the storage and conveying device, meanwhile, a water spraying and humidifying device is reasonably arranged at the outlet of a venturi, the sprayed atomized water reduces the temperature of the flue gas, under the action of moisture and oxygen, the activity of desulfurizing agent powder particles is greatly increased, the flue gas and the desulfurizing agent are fully mixed in the bed, and SO in the flue gas 2 The neutralization reaction is fast carried out on the liquid phase surface of the desulfurizing agent powder particles, the materials are in the circulating fluidized bed, the gas-solid two-phase flow generates intense turbulence and mixing due to the action of the air flow, the materials are fully contacted, the aggregates are continuously formed to return downwards in the rising process, the aggregates are continuously disintegrated and are lifted by the air flow again in the intense turbulence, so that the sliding speed between the gas and the solid is up to tens of times of the sliding speed of single particles, and the mass transfer and heat transfer between the gas and the solid are greatly enhanced by a gas-solid two-phase flow mechanism in the circulating fluidized bed. Through the internal circulation and friction of the circulating fluidized bed, the surface layer of the desulfurizer powder particles continuously falls off, and unreacted components are continuously exposed in the flue gas and are contacted with SO in the flue gas 2 The reaction is continued, and the reaction time of the desulfurizing agent is fully prolonged by fully utilizing the circulating desulfurizing agent. Purification of SO 2 The dust-containing flue gas is discharged from the reaction tower and enters the dust removal system, the solid particles trapped by the dust removal system are returned to the reaction tower through the feed back adjusting device of the recirculation system to continue to participate in the reaction, and the guarantee is provided for realizing high desulfurization rate.
Compared with the traditional desulfurization device, the multidirectional airflow material layer circulation semi-dry flue gas desulfurization system is innovatively designed with a desulfurizing agent storage and conveying device, the fluidity of materials is enhanced through air fluidization wind, and accurate control and adjustment of desulfurizing agent amount are realized by adopting weighing sensing element monitoring and feeding frequency. In order to prevent wet materials, scaling and dewing, the water spraying and humidifying device is uniformly arranged in multiple layers, each layer can independently operate, the dispersion and atomization effects of water spraying points are guaranteed, the activity of desulfurization materials is greatly enhanced, and the desulfurization efficiency of the reaction tower is greatly improved by controlling the flue gas quantity, the flue gas temperature and the moisture content in real time.
Meanwhile, the novel design of the return material adjusting device ensures that the desulfurization ash has better fluidity under the dynamic force of the fluidization wind and the attraction guiding action of the negative pressure of the reaction tower, the novel design of the desulfurization ash enables the control interlocking of the return material amount of the desulfurization agent, the inlet and outlet flue gas pressure difference, the flue gas characteristics, the water spraying amount and the desulfurization efficiency of the reaction tower, the high utilization rate of the desulfurization agent is ensured by adjusting the return material amount, the actual calcium-sulfur ratio and the bed pressure difference in the reaction tower are obviously improved, and the bottom of two sides of the return material adjusting device is additionally provided with the full-sealing three-way reversing valve for distributing and adjusting the ash conveying amount, so that the deactivated desulfurization ash can be ensured to be discharged outside through a conveying system.
It should be understood that the air inlet of the reaction tower is provided with a multidirectional air flow material layer for circulation, the air flow distribution and the air flow direction can be adjusted, and a low-resistance multidirectional venturi device which is innovatively designed at the bottom of the tower is further provided with a plurality of small venturi devices; and the upward smoke in the reaction tower is uniformly distributed, so that the smoke resistance is reduced, and the impact of the smoke on the tower body is reduced.
The desulfurizing agent conveying operation device with innovative design is adopted, the contact effect of the desulfurizing absorbent and the flue gas is more remarkable, more sufficient and stronger, the utilization rate and the desulfurizing efficiency of the desulfurizing agent are greatly improved, and the actual control of the bed pressure drop of the desulfurizing device is enhanced. And the operation treatment of combining the flue gas flow field, the size distribution control and the spray technology control is greatly improved, and the ultra-low emission control technology is improved. Compared with the traditional semi-dry desulfurization device, the device has the advantages of strong adaptability to flue gas, wide application range, convenient control, low energy consumption and more stable device operation.
Furthermore, the multidirectional airflow material layer circulation semi-dry flue gas desulfurization system is more compact in structure, small in occupied area, stable in operation and high in reliability. Not only improves the desulfurization efficiency, but also effectively improves the operation control level and effect, thoroughly solves the problems of low desulfurization speed and low efficiency of the traditional semi-dry flue gas desulfurization device, and realizes SO 2 The requirement of ultra-low emission meets the environmental protection requirement of industrial development of various industries. The multidirectional airflow material layer circulation semi-dry flue gas desulfurization system improves the control of bed pressure drop through the innovative design of operation control technologies such as desulfurizing agent, flue gas quantity and spraying, effectively ensures the stable operation of the device through the monitoring of the related loop instrument control element and the adjustment of the mechanical device, has good fluidization of the desulfurizing agent, increases the recycling times of the desulfurizing agent, greatly prolongs the contact time of the desulfurizing agent and flue gas, and greatly improves the utilization rate of the desulfurizing agent. Meanwhile, the operation and maintenance workload of the device is effectively reduced, the service life of the device is prolonged, and the energy consumption of a desulfurization system is obviously reduced.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The embodiments of the present application have been described above, the foregoing description is exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (7)
1. A multi-directional airflow material layer circulation semi-dry flue gas desulfurization system comprises a desulfurizing agent storage and conveying device, a reaction tower, a water spraying and humidifying device, a dust removing system and a return material adjusting device, and is characterized in that,
an air inlet of the reaction tower is provided with an adjustable air flow distribution device, and the adjustable air flow distribution device is used for enabling the uplink flue gas in the reaction tower to be uniformly distributed;
the bottom of the reaction tower is provided with a low-resistance Venturi device, a plurality of small Venturi devices are arranged in the low-resistance Venturi device, and the small Venturi devices are used for enabling the flue gas to circulate in a multidirectional airflow material layer;
The water spraying and humidifying device is arranged at the outlet of the low-resistance Venturi device and is used for spraying atomized water so that the temperature of the flue gas is reduced;
in the operation process of the multi-directional airflow material layer circulation semi-dry flue gas desulfurization system, flue gas is sprayed from the lower part of the reaction tower after passing through the desulfurizing agent storage and conveying device; the desulfurizing agent is mixed with the flue gas, sulfur dioxide in the flue gas is subjected to a rapid neutralization reaction on the particle liquid phase surface of the desulfurizing agent to obtain dust-containing flue gas after sulfur dioxide purification, the dust-containing flue gas is discharged from the reaction tower and enters the dust removal system, and the dust removal system is used for capturing solid particles in the dust-containing flue gas; passing the solid particles through the feed back adjusting device to return to the reaction tower for continuous reaction;
wherein, the water spray humidifying device also comprises a water spray flow regulating and controlling module;
wherein, the water spray flow regulation and control module includes:
a flue gas temperature acquisition unit for acquiring flue gas temperature values at a plurality of predetermined time points within a predetermined time period acquired by the temperature sensor;
a water spray flow obtaining unit for obtaining water spray flow values of the water spray humidification device at the plurality of preset time points;
The data structuring unit is used for carrying out data structuring processing on the flue gas temperature values at a plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at a plurality of preset time points so as to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector;
the time sequence correlation feature extraction unit is used for extracting time sequence correlation features between the flue gas temperature time sequence input vector and the water spraying flow time sequence input vector; and
a water spray flow control unit for determining a control strategy of water spray flow of the water spray humidification device based on the time sequence correlation characteristic;
wherein the timing-related feature extraction unit includes:
the convolution coding subunit is used for performing association coding on the flue gas temperature time sequence input vector and the water spraying flow time sequence input vector to obtain a flue gas temperature-water spraying flow time sequence association characteristic diagram through a time sequence association characteristic extractor based on a convolution neural network model after the flue gas temperature time sequence input vector and the water spraying flow time sequence input vector are used for performing association coding on the flue gas temperature-water spraying flow time sequence association matrix;
the strengthening subunit is used for enabling the flue gas temperature-water spraying flow time sequence correlation characteristic diagram to pass through a characteristic autocorrelation correlation strengthening module to obtain an autocorrelation strengthening flue gas temperature-water spraying flow time sequence correlation characteristic diagram; and
The time sequence correlation characteristic acquisition subunit is used for taking the time sequence correlation characteristic diagram of the self-correlation enhanced flue gas temperature-water spraying flow as the time sequence correlation characteristic;
wherein the reinforcement subunit comprises:
the first convolution secondary subunit is used for enabling the smoke temperature-water spray flow time sequence correlation characteristic diagram to pass through the first convolution layer to obtain a dimension reduction characteristic diagram;
the second convolution secondary subunit is used for enabling the dimension reduction feature map to pass through a second convolution layer to obtain an efficient association structure map;
a relationship matrix calculation secondary subunit, configured to calculate a relationship matrix of the efficient association structure diagram by using cosine similarity operation;
the normalization secondary subunit is used for performing normalization processing on the relation matrix by using a Softmax function to obtain a normalized relation matrix;
the element-by-element multiplication secondary subunit is used for completing modeling of the relation between any two feature values in the dimension reduction feature map by the normalized relation matrix by utilizing element-by-element multiplication operation so as to obtain a correlation feature map;
deconvolution secondary sub-unit, which is used for deconvoluting the correlation characteristic diagram to obtain deconvoluted correlation characteristic diagram;
element-by-element addition secondary subunit, configured to add the deconvoluted association feature map and the dimension-reduction feature map element-by-element to obtain a preliminary result feature map; and
And the residual error connection secondary subunit is used for carrying out channel expansion on the preliminary result characteristic diagram to obtain an expanded preliminary result characteristic diagram, and carrying out residual error connection on the expanded preliminary result characteristic diagram and the flue gas temperature-water spray flow time sequence correlation characteristic diagram to obtain the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram.
2. The multi-directional gas stream bed cycle semi-dry flue gas desulfurization system according to claim 1, wherein the data structuring unit is configured to:
and arranging the flue gas temperature values at the plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at the plurality of preset time points into the flue gas temperature time sequence input vector and the water spraying flow rate time sequence input vector according to time dimensions respectively.
3. The multi-directional gas stream bed circulating semi-dry flue gas desulfurization system of claim 2, wherein the time-series correlation feature extractor based on the convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer, and an output layer.
4. A multi-directional gas stream bed cycle semi-dry flue gas desulfurization system as recited in claim 3, wherein said water spray flow control unit comprises:
The characteristic distribution optimizing subunit is used for carrying out characteristic distribution optimization on the autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram so as to obtain an optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation characteristic diagram;
the classification subunit is used for enabling the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence association characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating that the water spray flow value of the water spray humidifying device should be increased, kept or decreased; and
and the control strategy acquisition subunit is used for using the classification result to represent the control strategy of the water spray flow of the water spray humidifying device.
5. The multi-directional gas stream bed cycle semi-dry flue gas desulfurization system of claim 4, wherein the classification subunit comprises:
the feature map expansion secondary subunit is used for expanding the optimized autocorrelation reinforced flue gas temperature-water spray flow time sequence correlation feature map into an optimized classification feature vector according to a row vector or a column vector;
the full-connection coding secondary subunit is used for carrying out full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and
And the coding classification secondary subunit is used for inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
6. A multi-directional airflow material layer circulation semi-dry flue gas desulfurization method is characterized by comprising the following steps:
acquiring flue gas temperature values at a plurality of preset time points in a preset time period acquired by a temperature sensor;
acquiring water spray flow values of the water spray humidifying device at a plurality of preset time points;
carrying out data structuring processing on the flue gas temperature values at a plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at a plurality of preset time points to obtain a flue gas temperature time sequence input vector and a water spraying flow rate time sequence input vector;
extracting time sequence correlation characteristics between the flue gas temperature time sequence input vector and the water spraying flow time sequence input vector; and
determining a control strategy of water spray flow of the water spray humidification device based on the time sequence correlation characteristic;
extracting time sequence correlation characteristics between the flue gas temperature time sequence input vector and the water spray flow time sequence input vector comprises the following steps:
the smoke temperature time sequence input vector and the water spraying flow time sequence input vector are coded into a smoke temperature-water spraying flow time sequence correlation matrix in a correlation way, and then a time sequence correlation characteristic extractor based on a convolutional neural network model is used for obtaining a smoke temperature-water spraying flow time sequence correlation characteristic diagram;
The smoke temperature-water spray flow time sequence correlation characteristic diagram is subjected to characteristic autocorrelation correlation strengthening module to obtain an autocorrelation strengthening smoke temperature-water spray flow time sequence correlation characteristic diagram; and
taking the time sequence correlation characteristic diagram of the self-correlation reinforced flue gas temperature-water spraying flow as the time sequence correlation characteristic;
the flue gas temperature-water spray flow time sequence correlation characteristic diagram is subjected to characteristic autocorrelation correlation strengthening module to obtain an autocorrelation strengthening flue gas temperature-water spray flow time sequence correlation characteristic diagram, which comprises the following steps:
passing the smoke temperature-water spray flow time sequence correlation characteristic map through a first convolution layer to obtain a dimension reduction characteristic map;
the dimension reduction feature map passes through a second convolution layer to obtain an efficient association structure map;
calculating a relation matrix of the efficient association structure diagram by cosine similarity operation;
normalizing the relation matrix by using a Softmax function to obtain a normalized relation matrix;
modeling the relation between any two feature values in the dimension reduction feature map by using the normalized relation matrix by element-by-element multiplication operation to obtain a correlation feature map;
deconvolution operation is carried out on the correlation feature map so as to obtain a deconvoluted correlation feature map;
Adding the deconvoluted association feature map and the dimension reduction feature map element by element to obtain a preliminary result feature map; and
and after the preliminary result feature map is subjected to channel expansion to obtain an expanded preliminary result feature map, connecting the expanded preliminary result feature map with the smoke temperature-water spray flow time sequence correlation feature map in a residual way to obtain the autocorrelation reinforced smoke temperature-water spray flow time sequence correlation feature map.
7. The multi-directional gas stream bed cycle semi-dry flue gas desulfurization method according to claim 6, wherein the data structuring process is performed on the flue gas temperature values at the plurality of predetermined time points and the water spray flow rate values of the water spray humidifying device at the plurality of predetermined time points to obtain a flue gas temperature time sequence input vector and a water spray flow rate time sequence input vector, comprising:
and arranging the flue gas temperature values at the plurality of preset time points and the water spraying flow rate values of the water spraying and humidifying device at the plurality of preset time points into the flue gas temperature time sequence input vector and the water spraying flow rate time sequence input vector according to time dimensions respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465508.4A CN117180952B (en) | 2023-11-07 | 2023-11-07 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465508.4A CN117180952B (en) | 2023-11-07 | 2023-11-07 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117180952A CN117180952A (en) | 2023-12-08 |
| CN117180952B true CN117180952B (en) | 2024-02-02 |
Family
ID=89002011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311465508.4A Active CN117180952B (en) | 2023-11-07 | 2023-11-07 | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117180952B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2581056Y (en) * | 2002-11-19 | 2003-10-22 | 北京中科通用能源环保有限责任公司 | Smoke desulfurizing device for circulation fluidized bed |
| CN109034378A (en) * | 2018-09-04 | 2018-12-18 | 腾讯科技（深圳）有限公司 | Network representation generation method, device, storage medium and the equipment of neural network |
| WO2020233427A1 (en) * | 2019-05-17 | 2020-11-26 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining features of target |
| WO2021088700A1 (en) * | 2019-11-05 | 2021-05-14 | 京东数科海益信息科技有限公司 | Nozzle control method and apparatus, computer device and storage medium |
| CN113304585A (en) * | 2021-05-22 | 2021-08-27 | 北京铝能清新环境技术有限公司 | Semi-dry desulfurization system suitable for low-sulfur flue gas |
| WO2021208343A1 (en) * | 2020-04-17 | 2021-10-21 | 广西电网有限责任公司电力科学研究院 | Neural network model-based method and apparatus for water spray adjustment of water spray desuperheater |
| CN216909833U (en) * | 2022-01-11 | 2022-07-08 | 山东中新环境工程有限公司 | Semidry method flue gas desulfurization device |
| CN116272363A (en) * | 2023-05-17 | 2023-06-23 | 浙江浙能迈领环境科技有限公司 | Ship exhaust gas mixed desulfurization system and method thereof |
| CN116688754A (en) * | 2023-07-05 | 2023-09-05 | 浙江浙能迈领环境科技有限公司 | Ship flue gas desulfurization automatic control system and method thereof |
| WO2023206724A1 (en) * | 2022-04-29 | 2023-11-02 | 福建德尔科技股份有限公司 | Rectification control system and control method for preparation of electronic-grade difluoromethane |
| CN116983819A (en) * | 2023-08-11 | 2023-11-03 | 浙江浙能迈领环境科技有限公司 | Flue gas desulfurization washing tower and method thereof |
-
2023
- 2023-11-07 CN CN202311465508.4A patent/CN117180952B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2581056Y (en) * | 2002-11-19 | 2003-10-22 | 北京中科通用能源环保有限责任公司 | Smoke desulfurizing device for circulation fluidized bed |
| CN109034378A (en) * | 2018-09-04 | 2018-12-18 | 腾讯科技（深圳）有限公司 | Network representation generation method, device, storage medium and the equipment of neural network |
| WO2020233427A1 (en) * | 2019-05-17 | 2020-11-26 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining features of target |
| WO2021088700A1 (en) * | 2019-11-05 | 2021-05-14 | 京东数科海益信息科技有限公司 | Nozzle control method and apparatus, computer device and storage medium |
| WO2021208343A1 (en) * | 2020-04-17 | 2021-10-21 | 广西电网有限责任公司电力科学研究院 | Neural network model-based method and apparatus for water spray adjustment of water spray desuperheater |
| CN113304585A (en) * | 2021-05-22 | 2021-08-27 | 北京铝能清新环境技术有限公司 | Semi-dry desulfurization system suitable for low-sulfur flue gas |
| CN216909833U (en) * | 2022-01-11 | 2022-07-08 | 山东中新环境工程有限公司 | Semidry method flue gas desulfurization device |
| WO2023206724A1 (en) * | 2022-04-29 | 2023-11-02 | 福建德尔科技股份有限公司 | Rectification control system and control method for preparation of electronic-grade difluoromethane |
| CN116272363A (en) * | 2023-05-17 | 2023-06-23 | 浙江浙能迈领环境科技有限公司 | Ship exhaust gas mixed desulfurization system and method thereof |
| CN116688754A (en) * | 2023-07-05 | 2023-09-05 | 浙江浙能迈领环境科技有限公司 | Ship flue gas desulfurization automatic control system and method thereof |
| CN116983819A (en) * | 2023-08-11 | 2023-11-03 | 浙江浙能迈领环境科技有限公司 | Flue gas desulfurization washing tower and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117180952A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020088485A1 (en) | Intelligent multi-pollutant ultra-low emission system and global optimization method | |
| Zhong et al. | A model for performance optimization of wet flue gas desulfurization systems of power plants | |
| Zhang et al. | Evaluating co-benefits of energy efficiency and air pollution abatement in China’s cement industry | |
| CN107243257B (en) | It is suitble to the intelligence spray ammonia control system of full load | |
| US9910413B2 (en) | Automatic tuning control system for air pollution control systems | |
| JPH084709B2 (en) | Wet Flue Gas Desulfurization Controller | |
| Wang et al. | Simulation of the heterogeneous semi-dry flue gas desulfurization in a pilot CFB riser using the two-fluid model | |
| Martínez et al. | Operation of a cyclonic preheater in the Ca-looping for CO2 capture | |
| CN110263452B (en) | Flue gas time distribution characteristic analysis method and system in flue and denitration system | |
| Qiao et al. | An investigation on data mining and operating optimization for wet flue gas desulfurization systems | |
| WO2006036819A2 (en) | Method and system for increasing efficiency of fgd operation in fossil fuel boilers | |
| CN109711589A (en) | A kind of SCR denitration system running optimizatin method and system based on big data | |
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN111460726A (en) | Optimization method for ammonia escape of coal slime fluidized bed boiler denitration system | |
| Lee et al. | Optimizing the specific surface area of fly ash-based sorbents for flue gas desulfurization | |
| CN111598308A (en) | Method for solving combination optimization of slurry circulating pump based on regression and double PSO algorithm | |
| CN115145152A (en) | Boiler combustion and denitration process collaborative optimization control method | |
| CN106485022A (en) | A kind of modeling method of circulating fluid bed boiler desulfurization denitration running optimizatin control | |
| CN113175678A (en) | Method and device for monitoring garbage incineration | |
| Cai et al. | Numerical simulation and optimization of semi-dry flue gas desulfurization in a CFB based on the two-film theory using response surface methodology | |
| Fu et al. | Control strategy for denitrification efficiency of coal-fired power plant based on deep reinforcement learning | |
| CN117180952B (en) | Multi-directional airflow material layer circulation semi-dry flue gas desulfurization system and method thereof | |
| Yang et al. | Dynamic optimization oriented modeling and nonlinear model predictive control of the wet limestone FGD system | |
| Liu et al. | Multiobjective economic model predictive control using utopia-tracking for the wet flue gas desulphurization system | |
| JP2023081485A (en) | Quantity-of-state prediction device and quantity-of-state prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |