CN116832588A - Acid regeneration flue gas purifying device and method thereof - Google Patents
Acid regeneration flue gas purifying device and method thereof Download PDFInfo
- Publication number
- CN116832588A CN116832588A CN202311080709.2A CN202311080709A CN116832588A CN 116832588 A CN116832588 A CN 116832588A CN 202311080709 A CN202311080709 A CN 202311080709A CN 116832588 A CN116832588 A CN 116832588A
- Authority
- CN
- China
- Prior art keywords
- flue gas
- time sequence
- feature
- smoke
- gas flow
- 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.)
- Granted
Links
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 title claims abstract description 151
- 239000003546 flue gas Substances 0.000 title claims abstract description 151
- 239000002253 acid Substances 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000011069 regeneration method Methods 0.000 title claims abstract description 44
- 230000008929 regeneration Effects 0.000 title claims abstract description 42
- 239000000779 smoke Substances 0.000 claims abstract description 117
- 230000003247 decreasing effect Effects 0.000 claims abstract description 22
- 238000000746 purification Methods 0.000 claims abstract description 18
- 238000010219 correlation analysis Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 139
- 239000011159 matrix material Substances 0.000 claims description 64
- 238000013507 mapping Methods 0.000 claims description 57
- 238000009826 distribution Methods 0.000 claims description 46
- 238000004140 cleaning Methods 0.000 claims description 37
- 238000012546 transfer Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 8
- 238000004088 simulation Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 239000003517 fume Substances 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000007789 gas Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- KRHYYFGTRYWZRS-UHFFFAOYSA-N Fluorane Chemical compound F KRHYYFGTRYWZRS-UHFFFAOYSA-N 0.000 description 3
- 230000004913 activation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 3
- 239000010931 gold Substances 0.000 description 3
- 229910052737 gold Inorganic materials 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- QAOWNCQODCNURD-UHFFFAOYSA-N Sulfuric acid Chemical compound OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- GRYLNZFGIOXLOG-UHFFFAOYSA-N Nitric acid Chemical compound O[N+]([O-])=O GRYLNZFGIOXLOG-UHFFFAOYSA-N 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009835 boiling Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000005555 metalworking Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- QPJSUIGXIBEQAC-UHFFFAOYSA-N n-(2,4-dichloro-5-propan-2-yloxyphenyl)acetamide Chemical compound CC(C)OC1=CC(NC(C)=O)=C(Cl)C=C1Cl QPJSUIGXIBEQAC-UHFFFAOYSA-N 0.000 description 1
- 229910017604 nitric acid Inorganic materials 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/30—Controlling by gas-analysis apparatus
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
An acid regeneration flue gas purifying device and a method thereof are disclosed. Firstly, acquiring smoke flow values, temperature values and pressure values at a plurality of preset time points in a preset time period through a sensor group, then, carrying out time sequence collaborative correlation analysis on the smoke flow values, the temperature values and the pressure values at the preset time points to obtain smoke parameter time sequence collaborative features, and then, determining that the smoke flow value at the current time point should be increased or decreased based on the smoke parameter time sequence collaborative features. Therefore, the dynamic automatic control of the flue gas flow can be performed based on the actual flue gas parameters, so that better purification effect and energy utilization rate are realized.
Description
Technical Field
The present disclosure relates to the field of purification devices, and more particularly, to an acid regeneration flue gas purification device and a method thereof.
Background
In the metal working process, surface treatment is generally required in order to prevent oxidation of the metal material at normal temperature, wherein one common treatment method is acid washing using strong acid. However, during the treatment of metal surfaces, a large amount of acid gases are generated, mainly including hydrochloric acid (HCl), sulfuric acid (H 2 SO 4 ) Nitric acid (HNO) 3 ) And hydrofluoric acid (HF). For example, in gold jewelry production, gold jewelry is subjected to acid frying treatment, i.e., immersing gold jewelry in boiling strong acid for acid washing, which produces a large amount of extremely high concentration acid mist, has strong corrosiveness, and is accompanied by obvious white smoke, which can have serious influence on the surrounding environment. Not only is it possible to do so,the discharge of acid gases also results in waste of resources. To solve this problem, an acid-regenerated flue gas cleaning apparatus has been developed.
The acid regenerated fume purifier is one for treating acid gas and white fume produced in metal processing, and aims at eliminating acid gas and white fume in fume through specific technological process and equipment to purify and recover acid gas in fume and to purify fume and protect environment.
However, conventional acid regeneration flue gas cleaning devices typically require a significant amount of energy to heat the acid solution in the regeneration tower to separate the acid. This results in higher energy consumption and increased operating costs. In addition, the conventional device generally adopts fixed operation parameters and flow to treat the flue gas, and cannot be dynamically adjusted according to actual conditions, so that the instability of the purification effect and the energy utilization rate is caused, and the change of the flue gas emission is difficult to adapt.
Accordingly, an optimized acid regeneration flue gas cleaning device is desired.
Disclosure of Invention
In view of this, the disclosure provides an acid regeneration flue gas purification device and a method thereof, which can collect and monitor a flue gas flow value, a temperature value and a pressure value through a sensor group, and introduce a data processing and analysis algorithm at the rear end to perform data time sequence collaborative analysis of flue gas parameters so as to adaptively adjust the flue gas flow.
According to an aspect of the present disclosure, there is provided an acid-regenerated flue gas purifying method including:
acquiring flue gas flow values, temperature values and pressure values at a plurality of preset time points in a preset time period through a sensor group;
carrying out time sequence collaborative correlation analysis on the flue gas flow values, the temperature values and the pressure values at a plurality of preset time points to obtain time sequence collaborative characteristics of flue gas parameters; and
and determining that the smoke flow value at the current time point is increased or decreased based on the smoke parameter time sequence cooperative characteristic.
According to another aspect of the present disclosure, there is provided an acid regeneration flue gas cleaning device, wherein the acid regeneration flue gas cleaning device is for performing the acid regeneration flue gas cleaning method as described above.
According to the embodiment of the disclosure, firstly, a plurality of smoke flow values, temperature values and pressure values at preset time points in a preset time period are acquired through a sensor group, then, time sequence collaborative correlation analysis is carried out on the smoke flow values, the temperature values and the pressure values at the preset time points to obtain smoke parameter time sequence collaborative features, and then, based on the smoke parameter time sequence collaborative features, the fact that the smoke flow value at the current time point should be increased or decreased is determined. Therefore, the dynamic automatic control of the flue gas flow can be performed based on the actual flue gas parameters, so that better purification effect and energy utilization rate are realized.
Other features and aspects of the present disclosure 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 disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 shows a flow chart of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Fig. 2 shows an architectural schematic diagram of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Fig. 3 shows a flowchart of substep S120 of the acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Fig. 4 shows a flowchart of substep S130 of the acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Fig. 5 shows a flowchart of sub-step S133 of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Fig. 6 shows a block diagram of an acid regeneration flue gas cleaning system according to an embodiment of the present disclosure.
Fig. 7 shows an application scenario diagram of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure 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 disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, 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 disclosure will be described in detail below with reference to the 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 disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Aiming at the technical problems, the technical concept of the present disclosure is to collect and monitor the smoke flow value, the temperature value and the pressure value through the sensor group, and introduce a data processing and analyzing algorithm at the rear end to perform the data time sequence collaborative analysis of the smoke parameters so as to perform self-adaptive adjustment on the smoke flow.
Fig. 1 shows a flow chart of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure. Fig. 2 shows an architectural schematic diagram of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure. As shown in fig. 1 and 2, the acid regeneration flue gas cleaning method according to an embodiment of the present disclosure includes the steps of: s110, acquiring flue gas flow values, temperature values and pressure values at a plurality of preset time points in a preset time period through a sensor group; s120, carrying out time sequence collaborative correlation analysis on the flue gas flow values, the temperature values and the pressure values at a plurality of preset time points to obtain time sequence collaborative characteristics of flue gas parameters; and S130, determining that the smoke flow value at the current time point is increased or decreased based on the smoke parameter time sequence cooperative characteristic.
Specifically, in the technical scheme of the present disclosure, first, a flue gas flow value, a temperature value, and a pressure value at a plurality of predetermined time points within a predetermined period of time are acquired. Then, considering that the flue gas flow value, the temperature value and the pressure value have time sequence dynamic change rules in the time dimension, and the flue gas parameter data also have time sequence cooperative association relations, so that the flue gas purification effect and the flue gas efficiency are influenced together. Therefore, in order to perform dynamic self-adaptive adjustment of the flue gas flow based on actual conditions, so as to achieve better purification effect and energy utilization rate, in the technical scheme of the disclosure, the flue gas flow value, the temperature value and the pressure value at the plurality of preset time points need to be respectively arranged into a flue gas flow time sequence input vector, a temperature time sequence input vector and a pressure time sequence input vector according to a time dimension so as to respectively integrate time sequence distribution information of the flue gas flow value, the temperature value and the pressure value in the time dimension.
And then, carrying out feature mining on the smoke flow time sequence input vector, the temperature time sequence input vector and the pressure time sequence input vector in a time sequence feature extractor based on a one-dimensional convolution layer so as to extract time sequence dynamic associated feature information of the smoke flow value, the temperature value and the pressure value in a time dimension respectively, thereby obtaining a smoke flow time sequence feature vector, a temperature time sequence feature vector and a pressure time sequence feature vector.
Further, the flue gas flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector are fused. It should be appreciated that a Bayesian-like probability model is a Bayesian-theorem-based probability model that can be used to infer posterior probability distributions of unknown parameters. Therefore, in the technical scheme of the disclosure, the flue gas flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector are fused by using a Bayesian-like probability model to obtain a parameter posterior feature vector. By using the Bayesian probability-like model, the relevance and the dependency relationship between different feature vectors can be considered, and reasonable probability inference can be performed. Therefore, the parameter posterior feature vector can be estimated more accurately, and the estimation and regulation capacity of the current time point smoke flow value is improved. Specifically, the Bayesian probability model can calculate probability distribution of the parameter posterior feature vector by using the known time sequence feature vector of the flue gas flow, the known time sequence feature vector of the temperature and the known time sequence feature vector of the pressure and combining prior knowledge, wherein the parameter posterior feature vector can comprehensively consider information of a plurality of features to provide more comprehensive and accurate feature representation, and is beneficial to real-time accurate control of the flue gas flow.
Then, in order to further improve the accuracy of the real-time control of the flue gas flow, a transfer matrix of the flue gas flow time sequence feature vector relative to the parameter posterior feature vector needs to be further calculated, so that the time sequence feature of the flue gas flow is mapped into a high-dimensional space of the flue gas parameter time sequence cooperative correlation feature, and a flue gas flow time sequence mapping feature matrix related to time sequence change feature information of the flue gas flow under the background of the time sequence cooperative correlation feature of the flue gas parameter is obtained.
Accordingly, as shown in fig. 3, performing time sequence collaborative correlation analysis on the flue gas flow values, the temperature values and the pressure values at the plurality of preset time points to obtain time sequence collaborative features of flue gas parameters, including: s121, arranging the flue gas flow rate values, the temperature values and the pressure values of the plurality of preset time points into a flue gas flow rate time sequence input vector, a temperature time sequence input vector and a pressure time sequence input vector according to time dimensions respectively; s122, extracting time sequence features of the smoke flow time sequence input vector, the temperature time sequence input vector and the pressure time sequence input vector through a time sequence feature extractor based on a deep neural network model to obtain a smoke flow time sequence feature vector, a temperature time sequence feature vector and a pressure time sequence feature vector; and S123, fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector to obtain the smoke parameter time sequence cooperative feature. It should be understood that in step S121, the flue gas flow value, the temperature value and the pressure value at a plurality of predetermined time points are arranged into a flue gas flow time sequence input vector, a temperature time sequence input vector and a pressure time sequence input vector according to the time dimension, and the purpose of this step is to arrange the flue gas flow, the temperature and the pressure values at different time points into time sequence input vectors, and by arranging according to the time dimension, the time correlation can be considered in preparation for the subsequent time sequence feature extraction. In step S122, using a time sequence feature extractor based on the deep neural network model, extracting time sequence features of the flue gas flow time sequence input vector, the temperature time sequence input vector and the pressure time sequence input vector respectively, where the purpose of this step is to extract time sequence features of the flue gas flow, the temperature and the pressure through the deep neural network model, and the deep neural network model can learn complex time sequence patterns and association relations in the data, so as to extract feature vectors with characterization capability. In step S123, the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector are fused to obtain the time sequence cooperative feature of the smoke parameter, the time sequence features of the smoke flow, the temperature and the pressure are fused to obtain the feature vector comprehensively reflecting the time sequence cooperative relationship of the smoke parameter, and the mutual influence and cooperative change between the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector can be captured by fusing the time sequence features of different parameters to provide more comprehensive information. In general, this process obtains time sequence cooperative features of flue gas parameters by sorting and extracting time sequence features of flue gas flow, temperature and pressure, and fusing them together, which can be used for subsequent analysis and modeling to reveal relationships and laws between flue gas parameters.
More specifically, in step S122, the timing feature extractor based on the deep neural network model is a timing feature extractor based on a one-dimensional convolution layer. It is worth mentioning that one-dimensional convolution layer is a common layer in deep neural networks for processing data with a time-series structure. In time series data, each input sample typically consists of a sequence or time series. The one-dimensional convolution layer extracts local features in time series data by performing convolution operation on input data in a time dimension, performs sliding window operation on the input sequence by using a one-dimensional convolution kernel (one-dimensional filter), and performs convolution operation on data in a window. The convolution operation may capture local patterns and features at different points in time. The one-dimensional convolution layer has the following functions in time sequence feature extraction: 1. feature extraction: the one-dimensional convolution layer can extract local features from the time series data through convolution operation, and can capture modes and rules at different time points, such as trends, periodicity, abrupt points and the like in the time series. 2. Parameter sharing: the one-dimensional convolution layer has the characteristic of parameter sharing, namely that the convolution kernels use the same weight at different positions, so that the parameter quantity of a model can be reduced, the efficiency of the model is improved, and translational invariance of input data can be better processed, namely that for the same mode, no matter which position of a sequence is present, the mode can be detected. 3. And (3) reducing and compressing: the one-dimensional convolution layer can control the output dimension by adjusting the size and the stride of the convolution kernel during convolution operation, so that the time sequence data can be reduced and compressed, and the calculation amount and the storage space are reduced. The time sequence feature extractor based on the one-dimensional convolution layer can effectively extract important local features from time sequence data, and provides feature representation with more characterization capability for subsequent analysis and modeling.
More specifically, in step S123, fusing the flue gas flow time series feature vector, the temperature time series feature vector and the pressure time series feature vector to obtain the flue gas parameter time series cooperative feature includes: and fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector by using a Bayesian probability model to obtain a parameter posterior feature vector as the smoke parameter time sequence cooperative feature. It should be noted that the bayesian-like probability model is a probability model based on bayesian theory and is used for modeling and deducing the relationship between variables. In the process of fusion of the smoke parameter time sequence cooperative features, a Bayesian-like probability model is used for fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector to obtain a parameter posterior feature vector as the time sequence cooperative feature of the smoke parameter. The main roles of the Bayesian probability model are as follows: 1. unified modeling framework: the Bayesian probability model provides a unified modeling framework, the relation between different feature vectors can be modeled, and the information of different features can be integrated and fused by considering the conditional probability distribution and the joint probability distribution among the features. 2. Uncertainty modeling: the Bayesian probability-like model can model uncertainty, and can quantify and process the uncertainty of parameters by introducing prior probability and posterior probability, which is very useful for fusion of the time sequence cooperative characteristics of the smoke parameters, because a certain uncertainty may exist in the relation between different parameters. 3. Inference and prediction: the Bayesian probability model can infer posterior distribution of parameters from observed data by a Bayesian inference method, so that the time sequence cooperative characteristics of the smoke parameters can be predicted by utilizing the existing characteristic vectors, and the relationship and rule among the parameters can be revealed by inference and prediction, thereby providing a basis for subsequent analysis and decision. In general, the Bayesian probability model provides a flexible modeling and inference method, and the time sequence features of the flue gas flow, the temperature and the pressure can be fused to obtain a parameter posterior feature vector as the time sequence cooperative feature of the flue gas parameters, so that the association relationship between the flue gas parameters can be more comprehensively described, and more accurate feature representation is provided for further analysis and application.
And then, the flue gas flow time sequence mapping feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flue gas flow value at the current time point should be increased or decreased. That is, the characteristic high-dimensional space is mapped to the dynamic change characteristic of the smoke flow time sequence to carry out classification treatment, so that the smoke flow value at the current time point is adaptively controlled, the smoke purification effect can adapt to the change of smoke emission, and therefore, better purification effect and energy utilization rate are realized.
Accordingly, as shown in fig. 4, based on the smoke parameter time sequence cooperative feature, determining that the smoke flow value at the current time point should be increased or decreased includes: s131, calculating a transfer matrix of the smoke flow time sequence feature vector relative to the parameter posterior feature vector to obtain a smoke flow time sequence mapping feature matrix; s132, carrying out probability density feature imitation model-based distribution gain on the flue gas flow time sequence mapping feature matrix to obtain a gain flue gas flow time sequence mapping feature matrix; and S133, passing the time sequence mapping feature matrix of the flue gas flow after gain through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flue gas flow value at the current time point should be increased or decreased. It should be understood that in determining whether the current time point of the flue gas flow value should be increased or decreased, the following steps are included: s131: calculating a transfer matrix of the smoke flow time sequence feature vector relative to the parameter posterior feature vector to obtain a smoke flow time sequence mapping feature matrix, wherein the step is used for obtaining a mapping feature matrix describing the relation between the smoke flow time sequence feature vector and the parameter posterior feature vector by calculating the transfer matrix between the smoke flow time sequence feature vector and the parameter posterior feature vector, and the mapping feature matrix can reflect the cooperative relation between the smoke flow and other parameters so as to provide a basis for subsequent analysis and decision; s132: the method comprises the steps of performing distribution gain based on a probability density characteristic imitation paradigm on a smoke flow time sequence mapping feature matrix to obtain the smoke flow time sequence mapping feature matrix after gain, wherein the step aims to perform distribution gain on the smoke flow time sequence mapping feature matrix by applying the probability density characteristic imitation paradigm, so that the mapping feature of the smoke flow can be adjusted to more accurately reflect the change trend and feature of the smoke flow; s133: the method comprises the steps of obtaining a classification result by passing a gained smoke flow time sequence mapping feature matrix through a classifier, wherein the classification result is used for indicating whether the smoke flow value at the current time point should be increased or decreased. Comprehensively, the steps are used for carrying out distribution gain and classification by calculating a transfer matrix between the time sequence feature vector of the smoke flow and the posterior feature vector of the parameter, so as to determine whether the smoke flow value at the current time point should be increased or decreased, and the process can help to monitor and regulate the smoke flow in real time so as to meet specific requirements and targets.
It should be noted that the distribution gain based on the probability density characteristic simulation paradigm is a method for adjusting and gain of probability density distribution of input data by simulating a target probability density function. In the distribution gain process of the flue gas flow time sequence mapping feature matrix, a probability density feature-based modeling method is adopted, namely, the distribution of the flue gas flow time sequence mapping feature matrix is adjusted by modeling the features of a target probability density function. Specifically, the process of distributing gain can be divided into the following steps: 1. modeling a target probability density function: first, a target probability density function, which may be derived from a priori knowledge or historical data, is modeled to describe the desired flue gas flow distribution. 2. Feature extraction: features, such as statistical features of mean, variance, skewness and the like, are extracted from the flue gas flow time sequence mapping feature matrix. 3. Probability density feature simulation: and comparing the extracted features with the features of the target probability density function, and calculating the difference or similarity between the extracted features and the features of the target probability density function. And adjusting the distribution of the time sequence mapping feature matrix of the smoke flow according to the difference or the similarity. 4. And (3) distribution adjustment: according to the probability density characteristic simulation result, the distribution of the flue gas flow time sequence mapping characteristic matrix is adjusted, and the distribution can be adjusted in a scaling, translation or transformation mode and the like, so that the flue gas flow time sequence mapping characteristic matrix is closer to a target probability density function. The distribution of the smoke flow time sequence mapping characteristic matrix can be more in accordance with the expected distribution through the distribution gain based on the probability density characteristic simulation paradigm, which is helpful for improving the accuracy and reliability of the subsequent classification task and the judgment capability of increasing or decreasing the smoke flow.
In particular, in the technical solution of the present disclosure, the smoke flow timing feature vector, the temperature timing feature vector, and the pressure timing feature vector express local timing correlation features of a smoke flow value, a temperature value, and a pressure value, respectively, after feature probability distribution calculation by a bayesian-like probability model, the parameter posterior feature vector conforms to a posterior bayesian probability feature distribution of local timing correlation features based on the smoke flow value, the temperature value, and the pressure value, which is also substantially aligned in time series with the smoke flow timing feature vector, so that, in the case of calculating a transfer matrix of the smoke flow timing feature vector with respect to the parameter posterior feature vector, an inner product of a line feature vector and a transfer source feature vector of the transfer matrix obtains a corresponding feature value of a transfer destination feature vector, and therefore, if the local timing correlation features of the transfer source feature vector are regarded as foreground object features, a column-direction background distribution noise related to feature distribution interference under a line-direction local time series correlation is also introduced when domain transfer feature calculation is performed, and the smoke flow timing map feature matrix also has a line and column-sequence direction temporal map feature distribution, thereby, the expected flow map is expressed based on the expected flow rate classification feature distribution. Accordingly, applicants of the present disclosure subject the flue gas flow timing mapping feature matrix to a distribution gain based on a probability density feature emulation paradigm.
Accordingly, in a specific example, performing a distribution gain based on a probability density feature imitation paradigm on the flue gas flow time sequence mapping feature matrix to obtain a gain flue gas flow time sequence mapping feature matrix, including: the time sequence mapping characteristic of the flue gas flow is characterized by the following optimization formulaThe matrix carries out distribution gain based on probability density characteristic imitation paradigm to obtain a smoke flow time sequence mapping characteristic matrix after gain; wherein, the optimization formula is:wherein (1)>Is the characteristic matrix of the time sequence mapping of the smoke flow rate, < >>Is the +.f. of the smoke flow timing mapping feature matrix>Characteristic value of the location->Is the scale of the smoke flow time sequence mapping characteristic matrix, < >>Representing the square of the F norm of the flue gas flow time sequence mapping characteristic matrix, and +.>Is a weighted superparameter,/->Representing an exponential operation, ++>Is the +.f. of the post-gain smoke flow timing mapping feature matrix>Characteristic values of the location.
Here, based on the characteristic simulation paradigm of the standard cauchy distribution on the probability density for the natural gaussian distribution, the distribution gain based on the probability density characteristic simulation paradigm can use the characteristic scale as a simulation mask to distinguish foreground object characteristics and background distribution noise in a high-dimensional characteristic space, so that the unconstrained distribution gain of the high-dimensional characteristic distribution is obtained based on hierarchical cognition distribution soft matching of characteristic space mapping of the high-dimensional space by means of row and column time sequence distribution of the high-dimensional characteristics and hierarchical representation under a priori-posterior probability transition distribution, and the expression effect of the smoke flow time sequence mapping characteristic matrix based on characteristic distribution characteristics is improved, and the accuracy of classification results obtained by the classifier of the smoke flow time sequence mapping characteristic matrix is also improved. Therefore, the dynamic self-adaptive control of the flue gas flow can be performed in real time based on the actual flue gas parameter cooperative change, so that better purification effect and energy utilization rate are realized.
Further, in step S133, as shown in fig. 5, the post-gain flue gas flow timing mapping feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the flue gas flow value at the current time point should be increased or decreased, and the method includes: s1331, expanding the time sequence mapping feature matrix of the flue gas flow after gain into classification feature vectors according to row vectors or column vectors; s1332, performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and S1333, inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present disclosure, the labels of the classifier include that the smoke flow value at the current time point should be increased (first label) and that the smoke flow value at the current time point should be decreased (second label), where the classifier determines, through a soft maximum function, to which classification label the post-gain smoke flow timing mapping feature matrix belongs. It should be noted that the first tag p1 and the second tag p2 do not include the concept of artificial setting, and in fact, during the training process, the computer model does not have the concept of "the smoke flow value at the current time point should be increased or decreased", which is only two kinds of classification tags, and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result that the smoke flow value at the current time point should be increased or decreased is actually converted into the classified probability distribution conforming to the two classifications of the natural law through classifying the tags, and the physical meaning of the natural probability distribution of the tags is essentially used instead of the language text meaning that the smoke flow value at the current time point should be increased or decreased.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
It should be noted that the full-connection coding refers to a process of coding input data through a full-connection layer. In step S1332, the gained flue gas flow time sequence mapping feature matrix is unfolded to be a classification feature vector, and the vector is encoded through the full connection layer to obtain an encoded classification feature vector. Fully connected layers are a common layer type in neural networks, where each neuron is connected to all neurons of the previous layer. Each neuron of the fully connected layer has a set of weights and biases for linear transformation and nonlinear activation of the input data. The dimension of the input data can be adjusted and converted through the coding process of the full connection layer, so that the characteristic representation of a higher level is extracted. The function of the full-connection coding mainly comprises the following points: 1. feature extraction: through linear transformation and nonlinear activation of the full connection layer, important features in input data can be extracted, and the coding classification feature vector contains feature representations processed by the full connection layer, and the features can better represent key information in a smoke flow time sequence mapping feature matrix. 2. Dimension conversion: the full-connection coding can convert the original smoke flow time sequence mapping feature matrix into coding classification feature vectors with more proper dimensions, which is helpful for reducing the dimensions of data and extracting more compact and useful feature representations, thereby reducing the complexity of subsequent classification tasks. 3. Nonlinear modeling: by the nonlinear activation function of the full-connection layer, nonlinear transformation can be introduced, so that complex relations in the smoke flow time sequence mapping feature matrix can be captured and modeled better, and the judgment capability of the classifier on the increase or decrease of the smoke flow can be improved. The full-connection coding codes the gained smoke flow time sequence mapping feature matrix through the full-connection layer to obtain coding classification feature vectors, and the process can extract important features, convert dimensions and introduce nonlinear modeling to provide more effective feature representation for subsequent classification tasks.
In summary, according to the acid regeneration flue gas purification method disclosed by the embodiment of the disclosure, the dynamic automatic control of the flue gas flow can be performed based on the actual flue gas parameters, so that better purification effect and energy utilization rate are realized.
Further, in an embodiment of the present disclosure, there is also provided an acid regeneration flue gas cleaning device for performing the acid regeneration flue gas cleaning method as described above.
Fig. 6 shows a block diagram of an acid regeneration flue gas cleaning system 100 according to an embodiment of the present disclosure. As shown in fig. 6, the acid-regenerated flue gas cleaning system 100 according to the embodiment of the present disclosure includes: a data acquisition module 110, configured to acquire, by using a sensor group, a flue gas flow value, a temperature value, and a pressure value at a plurality of predetermined time points within a predetermined period of time; the time sequence collaborative correlation analysis module 120 is configured to perform time sequence collaborative correlation analysis on the flue gas flow values, the temperature values and the pressure values at the plurality of predetermined time points to obtain flue gas parameter time sequence collaborative features; and a smoke flow control module 130, configured to determine, based on the smoke parameter timing coordination feature, whether the smoke flow value at the current time point should be increased or decreased.
In one possible implementation, the timing coordination association analysis module 120 includes: the input vector arrangement unit is used for respectively arranging the flue gas flow rate values, the temperature values and the pressure values of the plurality of preset time points into a flue gas flow rate time sequence input vector, a temperature time sequence input vector and a pressure time sequence input vector according to the time dimension; the time sequence feature extraction unit is used for extracting time sequence features of the smoke flow time sequence input vector, the temperature time sequence input vector and the pressure time sequence input vector through a time sequence feature extractor based on a deep neural network model so as to obtain a smoke flow time sequence feature vector, a temperature time sequence feature vector and a pressure time sequence feature vector; and the fusion unit is used for fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector to obtain the smoke parameter time sequence cooperative feature.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described acid-regeneration flue gas cleaning system 100 have been described in detail in the above description of the acid-regeneration flue gas cleaning method with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
As described above, the acid regeneration flue gas cleaning system 100 according to the embodiment of the present disclosure may be implemented in various wireless terminals, such as a server or the like having an acid regeneration flue gas cleaning algorithm. In one possible implementation, the acid regeneration flue gas cleaning system 100 according to embodiments of the present disclosure may be integrated into a wireless terminal as one software module and/or hardware module. For example, the acid regeneration flue gas cleaning system 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the acid regeneration flue gas cleaning system 100 may also be one of a number of hardware modules of the wireless terminal.
Alternatively, in another example, the acid regeneration flue gas cleaning system 100 and the wireless terminal may be separate devices, and the acid regeneration flue gas cleaning system 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 7 shows an application scenario diagram of an acid regeneration flue gas cleaning method according to an embodiment of the present disclosure. As shown in fig. 7, in this application scenario, first, a smoke flow value (e.g., D1 illustrated in fig. 7), a temperature value (e.g., D2 illustrated in fig. 7), and a pressure value (e.g., D3 illustrated in fig. 7) at a plurality of predetermined time points within a predetermined period of time are acquired by a sensor group, and then the smoke flow value, the temperature value, and the pressure value at the plurality of predetermined time points are input to a server (e.g., S illustrated in fig. 7) where an acid regeneration smoke purification algorithm is deployed, wherein the server is capable of processing the smoke flow value, the temperature value, and the pressure value at the plurality of predetermined time points using the acid regeneration smoke purification algorithm to obtain a classification result for indicating that the smoke flow value at the current time point should be increased or decreased.
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 disclosure. 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 foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or 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 (8)
1. An acid regeneration flue gas purification method, characterized by comprising:
acquiring flue gas flow values, temperature values and pressure values at a plurality of preset time points in a preset time period through a sensor group;
carrying out time sequence collaborative correlation analysis on the flue gas flow values, the temperature values and the pressure values at a plurality of preset time points to obtain time sequence collaborative characteristics of flue gas parameters; and
and determining that the smoke flow value at the current time point is increased or decreased based on the smoke parameter time sequence cooperative characteristic.
2. The acid regeneration flue gas purification method according to claim 1, wherein performing time-series collaborative correlation analysis on the flue gas flow rate values, the temperature values, and the pressure values at the plurality of predetermined time points to obtain flue gas parameter time-series collaborative features comprises:
arranging the flue gas flow rate values, the temperature values and the pressure values of the plurality of preset time points into a flue gas flow rate time sequence input vector, a temperature time sequence input vector and a pressure time sequence input vector according to time dimensions respectively;
respectively extracting time sequence features of the smoke flow time sequence input vector, the temperature time sequence input vector and the pressure time sequence input vector through a time sequence feature extractor based on a deep neural network model to obtain a smoke flow time sequence feature vector, a temperature time sequence feature vector and a pressure time sequence feature vector; and
and fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector to obtain the smoke parameter time sequence cooperative feature.
3. The acid regeneration flue gas cleaning method according to claim 2, wherein the time series feature extractor based on the deep neural network model is a time series feature extractor based on a one-dimensional convolution layer.
4. The acid regeneration flue gas cleaning method according to claim 3, wherein fusing the flue gas flow timing feature vector, the temperature timing feature vector, and the pressure timing feature vector to obtain the flue gas parameter timing cooperative feature comprises:
and fusing the smoke flow time sequence feature vector, the temperature time sequence feature vector and the pressure time sequence feature vector by using a Bayesian probability model to obtain a parameter posterior feature vector as the smoke parameter time sequence cooperative feature.
5. The acid regeneration flue gas cleaning method according to claim 4, wherein determining that the flue gas flow value at the current time point should be increased or decreased based on the flue gas parameter timing cooperative feature comprises:
calculating a transfer matrix of the smoke flow time sequence feature vector relative to the parameter posterior feature vector to obtain a smoke flow time sequence mapping feature matrix;
carrying out distribution gain based on probability density characteristic imitation paradigm on the flue gas flow time sequence mapping characteristic matrix to obtain a gain flue gas flow time sequence mapping characteristic matrix; and
and the gained smoke flow time sequence mapping feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the smoke flow value at the current time point should be increased or decreased.
6. The acid regeneration flue gas purification method according to claim 5, wherein performing a distribution gain based on a probability density feature imitation paradigm on the flue gas flow timing mapping feature matrix to obtain a post-gain flue gas flow timing mapping feature matrix comprises:
carrying out probability density feature imitation model-based distribution gain on the flue gas flow time sequence mapping feature matrix by using the following optimization formula to obtain the gain flue gas flow time sequence mapping feature matrix;
wherein, the optimization formula is:wherein (1)>Is the characteristic matrix of the time sequence mapping of the smoke flow rate, < >>Is the +.f. of the smoke flow timing mapping feature matrix>Characteristic value of the location->Is the scale of the smoke flow time sequence mapping characteristic matrix, < >>Representing the square of the F norm of the flue gas flow time sequence mapping characteristic matrix, and +.>Is a weighted superparameter,/->Representing an exponential operation, ++>Is the +.f. of the post-gain smoke flow timing mapping feature matrix>Characteristic values of the location.
7. The acid regeneration flue gas cleaning method according to claim 6, wherein the step of passing the post-gain flue gas flow timing mapping feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flue gas flow value at the current time point should be increased or decreased, and the step of:
expanding the gain flue gas flow time sequence mapping feature matrix into classification feature vectors according to row vectors or column vectors;
performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and
and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
8. An acid-regenerated flue gas cleaning apparatus characterized in that the acid-regenerated flue gas cleaning apparatus is used to perform the acid-regenerated flue gas cleaning method according to claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080709.2A CN116832588B (en) | 2023-08-25 | 2023-08-25 | Acid regeneration flue gas purifying device and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080709.2A CN116832588B (en) | 2023-08-25 | 2023-08-25 | Acid regeneration flue gas purifying device and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116832588A true CN116832588A (en) | 2023-10-03 |
| CN116832588B CN116832588B (en) | 2024-02-02 |
Family
ID=88160221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311080709.2A Active CN116832588B (en) | 2023-08-25 | 2023-08-25 | Acid regeneration flue gas purifying device and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116832588B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117102988A (en) * | 2023-10-16 | 2023-11-24 | 杭州泓芯微半导体有限公司 | Centerless grinding machine and control method thereof |
| CN117222069A (en) * | 2023-10-12 | 2023-12-12 | 深圳市诺文博科技有限公司 | Intelligent control method of illumination driving power supply |
| CN117355009A (en) * | 2023-10-11 | 2024-01-05 | 惠州市沃生照明有限公司 | Method and system for adjusting illumination brightness of desk lamp |
| CN117861296A (en) * | 2024-03-13 | 2024-04-12 | 晋江艺森建筑工程有限公司 | Sewage station solid impurity interception and filtration device |
| CN117968088A (en) * | 2024-04-01 | 2024-05-03 | 新疆凯龙清洁能源股份有限公司 | Flue gas waste heat recovery control system and method for natural gas power generation device |
| CN118064197A (en) * | 2024-04-23 | 2024-05-24 | 新疆凯龙清洁能源股份有限公司 | Method and system for removing hydrocarbon from natural gas |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207913520U (en) * | 2017-12-26 | 2018-09-28 | 中冶京诚工程技术有限公司 | Sintering flue gas denitration desulfurization system |
| CN110263452A (en) * | 2019-06-25 | 2019-09-20 | 华电国际电力股份有限公司技术服务分公司 | Flue gas Annual distribution characteristic analysis method, system and denitrating system in a kind of flue |
| CN110309867A (en) * | 2019-06-21 | 2019-10-08 | 北京工商大学 | A kind of Mixed gas identification method based on convolutional neural networks |
| US20200387783A1 (en) * | 2019-06-07 | 2020-12-10 | XNOR.ai, Inc. | Fast Nearest Neighbor Search for Output Generation of Convolutional Neural Networks |
| CN215196300U (en) * | 2020-12-10 | 2021-12-17 | 中建材创新科技研究院有限公司 | Desulfurizing tower |
| CN114177747A (en) * | 2021-12-02 | 2022-03-15 | 昆岳互联环境技术(江苏)有限公司 | Flue gas desulfurization sulfur dioxide concentration prediction method based on machine learning algorithm |
| CN114748989A (en) * | 2021-01-08 | 2022-07-15 | 中冶长天国际工程有限责任公司 | Ammonia dilution control method and device and readable storage medium |
| CN115034486A (en) * | 2022-06-16 | 2022-09-09 | 浙江省生态环境科学设计研究院 | Prediction control method for iSNCR denitration of cement kiln flue gas |
| CN115245735A (en) * | 2022-06-16 | 2022-10-28 | 浙江省生态环境科学设计研究院 | Cement kiln flue gas iSNCR control method based on predictive control model |
| CN115437416A (en) * | 2022-10-17 | 2022-12-06 | 杭州市燃气集团有限公司 | Pressure control method for natural gas turbine expansion power generation system |
| CN116086790A (en) * | 2023-04-11 | 2023-05-09 | 杭州鄂达精密机电科技有限公司 | Performance detection method and system for high-pressure valve of hydrogen fuel cell |
| CN116186612A (en) * | 2023-04-28 | 2023-05-30 | 福建省杭氟电子材料有限公司 | Sulfur hexafluoride recycling management system |
| CN116184972A (en) * | 2023-04-28 | 2023-05-30 | 福建德尔科技股份有限公司 | Control system and method for air separation device |
| CN116312861A (en) * | 2023-05-09 | 2023-06-23 | 济南作为科技有限公司 | Denitration system gas concentration prediction method, device, equipment and storage medium |
| CN116392930A (en) * | 2023-04-24 | 2023-07-07 | 浙江浙能迈领环境科技有限公司 | Ship tail gas desulfurization process and system thereof |
| CN116477663A (en) * | 2023-05-31 | 2023-07-25 | 江西江钒科技实业有限公司 | Purification preparation method and system of battery-grade vanadium pentoxide |
| CN116603390A (en) * | 2023-07-05 | 2023-08-18 | 浙江浙能迈领环境科技有限公司 | Ship tail gas washing system and method thereof |
| CN116625438A (en) * | 2023-07-25 | 2023-08-22 | 克拉玛依市燃气有限责任公司 | Gas pipe network safety on-line monitoring system and method thereof |
-
2023
- 2023-08-25 CN CN202311080709.2A patent/CN116832588B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207913520U (en) * | 2017-12-26 | 2018-09-28 | 中冶京诚工程技术有限公司 | Sintering flue gas denitration desulfurization system |
| US20200387783A1 (en) * | 2019-06-07 | 2020-12-10 | XNOR.ai, Inc. | Fast Nearest Neighbor Search for Output Generation of Convolutional Neural Networks |
| CN110309867A (en) * | 2019-06-21 | 2019-10-08 | 北京工商大学 | A kind of Mixed gas identification method based on convolutional neural networks |
| CN110263452A (en) * | 2019-06-25 | 2019-09-20 | 华电国际电力股份有限公司技术服务分公司 | Flue gas Annual distribution characteristic analysis method, system and denitrating system in a kind of flue |
| CN215196300U (en) * | 2020-12-10 | 2021-12-17 | 中建材创新科技研究院有限公司 | Desulfurizing tower |
| CN114748989A (en) * | 2021-01-08 | 2022-07-15 | 中冶长天国际工程有限责任公司 | Ammonia dilution control method and device and readable storage medium |
| CN114177747A (en) * | 2021-12-02 | 2022-03-15 | 昆岳互联环境技术(江苏)有限公司 | Flue gas desulfurization sulfur dioxide concentration prediction method based on machine learning algorithm |
| CN115245735A (en) * | 2022-06-16 | 2022-10-28 | 浙江省生态环境科学设计研究院 | Cement kiln flue gas iSNCR control method based on predictive control model |
| CN115034486A (en) * | 2022-06-16 | 2022-09-09 | 浙江省生态环境科学设计研究院 | Prediction control method for iSNCR denitration of cement kiln flue gas |
| CN115437416A (en) * | 2022-10-17 | 2022-12-06 | 杭州市燃气集团有限公司 | Pressure control method for natural gas turbine expansion power generation system |
| CN116086790A (en) * | 2023-04-11 | 2023-05-09 | 杭州鄂达精密机电科技有限公司 | Performance detection method and system for high-pressure valve of hydrogen fuel cell |
| CN116392930A (en) * | 2023-04-24 | 2023-07-07 | 浙江浙能迈领环境科技有限公司 | Ship tail gas desulfurization process and system thereof |
| CN116186612A (en) * | 2023-04-28 | 2023-05-30 | 福建省杭氟电子材料有限公司 | Sulfur hexafluoride recycling management system |
| CN116184972A (en) * | 2023-04-28 | 2023-05-30 | 福建德尔科技股份有限公司 | Control system and method for air separation device |
| CN116312861A (en) * | 2023-05-09 | 2023-06-23 | 济南作为科技有限公司 | Denitration system gas concentration prediction method, device, equipment and storage medium |
| CN116477663A (en) * | 2023-05-31 | 2023-07-25 | 江西江钒科技实业有限公司 | Purification preparation method and system of battery-grade vanadium pentoxide |
| CN116603390A (en) * | 2023-07-05 | 2023-08-18 | 浙江浙能迈领环境科技有限公司 | Ship tail gas washing system and method thereof |
| CN116625438A (en) * | 2023-07-25 | 2023-08-22 | 克拉玛依市燃气有限责任公司 | Gas pipe network safety on-line monitoring system and method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 吴魁;王仙勇;孙洁;黄玉龙;: "基于深度卷积网络的多传感器信号故障诊断方法研究", 计算机测量与控制, no. 01 * |
| 湛腾西;郭观七;: "电厂烟气含氧量的智能混合预测方法", 仪器仪表学报, no. 08 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117355009A (en) * | 2023-10-11 | 2024-01-05 | 惠州市沃生照明有限公司 | Method and system for adjusting illumination brightness of desk lamp |
| CN117222069A (en) * | 2023-10-12 | 2023-12-12 | 深圳市诺文博科技有限公司 | Intelligent control method of illumination driving power supply |
| CN117222069B (en) * | 2023-10-12 | 2024-04-30 | 深圳市诺文博科技有限公司 | Intelligent control method of illumination driving power supply |
| CN117102988A (en) * | 2023-10-16 | 2023-11-24 | 杭州泓芯微半导体有限公司 | Centerless grinding machine and control method thereof |
| CN117102988B (en) * | 2023-10-16 | 2024-01-05 | 杭州泓芯微半导体有限公司 | Centerless grinding machine and control method thereof |
| CN117861296A (en) * | 2024-03-13 | 2024-04-12 | 晋江艺森建筑工程有限公司 | Sewage station solid impurity interception and filtration device |
| CN117861296B (en) * | 2024-03-13 | 2024-06-04 | 晋江艺森建筑工程有限公司 | Sewage station solid impurity interception and filtration device |
| CN117968088A (en) * | 2024-04-01 | 2024-05-03 | 新疆凯龙清洁能源股份有限公司 | Flue gas waste heat recovery control system and method for natural gas power generation device |
| CN118064197A (en) * | 2024-04-23 | 2024-05-24 | 新疆凯龙清洁能源股份有限公司 | Method and system for removing hydrocarbon from natural gas |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116832588B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116832588B (en) | Acid regeneration flue gas purifying device and method thereof | |
| Khodayar et al. | Rough deep neural architecture for short-term wind speed forecasting | |
| Xu et al. | Predicting pipeline leakage in petrochemical system through GAN and LSTM | |
| Liu et al. | A hybrid WA–CPSO-LSSVR model for dissolved oxygen content prediction in crab culture | |
| CN116625438B (en) | Gas pipe network safety on-line monitoring system and method thereof | |
| Lin et al. | Effective recognition of control chart patterns in autocorrelated data using a support vector machine based approach | |
| Huang et al. | Deep hybrid neural network and improved differential neuroevolution for chaotic time series prediction | |
| Zhang et al. | Gated recurrent unit-enhanced deep convolutional neural network for real-time industrial process fault diagnosis | |
| CN117037427B (en) | Geological disaster networking monitoring and early warning system | |
| CN117784710B (en) | Remote state monitoring system and method for numerical control machine tool | |
| CN117041017A (en) | Intelligent operation and maintenance management method and system for data center | |
| CN117308077A (en) | Water supply control system for evaporator of nuclear power unit of reactor | |
| CN116844088A (en) | Online dust remover control system and method thereof | |
| CN117006654A (en) | Air conditioner load control system and method based on edge calculation | |
| CN117193179A (en) | Flue gas desulfurization process monitoring and management system and method thereof | |
| CN117237095A (en) | Small micro financial industry risk early warning and monitoring platform based on big data analysis | |
| CN117094431A (en) | DWTfar meteorological data time sequence prediction method and equipment for multi-scale entropy gating | |
| CN116578858A (en) | Air compressor fault prediction and health degree evaluation method and system based on graphic neural network | |
| Lv et al. | A spatial–temporal variational graph attention autoencoder using interactive information for fault detection in complex industrial processes | |
| CN114638379A (en) | Edge side multi-agent OPC UA information analysis and decision method | |
| AL-ASADI | Interval-valued data analysis: a review | |
| CN117989588B (en) | Heat exchange station automatic control system of heat supply facility | |
| Xin et al. | An intelligent evidence-theory-based structural reliability analysis method based on convolutional neural network model | |
| CN117070741B (en) | Control method and system of pickling line | |
| Gunasekaran et al. | Evaluation of artificial immune system with artificial neural network for predicting Bombay stock exchange trends |
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 |