CN114169235B - Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method - Google Patents

Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method Download PDF

Info

Publication number
CN114169235B
CN114169235B CN202111462684.3A CN202111462684A CN114169235B CN 114169235 B CN114169235 B CN 114169235B CN 202111462684 A CN202111462684 A CN 202111462684A CN 114169235 B CN114169235 B CN 114169235B
Authority
CN
China
Prior art keywords
oxidation
data
algorithm model
machine learning
desulfurization device
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
Application number
CN202111462684.3A
Other languages
Chinese (zh)
Other versions
CN114169235A (en
Inventor
周玲霞
贾义
李承泉
陈效良
张勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Kunlun Internet Technology Co ltd
Original Assignee
Jiangsu Kunlun Internet Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Kunlun Internet Technology Co ltd filed Critical Jiangsu Kunlun Internet Technology Co ltd
Priority to CN202111462684.3A priority Critical patent/CN114169235B/en
Publication of CN114169235A publication Critical patent/CN114169235A/en
Application granted granted Critical
Publication of CN114169235B publication Critical patent/CN114169235B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • B01D53/34—Chemical or biological purification of waste gases
    • B01D53/46—Removing components of defined structure
    • B01D53/48—Sulfur compounds
    • B01D53/50—Sulfur oxides
    • B01D53/501—Sulfur oxides by treating the gases with a solution or a suspension of an alkali or earth-alkali or ammonium compound
    • 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
    • B01D53/34—Chemical or biological purification of waste gases
    • B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
    • B01D53/77—Liquid phase processes
    • B01D53/78—Liquid phase processes with gas-liquid contact
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01D—SEPARATION
    • B01D2258/00—Sources of waste gases
    • B01D2258/02—Other waste gases
    • B01D2258/0283—Flue gases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Environmental & Geological Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Oil, Petroleum & Natural Gas (AREA)
  • Medical Informatics (AREA)
  • Analytical Chemistry (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Treating Waste Gases (AREA)

Abstract

The invention provides a machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method. The invention applies a machine learning algorithm model to the fault prediction and early warning of the oxidation air system of the flue gas desulfurization device. Through machine learning, historical operation data of the wet desulfurization device is analyzed by adopting an OLS linear regression algorithm model, and internal logic of each operation characteristic parameter and oxidation performance of the desulfurization device is excavated, so that a principle model of oxidation reaction is made dominant, the method is used for predicting faults of the wet desulfurization device, and operators can conveniently grasp the health state of an oxidation air system of the desulfurization device in real time. The wet desulfurization device oxidation air system fault prediction early warning is realized, the algorithm model participates in operation control, and the oxidation tank liquid level height is reduced by timely reducing the oxidation air excess, optimizing the oxidation liquid density and the PH value, so that the power consumption of an oxidation fan can be reduced, and the operation cost of the desulfurization device is reduced.

Description

Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method
Technical Field
The invention belongs to the field of industrial flue gas treatment, and particularly relates to a flue gas desulfurization and oxidation system fault prediction method based on a machine learning algorithm.
Background
The coal is a large country, the current industrial fuel is mainly coal, and a large amount of pollutants such as particulate matters, SO 2, greenhouse gases and the like can be produced while the coal releases heat in the combustion process, SO that the ecological environment is polluted. The wet flue gas desulfurization technology is one of the desulfurization methods commercially applied in the world, can efficiently remove sulfur oxides in flue gas, is easy for recycling byproducts, and is the most effective flue gas desulfurization technology for controlling the pollution of atmospheric SO 2. The flue gas containing SO 2 enters a desulfurization device, contacts with spraying liquid containing absorbent in a desulfurization tower, and the SO 2 in the flue gas is absorbed and removed, and the flue gas after washing and purifying is discharged through a chimney. SO 2 in the flue gas is absorbed by the spray liquid, reacts with a desulfurizing agent to generate sulfite such as calcium sulfite, ammonium sulfite and the like, and continuously reacts with oxygen in the blown air to generate sulfate such as calcium sulfate, ammonium sulfate and the like which are desulfurization byproducts.
The oxidation efficiency of sulfite in wet desulfurization is related to the flow rate of oxidizing air, the quality of sulfur dioxide removed by the device (such as excess coefficient of oxidizing air, etc.), and the operation parameters (such as flue gas temperature, pressure, flow rate, humidity, oxygen content, SO 2 concentration, and other flue gas components; temperature, pressure, flow rate, density, PH value, oxidation rate, components, etc.) of oxidizing liquid. The higher the oxidation efficiency, the less sulfite in the desulfurization by-product and the higher the quality. Otherwise, if the wet desulfurization device oxidation system fails, the oxidation efficiency is reduced, so that the desulfurization efficiency is reduced, the crystallization of desulfurization byproducts is difficult, particles are thinned, dehydration is difficult, the quality is poor, and the recycling utilization is affected. For the same inlet flue gas condition, higher oxidation efficiency can be obtained by increasing the oxidation air flow, increasing the liquid level of an oxidation liquid tank, reducing the PH value of the oxidation liquid and the like, thereby facilitating the growth of crystallization particles of desulfurization byproducts, facilitating dehydration, reducing byproduct impurities and improving the quality. On the other hand, increasing the oxidation air flow rate and the liquid level of the oxidation liquid tank can cause overload operation of the oxidation fan, increase energy consumption and increase fault risk; lower PH of the absorption liquid also favors SO 2 absorption. Therefore, in actual production, the health state of an oxidation air system of the wet flue gas desulfurization device needs to be closely monitored.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a flue gas desulfurization and oxidation system fault prediction method based on a machine learning algorithm.
In order to achieve the above purpose, the invention adopts the following technical scheme: a flue gas desulfurization oxidation system fault prediction method based on a machine learning algorithm comprises the following steps:
S1: collecting historical operation data of a flue gas desulfurization device as sample set data;
s2: the sample set data acquired in the step S1 are arranged into types and formats required by machine learning, and the sample set data of the machine learning are formed through data cleaning;
s2-1: deleting missing values in the sample set, and sequencing from small to large to obtain a sequence { X 1,X2,X3,……Xn } of each parameter;
S2-2: let ql=x (n/4),QU＝X(3n/4), iqr=qu-QL; n/4, 3n/4 are rounded off to integer;
QL is the lower quartile; QU is the upper quartile; IQR is the quartile range;
x (n/4)、X(3n/4) is the value corresponding to the array { X 1,X2,X3,……Xn };
S2-3: removing values greater than Q U +1.5IQR and less than Q L -1.5IQR in the S2-1 sequence, and forming a new data sample by rusted data for machine learning;
s3: establishing a machine learning algorithm model:
S3-1: sample oxidation fan current established through sample data after S2 cleaning is used as a dependent variable Yi, and oxidation tank liquid level, oxidation liquid density, oxidation air flow and pressure are used as independent variables, and a linear algorithm model is established:
Yi＝β0+β1Xi1+β2Xi2+...+βpXip+εi,i＝1,...,n.
S3-2: establishing a matrix of samples:
Y＝Xβ+ε；
Wherein Y refers to a column vector including observations Y 1,...,Yn; epsilon comprises a random component epsilon 1,...,εn which is an observation and an observation matrix X of regression quantity;
S3-3: solving beta and epsilon for a linear regression equation by using a least square method;
s4: training the algorithm model established in the step S3 by using the sample data in the step S2; the algorithm model parameters are adjusted through testing, so that the accuracy and precision of the result are improved;
s5: inputting real-time operation data, and predicting the characteristic current of the oxidation fan by using the adjusted algorithm model obtained in the step S4;
s6: judging the characteristic current of the predictive oxidation fan obtained in the step S5;
If the set value is exceeded, outputting an alarm event, and storing an algorithm model to enter the next prediction; if the set value is not exceeded, comparing with the measured value;
S7: if the measured value accords with the predicted value, the algorithm model is saved to enter the next prediction; if the actual measurement value does not accord with the predicted value, the group of operation data enters a historical database, algorithm model training and testing are conducted again, and the iterative algorithm model is used for predicting the characteristic current of the S5 oxidation fan;
training and testing are to repeat the working contents in the steps S3 and S4;
the iteration is a process of replacing the original algorithm model by constructing a history database by using the S7 rule and repeating the steps S2 to S4 to obtain a new algorithm model.
Preferably, the historical operation data of the wet flue gas desulfurization device collected in the step S1 comprises the temperature, the liquid level, the density, the PH value, the oxidation rate and the components of the oxidation liquid; flow, pressure, temperature, composition of the oxidizing air; flow, full pressure, current of the oxidation blower.
Preferably, the method for cleaning data in S2 includes two methods, namely a data-based method and a rule-based method; the data-based mode comprises a classification method, a neighbor method, a clustering method and a statistical method; the rule-based approach includes data that is constant over time, data that varies too much, measured value that exceeds a span, and data that exceeds a threshold.
Preferably, the method for establishing the machine learning algorithm model in the step S3 adopts a linear regression OLS machine learning algorithm model; .
Preferably, the step S4 further includes the steps of:
S4-1: dividing the operation parameter matrix of the desulfurization device into a training set matrix and a testing set matrix according to time;
S4-2: inputting the selected parameter matrix of the training set desulfurization device into training input of a machine learning algorithm model, constructing an algorithm model taking the oxidation fan current as a prediction target, and predicting the oxidation fan current corresponding to the operation parameter matrix of the training set desulfurization device.
Preferably, the alarm threshold and the alarm form in the step S6 may be set and modified according to actual use requirements.
Compared with the prior art, the invention has the beneficial effects that:
(1) Through machine learning, historical operation data of the wet desulfurization device is analyzed by adopting an OLS linear regression algorithm model, and internal logic of each operation characteristic parameter and oxidation performance of the desulfurization device is excavated, so that a principle model of oxidation reaction is made dominant, the method is used for predicting faults of the wet desulfurization device, and operators can conveniently grasp the health state of an oxidation air system of the desulfurization device in real time.
(2) The wet desulfurization device oxidation air system fault prediction early warning is realized, operation and maintenance personnel maintain equipment in advance, an air pipeline is flushed and dredged, operation parameters such as oxidation tank liquid level, oxidation liquid density, PH value and the like are timely adjusted, oxidation efficiency can be effectively improved, system fault rate is reduced, and stable standard emission of the flue gas desulfurization device is realized.
(3) The wet desulfurization device oxidation air system fault prediction early warning is realized, the algorithm model participates in operation control, and the oxidation tank liquid level height is reduced by timely reducing the oxidation air excess, optimizing the oxidation liquid density and the PH value, so that the power consumption of an oxidation fan can be reduced, and the operation cost of the desulfurization device is reduced.
Drawings
FIG. 1 is a schematic of a wet flow process of the present invention;
FIG. 2 is an example wet desulfurization unit operation history data;
FIG. 3 illustrates an example of linear regression analysis of wet desulfurization unit operation history data OLS;
FIG. 4 illustrates an example of wet desulfurization unit oxidation air system fault warning.
Detailed Description
For a further understanding of the objects, construction, features, and functions of the invention, reference should be made to the following detailed description of the preferred embodiments.
Referring to fig. 1, fig. 2, fig. 3 and fig. 4 in combination, the invention provides a method for predicting a fault of a flue gas desulfurization and oxidation system based on a machine learning algorithm, which is characterized in that: the method comprises the following steps:
S1: collecting historical operation data of a flue gas desulfurization device as sample set data;
s2: the sample set data acquired in the step S1 are arranged into types and formats required by machine learning, and the sample set data of the machine learning are formed through data cleaning;
s2-1: deleting missing values in the sample set, and sequencing from small to large to obtain a sequence { X 1,X2,X3,……Xn } of each parameter;
S2-2: let Q L＝X(n/4),QU＝X(3n/4),IQR＝QU-QL be; n/4, 3n/4 are rounded off to integer;
Q L is the lower quartile; q U is the upper quartile; IQR is the quartile range;
x (n/4)、X(3n/4) is the value corresponding to the array { X 1,X2,X3,……Xn };
S2-3: removing values greater than Q U +1.5IQR and less than Q L -1.5IQR in the S2-1 sequence, and forming a new data sample by rusted data for machine learning;
s3: establishing a machine learning algorithm model:
S3-1: sample oxidation fan current established through sample data after S2 cleaning is used as a dependent variable Yi, and oxidation tank liquid level, oxidation liquid density, oxidation air flow and pressure are used as independent variables, and a linear algorithm model is established:
Yi＝β0+β1Xi1+β2Xi2+...+βpXip+εi,i＝1,...,n.
S3-2: establishing a matrix of samples:
Y＝Xβ+ε；
Wherein Y refers to a column vector including observations Y 1,...,Yn; epsilon comprises a random component epsilon 1,...,εn which is an observation and an observation matrix X of regression quantity;
S3-3: solving beta and epsilon for a linear regression equation by using a least square method;
s4: training the algorithm model established in the step S3 by using the sample data in the step S2; the algorithm model parameters are adjusted through testing, so that the accuracy and precision of the result are improved;
s5: inputting real-time operation data, and predicting the characteristic current of the oxidation fan by using the adjusted algorithm model obtained in the step S4;
s6: judging the characteristic current of the predictive oxidation fan obtained in the step S5;
If the set value is exceeded, outputting an alarm event, and storing an algorithm model to enter the next prediction; if the set value is not exceeded, comparing with the measured value;
S7: if the measured value accords with the predicted value, the algorithm model is saved to enter the next prediction; if the actual measurement value does not accord with the predicted value, the group of operation data enters a historical database, algorithm model training and testing are conducted again, and the iterative algorithm model is used for predicting the characteristic current of the S5 oxidation fan;
training and testing are to repeat the working contents in the steps S3 and S4;
the iteration is a process of replacing the original algorithm model by constructing a history database by using the S7 rule and repeating the steps S2 to S4 to obtain a new algorithm model.
Preferably, the historical operation data of the wet flue gas desulfurization device collected in the step S1 comprises the temperature, the liquid level, the density, the PH value, the oxidation rate and the components of the oxidation liquid; flow, pressure, temperature, composition of the oxidizing air; flow, full pressure, current of the oxidation blower.
Preferably, the method for cleaning data in S2 includes two methods, namely a data-based method and a rule-based method; the data-based mode comprises a classification method, a neighbor method, a clustering method and a statistical method; the rule-based approach includes data that is constant over time, data that varies too much, measured value that exceeds a span, and data that exceeds a threshold.
Preferably, the method for establishing the machine learning algorithm model in S3 adopts a linear regression OLS machine learning algorithm model.
Through machine learning, historical operation data of the wet desulfurization device is analyzed by adopting an OLS linear regression algorithm model, and internal logic of each operation characteristic parameter and oxidation performance of the desulfurization device is excavated, so that a principle model of oxidation reaction is made dominant, the method is used for predicting faults of the wet desulfurization device, and operators can conveniently grasp the health state of an oxidation air system of the desulfurization device in real time.
The wet desulfurization device oxidation air system fault prediction early warning is realized, operation and maintenance personnel maintain equipment in advance, an air pipeline is flushed and dredged, operation parameters such as oxidation tank liquid level, oxidation liquid density, PH value and the like are timely adjusted, oxidation efficiency can be effectively improved, system fault rate is reduced, and stable standard emission of the flue gas desulfurization device is realized.
Preferably, the step S4 further includes the steps of:
S4-1: dividing the operation parameter matrix of the desulfurization device into a training set matrix and a testing set matrix according to time;
S4-2: inputting the selected parameter matrix of the training set desulfurization device into training input of a machine learning algorithm model, constructing an algorithm model taking the oxidation fan current as a prediction target, and predicting the oxidation fan current corresponding to the operation parameter matrix of the training set desulfurization device.
Preferably, the alarm threshold and the alarm form in the step S6 may be set and modified according to actual use requirements.
The wet desulfurization device oxidation air system fault prediction early warning is realized, the algorithm model participates in operation control, and the oxidation tank liquid level height is reduced by timely reducing the oxidation air excess, optimizing the oxidation liquid density and the PH value, so that the power consumption of an oxidation fan can be reduced, and the operation cost of the desulfurization device is reduced.
The invention has been described with respect to the above-described embodiments, however, the above-described embodiments are merely examples of practicing the invention. It should be noted that the disclosed embodiments do not limit the scope of the invention. On the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

Claims (4)

1. A flue gas desulfurization oxidation system fault prediction method based on a machine learning algorithm is characterized by comprising the following steps of: the method comprises the following steps:
S1: collecting historical operation data of a flue gas desulfurization device as sample set data;
The historical operation data of the wet flue gas desulfurization device collected in the step S1 comprises the temperature, the liquid level, the density, the pH value, the oxidation rate and the components of the oxidation liquid; flow, pressure, temperature, composition of the oxidizing air; flow, full pressure, current of the oxidation blower; s2: the sample set data acquired in the step S1 are arranged into types and formats required by machine learning, and the sample set data of the machine learning are formed through data cleaning;
S2-1: deleting missing values in the sample set, and sequencing from small to large to obtain a sequence { X 1, X2 , X3 ,……Xn } of each parameter;
s2-2: let Q L= X（n/4）,QU=X（3n/4）,IQR= QU-QL be; n/4, 3n/4 are rounded off to integer;
Q L is the lower quartile; q U is the upper quartile; IQR is the quartile range;
X （n/4）、X（3n/4） is the value corresponding to the array { X 1, X2 , X3 ,……Xn };
s2-3: removing values greater than Q U +1.5IQR and less than Q L -1.5IQR in the S2-1 sequence, and forming a new data sample by the generated data for machine learning;
s3: establishing a machine learning algorithm model:
the method for establishing the machine learning algorithm model in the step S3 adopts a linear regression OLS machine learning algorithm model;
S3-1: sample oxidation fan current established through sample data after S2 cleaning is used as a dependent variable Yi, and oxidation tank liquid level, oxidation liquid density, oxidation air flow and pressure are used as independent variables, and a linear algorithm model is established:
；
S3-2: establishing a matrix of samples:
；
wherein Y refers to a column vector including observations Y 1,...,Yn; epsilon is an observation matrix X comprising an observed random component epsilon 1,...,εn, and a regression quantity;
，
S3-3: solving beta and epsilon for a linear regression equation by using a least square method;
s4: training the algorithm model established in the step S3 by using the sample data in the step S2; the algorithm model parameters are adjusted through testing, so that the accuracy and precision of the result are improved;
s5: inputting real-time operation data, and predicting the characteristic current of the oxidation fan by using the adjusted algorithm model obtained in the step S4;
s6: judging the characteristic current of the predictive oxidation fan obtained in the step S5;
If the set value is exceeded, outputting an alarm event, and storing an algorithm model to enter the next prediction; if the set value is not exceeded, comparing with the measured value;
S7: if the measured value accords with the predicted value, the algorithm model is saved to enter the next prediction; if the actual measurement value does not accord with the predicted value, the group of operation data enters a historical database, algorithm model training and testing are conducted again, and the iterative algorithm model is used for predicting the characteristic current of the S5 oxidation fan;
training and testing are to repeat the working contents in the steps S3 and S4;
the iteration is a process of replacing the original algorithm model by utilizing the S7 rule to form a historical database and repeating the steps S2-S4 to obtain a new algorithm model.
2. The machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method as set forth in claim 1, wherein: the method for cleaning the data in the S2 comprises two methods, namely a data-based mode and a rule-based mode; the data-based mode comprises a classification method, a neighbor method, a clustering method and a statistical method; the rule-based approach includes data that is constant over time, data that varies too much, measured value that exceeds a span, and data that exceeds a threshold.
3. The machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method as set forth in claim 1, wherein: the step S4 further comprises the following steps:
S4-1: dividing the operation parameter matrix of the desulfurization device into a training set matrix and a testing set matrix according to time;
S4-2: inputting the selected parameter matrix of the training set desulfurization device into training input of a machine learning algorithm model, constructing an algorithm model taking the oxidation fan current as a prediction target, and predicting the oxidation fan current corresponding to the operation parameter matrix of the training set desulfurization device.
4. The machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method as set forth in claim 1, wherein: and S6, setting and modifying alarm thresholds and alarm forms according to actual use requirements.
CN202111462684.3A 2021-12-02 2021-12-02 Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method Active CN114169235B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111462684.3A CN114169235B (en) 2021-12-02 2021-12-02 Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111462684.3A CN114169235B (en) 2021-12-02 2021-12-02 Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method

Publications (2)

Publication Number Publication Date
CN114169235A CN114169235A (en) 2022-03-11
CN114169235B true CN114169235B (en) 2024-08-13

Family

ID=80482610

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111462684.3A Active CN114169235B (en) 2021-12-02 2021-12-02 Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method

Country Status (1)

Country Link
CN (1) CN114169235B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115729184B (en) * 2022-11-14 2023-06-27 青芥一合碳汇(武汉)科技有限公司 Desulfurization optimization operation method and device based on big data analysis and edge control

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109034260A (en) * 2018-08-07 2018-12-18 东南大学 Desulfurizing tower oxidation fan fault diagnosis system and method based on Statistics and intelligent optimizing
CN110162553A (en) * 2019-05-21 2019-08-23 南京邮电大学 Users' Interests Mining method based on attention-RNN

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7193261B2 (en) * 2018-07-13 2022-12-20 三菱重工業株式会社 Wet type flue gas desulfurization equipment control method, wet type flue gas desulfurization equipment control device, and remote monitoring system provided with this wet type flue gas desulfurization equipment control device
CN113707228B (en) * 2021-07-29 2024-04-16 北京工业大学 Wet flue gas desulfurization optimization method based on LightGBM algorithm

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109034260A (en) * 2018-08-07 2018-12-18 东南大学 Desulfurizing tower oxidation fan fault diagnosis system and method based on Statistics and intelligent optimizing
CN110162553A (en) * 2019-05-21 2019-08-23 南京邮电大学 Users' Interests Mining method based on attention-RNN

Also Published As

Publication number Publication date
CN114169235A (en) 2022-03-11

Similar Documents

Publication Publication Date Title
CN108549792B (en) Soft measurement method for dioxin emission concentration in solid waste incineration process based on latent structure mapping algorithm
CN111077869B (en) Big data intelligent control bag-type dust collector optimization control method and system
CN114169235B (en) Machine learning algorithm-based flue gas desulfurization and oxidation system fault prediction method
CN114177747A (en) Flue gas desulfurization sulfur dioxide concentration prediction method based on machine learning algorithm
WO2021159585A1 (en) Dioxin emission concentration prediction method
Rahardja et al. Implementation of tensor flow in air quality monitoring based on artificial intelligence
CN107169277B (en) PM2.5 concentration data analysis and prediction model establishment method
CN114225662B (en) Hysteresis model-based flue gas desulfurization and denitrification optimal control method
CN113780383B (en) Dioxin emission concentration prediction method based on semi-supervised random forest and deep forest regression integration
CN110580936B (en) Method and system for predicting service life of medium-low temperature SCR denitration catalyst
CN117689107A (en) Carbon emission data monitoring and early warning method for power industry
CN112733876A (en) Soft measurement method for nitrogen oxides in urban solid waste incineration process based on modular neural network
Xia et al. Soft measuring method of dioxin emission concentration for MSWI process based on RF and GBDT
Qiu et al. An energy‐efficiency evaluation method for high‐sulfur natural gas purification system using artificial neural networks and particle swarm optimization
CN115290832B (en) Exhaust gas treatment monitoring method for plasma exhaust gas treatment equipment
CN117085495A (en) Method and system for treating ammonia-containing tail gas in sodium carbonate production
Xu et al. Prediction method of dioxin emission concentration based on PCA and deep forest regression
KR101237204B1 (en) Method for predicting corrosion life time of corrosion-resistant steel for desulfurization equipment
Qing et al. Prediction model of the NOx emissions based on long short-time memory neural network
CN111476433A (en) Data analysis-based flue gas emission prediction method and system
CN206500021U (en) A kind of processing unit for industrial waste gas
Xiaoxin et al. Current status of technology and standards of domestic solid waste Incineration in China
CN111467934A (en) Wet electrostatic dust collector SO of coal-fired power plant3Collaborative removal efficiency prediction method
LIU et al. Desulfurization Process Modeling by Using Deep AttLSTM-based Network
Wang Dynamic Parameter Optimization Method for Carbon Capture and Conversion Process in Power Plants Based on Machine Learning: Parameter optimization for carbon capture and conversion process in power plants

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
CB02 Change of applicant information

Address after: 224051 innovation center, 42 environmental protection Avenue, environmental protection science and Technology City, Tinghu District, Yancheng City, Jiangsu Province

Applicant after: Jiangsu Kunlun Internet Technology Co.,Ltd.

Address before: 224051 innovation center, 42 environmental protection Avenue, environmental protection science and Technology City, Tinghu District, Yancheng City, Jiangsu Province

Applicant before: Kunyue Internet Environmental Technology (Jiangsu) Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant