CN114218760A - Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator - Google Patents
Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator Download PDFInfo
- Publication number
- CN114218760A CN114218760A CN202111406508.8A CN202111406508A CN114218760A CN 114218760 A CN114218760 A CN 114218760A CN 202111406508 A CN202111406508 A CN 202111406508A CN 114218760 A CN114218760 A CN 114218760A
- Authority
- CN
- China
- Prior art keywords
- characteristic variable
- prediction model
- model
- prediction
- reconstruction
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 107
- 239000003344 environmental pollutant Substances 0.000 title claims abstract description 67
- 231100000719 pollutant Toxicity 0.000 title claims abstract description 67
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 230000000694 effects Effects 0.000 claims abstract description 19
- 238000010219 correlation analysis Methods 0.000 claims abstract description 16
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 238000012795 verification Methods 0.000 claims abstract description 12
- 239000003546 flue gas Substances 0.000 claims description 59
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 51
- 239000003638 chemical reducing agent Substances 0.000 claims description 31
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 24
- 239000001301 oxygen Substances 0.000 claims description 24
- 229910052760 oxygen Inorganic materials 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 239000000779 smoke Substances 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 239000007789 gas Substances 0.000 claims description 5
- 238000005507 spraying Methods 0.000 claims description 5
- 235000008733 Citrus aurantifolia Nutrition 0.000 claims description 4
- 235000011941 Tilia x europaea Nutrition 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 239000004571 lime Substances 0.000 claims description 4
- 239000002002 slurry Substances 0.000 claims description 4
- 239000000654 additive Substances 0.000 claims description 3
- 239000003463 adsorbent Substances 0.000 claims description 3
- 238000011068 loading method Methods 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 2
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 39
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 20
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 20
- 230000008569 process Effects 0.000 description 16
- 238000006243 chemical reaction Methods 0.000 description 15
- 238000002485 combustion reaction Methods 0.000 description 14
- 229910000069 nitrogen hydride Inorganic materials 0.000 description 10
- 229910021529 ammonia Inorganic materials 0.000 description 9
- 230000002829 reductive effect Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 239000000446 fuel Substances 0.000 description 8
- 239000002699 waste material Substances 0.000 description 8
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000007797 corrosion Effects 0.000 description 5
- 238000005260 corrosion Methods 0.000 description 5
- HGUFODBRKLSHSI-UHFFFAOYSA-N 2,3,7,8-tetrachloro-dibenzo-p-dioxin Chemical compound O1C2=CC(Cl)=C(Cl)C=C2OC2=C1C=C(Cl)C(Cl)=C2 HGUFODBRKLSHSI-UHFFFAOYSA-N 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004056 waste incineration Methods 0.000 description 4
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000001035 drying Methods 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 238000002347 injection Methods 0.000 description 3
- 239000007924 injection Substances 0.000 description 3
- 229910052757 nitrogen Inorganic materials 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000001179 sorption measurement Methods 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910021578 Iron(III) chloride Inorganic materials 0.000 description 2
- TWRXJAOTZQYOKJ-UHFFFAOYSA-L Magnesium chloride Chemical compound [Mg+2].[Cl-].[Cl-] TWRXJAOTZQYOKJ-UHFFFAOYSA-L 0.000 description 2
- CSNNHWWHGAXBCP-UHFFFAOYSA-L Magnesium sulfate Chemical compound [Mg+2].[O-][S+2]([O-])([O-])[O-] CSNNHWWHGAXBCP-UHFFFAOYSA-L 0.000 description 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 2
- 239000002253 acid Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 239000000460 chlorine Substances 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 229910001385 heavy metal Inorganic materials 0.000 description 2
- RBTARNINKXHZNM-UHFFFAOYSA-K iron trichloride Chemical compound Cl[Fe](Cl)Cl RBTARNINKXHZNM-UHFFFAOYSA-K 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000004033 plastic Substances 0.000 description 2
- 229920003023 plastic Polymers 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006722 reduction reaction Methods 0.000 description 2
- 239000005060 rubber Substances 0.000 description 2
- 239000010802 sludge Substances 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 1
- KKCBUQHMOMHUOY-UHFFFAOYSA-N Na2O Inorganic materials [O-2].[Na+].[Na+] KKCBUQHMOMHUOY-UHFFFAOYSA-N 0.000 description 1
- 239000007832 Na2SO4 Substances 0.000 description 1
- PMZURENOXWZQFD-UHFFFAOYSA-L Sodium Sulfate Chemical compound [Na+].[Na+].[O-]S([O-])(=O)=O PMZURENOXWZQFD-UHFFFAOYSA-L 0.000 description 1
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 1
- 239000002250 absorbent Substances 0.000 description 1
- 230000002745 absorbent Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- AZDRQVAHHNSJOQ-UHFFFAOYSA-N alumane Chemical class [AlH3] AZDRQVAHHNSJOQ-UHFFFAOYSA-N 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- AXCZMVOFGPJBDE-UHFFFAOYSA-L calcium dihydroxide Chemical compound [OH-].[OH-].[Ca+2] AXCZMVOFGPJBDE-UHFFFAOYSA-L 0.000 description 1
- 239000000920 calcium hydroxide Substances 0.000 description 1
- 229910001861 calcium hydroxide Inorganic materials 0.000 description 1
- 239000004202 carbamide Substances 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 229910052801 chlorine Inorganic materials 0.000 description 1
- 125000001309 chloro group Chemical group Cl* 0.000 description 1
- 239000000701 coagulant Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000006298 dechlorination reaction Methods 0.000 description 1
- 238000006477 desulfuration reaction Methods 0.000 description 1
- 230000023556 desulfurization Effects 0.000 description 1
- 239000011790 ferrous sulphate Substances 0.000 description 1
- 235000003891 ferrous sulphate Nutrition 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 229910001504 inorganic chloride Inorganic materials 0.000 description 1
- 229920000592 inorganic polymer Polymers 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- BAUYGSIQEAFULO-UHFFFAOYSA-L iron(2+) sulfate (anhydrous) Chemical compound [Fe+2].[O-]S([O-])(=O)=O BAUYGSIQEAFULO-UHFFFAOYSA-L 0.000 description 1
- 229910000359 iron(II) sulfate Inorganic materials 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 229910001629 magnesium chloride Inorganic materials 0.000 description 1
- 229910052943 magnesium sulfate Inorganic materials 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 229910017464 nitrogen compound Inorganic materials 0.000 description 1
- 150000002830 nitrogen compounds Chemical class 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000000197 pyrolysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000011780 sodium chloride Substances 0.000 description 1
- 229910052938 sodium sulfate Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000003039 volatile agent Substances 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Incineration Of Waste (AREA)
Abstract
The invention discloses a method and a device for constructing a model for predicting the discharge amount of secondary pollutants of an incinerator, wherein the method comprises the following steps: acquiring historical data of incinerator equipment, and acquiring sample data according to the historical data; selecting characteristic variables, wherein the characteristic variables comprise original characteristic variables and reconstructed characteristic variables; constructing a prediction model according to the original characteristic variables, the reconstructed characteristic variables and the characteristic variable reconstruction method; and carrying out precision verification on the prediction generated by training, and evaluating the effect of the model applied to the actual working condition. Based on the generation mechanism of the secondary pollutants of the garbage incinerator, the analysis of historical operation data and the correlation analysis, the original characteristic variable, the reconstructed characteristic variable and the characteristic variable reconstruction method for constructing the prediction model are obtained, effective judgment and selection can be carried out according to actual results, and the accuracy of the prediction model is improved. The invention can be widely applied to the technical field of secondary pollutant generation and emission.
Description
Technical Field
The invention relates to the technical field of secondary pollutant generation and emission, in particular to a construction method and a device of a prediction model of secondary pollutant emission of an incinerator.
Background
The process for removing secondary pollutants in the flue gas of the waste incinerator mainly comprises independent systems of denitration, deacidification, dust removal, dioxin removal, heavy metal removal and the like. At present, the acid gas in the waste incineration flue gas is mainly removed by adopting a semidry deacidification technology, CaO powder or calcium hydroxide powder is used as an absorbent, and the powder is directly sprayed into a deacidification tower or prepared into lime slurry and then sprayed to achieve the aim of deacidification. In the denitration process, mainly NO is removedXThe SNCR and SCR reduction methods are mainly adopted. By injecting a suitable reducing agent at a suitable location, temperature range, NO removal is achievedXThe effect of (1). The processes of removing dust, dioxin and heavy metal are mainly carried out by adopting an activated carbon jet adsorption and bag-type dust remover technology, and the emission concentration is reduced by a force adsorption mode.
However, the deacidification and denitration processes in the prior art are required to be in a proper range, especially in the denitration process, the temperature and the amount of the reducing agent are not controlled properly, the downstream air preheater is easy to block, and the excessive or insufficient reducing agent causes the environmental protection standard exceeding or causes the corrosion of a heat exchanger due to the escape of ammonia. In the deacidification process, because the garbage entering the furnace contains a large amount of waste plastics, waste rubber, kitchen garbage and biomass substances, Cl is caused in the flue gas2And the major sources of HCl. Meanwhile, during sludge blending combustion, inorganic polymer coagulant, ferric chloride, ferrous sulfate, polyaluminium chloride, polyaluminium ferric chloride and other ferric salts and aluminum salts are added to play a role in static neutralization and adsorption bridging in sludge modification regulation. These all cause the problem of excessive sulfur dioxide produced in the combustion process. Therefore, the deacidification outside the furnace does not meet the current situation of waste incineration, and the HCl with high concentration in the furnace and the chloride in the smoke particles can be deposited on the heated pipeline, so that the pipeline is corroded and exploded. In addition, manual operation and automatic control modes are mainly adopted in the denitration and desulfurization processes at the present stage, but both modes depend on the detection indexes of tail flue gas, have hysteresis, andthe fuel characteristics of the garbage incinerator have large fluctuation, and the mismatching of reducing agents is easily caused. Therefore, in the deacidification and denitration processes, the effective coordination of the emission of secondary pollutants in the flue gas and the inhibition process cannot be realized, so that the following problems are caused:
(1) pollutant discharge exceeds standard: due to the large fluctuation of the physical properties of the fuel, the emission detection index and the linkage hysteresis of the deacidification and denitration process cause sudden emission standard exceeding and influence the emission controllability.
(2) Increase the cost of reducing and deacidifying agents: in order to avoid the sudden excessive discharge and the limitation of the regulation of the reducing agent and the deacidification agent, the discharge amount needs to be reduced by increasing the dosage, and the environmental protection index is guaranteed.
(3) It is difficult to control the production of secondary pollutants, especially NO, from the sourceXAnd the production of HCl, causes corrosion of process equipment during flue gas flow.
Disclosure of Invention
In order to solve at least one of the technical problems in the prior art to a certain extent, the invention aims to provide a method and a device for constructing a model for predicting the discharge amount of secondary pollutants of an incinerator.
The technical scheme adopted by the invention is as follows:
a construction method of a model for predicting the discharge amount of secondary pollutants of an incinerator comprises the following steps:
acquiring historical data of incinerator equipment, and acquiring sample data according to the historical data;
determining influence factors influencing the discharge amount of secondary pollutants, and determining a primary original characteristic variable according to the influence factors;
according to a secondary pollutant generation mechanism and the analysis of the historical data, performing characteristic reconstruction on the primary original characteristic variable, and determining a primary reconstructed characteristic variable and a primary characteristic variable reconstruction method;
performing correlation analysis on the preliminary original characteristic variable, the preliminary reconstruction characteristic variable and a preliminary characteristic variable reconstruction method according to the sample data to obtain an original characteristic variable, a reconstruction characteristic variable and a characteristic variable reconstruction method;
and constructing a prediction model according to the original characteristic variables, the reconstructed characteristic variables and the characteristic variable reconstruction method.
Further, when the predictive model is used on NOXWhen the emission is predicted, the original characteristic variables include: velocity v of grate, feed rate m, pressure p of primary air chamber1And flow rate q1Pressure p of secondary air2Temperature T2And flow rate q2Amount of adsorbent added mtSpraying amount m of reducing agentsThe temperature T of the smoke at the outlet of the first flue1Concentration M of oxygen in flue gas1And flow rate, drum pressure paAnd superheater temperature Tg；
The reconstruction feature variables include: the total air volume, the average value of the oxygen content of the flue gas and the temperature T of the superheater, wherein the total air volume is primary air volume and secondary air volume;
the characteristic variable reconstruction method is a pure logic judgment method.
Further, when the prediction model is used for predicting the amount of HCl emission, the original characteristic variables include: velocity v and temperature T of the grate0The temperature T of the smoke at the outlet of the first flue1Concentration M of oxygen in flue gas2The flow rate, the input amount of the additive, the inlet flue gas temperature and the outlet flue gas temperature of the deacidification tower, the residence time, the concentration of the lime slurry and the concentration of HCl in tail gas emission;
the reconstruction feature variables include: the total air volume; the average value of the oxygen content of the flue gas and the temperature T of the superheater, wherein the total air quantity is primary air quantity and secondary air quantity;
the characteristic variable reconstruction method is a neural network algorithm.
Further, when the predictive model is used on NH3When the escape emission is predicted, the original characteristic variables include: outlet temperature of first flue, flow rate of flue gas, flow and pressure of reducing agent, and NO of flue gasXReduced concentration, primary air flow, secondary air flow and temperature;
the reconstructed feature variables include: total air quantity, average oxygen content of flue gas, flow of reducing agent and NO at flue outletxConcentration, wherein the total air volume is primary air volume and secondary air volume;
the characteristic variable reconstruction method is a neural network algorithm.
Further, the performing correlation analysis on the preliminary original characteristic variable, the preliminary reconstructed characteristic variable and the preliminary characteristic variable reconstruction method according to the sample data includes:
analyzing the effectiveness and the precision of the primary original characteristic variable and the primary reconstruction characteristic variable by adopting a logic comparison control method;
and performing correlation analysis on the preliminary original characteristic variable and the preliminary reconstruction characteristic variable by adopting a statistical relationship analysis method.
Further, the construction method further comprises the following steps:
and acquiring a training set according to the sample data, the original characteristic variables, the reconstructed characteristic variables and the characteristic variable reconstruction method, and training the prediction model by adopting a training prediction engine.
Further, the construction method further comprises the step of verifying the trained prediction model:
and carrying out accuracy verification on the trained prediction model by adopting the variance and standard deviation of the prediction error, and taking the prediction accuracy S as an evaluation effect index of the model verification, wherein the prediction accuracy S is 1-the variance of the difference between the predicted value and the actual value.
Further, the construction method further comprises the following steps:
obtaining a plurality of trained predictive models, including a predictive NOXPrediction model for emission amount, prediction model for predicting HCl emission amount, or prediction NH3At least two of the prediction models of the escape emissions;
and constructing a secondary pollutant in-furnace collaborative removal model according to the obtained prediction model.
Further, the obtaining the trained prediction model includes:
and loading the prediction model after offline training through an online algorithm.
The other technical scheme adopted by the invention is as follows:
a construction device of a model for predicting the discharge amount of secondary pollutants of an incinerator comprises:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The other technical scheme adopted by the invention is as follows:
a computer readable storage medium in which a processor executable program is stored, which when executed by a processor is for performing the method as described above.
The invention has the beneficial effects that: the method is based on the generation mechanism of the secondary pollutants of the garbage incinerator, the analysis of historical operation data and the correlation analysis, obtains the original characteristic variable, the reconstructed characteristic variable and the characteristic variable reconstruction method for constructing the prediction model, can effectively judge and select according to the actual result, and is beneficial to improving the precision of the prediction model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present invention or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart illustrating steps of a method for constructing a model for predicting the discharge amount of secondary pollutants from an incinerator according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for constructing a model for predicting the discharge amount of secondary pollutants of a garbage incinerator according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for constructing a furnace collaborative removal model of secondary pollutants in a garbage incinerator according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a pure logic judgment method in the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
As shown in fig. 1 and fig. 2, the embodiment provides a method for constructing a model for predicting the discharge amount of secondary pollutants of an incinerator, comprising the following steps:
and S1, acquiring historical data of the incinerator equipment, and acquiring sample data according to the historical data.
Data acquisition and processing: and selecting a data interval, acquiring historical data of a measuring point of the garbage incinerator equipment, and filtering and predicting the acquired historical data to obtain sample data. The preprocessing of the historical data specifically refers to cleaning unreasonable data in the acquired historical data, wherein the unreasonable data comprises error data, abnormal data and repeated data.
And S2, selecting characteristic variables, wherein the characteristic variables comprise original characteristic variables and reconstructed characteristic variables.
The step S2 specifically includes steps S21-S22:
s21, determining influence factors influencing the discharge amount of secondary pollutants, and determining a primary original characteristic variable according to the influence factors; and according to the generation mechanism of the secondary pollutants and the analysis of historical data, performing characteristic reconstruction on the primary original characteristic variable, and determining a primary reconstructed characteristic variable and a primary characteristic variable reconstruction method.
Determining the primary original characteristic variable and the primary reconstruction characteristic variable: determining influence factors influencing the discharge amount of the secondary pollutants according to the generation mechanism of the secondary pollutants in the furnace and the analysis of historical data, and determining a primary original characteristic variable according to the influence factors; and according to the generation mechanism of the secondary pollutants and the analysis of historical data, performing characteristic reconstruction on the primary original characteristic variable, and determining a primary reconstructed characteristic variable and a characteristic variable reconstruction method.
And S22, performing correlation analysis on the primary original characteristic variable, the primary reconstructed characteristic variable and the primary characteristic variable reconstruction method according to the sample data to obtain the original characteristic variable, the reconstructed characteristic variable and the characteristic variable reconstruction method.
And performing correlation analysis and importance calculation on each preliminary original characteristic variable, preliminary reconstructed characteristic variable and characteristic variable reconstruction method by using the sample data, selecting the original characteristic variable used for establishing the prediction model, and reconstructing the characteristic variable and the characteristic variable reconstruction method.
And S3, constructing a prediction model according to the original characteristic variables, the reconstructed characteristic variables and the characteristic variable reconstruction method.
Establishing a prediction model: and calculating the data value of the reconstructed characteristic variable by using the sample data through a characteristic variable reconstruction method, forming a prediction training sample together with the historical data corresponding to the original characteristic variable, and performing data modeling training by using a prediction training model to generate a prediction model.
In this embodiment, the training prediction engine is used to train the prediction model, wherein before the training of data modeling, the data is further converted, where the conversion refers to converting the data into a signal. The predictive training engine may employ a Huacheng cloud predictive training engine.
And S4, performing precision verification on the prediction generated by training, and evaluating the effect of the model applied to the actual working condition.
And performing accuracy verification on the generated prediction model by using the variance and standard deviation of the prediction error, specifically, taking the prediction accuracy S as an evaluation effect index of the model verification, wherein the prediction accuracy S is 1-the variance of the difference between the predicted value and the actual value.
And S5, obtaining a trained prediction model, namely a secondary pollutant emission prediction model, according to the prediction result generated by the furnace secondary pollutant prediction model in the steps S1-S4.
According to the embodiment, influence factors influencing the discharge amount of secondary pollutants are determined by analyzing historical data and according to the generation mechanism of the secondary pollutants in the furnace, and preliminary original characteristic variables are determined according to the influence factors (such as total air volume, proportion of primary air and secondary air, temperature and oxygen content of flue gas and the like); according to the generation mechanism of secondary pollutants and the analysis of historical data, performing characteristic reconstruction on primary original characteristic variables to determine primary reconstructed characteristic variables and characteristic variable reconstruction methods, performing correlation analysis and importance calculation on each primary original characteristic variable, each primary reconstructed characteristic variable and each characteristic variable reconstruction method by using the sample data, properly accepting or rejecting related variables based on actual conditions, and being beneficial to improving the precision of data samples, calculating the data values of the reconstructed characteristic variables by using the sample data through the characteristic variable reconstruction methods to form prediction training samples together with the historical data corresponding to the original characteristic variables, then performing data modeling training by using a prediction training engine, and predicting the emission of the secondary pollutants in the flue gas in the garbage incinerator by using the generated prediction model, the phenomenon of the predicted exhaust deflection working condition is warned, the problem that the existing control on the emission amount of pollutants in the flue gas has deflection can be effectively solved through the prediction result, the prediction and control model is high in precision, and production personnel can be effectively guided to intervene in advance to adjust the exhaust control of the secondary pollutants burned in the garbage furnace.
As an alternative embodiment, when the secondary pollutant NO is applied to the garbage incineratorXWhen the emission is subjected to prediction model construction, the original characteristic variables for the prediction model construction comprise: velocity v of grate, feed rate m, pressure p of primary air chamber1And flow rate q1Pressure p of secondary air2Temperature T2And flow rate q2Amount of adsorbent added mtSpraying amount m of reducing agentsThe temperature T of the smoke at the outlet of the first flue1Concentration M of oxygen in flue gas1And flow rate, temperature T of superheater3Pressure p of the steam drumaTemperature T of superheaterg。
The reconstructed feature variables used for predictive modeling include: total air volume (primary air volume + secondary air volume), average oxygen content of flue gas and superheater temperature T.
The characteristic variable reconstruction method for establishing the prediction model is a pure logic judgment method. The pure logic judgment method refers to a method of judging through logic constant values, such as: and comparing the measured value with the set value, if the measured value is larger than the set value, adjusting the control strategy, and if the measured value is smaller than the set value, performing the next action, as shown in FIG. 4.
Wherein the fuel type NOXIs formed by oxidizing nitrogen compounds in fuel in combustion and can be obtained at the temperature of 600-800 DEG CGenerating a fuel type; thermal NOXWhen the catalyst is combusted, nitrogen in air is oxidized under a high-temperature condition to generate the nitrogen, the generation process can be expressed by a Jieli multidimensional reaction formula, when the temperature is more than 1500 ℃, the temperature is not increased by 100 ℃, and the reaction rate is increased by 6-7 times; rapid NOXIs generated by the reaction of CH free radicals generated by the pyrolysis of hydrocarbons in fuel volatiles with nitrogen in the air.
From the mechanism of formation of nitrogen oxides, NOXThe generation of (A) is mainly directly related to the combustion process, the combustion temperature and the oxygen content, and the higher the temperature in the furnace is, the NO isxThe larger the amount of production, the lower the furnace temperature, NOxThe smaller the generated amount of the furnace is, the furnace temperature is mainly influenced by the total air volume and the proportion of primary air and secondary air, particularly the primary air is distributed on the grate, and the combustion condition in the furnace can be reflected by detecting the conditions of a drying section, a combustion section and an burnout section on the grate; the primary air volume is large, the oxygen content of the flue gas is high, the reaction of nitrogen oxides is sufficient in the combustion process, the generation amount is large, and the retention time in the flue is short. The larger the flow velocity of the secondary air is, the better the flue gas turbulence effect is, the full combustion of the flue gas is facilitated, and the lower the oxygen content in the flue gas is, the N and O in the garbage2The slower the reaction, the formation of NOXThe amount of (c) is reduced.
Determination of NO effects by analysis based on NOx formation mechanism and on historical data of operationXDetermining the primary original characteristic variables according to the influence factors (such as the total air volume, the proportion of primary air and secondary air, the temperature and oxygen content of flue gas and the like), wherein the primary original characteristic variables comprise NOXCarrying out characteristic reconstruction on the primary original characteristic variables to determine primary reconstructed characteristic variables, specifically, carrying out effectiveness and precision analysis on each primary original characteristic variable and each primary reconstructed characteristic variable by adopting a logic comparison control method, selecting the original characteristic variables and the reconstructed characteristic variables for establishing a prediction model after carrying out correlation analysis on each primary original characteristic variable and each primary reconstructed characteristic variable by adopting a statistical relationship analysis method, and establishing the prediction model capable of carrying out NO (nitric oxide) analysis on the NOXDischarge amount ofAnd performing effective prediction, wherein the reconstructed characteristic variables used for establishing the prediction model can assist in reflecting the combustion degree and characteristics of a drying section, a combustion section and a burnout section on the grate in the fuel process. Specifically, the flue gas oxygen content specifically includes an oxygen content of flue gas at a first flue outlet, the temperature includes a temperature at the first flue outlet, a temperature of secondary air and a temperature of a superheater, the total air volume includes air volumes of primary air and secondary air, and the measured values of the primary air and the secondary air include a pressure and a flow rate of a primary air chamber and a pressure, a temperature and a flow rate of the secondary air. The original characteristic variables are accurate to the characteristics of primary air and secondary air according to different positions in the garbage incinerator equipment, or the characteristics of a flue outlet in a flue are used for avoiding the condition that the characteristic variables at different positions deviate so as to cause the result of the characteristic variables to deviate, and the variance and the standard deviation of the prediction error are adopted to carry out accuracy verification on the generated prediction model, so that the training effect of a prediction training engine for carrying out data modeling training is guaranteed.
As an optional implementation manner, when the prediction model is constructed for the HCl emission amount in the flue gas of the waste incinerator, the original characteristic variables for the prediction model construction include: the velocity and temperature of the grate, the smoke temperature of the outlet of the first flue, the concentration and flow rate of oxygen in the smoke, the input amount of additives, the temperature of the smoke at the inlet of the deacidification tower, the temperature of the smoke at the outlet, the retention time, the concentration of lime slurry and the concentration of HCl in tail gas emission.
The reconstruction characteristic variables for establishing the prediction model comprise total air volume (primary air volume + secondary air volume), average value of oxygen content of flue gas and temperature T of the superheater. The characteristic variable reconstruction method for establishing the prediction model is a neural network algorithm.
The secondary pollutants generated in the waste incineration process mainly comprise HCl, and the two main sources of HCl are as follows: (1) organic chlorine in the garbage, such as PVC plastics, rubber, leather and the like, is decomposed to generate HCl when being combusted; (2) inorganic chloride in the garbage, such as NaCl (from kitchen garbage), reacts with other substances to generate HCl, and the chemical reaction is as follows:
H2O+2NaCl+SO2+0.5O2＝Na2SO4+2HCl (1)
2NaCl+mSiO2+H2O＝2HCl+Na2O·mSiO2(2) (where m is 2,4)
H2O+MgCl2+SO2+0.5O2＝MgSO4+2HCl (3)
In the flowing process of the flue gas, HCl and chloride in flue gas particles can be deposited on a heated pipeline, high-temperature corrosion of a superheater and low-temperature corrosion of a tail heated surface can be caused to the waste heat boiler, and the HCl in the flue gas can provide extra chlorine atoms to promote the formation of dioxin.
Determining influence factors influencing HCl emission through analyzing sample data according to the generation mechanism and the hazard characteristics of HCl, determining a preliminary original characteristic variable according to influencing factors (such as furnace temperature, primary air flow, oxygen concentration and flow speed in flue gas and the like), wherein the preliminary original characteristic variable comprises characteristic variables related to the discharge amount of HCl, performing characteristic reconstruction on the primary original characteristic variables, determining primary reconstructed characteristic variables, performing effectiveness and precision analysis on each primary original characteristic variable and each primary reconstructed characteristic variable by adopting a logic comparison control method, performing correlation analysis on each primary original characteristic variable and each primary reconstructed characteristic variable by adopting a statistical relationship analysis method, the original characteristic variables and the reconstructed characteristic variables used for building the prediction model are selected, and the built prediction model can effectively predict the discharge amount of HCl. Specifically, the furnace temperature includes values of a first flue outlet flue gas temperature, a drying section temperature, a combustion section temperature and a burnout section temperature on the grate, and the first flue outlet flue gas temperature specifically includes an average value of upper and lower, left and right temperatures of a flue outlet section.
As an alternative embodiment, when the prediction model is built for the NH3 escape emission in the flue gas of the waste incinerator, the original characteristic variables for the prediction model building include: the first flue outlet temperature, the flue gas flow velocity, the reducing agent flow and pressure, the flue gas NOX converted concentration, the primary air flow, the secondary air flow and the temperature.
The reconstructed feature variables used for predictive modeling include: total air volume (primary air volume and secondary air volume), average oxygen content of flue gas, flow of reducing agent, and concentration of NOx at an outlet of a flue. The characteristic variable reconstruction method for establishing the prediction model is a neural network algorithm.
The ammonia escape refers to the phenomenon that ammonia which does not participate in reduction reaction exists in the flue gas after the flue gas passes through denitration equipment or a denitration process. In SNCR denitration reaction, NH is used3As the reducing agent, in the temperature range of 900-1100 ℃, the chemical reaction equation for reducing NOx is mainly as follows:
4NH3+4NO+O2→4N2+6H2O (1)
4NH3+2NO+2O2→3N2+6H2O (2)
8NH3+6NO2→7N2+12H2O (3)
the main chemical reactions for reducing NOx using urea as a reducing agent are:
CO(NH2)2→2NH2+CO (4)
NH2+NO→N2+H2O (5)
CO+NO→N2+CO2 (6)
since most of NOx in the flue gas exists in the form of NO, the reaction is mainly based on the reaction (1) or (5) according to the type of the reducing agent, and theoretically 1mol of NH31mol of NO can be completely reduced. The ammonia escape rate is mainly influenced by the injection amount of the reducing agent in the denitration system, and the injection amount of the reducing agent is mainly adjusted according to the fixed ammonia nitrogen molar ratio or the control mode of the mass concentration of NOx at the SNCR outlet of the denitration system. When the denitration efficiency of the system is reduced or the partial concentration of NOx detected by an outlet is increased due to the fluctuation of the temperature of the flue gas or the fluctuation of the flow rate and the flow speed of the flue gas, the spraying amount of the reducing agent is adjusted upwards, the ammonia amount which cannot participate in the reaction is increased, and the ammonia escape rate is increased. The main causes of increased ammonia slip include: (1) the spraying amount of the reducing agent of each spray gun is distributed unevenly, the granularity is uneven, large particles are large in proportion, the flow rate is uneven, and the reducing agent cannot be mixed and reacted fully; (2) flue gas temperature, reaction temperature too low, NOx and ammoniaThe reaction rate of (2) is reduced, resulting in NH3The slip is increased, and when the temperature is too high, ammonia is decomposed and NO is generated, so NH3Needs to be in an optimal temperature range of 900 ℃ and 1100 DEG C](ii) a (3) The type and concentration configuration of the reducing agent are basically determined during the construction of the incinerator, but the concentration configuration of the reducing agent needs to be configured and adjusted by experience, and the operation difficulty is high. (4) During combustion and fuel fluctuation, the fluctuation range of the injected reducing agent and the NOx concentration in the flue gas is large, the injected reducing agent amount is increased in order to achieve standard emission, ammonia is caused to escape, corrosion of rear-end equipment is caused, and the safe operation of the system is influenced.
This example is based on NH3Mechanism of slip and analysis of operational history data to determine the effect on NH3Determining a preliminary original characteristic variable according to the influence factors (such as the first flue temperature, the injection amount of the reducing agent and the like), wherein the preliminary original characteristic variable comprises NH3The method comprises the steps of carrying out characteristic reconstruction on the primary original characteristic variables to determine primary reconstruction characteristic variables, carrying out effectiveness and precision analysis on each primary original characteristic variable and each primary reconstruction characteristic variable by adopting a logic comparison control method, selecting the original characteristic variables and the reconstruction characteristic variables for establishing a prediction model after carrying out correlation analysis on each primary original characteristic variable and each primary reconstruction characteristic variable by adopting a statistical relationship analysis method, and establishing the obtained prediction model to be capable of carrying out NH (NH) analysis3The amount of emissions of (a) is effectively predicted.
In an alternative embodiment, the first flue outlet flue gas temperature comprises a bulk average temperature of a front end of the reducing agent spray gun, and the injected amount of the reducing agent comprises a flow rate, a flow rate and a particle size diameter of the injected reducing agent.
As an alternative implementation manner, in step S22, validity and precision analysis is performed on each of the preliminary original characteristic variables and the preliminary reconstructed characteristic variables specifically by using a logical comparison control method, and correlation calculation is performed on each of the preliminary original characteristic variables and the preliminary reconstructed characteristic variables by using a statistical relationship analysis method.
Performing correlation analysis and importance calculation on each preliminary original characteristic variable, preliminary reconstructed characteristic variable and characteristic variable reconstruction method, selecting an original characteristic variable for prediction model establishment, and reconstructing the characteristic variable and the characteristic variable reconstruction method; the effectiveness and the precision of each primary original characteristic variable and each primary reconstruction characteristic variable are analyzed by adopting a logic comparison control method, and the correlation of each primary original characteristic variable and each primary reconstruction characteristic variable is analyzed by adopting a statistical relationship analysis method, so that the efficiency and the precision of the model are improved. The model adopts the change rate to carry out pure logic judgment. The method has the advantages that timely adaptive parameter adjustment and response are effectively carried out aiming at the problems of the combustion state of the garbage incinerator and large fluctuation of the discharge state of secondary pollutants. Optimization can be performed according to the judgment result of the multivariable, and an optimal output result is given.
As an alternative embodiment, in step S1, the data acquisition and processing: and selecting a data interval, acquiring historical data of a measuring point of the garbage incinerator equipment, and filtering and predicting the acquired historical data to obtain sample data.
Specifically, the preprocessing of the acquired historical data specifically refers to cleaning unreasonable data in the acquired historical data, the unreasonable data includes error data, abnormal data and repeated data, the error data mainly refers to data which is acquired by terminal equipment and is in error or mutation, the data is corrected by adopting a fitting method, the abnormal data includes null data and data which deviates by more than 50%, and the data is replaced and corrected by specifically adopting an interpolation method; the repeated data is the same data and the data which appears repeatedly. By preprocessing the acquired historical data, the interference of error data in model construction can be avoided, the quality of data is effectively improved, the prediction effect and precision of the model are improved, repeated data are reduced, and therefore the modeling and prediction efficiency of the prediction model is improved.
As an alternative embodiment, in step S3, before the training of the data modeling using the training prediction engine, the data transformation is further included.
The prediction engine firstly performs discrete Fourier transform on the data, can extract more deep-level information (information which cannot be directly embodied by the data) to ensure the prediction effect of the generated prediction model, and performs data modeling training by adopting the prediction training engine after the data are transformed, specifically, the discrete Fourier transform of the data is respectively embodied as the change rate and the acceleration of the data.
As an optional implementation manner, in step S4, the accuracy of the generated prediction model is verified by using the variance and standard deviation of the prediction error, and the specific method is as follows: and taking the prediction accuracy S as an evaluation effect index of model verification, wherein the prediction accuracy S is 1-the variance of the difference between the predicted value and the actual value.
The generated prediction model is subjected to accuracy verification by adopting the variance and the standard deviation of the prediction error, when the effect verification is carried out on the secondary pollutants continuously measured in the flue gas of the waste incinerator, correction is needed according to the fluctuation condition of the pollutant discharge amount, the fitting degree is high, the method for predicting the variance and the standard deviation of the error can better reflect the accuracy of the model and the fitting degree of data, and the prediction effect of the model is more reasonably reflected.
As an optional implementation manner, the method further includes performing optimization adjustment on the reconstructed feature variables and training feature parameters for data modeling training according to the accuracy of the prediction model obtained in step S4. The effects obtained by verifying the effects according to the prediction model produced by training, namely the training result of data modeling training by adopting a prediction training engine, are verified, and the reconstructed characteristic variables and the training characteristic parameters for data modeling training are properly adjusted, so that the prediction effect of the prediction model is optimal, and the prediction precision of the prediction model is improved.
As shown in fig. 3, the embodiment further provides a method for constructing a collaborative removal prediction model in a secondary pollutant furnace of a garbage incinerator, which includes the following steps a 1-A3:
a1, loading the prediction model trained offline by an online algorithm, and simultaneously calculating the original features in real timeAnd accessing the real-time calculation data values of the variable data values and the reconstruction characteristic variables into the model for calculation to generate a prediction result in real time. The prediction model is a secondary pollutant emission prediction model, and specifically comprises prediction of NOXPrediction model for emission amount, prediction model for predicting HCl emission amount, and prediction NH3And (4) a prediction model of escape emission. The prediction model can be constructed by the method.
And A2, constructing a secondary pollutant in-furnace collaborative removal model according to the prediction model, and verifying the prediction result.
A3, sending the predicted value of the furnace collaborative removal model to a user terminal through an application programming interface, and using a front-line operator as a reference for operation adjustment according to the predicted result.
The flue gas emission prediction algorithm issues prediction and warning results in an application programming interface mode, a third-party system is supported to call and store data, and in a production scene of the waste incineration power plant, pollutant prediction results are displayed in a scheduling room and a terminal production field in real time so as to assist managers in making decisions and workers in producing on the site. And the online algorithm preferentially loads the prediction model trained offline, and simultaneously accesses the real-time value of the original characteristic variable calculated in real time into the model for calculation to generate a prediction result and a furnace collaborative removal scheme in real time.
Specifically, the predicted value is sent to a user terminal display interface through an application programming interface, front-end operators perform advanced intervention and adjustment according to the predicted value displayed by the terminal and a collaborative removal scheme, the purpose of advanced adjustment is achieved, the display of the prediction effect and the collaborative removal scheme is visual and convenient, manual control and operation on removal of pollutants can be assisted in advance, and the pollutants can be accurately adjusted and controlled by an operator in advance.
Further, the data cloud method applied to the garbage incinerator equipment collects collected data of an automatic test terminal system, wherein the collected data comprise historical data, real-time collected data and predicted data, and the equipment is synchronized to a cloud data storage platform in real time to realize long-term storage for subsequent data analysis.
In summary, compared with the prior art, the method of the embodiment has the following beneficial effects: the method of the embodiment determines the influence factors (temperature, flow, oxygen content and the like of air distribution) influencing the discharge amount of the secondary pollutants based on the generation mechanism of the secondary pollutants of the garbage incinerator and the analysis of historical operation data and real-time operation data, determines the primary original characteristic variables, and performing a feature variable reconstruction on the preliminary feature variables to determine preliminary reconstructed feature variables, and further, by using the sample data to carry out correlation analysis and accuracy calculation on the primary original characteristic variables and the primary reconstructed characteristic variables, the effectiveness can be judged and selected according to the actual result, which is beneficial to improving the precision of the prediction model, and then, performing data modeling training by adopting a prediction training model, generating a prediction model capable of predicting the discharge amount of secondary pollutants generated by burning the garbage incinerator, and realizing efficient blending incineration and NO by optimizing graded air distribution and SNCR adjustment.XControlling the inside of the furnace efficiently; inhibit the generation of dioxin in the furnace by combining with the in-furnace dechlorination technology, and realize HCl, HF and SO2The method has the advantages that the secondary pollutants in the flue gas of the waste incinerator can be predicted in advance by the aid of the built prediction model after the acid gas is removed cooperatively, prediction accuracy is high, advanced guidance on manual operation can be achieved, the problem that sudden emission of pollutants exceeds standard in the current stage is solved, the consumption of a reducing agent is reduced, pollutants are reduced from the source, and production personnel are effectively guided to intervene in advance to adjust emission control of secondary pollutants burned in the waste incinerator.
The embodiment also provides a construction device of the prediction model of the discharge amount of secondary pollutants of the incinerator, which is characterized by comprising the following components:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method as shown in fig. 1.
The device for constructing the model for predicting the discharge amount of the secondary pollutants of the incinerator can execute the method for constructing the model for predicting the discharge amount of the secondary pollutants of the incinerator, can execute any combination of implementation steps of the method embodiments, and has corresponding functions and beneficial effects of the method.
The embodiment of the application also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor to cause the computer device to perform the method illustrated in fig. 1.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. 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/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A construction method of a model for predicting the discharge amount of secondary pollutants of an incinerator is characterized by comprising the following steps:
acquiring historical data of incinerator equipment, and acquiring sample data according to the historical data;
determining influence factors influencing the discharge amount of secondary pollutants, and determining a primary original characteristic variable according to the influence factors;
according to a secondary pollutant generation mechanism and the analysis of the historical data, performing characteristic reconstruction on the primary original characteristic variable, and determining a primary reconstructed characteristic variable and a primary characteristic variable reconstruction method;
performing correlation analysis on the preliminary original characteristic variable, the preliminary reconstruction characteristic variable and a preliminary characteristic variable reconstruction method according to the sample data to obtain an original characteristic variable, a reconstruction characteristic variable and a characteristic variable reconstruction method;
and constructing a prediction model according to the original characteristic variables, the reconstructed characteristic variables and the characteristic variable reconstruction method.
2. The method as claimed in claim 1, wherein when the prediction model is used for predicting NO emission, the model is constructedXWhen the emission is predicted, the original characteristic variables include: velocity v of grate, feed rate m, pressure p of primary air chamber1And flow rate q1Pressure p of secondary air2Temperature T2And flow rate q2Amount of adsorbent added mtSpraying amount m of reducing agentsThe temperature T of the smoke at the outlet of the first flue1Concentration M of oxygen in flue gas1And flow rate, drum pressure paAnd superheater temperature Tg；
The reconstruction feature variables include: the total air volume, the average value of the oxygen content of the flue gas and the temperature T of the superheater, wherein the total air volume is primary air volume and secondary air volume;
the characteristic variable reconstruction method is a pure logic judgment method.
3. The method for constructing a model for predicting the discharge amount of secondary pollutants of an incinerator according to claim 1, wherein when the prediction model is used for predicting the discharge amount of HCl, the original characteristic variables comprise: velocity v and temperature T of the grate0The temperature T of the smoke at the outlet of the first flue1Concentration M of oxygen in flue gas2Flow rate, additive input, inlet flue gas temperature, outlet flue gas temperature of the deacidification tower, residence time, lime slurry concentration and tail gas emissionThe concentration of HCl; the reconstruction feature variables include: the total air volume; the average value of the oxygen content of the flue gas and the temperature T of the superheater, wherein the total air quantity is primary air quantity and secondary air quantity;
the characteristic variable reconstruction method is a neural network algorithm.
4. The method as claimed in claim 1, wherein when the prediction model is used for NH, the method comprises3When the escape emission is predicted, the original characteristic variables include: outlet temperature of first flue, flow rate of flue gas, flow and pressure of reducing agent, and NO of flue gasXReduced concentration, primary air flow, secondary air flow and temperature;
the reconstruction feature variables include: total air quantity, average oxygen content of flue gas, flow of reducing agent and NO at flue outletxConcentration, wherein the total air volume is primary air volume and secondary air volume;
the characteristic variable reconstruction method is a neural network algorithm.
5. The method for constructing the model for predicting the discharge amount of the secondary pollutants of the incinerator according to claim 1, wherein the performing correlation analysis on the preliminary original characteristic variable, the preliminary reconstructed characteristic variable and the preliminary characteristic variable reconstruction method according to the sample data comprises:
analyzing the effectiveness and the precision of the primary original characteristic variable and the primary reconstruction characteristic variable by adopting a logic comparison control method;
and performing correlation analysis on the preliminary original characteristic variable and the preliminary reconstruction characteristic variable by adopting a statistical relationship analysis method.
6. The method for constructing the model for predicting the discharge amount of the secondary pollutants of the incinerator according to claim 1, further comprising the following steps:
and training the prediction model by adopting a training prediction engine.
7. The method for constructing the model for predicting the discharge amount of the secondary pollutants of the incinerator according to claim 1, further comprising the step of verifying the trained prediction model:
and carrying out accuracy verification on the trained prediction model by adopting the variance and standard deviation of the prediction error, and taking the prediction accuracy S as an evaluation effect index of the model verification, wherein the prediction accuracy S is 1-the variance of the difference between the predicted value and the actual value.
8. The method for constructing a model for predicting the discharge amount of secondary pollutants from an incinerator according to any one of claims 1 to 7, wherein the construction method further comprises:
obtaining a plurality of trained predictive models, including a predictive NOXPrediction model for emission amount, prediction model for predicting HCl emission amount, or prediction NH3At least two of the prediction models of the escape emissions;
and constructing a secondary pollutant in-furnace collaborative removal model according to the obtained prediction model.
9. The method for constructing the prediction model of the discharge amount of the secondary pollutants of the incinerator according to claim 1, wherein the obtaining of the trained prediction model comprises:
and loading the prediction model after offline training through an online algorithm.
10. The utility model provides an incinerator secondary pollutant emission prediction model's construction equipment which characterized in that includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111406508.8A CN114218760A (en) | 2021-11-24 | 2021-11-24 | Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111406508.8A CN114218760A (en) | 2021-11-24 | 2021-11-24 | Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218760A true CN114218760A (en) | 2022-03-22 |
Family
ID=80698173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111406508.8A Pending CN114218760A (en) | 2021-11-24 | 2021-11-24 | Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218760A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558367A (en) * | 2024-01-08 | 2024-02-13 | 科扬环境科技有限责任公司 | Volatile organic pollutant emission amount calculating method and device |
-
2021
- 2021-11-24 CN CN202111406508.8A patent/CN114218760A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558367A (en) * | 2024-01-08 | 2024-02-13 | 科扬环境科技有限责任公司 | Volatile organic pollutant emission amount calculating method and device |
| CN117558367B (en) * | 2024-01-08 | 2024-03-26 | 科扬环境科技有限责任公司 | Volatile organic pollutant emission amount calculating method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2673562C (en) | Dynamic control of selective non-catalytic reduction system for semi-batch-fed stoker-based municipal solid waste combustion | |
| CN105404145B (en) | The new cascade control method of denitration based on exponential forecasting and time lag predictive compensation | |
| Zhang et al. | Estimating source strengths of HCl and SO2 emissions in the flue gas from waste incineration | |
| CN113094986B (en) | Method for constructing prediction model of pollutant emission in flue gas of waste incinerator and application | |
| CN110263452B (en) | Flue gas time distribution characteristic analysis method and system in flue and denitration system | |
| CN103955751B (en) | Method for predicting multi-element nonlinear limestone-gypsum wet desulphurization efficiency | |
| SE520927C2 (en) | Method of operation of a heat-producing plant for combustion of chlorine-containing fuels | |
| CN111639782B (en) | SCR (Selective catalytic reduction) denitration device SO of coal-fired power plant2/SO3Conversion rate prediction method | |
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN102233239A (en) | System and method for controlling and reducing NOx emissions | |
| CN114218760A (en) | Method and device for constructing prediction model of secondary pollutant discharge amount of incinerator | |
| CN106647259B (en) | Coking flue gas desulfurization and denitrification integration apparatus centralized management system | |
| CN107909531A (en) | The definite method of coal-burned industrial boiler flue-gas denitration process | |
| CN110292848B (en) | CFD-based garbage incinerator deacidification equipment and method | |
| CN110652856B (en) | SNCR control system based on model | |
| CN109933884B (en) | Neural network inverse control method for SCR denitration system of coal-fired unit | |
| CN214233498U (en) | SNCR control system of double-PID (proportion integration differentiation) circulating fluidized bed boiler | |
| Arsie et al. | Development and Experimental Validation of a Control Oriented Model of SCR for Automotive Application | |
| Korpela et al. | Monitoring of spraying in semi-dry desulfurization processes in coal fired power plants | |
| CN111931358A (en) | Model-driven SCR denitration ammonia spraying targeting control loop | |
| CN115475514B (en) | Control system for pre-controlling denitration efficiency of gas boiler by using heat value and flow | |
| CN103257645A (en) | Environmental load evaluation and monitoring method for selective catalytic reduction of NOx in cement plant | |
| CN114543100A (en) | Furnace coupling removal system for secondary pollutants of garbage incinerator and control method | |
| Yin et al. | Selection of Factors Affecting NOx Emissions Concentration Forecast Modeling Based on BP Neural Network | |
| Srinivasn | Study of trona (sodium sesquicarbonate) reactivity with sulfur dioxide in a simulated flue gas |
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 |