CN114225662B - Hysteresis model-based flue gas desulfurization and denitrification optimal control method - Google Patents
Hysteresis model-based flue gas desulfurization and denitrification optimal control method Download PDFInfo
- Publication number
- CN114225662B CN114225662B CN202111483083.0A CN202111483083A CN114225662B CN 114225662 B CN114225662 B CN 114225662B CN 202111483083 A CN202111483083 A CN 202111483083A CN 114225662 B CN114225662 B CN 114225662B
- Authority
- CN
- China
- Prior art keywords
- data
- desulfurization
- model
- power plant
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 206
- 230000023556 desulfurization Effects 0.000 title claims abstract description 206
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 title claims abstract description 105
- 239000003546 flue gas Substances 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 98
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 claims abstract description 288
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims abstract description 134
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims abstract description 88
- 239000002002 slurry Substances 0.000 claims abstract description 77
- 238000012706 support-vector machine Methods 0.000 claims abstract description 63
- 238000000738 capillary electrophoresis-mass spectrometry Methods 0.000 claims abstract description 44
- 238000004088 simulation Methods 0.000 claims abstract description 43
- 238000005507 spraying Methods 0.000 claims abstract description 43
- 229910021529 ammonia Inorganic materials 0.000 claims abstract description 40
- 238000010521 absorption reaction Methods 0.000 claims abstract description 36
- 238000003745 diagnosis Methods 0.000 claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 238000011217 control strategy Methods 0.000 claims abstract description 13
- 238000012806 monitoring device Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 46
- 238000005259 measurement Methods 0.000 claims description 46
- 230000008859 change Effects 0.000 claims description 40
- 235000005770 birds nest Nutrition 0.000 claims description 39
- 235000005765 wild carrot Nutrition 0.000 claims description 39
- 230000000875 corresponding effect Effects 0.000 claims description 35
- 230000008569 process Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 30
- 238000010219 correlation analysis Methods 0.000 claims description 29
- 230000004927 fusion Effects 0.000 claims description 29
- 238000010801 machine learning Methods 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 239000010440 gypsum Substances 0.000 claims description 26
- 229910052602 gypsum Inorganic materials 0.000 claims description 26
- 235000019738 Limestone Nutrition 0.000 claims description 21
- 239000006028 limestone Substances 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 17
- 238000002347 injection Methods 0.000 claims description 15
- 239000007924 injection Substances 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000001276 controlling effect Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 241000544061 Cuculus canorus Species 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000002596 correlated effect Effects 0.000 claims description 9
- 238000003066 decision tree Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000007500 overflow downdraw method Methods 0.000 claims description 7
- VTYYLEPIZMXCLO-UHFFFAOYSA-L Calcium carbonate Chemical compound [Ca+2].[O-]C([O-])=O VTYYLEPIZMXCLO-UHFFFAOYSA-L 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 6
- 239000003245 coal Substances 0.000 claims description 6
- 230000018044 dehydration Effects 0.000 claims description 6
- 238000006297 dehydration reaction Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000003009 desulfurizing effect Effects 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000007664 blowing Methods 0.000 claims description 3
- 229910000019 calcium carbonate Inorganic materials 0.000 claims description 3
- 238000002485 combustion reaction Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000004134 energy conservation Methods 0.000 claims description 3
- 238000011049 filling Methods 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- KJONHKAYOJNZEC-UHFFFAOYSA-N nitrazepam Chemical compound C12=CC([N+](=O)[O-])=CC=C2NC(=O)CN=C1C1=CC=CC=C1 KJONHKAYOJNZEC-UHFFFAOYSA-N 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000004071 soot Substances 0.000 claims description 3
- 238000004065 wastewater treatment Methods 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 6
- 208000005156 Dehydration Diseases 0.000 description 5
- 230000003647 oxidation Effects 0.000 description 5
- 238000007254 oxidation reaction Methods 0.000 description 5
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 description 4
- 235000011114 ammonium hydroxide Nutrition 0.000 description 4
- 239000007789 gas Substances 0.000 description 4
- 239000000428 dust Substances 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 239000006096 absorbing agent Substances 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 239000002250 absorbent Substances 0.000 description 1
- 230000002745 absorbent Effects 0.000 description 1
- 238000003916 acid precipitation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010790 dilution Methods 0.000 description 1
- 239000012895 dilution Substances 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/346—Controlling the process
-
- 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
- B01D53/502—Sulfur oxides by treating the gases with a solution or a suspension of an alkali or earth-alkali or ammonium compound characterised by a specific solution or suspension
-
- 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
-
- 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
- B01D53/86—Catalytic processes
- B01D53/8621—Removing nitrogen compounds
- B01D53/8625—Nitrogen oxides
-
- 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
- B01D53/86—Catalytic processes
- B01D53/90—Injecting reactants
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Analytical Chemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention relates to a flue gas desulfurization and denitrification optimization control method based on a hysteresis model, which comprises the steps of establishing a simulation model of a desulfurization and denitrification system of a power plant through dynamic simulation software according to a modularized modeling and control strategy; establishing a first lag time prediction model for the time delay of determining the existence of the PH value of the absorption tower in the desulfurization system, and establishing a second lag time prediction model for the time delay of determining the existence of the concentration of the nitrogen oxides in the flue gas at the inlet of the denitration system through a flue gas online monitoring device CEMS; predicting the sulfur dioxide concentration at a desulfurization outlet and the nitrogen oxide concentration at a denitration inlet in a support vector machine model; controlling the slurry spraying amount according to the sulfur dioxide concentration predicted value and the first lag time predicted model, and controlling the ammonia spraying amount according to the nitrogen oxide concentration predicted value and the second lag time predicted model; and issuing the control parameters to a simulation model of the desulfurization and denitrification system for intelligent diagnosis.
Description
Technical Field
The invention belongs to the technical field of desulfurization and denitrification, and particularly relates to a flue gas desulfurization and denitrification optimization control method based on a hysteresis model.
Background
With the rapid development of various industries, the atmospheric pollution is increased, the emission of sulfur dioxide and nitrogen oxides is kept high, the problems of atmospheric pollution and acid rain are also increased, and a thermal power plant is one of the main sources of the emission of sulfur dioxide and nitrogen oxides, so that the control of the emission of sulfur dioxide and nitrogen oxides in the power plant is urgent. The national institutes correspondingly provide a desulfurization and denitrification work plan for enhancing pollutant emission and continuously pushing the electric power industry, the newly built coal-fired unit is required to comprehensively implement desulfurization and denitrification, standard emission is realized, the active coal-fired unit which is not provided with desulfurization and denitrification facilities is matched with flue gas desulfurization and denitrification facilities, and the unit which cannot stably reach the standard emission is required to be transformed.
The common process of the desulfurization system is limestone-gypsum wet flue gas desulfurization, and the whole flow mainly comprises an absorption tower system, a limestone slurry preparation system and a gypsum dehydration treatment system, wherein the absorption tower is provided with two outlets, one outlet is a gypsum slurry outlet, and the real-time PH value is detected, namely the PH value of the gypsum slurry outlet is detected; the other outlet is a clean flue gas outlet, and the concentration of the dioxide building is detected, namely the concentration of sulfur dioxide at the clean flue gas outlet is detected; however, the flue gas reaction of the absorption tower is a large-lag and slow-dynamic process, and meanwhile, the desulfurization system is a complex control system, the pH value is set or adjusted by a conventional PID control strategy according to experience, the spraying amount of limestone slurry is difficult to accurately control, and the pH value of the slurry is difficult to effectively control and ensure that the value is in an effective range.
The common process of the denitration system is SCR denitration, and the main influencing factors are the amount of ammonia water, the incomplete reaction can be caused by the too small amount of ammonia water, the concentration of nitrogen oxides at an outlet exceeds the standard, the excessive amount of ammonia water can be discharged out of the system along with flue gas, and the unreacted ammonia water can cause atmospheric pollution and downstream equipment blockage; the high-efficient steady operation of denitration system is the key that realizes power plant's flue gas nitrogen oxide emission concentration standard, because denitration system has characteristics such as nonlinearity, hysteresis characteristic, traditional PID control technique is difficult to maintain denitration system export nitrogen oxide concentration stable, produces too big export nitrogen oxide concentration fluctuation, leads to frequently appearing export nitrogen oxide concentration and exceeds standard phenomenon on the one hand, and on the other hand is to guaranteeing export nitrogen oxide concentration standard rate, needs to increase and spouts the ammonia volume, and denitration system spouts ammonia volume cost and improves thereupon.
How to solve the control difficulty brought by the hysteresis characteristic of the desulfurization and denitrification system of the power plant, ensure the effective control of the concentration of nitrogen oxides at the desulfurization outlet, reduce the fluctuation of the concentration of nitrogen oxides at the denitrification outlet, accurately control the slurry spraying quantity, and reduce the ammonia spraying cost of the denitrification system, thus being an important direction for the operation regulation and control of the desulfurization and denitrification system of the power plant.
Based on the technical problems, a new flue gas desulfurization and denitrification optimization control method based on a hysteresis model needs to be designed.
Disclosure of Invention
The invention aims to solve the technical problem of providing the flue gas desulfurization and denitrification optimization control method based on the hysteresis model, which can truly simulate the actual working scene of desulfurization and denitrification of a power plant, intuitively display and know the actual operation condition of desulfurization and denitrification of the power plant and adjust system parameters.
The technical scheme adopted by the invention is as follows:
a flue gas desulfurization and denitrification optimization control method based on a hysteresis model comprises the following steps: step 1: model construction is carried out on all parts of the desulfurization and denitrification of the power plant, a control system is built according to a field control strategy, and a complete simulation model of the desulfurization and denitrification system of the power plant is built; step 2: a first lag time prediction model is established for the time delay of determining the existence of the PH value of the absorption tower in the power plant desulfurization system, and a second lag time prediction model is established for the time delay of determining the existence of the nitrogen oxide concentration of the flue gas at the inlet of the power plant denitration system through a flue gas online monitoring device CEMS; step 3: predicting the concentration of sulfur dioxide in flue gas at the outlet of a desulfurization system of a power plant and the concentration of nitrogen oxides in flue gas at the inlet of a denitration system; step 4: controlling the slurry spraying amount of the desulfurization system according to the sulfur dioxide concentration predicted value and the first lag time predicted model, and controlling the ammonia spraying amount of the denitration system according to the nitrogen oxide concentration predicted value and the second lag time predicted model; step 5: and the slurry spraying quantity and the control parameters of the ammonia spraying quantity are issued to a simulation model of a desulfurization and denitrification system of the power plant for intelligent diagnosis.
Further, in step 1, after the dynamic simulation software builds the model of each component of the desulfurization and denitrification of the power plant according to the modularized modeling method, and builds a corresponding control system according to the on-site control strategy, a complete simulation model of the desulfurization and denitrification system of the power plant is built, which specifically comprises the following steps:
the power plant desulfurization system is a limestone-gypsum wet desulfurization system, and at least comprises a flue gas system, an absorption tower system, a limestone slurry preparation system, a gypsum slurry dehydration system, a wastewater treatment system and an electrical system; the power plant denitration system selects an SCR method flue gas denitration system and at least comprises a flue gas system, an SCR reactor system, a sound wave soot blowing system and a liquid ammonia storage and supply system;
the dynamic simulation software selects corresponding component modules from a model library and connects the corresponding component modules according to mass conservation, momentum conservation and energy conservation equations and the technological process of a limestone-gypsum wet desulfurization system and an SCR flue gas denitration system in the modeling process, and inputs initial data to complete the model construction of the desulfurization and denitration system of the power plant;
and constructing an analog quantity control system, a sequence control system and a logic control system according to a field control strategy, configuring by adopting a basic algorithm module, realizing the same function as an actual control system, and establishing a complete simulation model of the desulfurization and denitrification system of the power plant.
Further, the simulation model of the desulfurization and denitrification system of the power plant further comprises:
in the process of model development and debugging, physical data acquired by an actual power plant desulfurization and denitrification system and virtual data acquired based on a power plant desulfurization and denitrification simulation model are compared, whether errors exceed a threshold value is judged, if so, virtual data with larger errors are classified through cluster learning, corresponding historical data are combined as input, error learning is carried out through a neural network, correction coefficients are output to correct the error data of the virtual data, and virtual-real fusion is carried out on the corrected virtual data and the physical data to generate a verified power plant desulfurization and denitrification simulation model.
Further, in step 2, establishing a first lag time prediction model for determining a time delay existing in the PH of the absorber in the desulfurization system of the power plant by using the variable point detection, the time window sliding, the correlation analysis and the machine learning model includes: establishing a slurry PH value response lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a first lag time prediction model by adopting a machine learning model;
the slurry PH response lag time identification algorithm flow comprises:
After the PH value of the slurry in the absorption tower is adjusted, the working condition that the concentration value of sulfur dioxide at the outlet of the absorption tower is changed is selected as an identification object;
equally dividing the time window deltat into two equally spaced time windows deltat i1 And Deltat i2 Sliding forward on the time axis gradually, calculating the average difference value of the sulfur dioxide concentration in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the time window is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point;
based on the working condition change point t i And a time window delta t, respectively obtaining a slurry PH value time sequence and a sulfur dioxide concentration time sequence from the beginning of the working condition change to the end of the time window;
gradually advancing the sulfur dioxide concentration time sequence, setting a maximum movement step number k, obtaining a new sulfur dioxide concentration sequence through advancing, and constructing a sulfur dioxide concentration time lag matrix V;
calculating the Pelson correlation coefficient r of each column in the slurry PH value time sequence and matrix V, wherein the delay time corresponding to the maximum correlation coefficient is PH value response lag time t under the working condition 1 ；
The building of the first lag time prediction model using the machine learning model includes:
after original data features in a power plant desulfurization system are collected and preprocessed, substituting the original data features into the slurry PH value response lag time identification algorithm flow to carry out PH value delay identification, and acquiring the relation between delay time and different operation data features; the raw data features include at least: the load of the boiler, the air supply quantity of the boiler, the flow rate of limestone slurry, the input quantity of the limestone slurry, the sulfur dioxide content, the calcium carbonate content in the limestone and the distance data characteristic from the absorption tower to the PH measuring point;
Converting the operation data characteristics which are obtained through identification and can cause PH value change into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of the operation data characteristics and PH response lag time, wherein the higher the correlation coefficients are, the most correlation between the data characteristics and the lag time is shown;
the method comprises the steps of adopting a feature fusion method to fuse the running data features according to the height of a correlation coefficient to form new fusion features, taking original running data features and the new fusion features as sample data, inputting a training set in the sample data into a machine learning model according to a preset proportion, and establishing a first lag time prediction model under different running data change working conditions; and calculating the PH value response lag time according to different operation data characteristics through the first lag time prediction model.
Further, in step 2, establishing a second lag time prediction model for the time delay of determining the existence of the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system through the flue gas online monitoring device CEMS by using the variable point detection, the time window sliding, the correlation analysis and the machine learning model includes: establishing a CEMS measurement lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a second lag time prediction model by adopting a machine learning model;
The CEMS measurement lag time identification algorithm flow comprises:
after the concentration of the nitrogen oxide at the inlet is selected to change, the working condition that the CEMS measured value changes is selected as an identification object; the measurement of the concentration of the nitrogen oxides is carried out through the heat tracing pipe and the analysis cabinet, and the smoke flows in the heat tracing pipe and the concentration in the analysis cabinet is measured, so that a certain time lag exists;
equally dividing the time window deltat' into two equally spaced time windows deltat i1 ' and Δt i2 ' gradually sliding forward on a time axis, calculating the average difference value of CEMS measured values in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the threshold value is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point;
based on the working condition change point t i 'and a time window delta t', respectively acquiring a nitrogen oxide concentration value time sequence and a CEMS measurement value time sequence from the beginning of the working condition change to the end of the time window;
gradually advancing the CEMS measurement time sequence, setting a maximum movement step number k, obtaining a new CEMS measurement sequence through advancing, and constructing a CEMS measurement time lag matrix V';
calculating the pearson correlation coefficient r 'of each column in the time sequence and matrix V' of the nitrogen oxide concentration value, wherein the delay time corresponding to the maximum correlation coefficient is the nitrogen oxide concentration measurement lag time t under the working condition 2 ；
The building of the second lag time prediction model using the machine learning model includes:
after the original data characteristics in the power plant denitration system are collected and preprocessed, the original data characteristics are substituted into a CEMS measurement lag time identification algorithm flow to carry out delay identification, and the relationship between the delay time and different operation data characteristics is obtained; the raw data features include at least: boiler load, coal type, coal supply, combustion temperature, air quantity and smoke quantity;
converting the operation data characteristics which are obtained through identification and can cause the concentration change of the nitrogen oxides into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of each operation data characteristic and the nitrogen oxide concentration value measurement lag time, wherein the higher the correlation coefficient is, the most correlation between the data characteristic and the lag time is shown;
the method comprises the steps of adopting a feature fusion method to fuse the running data features according to the height of a correlation coefficient to form new fusion features, taking the original running data features and the new fusion features as sample data, inputting a training set in the sample data into a machine learning model according to a preset proportion, and establishing a second lag time prediction model under different running data change working conditions; and calculating CEMS measurement lag time according to different operation data characteristics through a second lag time prediction model.
Furthermore, the machine learning model selects an XGBoost model, which is an integrated learning algorithm adopting a boosting method, the base learner selects a CART decision tree, and k CART functions { f are applied 1 ,f 2 ,…,f k Adding to form an integrated tree model; the target function of the model consists of a loss function and a regular term, and the loss function approximates by adopting second-order Taylor expansion; performing optimization operation on key parameters to improve the accuracy of model prediction, wherein the key parameters comprise the maximum depth of a tree, subsamples, the number of randomly sampled columns of each tree, the minimum leaf node sample weight and the learning rate;
the construction of the model starts from a root node, training set data are ordered according to each data feature, a greedy method is adopted to calculate the benefit of each feature, the feature with the largest benefit is selected as a splitting feature, the training set data are mapped to corresponding leaf nodes, the generated leaf nodes are recursively subjected to constraint condition until the constraint condition is reached, the decision tree generation process is finished, then the first-order derivative and the second-order derivative of a loss function are used for calculating the weight of the decision tree leaf node, the weight is used as a fitting target of the next tree, the recursion is repeated until the condition is met, and the model establishment is finished.
Further, in step 3, after collecting the historical operation parameters of the power plant desulfurization system and the denitration system, selecting the operation parameters which are strongly related to the power plant desulfurization, inputting the operation parameters into the constructed first support vector machine model to predict the sulfur dioxide concentration in the flue gas at the outlet of the power plant desulfurization system, and specifically comprising:
taking the collected historical operation parameters of the power plant desulfurization system as sample data, carrying out correlation analysis on the sample data, removing the sample data with the correlation of the sulfur dioxide concentration in the flue gas at the outlet of the limestone-gypsum wet desulfurization system being smaller than a preset value, and taking the rest sample data as operation data which is strongly correlated with the desulfurization system; the historical operating parameters of the desulfurization system at least comprise sulfur dioxide concentration at an inlet, nitrogen oxide concentration, unit load, limestone slurry circulating pump current, slurry supply quantity, flue gas sulfur dioxide concentration at an outlet of an absorption tower and slurry PH value;
performing data preprocessing on the operation data which is strongly related to the desulfurization system, and constructing a first support vector machine model by utilizing the preprocessed data;
collecting real-time operation data related to power plant desulfurization, and inputting the real-time operation data into a constructed first support vector machine model to obtain a predicted value of the concentration of sulfur dioxide in flue gas at the outlet of a power plant desulfurization system;
Wherein the data preprocessing comprises: filling up missing values and abnormal values and normalizing the operation data which are strongly related to the desulfurization system to obtain a preprocessed desulfurization data sequence, wherein the preprocessed desulfurization data sequence is marked as F= [ F ] 1 ,f 2 ,f 3 ,…,f n ]，f i Number of desulfurization for the ith time point in the processed desulfurization data sequenceAccording to the above;
wavelet threshold denoising is carried out on the desulfurization data sequence F, wavelet decomposition is carried out on noisy data with noise, real data information is obtained, and the real data information is recorded as P= [ P ] 1 ,p 2 ,p 3 ,…,p m ]，p i Is the desulfurization data of the ith moment point in the real desulfurization data sequence.
Further, in step 3, selecting an operation parameter related to denitration intensity of the power plant, inputting the operation parameter to the constructed second support vector machine model to predict the concentration of the nitrogen oxides in the flue gas at the inlet of the denitration system of the power plant, specifically including:
taking the collected historical operation parameters of the power plant denitration system as sample data, calculating the correlation between the sample data and the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system by adopting a Pearson correlation coefficient, and selecting a data combination with high correlation as operation data which is strongly correlated with the denitration system according to the correlation; the denitration system historical operation data at least comprises ammonia injection mass flow, boiler load, SCR inlet flue gas temperature, SCR inlet flue gas oxygen content, SCR inlet nitrogen oxide concentration and SCR denitration efficiency;
Performing data preprocessing on operation data which are strongly related to the denitration system, and constructing a second support vector machine model by utilizing the preprocessed data;
acquiring real-time operation data related to power plant denitration and inputting the real-time operation data into a constructed second support vector machine model to acquire a flue gas nitrogen oxide concentration predicted value at an inlet of a power plant denitration system;
the data with strong correlation and extremely strong correlation are selected as the data with high correlation with the denitration system, and the calculation formula is as follows:
x is the characteristic of input sample data, Y is the concentration of nitrogen oxides at the inlet, cov (X, Y) represents the covariance of X, Y; sigma (sigma) X Sum sigma Y The standard deviation of X and Y respectively, ρ represents the correlation coefficient between two variables, and the value range is [ -1,1]The method comprises the steps of carrying out a first treatment on the surface of the When ρ is 0.8 or less<At 1, it is called extremely strong correlation; when ρ is 0.6 or less<At 0.8, it is called strong correlation; when ρ is 0.4 or less<0.6, referred to as moderate correlation; when 0.2 is less than or equal to ρ<0.4, called weak correlation; when 0.0 is less than or equal to ρ<At 0.2, it is said to be very weakly correlated or uncorrelated.
Further, constructing a first support vector machine model and a second support vector machine model, including: adopting a cuckoo optimization method to determine optimal support vector machine parameters: initializing parameters of a cuckoo optimization algorithm, and searching bird nest positions by step-length self-adaptive dynamic adjustment of Lewy flight according to the parameters of the cuckoo optimization method: i=1, 2, …, n; wherein x is i (t+1) A bird nest position of the ith bird nest in the t generation; a is a step control quantity, which is used for controlling the searching range of the step and obeys the front distribution; l (lambda) is a Lewy random walk; the step length self-adaptive dynamic adjustment strategy is as follows:
step i ＝step min +(step max -step min )d i
wherein step i Step for the current search step max Step is the maximum value of step length min Is the minimum value of the step length, n i Is the position of the ith nest, n best D, the bird nest position corresponding to the bird nest is the current minimum fitness max The current minimum fitness corresponds to the maximum value of the distance between the bird nest and other bird nests;
training a support vector machine model by adopting a training set in the preprocessed data, calculating the fitness of each bird nest position, and reserving the bird nest corresponding to the minimum fitness to the next iteration;
judging whether the minimum fitness meets a preset termination condition, if so, determining the bird nest position of the bird nest corresponding to the minimum fitness as the determined optimal support vector machine parameter, and if not, removing a plurality of bird nests with the highest fitness, and readjusting the bird nest position;
training a support vector machine model according to the determined optimal support vector machine parameters: establishing a support vector machine training program based on a kernel function, forming a mapping relation between an input variable and an output variable through a support vector machine model, performing learning training on training sample data by using the support vector machine training program, and obtaining N support vectors X through learning and training i * I=0, 1, …, N, forming a support vector machine model:
wherein X is i * Support vector representing desulfurization or denitrification system of power plant, Y i Sulfur dioxide concentration representing power plant desulfurization system support vector or nitrogen oxide concentration representing denitration system support vector, alpha i The coefficient representing the ith support vector, X is the input preprocessed desulfurization data or denitration data, Y (X) represents the sulfur dioxide concentration predicted value of the support vector of the desulfurization system of the power plant or the nitrogen oxide concentration predicted value of the support vector of the denitration system, K (·) represents the kernel function of the support vector machine, and the kernel function selects one of a Gaussian function, a polynomial function, a linear function and a radial basis function.
Further, step 5 includes the following steps: after the slurry spraying quantity control parameter, the ammonia spraying quantity control parameter and the relevant configuration parameters of the operation of the power plant desulfurization and denitrification system are input into the power plant desulfurization and denitrification system simulation model, comparing the acquired real-time operation parameters of the power plant desulfurization and denitrification system with simulation result data of the simulation model through a set expert diagnosis module to obtain deviation, and realizing pre-alarm through whether the deviation exceeds a preset threshold value;
The expert diagnosis module is internally provided with an intelligent diagnosis strategy, and is used for judging the related running state, data deviation and pre-alarm information conditions through preset logic, comprehensively outputting diagnosis preliminary result information, then calling expert database knowledge information for comparison, analyzing whether conclusion information obtained by the intelligent diagnosis strategy is related to or consistent with the expert database knowledge information, and outputting diagnosis analysis results, running instructions or task sheets; the knowledge information of the expert database comprises stored preset knowledge and information of abnormal faults; the pre-alarm comprises a parameter exceeding a preset threshold value, and time when the parameter exceeds the preset threshold value and abnormal fault information.
The invention has the positive effects that:
(1) According to the invention, after the dynamic simulation software is used for carrying out model construction on all parts of the desulfurization and denitrification of the power plant according to the modularized modeling method, a corresponding control system is built according to the on-site control strategy, and a complete simulation model of the desulfurization and denitrification system of the power plant is built, so that the actual working scene of the desulfurization and denitrification of the power plant can be truly simulated, the actual operation condition of the desulfurization and denitrification of the power plant can be intuitively displayed and known, and the system parameters can be adjusted;
(2) According to the invention, in the process of model development and debugging, physical data acquired by an actual power plant desulfurization and denitrification system are compared with virtual data acquired based on a power plant desulfurization and denitrification simulation model, whether errors exceed a threshold value is judged, if so, virtual data with larger errors are classified through cluster learning, corresponding historical data are combined as input, error learning is carried out through a neural network, correction coefficients are output to correct the error data of the virtual data, and the corrected virtual data and the physical data are subjected to virtual-actual fusion to generate a verified power plant desulfurization and denitrification simulation model, so that errors can be corrected through a neural network after virtual-actual data comparison and analysis, the accuracy and the accuracy of the power plant desulfurization and denitrification simulation model are improved, and a foundation is made for the follow-up desulfurization and denitrification system to carry out pre-measurement and control;
(3) According to the invention, a first lag time prediction model is built for the time delay of determining the existence of the PH value of the absorption tower in the power plant desulfurization system by adopting the variable point detection, the time window sliding, the correlation analysis and the machine learning model, and a second lag time prediction model is built for the time delay of determining the existence of the nitrogen oxide concentration of the flue gas at the inlet of the power plant denitration system by using the flue gas online monitoring device CEMS, so that the lag time existing in the power plant desulfurization and denitration system can be analyzed, calculated and a prediction model is built, and the corresponding lag influence data characteristics and the lag time can be rapidly and effectively obtained;
(4) According to the method, after historical operation parameters of a power plant desulfurization system and a denitration system are collected, the operation parameters related to the power plant desulfurization intensity are selected and input into a constructed first support vector machine model to predict the sulfur dioxide concentration in flue gas at the outlet of the power plant desulfurization system, the operation parameters related to the power plant denitration intensity are selected and input into a constructed second support vector machine model to predict the nitrogen oxide concentration in flue gas at the inlet of the power plant denitration system, the sulfur dioxide concentration value in flue gas at the outlet of the desulfurization system can be predicted through the support vector machine model, the nitrogen oxide concentration value at the inlet of the denitration system is predicted, and the accuracy of the predicted value is improved;
(5) According to the method, the slurry spraying amount of the desulfurization system is controlled according to the sulfur dioxide concentration predicted value in combination with the first lag time predicted model, the ammonia spraying amount of the denitration system is controlled according to the nitrogen oxide concentration predicted value in combination with the second lag time predicted model, the nitrogen oxide concentration of the desulfurization outlet can be effectively controlled in combination with the first lag time, the slurry spraying amount is accurately controlled, the pH value of the slurry is controlled within an effective range, meanwhile, the nitrogen oxide concentration fluctuation of the denitration outlet is reduced in combination with the second lag time, the ammonia spraying amount is accurately controlled, and the ammonia spraying cost of the denitration system is reduced;
(6) According to the invention, the slurry spraying quantity and the control parameters of the ammonia spraying quantity are issued to the simulation model of the desulfurization and denitrification system of the power plant for intelligent diagnosis, expert database knowledge information and an intelligent diagnosis strategy are set in an expert diagnosis module to compare the real-time operation parameters of the system with the simulation data so as to realize alarm and diagnosis, and a diagnosis analysis result, an operation instruction or a task list are output, so that the effective processing and diagnosis analysis of the data of the desulfurization and denitrification system of the power plant are realized.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a process flow diagram of a limestone-gypsum wet desulfurization system of the present invention;
Fig. 3 is a schematic diagram of an inlet CEMS device in the flue gas denitration system by the SCR method according to the present invention.
Detailed Description
As shown in fig. 1, this embodiment 1 provides a flue gas desulfurization and denitrification optimization control method based on a hysteresis model, where the flue gas desulfurization and denitrification optimization control method includes:
after the dynamic simulation software builds the model of each part of the desulfurization and denitrification system of the power plant according to the modularized modeling method, building a corresponding control system according to the on-site control strategy, and building a complete simulation model of the desulfurization and denitrification system of the power plant; the power plant desulfurization system adopts a limestone-gypsum wet desulfurization system, and the power plant denitration system adopts an SCR flue gas denitration system;
a first lag time prediction model is established for the time delay of determining the existence of the PH value of the absorption tower in the power plant desulfurization system, and a second lag time prediction model is established for the time delay of determining the existence of the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system through a flue gas online monitoring device CEMS;
after the historical operation parameters of the power plant desulfurization system and the denitration system are collected, the operation parameters related to the power plant desulfurization intensity are selected and input into a constructed first support vector machine model to predict the concentration of sulfur dioxide in the flue gas at the outlet of the power plant desulfurization system, and the operation parameters related to the power plant denitration intensity are selected and input into a constructed second support vector machine model to predict the concentration of nitrogen oxides in the flue gas at the inlet of the power plant denitration system;
Controlling the slurry spraying amount of the desulfurization system according to the sulfur dioxide concentration predicted value and the first lag time predicted model, and controlling the ammonia spraying amount of the denitration system according to the nitrogen oxide concentration predicted value and the second lag time predicted model;
and issuing the control parameters of the slurry spraying quantity and the ammonia spraying quantity to a simulation model of the desulfurization and denitrification system of the power plant for model verification and intelligent diagnosis.
The slurry spraying amount of the desulfurization system is controlled according to the sulfur dioxide concentration predicted value and the first lag time predicted model: the set value is an output target value, and in an actual system, the set value is the concentration of sulfur dioxide in the flue gas at the outlet; the controllable variable is the spraying amount of the slurry, the size of the controllable variable can be adjusted by the controller to enable the controllable variable to act on a target object, the output reaches an expected value, the PH value detection needs to be carried out in advance for a certain time in consideration of the PH value measurement hysteresis effect in the control process, and the slurry control valve is opened in advance to control the spraying amount of the slurry. And controlling the ammonia injection amount of the denitration system according to the predicted value of the nitrogen oxide concentration and the second lag time prediction model: calculating a first ammonia injection amount of the current operation condition according to the predicted value of the concentration of the nitrogen oxide at the inlet, sending the first ammonia injection amount to a denitration system, measuring an actual measurement value of the concentration of the nitrogen oxide at the outlet, inputting the actual measurement value and a set value of the concentration of the nitrogen oxide at the outlet into a controller to obtain a second ammonia injection amount after deviation, and sending the second ammonia injection amount to the denitration system, wherein the denitration system controls the ammonia injection amount of a denitration reactor according to the first ammonia injection amount and the second ammonia injection amount, and taking the hysteresis influence of the measurement of the concentration value of the nitrogen oxide into consideration in the control process, so that the measurement of the concentration value of the nitrogen oxide needs to be carried out in advance for a certain time so as to control the ammonia injection amount in advance.
In this embodiment, after the model construction is performed on each component of the power plant desulfurization and denitrification by the dynamic simulation software according to the modularized modeling method, and a corresponding control system is built according to the on-site control strategy, a complete simulation model of the power plant desulfurization and denitrification system is built, including:
the power plant desulfurization system is a limestone-gypsum wet desulfurization system, and at least comprises a flue gas system, an absorption tower system, a limestone slurry preparation system, a gypsum slurry dehydration system, a wastewater treatment system and an electrical system; the power plant denitration system selects an SCR method flue gas denitration system and at least comprises a flue gas system, an SCR reactor system, a sound wave soot blowing system and a liquid ammonia storage and supply system;
the dynamic simulation software selects corresponding component modules from a model library and connects the corresponding component modules according to mass conservation, momentum conservation and energy conservation equations and the technological process of a limestone-gypsum wet desulfurization system and an SCR flue gas denitration system in the modeling process, and inputs initial data to complete the model construction of the desulfurization and denitration system of the power plant;
and constructing an analog quantity control system, a sequence control system and a logic control system according to a field control strategy, configuring by adopting a basic algorithm module, realizing the same function as an actual control system, and establishing a complete simulation model of the desulfurization and denitrification system of the power plant.
According to the invention, after the dynamic simulation software is used for carrying out model construction on all parts of the desulfurization and denitrification of the power plant according to the modularized modeling method, a corresponding control system is built according to the on-site control strategy, and a complete simulation model of the desulfurization and denitrification system of the power plant is built, so that the actual working scene of the desulfurization and denitrification of the power plant can be truly simulated, the actual operation condition of the desulfurization and denitrification of the power plant can be intuitively displayed and known, and the system parameters can be adjusted.
As shown in fig. 2, the main process sequence of desulfurization and denitrification is denitration, dust removal and desulfurization. The limestone-gypsum wet desulfurization system that this patent adopted includes the technological process: after passing through a denitration system and a dry electric dust collector, raw flue gas from the tail of the boiler enters an absorption tower under the action of a draught fan, the whole absorption tower integrates absorption and oxidation, the upper part is an absorption area, and the lower part is an oxidation area. The oxidation fan at the bottom of the tower continuously blows in oxidation air, the slurry circulating pump continuously pumps limestone slurry from the bottom of the absorption tower to the upper spraying layer, flue gas entering the absorption tower is in contact with the limestone slurry sprayed from the upper part in the opposite direction, and after fog drops carried in the gas are removed by the demister at the upper part of the absorption tower, the fully reacted clean flue gas is directly discharged into the inner space of the sea-tangle type air cooling system from the top of the absorption tower, and finally is discharged into the atmosphere along with water vapor in the cooling tower. Along with the progress of the reaction, the density of the gypsum slurry in the absorption tower slurry is continuously increased, when the density reaches a certain value, a gypsum discharge pump is started, the gypsum slurry is sent to a gypsum dehydration system, by-product gypsum is formed after dehydration, and the residual slurry returns to the system for recycling, so that the utilization rate of the desulfurization absorbent is improved.
In the technological process of the limestone-gypsum wet flue gas desulfurization system, the main process is as follows: the process of obtaining the byproduct gypsum through chemical reactions such as dissolution, oxidation and the like of sulfur dioxide and limestone slurry is the most main process of the whole process flow.
The flue gas denitration process flow by the SCR method comprises the following steps: the liquid ammonia tank car sends liquid ammonia into the liquid ammonia storage tank through the discharge compressor, and the liquid ammonia in the storage tank enters into the liquid ammonia evaporator through self pressure to evaporate into ammonia through water bath heating, and then is sent into the SCR reaction zone after entering into the steady voltage in the ammonia buffer tank. Before entering the SCR reactor, the air and ammonia sent by the dilution fan are uniformly mixed and then are led into the SCR reactor to participate in chemical reaction.
In this embodiment, the simulation model of the desulfurization and denitrification system of the power plant further includes:
in the process of model development and debugging, physical data acquired by an actual power plant desulfurization and denitrification system and virtual data acquired based on a power plant desulfurization and denitrification simulation model are compared, whether errors exceed a threshold value is judged, if so, virtual data with larger errors are classified through cluster learning, corresponding historical data are combined as input, error learning is carried out through a neural network, correction coefficients are output to correct the error data of the virtual data, and virtual-real fusion is carried out on the corrected virtual data and the physical data to generate a verified power plant desulfurization and denitrification simulation model.
According to the invention, in the process of model development and debugging, errors can be corrected by adopting a neural network after virtual-real data comparison and analysis, so that the accuracy and the accuracy of a desulfurization and denitrification simulation model of a power plant are improved, and a foundation is made for the follow-up desulfurization and denitrification system to perform pre-measurement and control.
In this embodiment, the establishing the first lag time prediction model for determining the time delay existing in the PH value of the absorber in the power plant desulfurization system by using the variable point detection, the time window sliding, the correlation analysis and the machine learning model includes: establishing a slurry PH value response lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a first lag time prediction model by adopting a machine learning model;
the slurry PH response lag time identification algorithm flow comprises:
after the PH value of the slurry in the absorption tower is adjusted, the working condition that the concentration value of sulfur dioxide at the outlet of the absorption tower is changed is selected as an identification object;
equally dividing the time window deltat into two equally spaced time windows deltat i1 And Deltat i2 Sliding forward on the time axis gradually, calculating the average difference value of the sulfur dioxide concentration in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the time window is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point;
based on the working condition change point t i And a time window delta t, respectively obtaining a slurry PH value time sequence and a sulfur dioxide concentration time sequence from the beginning of the working condition change to the end of the time window;
gradually advancing the sulfur dioxide concentration time sequence, setting a maximum movement step number k, obtaining a new sulfur dioxide concentration sequence through advancing, and constructing a sulfur dioxide concentration time lag matrix V;
calculating the Pelson correlation coefficient r of each column in the slurry PH value time sequence and matrix V, wherein the delay time corresponding to the maximum correlation coefficient is PH value response lag time t under the working condition 1 ；
The building of the first lag time prediction model using the machine learning model includes:
after original data features in a power plant desulfurization system are collected and preprocessed, substituting the original data features into the slurry PH value response lag time identification algorithm flow to carry out PH value delay identification, and acquiring the relation between delay time and different operation data features; the raw data features include at least: the load of the boiler, the air supply quantity of the boiler, the flow rate of limestone slurry, the input quantity of the limestone slurry, the sulfur dioxide content, the calcium carbonate content in the limestone and the distance data characteristic from the absorption tower to the PH measuring point;
Converting the operation data characteristics which are obtained through identification and can cause PH value change into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of the operation data characteristics and PH response lag time, wherein the higher the correlation coefficients are, the most correlation between the data characteristics and the lag time is shown;
the method comprises the steps of adopting a feature fusion method to fuse the running data features according to the height of a correlation coefficient to form new fusion features, taking original running data features and the new fusion features as sample data, inputting a training set in the sample data into a machine learning model according to a preset proportion, and establishing a first lag time prediction model under different running data change working conditions; and calculating the PH value response lag time according to different operation data characteristics through the first lag time prediction model.
In addition, because of the installation position of the PH value measuring element in the desulfurization system, the time required by the detection by adopting the special PH detector and the reaction time of the limestone slurry and sulfur dioxide can cause pure lag of PH value detection, and the pure lag can not timely reflect the change of PH value of absorption liquid in the absorption tower by a measuring signal, so that the time delay is generated for PH value measured by an electrode of the PH detector.
In this embodiment, the establishing the second lag time prediction model for the time delay of determining the existence of the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system by using the variable point detection, the time window sliding, the correlation analysis and the machine learning model through the flue gas online monitoring device CEMS includes: establishing a CEMS measurement lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a second lag time prediction model by adopting a machine learning model;
the CEMS measurement lag time identification algorithm flow comprises:
after the concentration of the nitrogen oxide at the inlet is selected to change, the working condition that the CEMS measured value changes is selected as an identification object; the measurement of the concentration of the nitrogen oxides is performed through the heat tracing pipe and the analysis cabinet, and the smoke flows in the heat tracing pipe and the concentration in the analysis cabinet is measured, so that a certain time lag exists;
equally dividing the time window deltat' into two equally spaced time windows deltat i1 ' and Δt i2 ' gradually sliding forward on a time axis, calculating the average difference value of CEMS measured values in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the threshold value is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point;
Based on the working condition change point t i 'and a time window delta t', respectively acquiring a nitrogen oxide concentration value time sequence and a CEMS measurement value time sequence from the beginning of the working condition change to the end of the time window;
gradually advancing the CEMS measurement time sequence, setting a maximum movement step number k, obtaining a new CEMS measurement sequence through advancing, and constructing a CEMS measurement time lag matrix V';
calculating the pearson correlation coefficient r 'of each column in the time sequence and matrix V' of the nitrogen oxide concentration value, wherein the delay time corresponding to the maximum correlation coefficient is the nitrogen oxide concentration measurement lag time t under the working condition 2 ；
The building of the second lag time prediction model using the machine learning model includes:
after the original data characteristics in the power plant denitration system are collected and preprocessed, the original data characteristics are substituted into the CEMS measurement lag time identification algorithm flow to carry out delay identification, and the relationship between the delay time and different operation data characteristics is obtained; the raw data features include at least: boiler load, coal type, coal supply, combustion temperature, air quantity and smoke quantity;
converting the operation data characteristics which are obtained through identification and can cause the concentration change of the nitrogen oxides into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
Carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of each operation data characteristic and the nitrogen oxide concentration value measurement lag time, wherein the higher the correlation coefficient is, the most correlation between the data characteristic and the lag time is shown;
the method comprises the steps of adopting a feature fusion method to fuse the running data features according to the height of a correlation coefficient to form new fusion features, taking the original running data features and the new fusion features as sample data, inputting a training set in the sample data into a machine learning model according to a preset proportion, and establishing a second lag time prediction model under different running data change working conditions; and calculating CEMS measurement lag time according to different operation data characteristics through the second lag time prediction model.
According to the invention, the first lag time prediction model is built for the time delay of determining the existence of the PH value of the absorption tower in the power plant desulfurization system by adopting the variable point detection, the time window sliding, the correlation analysis and the machine learning model, the second lag time prediction model is built for the time delay of determining the existence of the nitrogen oxide concentration of the flue gas at the inlet of the power plant denitration system by using the flue gas online monitoring device CEMS, the lag time existing in the power plant desulfurization and denitration system can be analyzed, calculated and the prediction model is built, and the corresponding lag influence data characteristics and the lag time can be rapidly and effectively obtained.
As shown in fig. 3, the measurement of the concentration of the nitrogen oxide in the denitration system adopts a flue gas online monitoring system (CEMS), and a measurement lag with a certain time length exists in the CEMS measurement process. The CEMS flue gas online monitoring system extracts gas from the flue through a heat pipe extraction sampling mode, and the gas is guided to the pretreatment system through links such as dust removal, heating, heat preservation and the like to remove particulate matters and H 2 O and corrosive gas are treated and finally conveyed to a flue gas analyzer, in the treatment process, the concentration of nitrogen oxides in the flue gas can be measured through a heat tracing pipe and an analysis cabinet, the flow of the flue gas and the concentration in the analysis cabinet are required to be measured for a certain time, so that certain time delay exists in CEMS measurement, the measurement time delay can influence the control of the ammonia injection amount of a subsequent denitration system, the ammonia injection amount cannot be responded in time in the control process, the difficulty of ammonia injection amount control is increased, and the concentration of nitrogen oxides at the outlet of the denitration systemThe degree of fluctuation will also be greater, with greater measurement hysteresis error as the inlet nox concentration changes more rapidly.
It should be noted that, the data with strong and weak correlation in the original data can be found through the analysis and calculation of the data correlation strength, however, the lower correlation coefficient cannot represent that there is no relation between the data characteristic and the output quantity, only the linear correlation degree between the data characteristic and the output quantity is not high, but some nonlinear correlation may exist, and the fusion characteristic related to the output quantity can be studied through the data fusion mode.
The fusion method based on linear regression and multi-layer perceptron algorithm is essentially to construct a basic prediction model y=f (x), and learn the model y=f (x)As a new fusion feature, if the mapping function f (·) is a linear (e.g., linear regression) function, the obtained fusion feature will also be a linear combination of the original features; if the mapping function f (·) is a non-linear (e.g., multi-layer perceptron) function, the resulting fusion feature will be a non-linear combination of the original features.
Besides the feature linear fusion, the nonlinear relation in the original features can be extracted through a multilayer perceptron, and feature data is input into a model to fit the concentration of the nitrogen oxide, so that the nonlinear feature fusion feature F is obtained MLP . Wherein the nodes of the hidden layer are set to 100, the iteration times are set to 200 generations, and the relu function is used as the activation function. For combining features by exponential fusion, the nature is different from the two mapping-fit-based methods described above.
Exponential fusion-based methods are where the original features are combined together in the form of exponentiations to form new fusion features, e.gWherein f 1 ,f 2 ,…f k For the original features to be screened out, a, b, …, m are parameters to be determined for each feature. Acquiring a fused feature space by searching for different parameter combinations in one parameter space . And calculating the correlation coefficient of each index fusion feature and the delay time in the fusion feature space, wherein the feature with the largest correlation coefficient is used as the final fusion feature.
In this embodiment, the machine learning model selects an XGBoost model, which is an integrated learning algorithm using boosting method, and the base learner selects a CART decision tree, and applies k CART functions { f } 1 ,f 2 ,…,f k Adding to form an integrated tree model; the target function of the model consists of a loss function and a regular term, and the loss function approximates by adopting second-order Taylor expansion; performing optimization operation on key parameters to improve the accuracy of model prediction, wherein the key parameters comprise the maximum depth of a tree, subsamples, the number of randomly sampled columns of each tree, the minimum leaf node sample weight and the learning rate;
the construction of the model starts from a root node, training set data are ordered according to each data feature, a greedy method is adopted to calculate the benefit of each feature, the feature with the largest benefit is selected as a splitting feature, the training set data are mapped to corresponding leaf nodes, the generated leaf nodes are recursively subjected to constraint condition until the constraint condition is reached, the decision tree generation process is finished, then the first-order derivative and the second-order derivative of a loss function are used for calculating the weight of the decision tree leaf node, the weight is used as a fitting target of the next tree, the recursion is repeated until the condition is met, and the model establishment is finished.
In this embodiment, after the historical operation parameters of the power plant desulfurization system and the denitration system are collected, the operation parameters which are strongly related to the power plant desulfurization are selected and input into the constructed first support vector machine model to predict the sulfur dioxide concentration in the flue gas at the outlet of the power plant desulfurization system, and specifically includes:
taking the collected historical operation parameters of the power plant desulfurization system as sample data, carrying out correlation analysis on the sample data, removing the sample data with the correlation of the sulfur dioxide concentration in the flue gas at the outlet of the limestone-gypsum wet desulfurization system being smaller than a preset value, and taking the rest sample data as operation data which is strongly correlated with the desulfurization system; the historical operation parameters of the desulfurization system at least comprise sulfur dioxide concentration at an inlet, nitrogen oxide concentration, unit load, limestone slurry circulating pump current, slurry supply quantity, flue gas sulfur dioxide concentration at an outlet of an absorption tower and slurry PH value;
performing data preprocessing on the operation data which is strongly related to the desulfurization system, and constructing a first support vector machine model by utilizing the preprocessed data;
and acquiring real-time operation data related to power plant desulfurization, and inputting the real-time operation data into a constructed first support vector machine model to acquire a predicted value of the concentration of sulfur dioxide in flue gas at the outlet of a power plant desulfurization system.
Wherein the data preprocessing comprises: filling up missing values and abnormal values and normalizing the operation data which are strongly related to the desulfurization system to obtain a preprocessed desulfurization data sequence, wherein the preprocessed desulfurization data sequence is marked as F= [ F ] 1 ,f 2 ,f 3 ,…,f n ]，f i Desulfurizing data of the ith moment point in the processed desulfurizing data sequence;
wavelet threshold denoising is carried out on the desulfurization data sequence F, wavelet decomposition is carried out on noisy data with noise, real data information is obtained, and the real data information is recorded as P= [ P ] 1 ,p 2 ,p 3 ,…,p m ]，p i Is the desulfurization data of the ith moment point in the real desulfurization data sequence.
In this embodiment, the selecting the operation parameter related to the denitration intensity of the power plant is input into the constructed second support vector machine model to predict the concentration of the nitrogen oxides in the flue gas at the inlet of the denitration system of the power plant, and specifically includes:
taking the collected historical operation parameters of the power plant denitration system as sample data, calculating the correlation between the sample data and the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system by adopting a Pearson correlation coefficient, and selecting a data combination with high correlation as operation data which is strongly correlated with the denitration system according to the correlation; the historical operation data of the denitration system at least comprises ammonia injection mass flow, boiler load, SCR inlet flue gas temperature, SCR inlet flue gas oxygen content, SCR inlet nitrogen oxide concentration and SCR denitration efficiency;
Performing data preprocessing on the operation data which is strongly related to the denitration system, and constructing a second support vector machine model by utilizing the preprocessed data;
acquiring real-time operation data related to power plant denitration and inputting the real-time operation data into a constructed second support vector machine model to acquire a flue gas nitrogen oxide concentration predicted value at an inlet of a power plant denitration system;
the data with strong correlation and extremely strong correlation are selected as the data with high correlation with the denitration system, and the calculation formula is as follows:
x is the characteristic of input sample data, Y is the concentration of nitrogen oxides at the inlet, cov (X, Y) represents the covariance of X, Y; sigma (sigma) X Sum sigma Y The standard deviation of X and Y respectively, ρ represents the correlation coefficient between two variables, and the value range is [ -1,1]The method comprises the steps of carrying out a first treatment on the surface of the When ρ is 0.8 or less<At 1, it is called extremely strong correlation; when ρ is 0.6 or less<At 0.8, it is called strong correlation; when ρ is 0.4 or less<0.6, referred to as moderate correlation; when 0.2 is less than or equal to ρ<0.4, called weak correlation; when 0.0 is less than or equal to ρ<At 0.2, it is said to be very weakly correlated or uncorrelated.
It should be noted that, the data preprocessing of the operation data strongly related to the denitration system includes: duplicate data, time-alignment, resampling, missing value padding, outlier substitution processing, and the like are removed.
In this embodiment, the constructing a first support vector machine model and a second support vector machine model includes:
adopting a cuckoo optimization method to determine optimal support vector machine parameters: initializing parameters of a cuckoo optimization algorithm, and searching bird nest positions by step-length self-adaptive dynamic adjustment of Lewy flight according to the parameters of the cuckoo optimization method:i=1, 2, …, n; wherein x is i (t+1) A bird nest position of the ith bird nest in the t generation; a is a step control quantity, which is used for controlling the searching range of the step and obeys the front distribution; l (lambda) is Lewy randomA walk path; the step length self-adaptive dynamic adjustment strategy is as follows:
step i ＝step min +(step max -step min )d i
wherein step i Step for the current search step max Step is the maximum value of step length min Is the minimum value of the step length, n i Is the position of the ith nest, n best D, the bird nest position corresponding to the bird nest is the current minimum fitness max The current minimum fitness corresponds to the maximum value of the distance between the bird nest and other bird nests;
training a support vector machine model by adopting a training set in the preprocessed data, calculating the fitness of each bird nest position, and reserving the bird nest corresponding to the minimum fitness to the next iteration;
judging whether the minimum fitness meets a preset termination condition, if so, determining the bird nest position of the bird nest corresponding to the minimum fitness as the determined optimal support vector machine parameter, and if not, removing a plurality of bird nests with the highest fitness, and readjusting the bird nest position;
Training a support vector machine model according to the determined optimal support vector machine parameters: establishing a support vector machine training program based on a kernel function, forming a mapping relation between an input variable and an output variable through a support vector machine model, performing learning training on training sample data by using the support vector machine training program, and obtaining N support vectors X through learning and training i * I=0, 1, …, N, forming a support vector machine model:
wherein X is i * Support vector representing desulfurization or denitrification system of power plant, Y i Dioxidation representing support vector of desulfurization system of power plantSulfur concentration or nitrogen oxide concentration of support vector of denitration system, alpha i The coefficient representing the ith support vector, X is the input preprocessed desulfurization data or denitration data, Y (X) represents the sulfur dioxide concentration predicted value of the support vector of the desulfurization system of the power plant or the nitrogen oxide concentration predicted value of the support vector of the denitration system, K (·) represents the kernel function of the support vector machine, and the kernel function selects one of a Gaussian function, a polynomial function, a linear function and a radial basis function.
According to the method, after historical operation parameters of a power plant desulfurization system and a denitration system are collected, the operation parameters related to the power plant desulfurization intensity are selected and input into a constructed first support vector machine model to predict the sulfur dioxide concentration in flue gas at the outlet of the power plant desulfurization system, the operation parameters related to the power plant denitration intensity are selected and input into a constructed second support vector machine model to predict the nitrogen oxide concentration in flue gas at the inlet of the power plant denitration system, the sulfur dioxide concentration value in flue gas at the outlet of the desulfurization system can be predicted through the support vector machine model, the nitrogen oxide concentration value at the inlet of the denitration system is predicted, and the accuracy of the predicted value is improved.
In practical application, the correctness of the predicted sulfur dioxide concentration in the flue gas at the outlet and the predicted nitrogen oxide concentration in the flue gas at the inlet are evaluated through the Root Mean Square Error (RMSE) and the average absolute percentage error (MAPE), and the calculation formula is as follows:
wherein y is i Is the actual value of the concentration of sulfur dioxide at the outlet or the concentration of nitrogen oxides in the flue gas at the inlet,to predict the predicted value of sulfur dioxide concentration at the outlet or at the inletThe smaller the RMSE and MAPE values, the more real the predicted value of the sulfur dioxide concentration at the outlet or the predicted value of the nitrogen oxide concentration at the inlet, and the higher the precision.
In this embodiment, the issuing the control parameters of the slurry spraying amount and the ammonia spraying amount to the simulation model of the power plant desulfurization and denitrification system for model verification and intelligent diagnosis includes:
after the slurry spraying quantity control parameter, the ammonia spraying quantity control parameter and the relevant configuration parameters of the operation of the power plant desulfurization and denitrification system are input into the power plant desulfurization and denitrification system simulation model, comparing the acquired real-time operation parameters of the power plant desulfurization and denitrification system with simulation result data of the simulation model through a set expert diagnosis module to obtain deviation, and realizing pre-alarm through whether the deviation exceeds a preset threshold value;
The expert diagnosis module is internally provided with an intelligent diagnosis strategy, and judges the related running state, data deviation and pre-alarm information conditions through preset logic, comprehensively outputs diagnosis preliminary result information, then invokes expert database knowledge information for comparison, analyzes whether conclusion information obtained by the intelligent diagnosis strategy is related to or consistent with the expert database knowledge information, and outputs diagnosis analysis results, running instructions or task sheets; the knowledge information of the expert database comprises stored preset knowledge and information of abnormal faults; the pre-alarm comprises a parameter exceeding a preset threshold value, and time when the parameter exceeds the preset threshold value and abnormal fault information.
According to the invention, the slurry spraying amount of the desulfurization system is controlled according to the sulfur dioxide concentration predicted value in combination with the first lag time predicted model, the ammonia spraying amount of the denitration system is controlled according to the nitrogen oxide concentration predicted value in combination with the second lag time predicted model, the nitrogen oxide concentration of the desulfurization outlet can be effectively controlled in combination with the first lag time, the slurry spraying amount is accurately controlled, the pH value of the slurry is controlled within an effective range, meanwhile, the nitrogen oxide concentration fluctuation of the denitration outlet is reduced in combination with the second lag time, the ammonia spraying amount is accurately controlled, and the ammonia spraying cost of the denitration system is reduced.
According to the invention, the slurry spraying quantity and the control parameters of the ammonia spraying quantity are issued to the simulation model of the desulfurization and denitrification system of the power plant for intelligent diagnosis, expert database knowledge information and an intelligent diagnosis strategy are set in an expert diagnosis module to compare the real-time operation parameters of the system with the simulation data so as to realize alarm and diagnosis, and a diagnosis analysis result, an operation instruction or a task list are output, so that the effective processing and diagnosis analysis of the data of the desulfurization and denitrification system of the power plant are realized.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.
Claims (4)
1. The flue gas desulfurization and denitrification optimization control method based on the hysteresis model is characterized by comprising the following steps of:
step 1: model construction is carried out on all parts of the desulfurization and denitrification of the power plant, a control system is built according to a field control strategy, and a complete simulation model of the desulfurization and denitrification system of the power plant is built;
step 2: a first lag time prediction model is established for the time delay of determining the existence of the PH value of the absorption tower in the power plant desulfurization system, and a second lag time prediction model is established for the time delay of determining the existence of the nitrogen oxide concentration of the flue gas at the inlet of the power plant denitration system through a flue gas online monitoring device CEMS;
step 3: predicting the concentration of sulfur dioxide in flue gas at the outlet of a desulfurization system of a power plant and the concentration of nitrogen oxides in flue gas at the inlet of a denitration system;
step 4: controlling the slurry spraying amount of the desulfurization system according to the sulfur dioxide concentration predicted value and the first lag time predicted model, and controlling the ammonia spraying amount of the denitration system according to the nitrogen oxide concentration predicted value and the second lag time predicted model;
step 5: the control parameters of the slurry spraying quantity and the ammonia spraying quantity are issued to a simulation model of a desulfurization and denitrification system of the power plant for intelligent diagnosis;
in step 2, establishing a first lag time prediction model for determining a time delay existing in the PH value of the absorption tower in the power plant desulfurization system by using a variable point detection, time window sliding, correlation analysis and machine learning model comprises: establishing a slurry PH value response lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a first lag time prediction model by adopting a machine learning model;
The slurry PH response lag time identification algorithm flow comprises:
after the PH value of the slurry in the absorption tower is adjusted, the working condition that the concentration value of sulfur dioxide at the outlet of the absorption tower is changed is selected as an identification object; equally dividing the time window Δt into two equally spaced time windows Δt i1 And Deltat i2 Sliding forward on the time axis gradually, calculating the average difference value of the sulfur dioxide concentration in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the time window is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point; based on the working condition change point t i And a time window delta t, respectively obtaining a slurry PH value time sequence and a sulfur dioxide concentration time sequence from the beginning of the working condition change to the end of the time window;
gradually advancing the sulfur dioxide concentration time sequence, setting a maximum movement step number k, obtaining a new sulfur dioxide concentration sequence through advancing, and constructing a sulfur dioxide concentration time lag matrix V;
calculating the Pelson correlation coefficient r of each column in the slurry PH value time sequence and matrix V, wherein the delay time corresponding to the maximum correlation coefficient is PH value response lag time t under the working condition 1 ；
The building of the first lag time prediction model using the machine learning model includes:
After original data features in a power plant desulfurization system are collected and preprocessed, substituting the original data features into the slurry PH value response lag time identification algorithm flow to carry out PH value delay identification, and acquiring the relation between delay time and different operation data features; the raw data features include at least: the load of the boiler, the air supply quantity of the boiler, the flow rate of limestone slurry, the input quantity of the limestone slurry, the sulfur dioxide content, the calcium carbonate content in the limestone and the distance data characteristic from the absorption tower to the PH measuring point;
converting the operation data characteristics which are obtained through identification and can cause PH value change into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of the operation data characteristics and PH response lag time, wherein the higher the correlation coefficients are, the most correlation between the data characteristics and the lag time is shown;
adopts a characteristic fusion method to fuse the operation data characteristics according to the height of the correlation coefficient to form new fusion characteristics,
Taking the original operation data characteristics and the new fusion characteristics as sample data, and inputting a training set in the sample data into a machine learning model according to a preset proportion to establish a first lag time prediction model under different operation data change working conditions; the PH value response lag time can be calculated according to different operation data characteristics through the first lag time prediction model;
in step 2, establishing a second lag time prediction model for the time delay of determining the existence of the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system through the flue gas online monitoring device CEMS by adopting a variable point detection, time window sliding, correlation analysis and machine learning model comprises the following steps: establishing a CEMS measurement lag time identification algorithm flow by adopting a variable point detection, time window sliding and correlation analysis method and establishing a second lag time prediction model by adopting a machine learning model;
the CEMS measurement lag time identification algorithm flow comprises:
after the concentration of the nitrogen oxide at the inlet is selected to change, the working condition that the CEMS measured value changes is selected as an identification object; the measurement of the concentration of the nitrogen oxides is carried out through the heat tracing pipe and the analysis cabinet, and the smoke flows in the heat tracing pipe and the concentration in the analysis cabinet is measured, so that a certain time lag exists;
Equally dividing the time window Δt' into two equally spaced time windows Δt i1 ' and Deltat i2 ' gradually sliding forward on a time axis, calculating the average difference value of CEMS measured values in two time windows, and if the average difference value exceeds a set threshold value, taking the moment as a working condition change point t i If the threshold value is smaller than the set threshold value, continuing to slide the time window forwards until the working condition change point is detected or the time window slides to the cut-off time point;
based on the working condition change point t i 'and time window Deltat', respectively obtaining a nitrogen oxide concentration value time sequence from the beginning of working condition change to the end of the time window and a CEMS measurement value time sequence;
gradually advancing the CEMS measurement time sequence, setting a maximum movement step number k, obtaining a new CEMS measurement sequence through advancing, and constructing a CEMS measurement time lag matrix V';
calculating the pearson correlation coefficient r 'of each column in the time sequence and matrix V' of the nitrogen oxide concentration value, wherein the delay time corresponding to the maximum correlation coefficient is the nitrogen oxide concentration measurement lag time t under the working condition 2 ；
The building of the second lag time prediction model using the machine learning model includes:
after the original data characteristics in the power plant denitration system are collected and preprocessed, the original data characteristics are substituted into a CEMS measurement lag time identification algorithm flow to carry out delay identification, and the relationship between the delay time and different operation data characteristics is obtained;
The raw data features include at least: boiler load, coal type, coal supply, combustion temperature, air quantity and smoke quantity;
converting the operation data characteristics which are obtained through identification and can cause the concentration change of the nitrogen oxides into characteristics with more working condition characteristics through a characteristic conversion mode, reducing the correlation among the data characteristics, and eliminating the influence caused by dimension through carrying out normalization processing on the converted data characteristics;
carrying out correlation analysis on the original operation data characteristics by adopting a correlation analysis method to obtain correlation coefficients of each operation data characteristic and the nitrogen oxide concentration value measurement lag time, wherein the higher the correlation coefficient is, the most correlation between the data characteristic and the lag time is shown;
the method comprises the steps of adopting a feature fusion method to fuse the running data features according to the height of a correlation coefficient to form new fusion features, taking the original running data features and the new fusion features as sample data, inputting a training set in the sample data into a machine learning model according to a preset proportion, and establishing a second lag time prediction model under different running data change working conditions; calculating CEMS measurement lag time according to different operation data characteristics through a second lag time prediction model;
The machine learning model selects an XGBoost model, is an integrated learning algorithm adopting a boosting method, and a base learner selects a CART decision tree and applies k CART functions { f } 1 ,f 2 ,…f k Adding to form an integrated tree model; the target function of the model consists of a loss function and a regular term, and the loss function approximates by adopting second-order Taylor expansion; performing optimization operation on key parameters to improve the accuracy of model prediction, wherein the key parameters comprise the maximum depth of a tree, subsamples, the number of randomly sampled columns of each tree, the minimum leaf node sample weight and the learning rate;
the construction of the model starts from a root node, training set data are ordered according to each data feature, a greedy method is adopted to calculate the benefit of each feature, the feature with the largest benefit is selected as a splitting feature, the training set data are mapped to corresponding leaf nodes, the generated leaf nodes are recursively subjected to constraint condition until the constraint condition is reached, the decision tree generation process is finished, then the first-order derivative and the second-order derivative of a loss function are used for calculating the weight of the decision tree leaf node, the weight is used as a fitting target of the next tree, the recursion is repeated until the condition is met, and the model establishment is finished;
In step 3, after collecting historical operation parameters of a power plant desulfurization system and a denitration system, selecting operation parameters which are strongly related to power plant desulfurization, inputting the operation parameters into a constructed first support vector machine model to predict the concentration of sulfur dioxide in flue gas at an outlet of the power plant desulfurization system, and specifically comprising the following steps:
taking the collected historical operation parameters of the power plant desulfurization system as sample data, carrying out correlation analysis on the sample data, removing the sample data with the correlation of the sulfur dioxide concentration in the flue gas at the outlet of the limestone-gypsum wet desulfurization system being smaller than a preset value, and taking the rest sample data as operation data which is strongly correlated with the desulfurization system; the historical operating parameters of the desulfurization system at least comprise sulfur dioxide concentration at an inlet, nitrogen oxide concentration, unit load, limestone slurry circulating pump current, slurry supply quantity, flue gas sulfur dioxide concentration at an outlet of an absorption tower and slurry PH value;
performing data preprocessing on the operation data which is strongly related to the desulfurization system, and constructing a first support vector machine model by utilizing the preprocessed data;
collecting real-time operation data related to power plant desulfurization, and inputting the real-time operation data into a constructed first support vector machine model to obtain a predicted value of the concentration of sulfur dioxide in flue gas at the outlet of a power plant desulfurization system;
Wherein the data preprocessing comprises: filling up missing values and abnormal values and normalizing the operation data which are strongly related to the desulfurization system to obtain a preprocessed desulfurization data sequence, wherein the preprocessed desulfurization data sequence is marked as F= [ F ] 1 ,f 2 ,f 3 ,…,f n ]，f i Desulfurizing data of the ith moment point in the processed desulfurizing data sequence;
wavelet threshold denoising is carried out on the desulfurization data sequence F, wavelet decomposition is carried out on noisy data with noise, real data information is obtained, and the real data information is recorded as P= [ P ] 1 ,p 2 ,p 3 ,…,p m ]，p i The desulfurization data of the ith moment point in the real desulfurization data sequence;
in step 3, selecting an operation parameter related to the denitration intensity of the power plant, inputting the operation parameter to a constructed second support vector machine model, and predicting the concentration of the nitrogen oxides in the flue gas at the inlet of the denitration system of the power plant, wherein the method specifically comprises the following steps:
taking the collected historical operation parameters of the power plant denitration system as sample data, calculating the correlation between the sample data and the concentration of the nitrogen oxides in the flue gas at the inlet of the power plant denitration system by adopting a Pearson correlation coefficient, and selecting a data combination with high correlation as operation data which is strongly correlated with the denitration system according to the correlation; the denitration system historical operation data at least comprises ammonia injection mass flow, boiler load, SCR inlet flue gas temperature, SCR inlet flue gas oxygen content, SCR inlet nitrogen oxide concentration and SCR denitration efficiency;
Performing data preprocessing on operation data which are strongly related to the denitration system, and constructing a second support vector machine model by utilizing the preprocessed data;
acquiring real-time operation data related to power plant denitration and inputting the real-time operation data into a constructed second support vector machine model to acquire a flue gas nitrogen oxide concentration predicted value at an inlet of a power plant denitration system;
the data with strong correlation and extremely strong correlation are selected as the data with high correlation with the denitration system, and the calculation formula is as follows:
x is the characteristic of input sample data, Y is the concentration of nitrogen oxides at the inlet, cov (X, Y) represents the covariance of X, Y; sigma (sigma) X Sum sigma Y The standard deviation of X and Y respectively, ρ represents the correlation coefficient between two variables, and the value range is [ -1,1]The method comprises the steps of carrying out a first treatment on the surface of the When ρ is 0.8 or less<At 1, it is called extremely strong correlation; when ρ is 0.6 or less<At 0.8, it is called strong correlation; when ρ is 0.4 or less<0.6, referred to as moderate correlation; when 0.2 is less than or equal to ρ<0.4, called weak correlation; when 0.0 is less than or equal to ρ<0.2, is referred to as very weakly correlated or uncorrelated; constructing a first support vector machine model and a second support vector machine model, comprising: adopting a cuckoo optimization method to determine optimal support vector machine parameters: initializing parameters of a cuckoo optimization algorithm, and searching bird nest positions by step-length self-adaptive dynamic adjustment of Lewy flight according to the parameters of the cuckoo optimization method: x is x i (t+1) ＝x i (t) +a⊕L(λ)，i＝1,2,…,n；
Wherein x is i (t+1) A bird nest position of the ith bird nest in the t generation; a is a step control quantity, which is used for controlling the searching range of the step and obeys the front distribution; l (lambda) is a Lewy random walk; the step length self-adaptive dynamic adjustment strategy is as follows:
step i ＝step min +(step max -step min )d i ；
wherein step i Step for the current search step max Step is the maximum value of step length min Is the minimum value of the step length, n i Is the position of the ith nest, n best D, the bird nest position corresponding to the bird nest is the current minimum fitness max The current minimum fitness corresponds to the maximum value of the distance between the bird nest and other bird nests;
training a support vector machine model by adopting a training set in the preprocessed data, calculating the fitness of each bird nest position, and reserving the bird nest corresponding to the minimum fitness to the next iteration;
judging whether the minimum fitness meets a preset termination condition, if so, determining the bird nest position of the bird nest corresponding to the minimum fitness as the determined optimal support vector machine parameter, and if not, removing a plurality of bird nests with the highest fitness, and readjusting the bird nest position;
training a support vector machine model according to the determined optimal support vector machine parameters: establishing a support vector machine training program based on a kernel function, forming a mapping relation between an input variable and an output variable through a support vector machine model, performing learning training on training sample data by using the support vector machine training program, and obtaining N support vectors X through learning and training i * I=0, 1, …, N, forming a support vector machine model:
wherein X is i * Support vector representing desulfurization or denitrification system of power plant, Y i Sulfur dioxide concentration representing power plant desulfurization system support vector or nitrogen oxide concentration representing denitration system support vector, alpha i The coefficient representing the ith support vector, X is the input preprocessed desulfurization data or denitration data, Y (X) represents the sulfur dioxide concentration predicted value of the support vector of the desulfurization system of the power plant or the nitrogen oxide concentration predicted value of the support vector of the denitration system, K (·) represents the kernel function of the support vector machine, and the kernel function selects one of a Gaussian function, a polynomial function, a linear function and a radial basis function.
2. The method for optimizing control over desulfurization and denitrification of flue gas based on a hysteresis model according to claim 1, wherein in step 1, after the model construction is carried out on each component of desulfurization and denitrification of a power plant according to a modularized modeling method by dynamic simulation software, a corresponding control system is built according to a field control strategy, and a complete simulation model of the desulfurization and denitrification system of the power plant is built, which comprises the following steps: the power plant desulfurization system is a limestone-gypsum wet desulfurization system, and at least comprises a flue gas system, an absorption tower system, a limestone slurry preparation system, a gypsum slurry dehydration system, a wastewater treatment system and an electrical system; the power plant denitration system selects an SCR method flue gas denitration system and at least comprises a flue gas system, an SCR reactor system, a sound wave soot blowing system and a liquid ammonia storage and supply system; the dynamic simulation software selects and connects corresponding component modules from a model library according to mass conservation, momentum conservation and energy conservation equations and the technological process of a limestone-gypsum wet desulfurization system and an SCR flue gas denitration system in the modeling process, and inputs initial data to complete the model construction of the power plant desulfurization and denitration system; and constructing an analog quantity control system, a sequence control system and a logic control system according to a field control strategy, configuring by adopting a basic algorithm module, realizing the same function as an actual control system, and establishing a complete simulation model of the desulfurization and denitrification system of the power plant.
3. The hysteresis model-based flue gas desulfurization and denitrification optimization control method according to claim 2, wherein the simulation model of the power plant desulfurization and denitrification system further comprises: in the process of model development and debugging, physical data acquired by an actual power plant desulfurization and denitrification system and virtual data acquired based on a power plant desulfurization and denitrification simulation model are compared, whether errors exceed a threshold value is judged, if so, virtual data with larger errors are classified through cluster learning, corresponding historical data are combined as input, error learning is carried out through a neural network, correction coefficients are output to correct the error data of the virtual data, and virtual-real fusion is carried out on the corrected virtual data and the physical data to generate a verified power plant desulfurization and denitrification simulation model.
4. The method for optimizing control over flue gas desulfurization and denitrification based on hysteresis model according to claim 1, wherein the step 5 comprises the following steps: after the slurry spraying quantity control parameter, the ammonia spraying quantity control parameter and the relevant configuration parameters of the operation of the power plant desulfurization and denitrification system are input into the power plant desulfurization and denitrification system simulation model, comparing the acquired real-time operation parameters of the power plant desulfurization and denitrification system with simulation result data of the simulation model through a set expert diagnosis module to obtain deviation, and realizing pre-alarm through whether the deviation exceeds a preset threshold value; the expert diagnosis module is internally provided with an intelligent diagnosis strategy, and is used for judging the related running state, data deviation and pre-alarm information conditions through preset logic, comprehensively outputting diagnosis preliminary result information, then calling expert database knowledge information for comparison, analyzing whether conclusion information obtained by the intelligent diagnosis strategy is related to or consistent with the expert database knowledge information, and outputting diagnosis analysis results, running instructions or task sheets; the knowledge information of the expert database comprises stored preset knowledge and information of abnormal faults; the pre-alarm comprises a parameter exceeding a preset threshold value, and time when the parameter exceeds the preset threshold value and abnormal fault information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111483083.0A CN114225662B (en) | 2021-12-07 | 2021-12-07 | Hysteresis model-based flue gas desulfurization and denitrification optimal control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111483083.0A CN114225662B (en) | 2021-12-07 | 2021-12-07 | Hysteresis model-based flue gas desulfurization and denitrification optimal control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114225662A CN114225662A (en) | 2022-03-25 |
| CN114225662B true CN114225662B (en) | 2024-02-13 |
Family
ID=80753603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111483083.0A Active CN114225662B (en) | 2021-12-07 | 2021-12-07 | Hysteresis model-based flue gas desulfurization and denitrification optimal control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114225662B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708924B (en) * | 2022-03-28 | 2024-06-18 | 大唐环境产业集团股份有限公司 | Model construction method and device for predicting soot blower soot blowing interval time in SCR system |
| CN115146833B (en) * | 2022-06-14 | 2024-07-19 | 北京全应科技有限公司 | Prediction method for generation concentration of nitrogen oxides of boiler |
| CN115828757B (en) * | 2022-12-12 | 2024-02-23 | 福建中锐汉鼎数字科技有限公司 | Flood discharge hysteresis characteristic structure and selection method for drainage basin water level prediction |
| CN117190173B (en) * | 2023-09-25 | 2024-03-29 | 天津大学 | Optimal control method and control system for flue gas recirculation and boiler coupling system |
| CN117273497B (en) * | 2023-11-20 | 2024-02-09 | 一夫科技股份有限公司 | Production optimization method and system for high-strength gypsum |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565274A (en) * | 2012-01-17 | 2012-07-11 | 广东电网公司电力科学研究院 | Modifying method for catalyst activity in power plant SCR (selective catalytic reduction) denitration system |
| CN106000041A (en) * | 2016-05-30 | 2016-10-12 | 安徽工业大学 | Ammonia process desulfurization spraying tower system and method for determining SO2 absorption mass transfer coefficient |
| CN108636094A (en) * | 2018-07-12 | 2018-10-12 | 浙江大学 | A kind of accurate PREDICTIVE CONTROL in wet desulfurizing process and energy conserving system and method |
| CN108803309A (en) * | 2018-07-02 | 2018-11-13 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and model adaptation |
| CN111589301A (en) * | 2020-05-29 | 2020-08-28 | 广东电科院能源技术有限责任公司 | Method, device, equipment and storage medium for predicting SCR denitration performance of coal-fired power plant |
| CN112206640A (en) * | 2020-09-16 | 2021-01-12 | 西安热工研究院有限公司 | Limestone slurry pH value concentration fly-up detection system, method, control system and desulfurization system |
| CN112580250A (en) * | 2020-11-12 | 2021-03-30 | 山东纳鑫电力科技有限公司 | Thermal power generating unit denitration system based on deep learning and optimization control method |
| CN112892209A (en) * | 2021-01-25 | 2021-06-04 | 山东戈尔环境科技有限公司 | Ammonia spraying control system |
| CN113082954A (en) * | 2021-04-07 | 2021-07-09 | 浙江大学 | Whole-process intelligent operation regulation and control system of wet desulphurization device |
| WO2021208396A1 (en) * | 2020-04-13 | 2021-10-21 | 西安热工研究院有限公司 | Efficient double-inlet channel rotational flow atomization desulfurization nozzle |
-
2021
- 2021-12-07 CN CN202111483083.0A patent/CN114225662B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565274A (en) * | 2012-01-17 | 2012-07-11 | 广东电网公司电力科学研究院 | Modifying method for catalyst activity in power plant SCR (selective catalytic reduction) denitration system |
| CN106000041A (en) * | 2016-05-30 | 2016-10-12 | 安徽工业大学 | Ammonia process desulfurization spraying tower system and method for determining SO2 absorption mass transfer coefficient |
| CN108803309A (en) * | 2018-07-02 | 2018-11-13 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and model adaptation |
| CN108636094A (en) * | 2018-07-12 | 2018-10-12 | 浙江大学 | A kind of accurate PREDICTIVE CONTROL in wet desulfurizing process and energy conserving system and method |
| WO2021208396A1 (en) * | 2020-04-13 | 2021-10-21 | 西安热工研究院有限公司 | Efficient double-inlet channel rotational flow atomization desulfurization nozzle |
| CN111589301A (en) * | 2020-05-29 | 2020-08-28 | 广东电科院能源技术有限责任公司 | Method, device, equipment and storage medium for predicting SCR denitration performance of coal-fired power plant |
| CN112206640A (en) * | 2020-09-16 | 2021-01-12 | 西安热工研究院有限公司 | Limestone slurry pH value concentration fly-up detection system, method, control system and desulfurization system |
| CN112580250A (en) * | 2020-11-12 | 2021-03-30 | 山东纳鑫电力科技有限公司 | Thermal power generating unit denitration system based on deep learning and optimization control method |
| CN112892209A (en) * | 2021-01-25 | 2021-06-04 | 山东戈尔环境科技有限公司 | Ammonia spraying control system |
| CN113082954A (en) * | 2021-04-07 | 2021-07-09 | 浙江大学 | Whole-process intelligent operation regulation and control system of wet desulphurization device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114225662A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114225662B (en) | Hysteresis model-based flue gas desulfurization and denitrification optimal control method | |
| CN114191953B (en) | Flue gas desulfurization and denitrification control method based on convolutional neural network and XGBoost | |
| Wang et al. | A hybrid NOx emission prediction model based on CEEMDAN and AM-LSTM | |
| CN108549792B (en) | Soft measurement method for dioxin emission concentration in solid waste incineration process based on latent structure mapping algorithm | |
| CN113433911B (en) | Accurate control system and method for ammonia spraying of denitration device based on accurate concentration prediction | |
| CN107168065A (en) | A kind of control method and system for selective catalytic reduction denitration device | |
| CN102693451A (en) | Method for predicting ammonia process flue gas desulphurization efficiency based on multiple parameters | |
| CN109190848A (en) | A kind of SCR system NO based on Time-delay PredictionxConcentration of emission prediction technique | |
| CN112613237B (en) | CFB unit NOx emission concentration prediction method based on LSTM | |
| CN110716512A (en) | Environmental protection equipment performance prediction method based on coal-fired power plant operation data | |
| CN112742187A (en) | Method and device for controlling pH value in desulfurization system | |
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN112364562B (en) | Flue gas environment-friendly island cooperative control method and system | |
| Liu et al. | Operation strategy optimization of desulfurization system based on data mining | |
| CN113440990A (en) | EMD-LSTM based outlet SO2Concentration prediction method | |
| CN112365065B (en) | WFGD self-adaptive online optimization scheduling method | |
| WO2024130992A1 (en) | Online soft measurement method for dioxin (dxn) emission concentration during mswi process | |
| JP7273202B2 (en) | Method and system for performance optimization of flue gas desulfurization (FGD) units | |
| CN111589301A (en) | Method, device, equipment and storage medium for predicting SCR denitration performance of coal-fired power plant | |
| CN114330845A (en) | MSWI process dioxin emission prediction method based on multi-window concept drift detection | |
| CN117829342A (en) | Coal-fired power plant nitrogen oxide emission prediction method based on improved random forest algorithm | |
| CN109933884B (en) | Neural network inverse control method for SCR denitration system of coal-fired unit | |
| Xu et al. | Prediction method of dioxin emission concentration based on PCA and deep forest regression | |
| CN116312869A (en) | Method, device and system for predicting nitrogen oxides in catalytic cracking regenerated flue gas | |
| CN113204189B (en) | Desulfurization system control model, establishment method thereof and desulfurization system control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |