CN112530530A - Method for calculating limestone slurry density optimal value algorithm model based on Matlab software - Google Patents
Method for calculating limestone slurry density optimal value algorithm model based on Matlab software Download PDFInfo
- Publication number
- CN112530530A CN112530530A CN202011483203.2A CN202011483203A CN112530530A CN 112530530 A CN112530530 A CN 112530530A CN 202011483203 A CN202011483203 A CN 202011483203A CN 112530530 A CN112530530 A CN 112530530A
- Authority
- CN
- China
- Prior art keywords
- limestone slurry
- optimal value
- density
- data
- algorithm model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002002 slurry Substances 0.000 title claims abstract description 83
- 235000019738 Limestone Nutrition 0.000 title claims abstract description 82
- 239000006028 limestone Substances 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 29
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims abstract description 32
- 239000003546 flue gas Substances 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 28
- 230000001105 regulatory effect Effects 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 24
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000000227 grinding Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 10
- 239000000706 filtrate Substances 0.000 description 4
- 239000010440 gypsum Substances 0.000 description 4
- 229910052602 gypsum Inorganic materials 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004537 pulping Methods 0.000 description 2
- 238000001238 wet grinding Methods 0.000 description 2
- 238000003916 acid precipitation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000006477 desulfuration reaction Methods 0.000 description 1
- 230000023556 desulfurization Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009837 dry grinding Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000003134 recirculating effect Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2251/00—Reactants
- B01D2251/40—Alkaline earth metal or magnesium compounds
- B01D2251/404—Alkaline earth metal or magnesium compounds of calcium
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2251/00—Reactants
- B01D2251/60—Inorganic bases or salts
- B01D2251/602—Oxides
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- General Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Feedback Control In General (AREA)
- Treating Waste Gases (AREA)
Abstract
A method for calculating a limestone slurry density optimal value algorithm model based on Matlab software is characterized by comprising the following steps: the method comprises the following steps: the method comprises the following steps: collecting historical data: leading out raw flue gas SO from DCS system2Historical data of concentration, unit load, raw flue gas flow, pH value and net flue gas flow, wherein the sampling time interval is 1s, and abnormal data are removed; step two: training a model to obtain an optimal value algorithm model; step three: embedding a DCS system: the DCS calculates the density of limestone slurry corresponding to the optimal value algorithm model at the moment according to the calculated density; step four: regulating deviceDensity of whole limestone slurry: and introducing the actually measured density of the limestone slurry into a DCS (distributed control system), and adjusting the density of the limestone slurry. According to the scheme, the optimal value ranges of the density of the limestone slurry under different working conditions are found, the density of the limestone slurry is automatically configured according to the optimal value, SO that the density of the limestone slurry is close to or reaches the optimal value range, and therefore when the operation working conditions are suddenly changed, the purpose of guaranteeing the clean flue gas SO is achieved2The concentration is not over standard.
Description
Technical Field
The invention belongs to the technical field of wet desulphurization, and particularly relates to a method for calculating a limestone slurry density optimal value algorithm model based on Matlab software.
Background
With the rapid development of global economy and the continuous promotion of industrialization, the emission of sulfur dioxide in the atmosphere is increased day by day, so that the pH value of precipitation is reduced, and acid rain is formed in local places, thereby bringing great influence on human health and atmospheric environment. In order to reduce the emission of sulfur dioxide in the air, improve the air quality and prevent the further deterioration of the environment, a flue gas desulfurization device must be installed in a coal-fired power plant. . Therefore, environmental protection equipment is vigorously developed, and the cleaning of the ecological environment is also an important task. At present, limestone/gypsum wet desulphurization is the most widely used in coal-fired power plants.
At present, there are three main methods for preparing limestone slurry by wet desulphurization, which are: purchasing limestone powder, and directly adding water for pulping; purchasing limestone, preparing slurry and purchasing limestone by using a wet ball mill, preparing powder by using a dry ball mill, and adding water to prepare slurry.
The purchased limestone powder is high in price, the investment of a dry grinding system is large, the power consumption is high, and compared with the wet grinding system, the investment of the wet grinding system is small, the cost is low, and the main stream position of the configuration of the desulfurized limestone slurry of the thermal power plant is occupied.
When the system is operated, in order to control the limestone amount required by the operation of the device, the variable-frequency weighing belt feeder is adopted to control the limestone amount entering the wet ball mill, the amount of filtered water entering the mill is controlled by a flow control valve on a water supplementing pipeline at the inlet of the mill according to the amount of limestone entering the mill, the milled slurry automatically flows to a slurry recirculation box of the mill from the outlet of the mill, meanwhile, gypsum filtrate water is pumped into a limestone slurry recirculation tank through a filtering water pit pump to dilute limestone slurry, the flow rate of the filtrate water entering the limestone slurry recirculation tank is controlled through an electric regulating valve, and then is sent into a limestone cyclone through a grinding machine limestone slurry recirculation pump (1 transport 1 spare), and after the overflow slurry of the cyclone meets the requirements of system output and fineness, and the limestone slurry enters a limestone slurry tank, and the underflow slurry returns to the feeding hole of the mill to participate in the regrinding of the wet mill. Under abnormal working conditions, the underflow and the overflow of the cyclone station return to the mill recirculating slurry tank. The qualified slurry which is stored in the limestone slurry tank and meets the requirement of slurry density is sent into a limestone slurry supply adjusting system of the absorption tower through a limestone slurry pump to finish the adjustment of the PH of the slurry in the absorption tower.
The method comprises the steps of pulping by a wet ball mill, wherein the proportion of limestone and water is generally fixed, gypsum filtrate water is pumped into a mill recirculation tank by a prepared limestone slurry through a filtering water pit pump to be diluted, then the gypsum filtrate water is pumped into a limestone slurry tank by a limestone slurry recirculation pump, a flow regulating door is arranged on a pipeline from the filtered water to the mill recirculation tank, the flow regulating door is only used for regulating the flow according to the liquid level of the recirculation tank, if the density of the limestone slurry is changed, manual intervention is needed, the concentration of SO2 at an original flue gas inlet, the load of a machine set, the flow of the original flue gas and the like are sharply increased, the supply flow of the limestone slurry reaches a designed value, and under the condition that the concentration of clean flue gas SO2 is continuously increased and cannot be controlled, the concentration time of the clean flue gas SO2 is controlled in a mode of increasing the density of the limestone.
Disclosure of Invention
The purpose of the invention is to provideA method for calculating an optimal value algorithm model of limestone slurry density based on Matlab software aims to solve the problem of clean flue gas SO caused by low limestone slurry density in the prior art2The technical problem of exceeding standard.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for calculating a limestone slurry density optimal value algorithm model based on Matlab software is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: collecting historical data: leading out raw flue gas SO from DCS system2Historical data of concentration, unit load, raw flue gas flow, pH value and net flue gas flow, wherein the sampling time interval is 1s, and abnormal data are removed;
step two: model training: training by taking a BP neural network model of Matlab software as a practical model to obtain a model example, predicting and comparing actual operation conditions by using the model example, repeatedly training and verifying by changing model parameters until the error between the model example and the actual operation conditions is within an allowable range, and obtaining an optimal value algorithm model;
step three: embedding a DCS system: obtaining the authority of the DCS system from a manufacturer, embedding an optimal value algorithm model into the DCS system, and according to the original SO of the flue gas at a certain moment2The density of limestone slurry corresponding to the moment of the optimal value algorithm model is calculated by a DCS (distributed control System) according to the concentration, the unit load, the flow rate of raw flue gas, the pH value and the flow rate of clean flue gas;
step four: adjusting the density of limestone slurry: and (3) introducing the actually measured limestone slurry density into a DCS (distributed control system), adjusting the opening of a filtering water adjusting valve of a recirculation tank of the grinding machine by utilizing a PID (proportion integration differentiation) according to the deviation between the calculated value and the actually measured value of the optimal value algorithm model by the DCS, controlling the filtering water flow of the recirculation tank, adjusting the density of the limestone slurry, and finally enabling the error between the actually measured density value and the formula calculated value to be within an allowable range.
Further preferably, the second step specifically includes the following steps:
step 1, importing historical data: selecting data to be modeled from DCS historical data, exporting the data to be in a csv format, and uploading the exported data to matlab software;
step 2, software operation: selecting separators, import ranges and str types according to requirements, and then selecting a matrix mode;
step 3, data preprocessing: the neural network uses each column as a sample, each row is a single variable, so that the imported data needs to be transposed, and the following commands are input into a command line window to transpose the data for input and output:
command: data = Assaydatabulian2';
taking 2 to 14 lines as input x, automatically outputting a target variable y, and inputting the following commands in a command line window to select the input data x:
command: x _ raw = data (2: 14:): y _ raw = data (1:);
step 4, normalizing the input data x and the target variable y:
inputting the following commands in a command line window, and normalizing input data x and a target variable y:
command: [ x, inputps ] = mapminmax (x _ raw);
[y,outputps]=mapminmax(y_raw);
the normalized calculation method comprises the following steps: 2 x (x-xmin)/(xmax-xmin) + (-1), xman expressing maximum data for x, xmin expressing minimum data for x;
step 5, training and establishing a neural network model by using the y value: clicking an Import button to generate an input export window, selecting x as input data, importing a target variable y, automatically training a y value by software, and simultaneously creating a neural network model;
and 6, performing inverse normalization processing on the target variable y: after the calculation of the neural network model, the target variable y of the output data needs to be subjected to inverse normalization, so that the following commands are input in a command line window by matching the actual output of the system, and the target variable y is subjected to inverse normalization:
command y _ pre = mapminmax ('reverse', y _ tem, outputps);
and y _ pre is the limestone slurry optimal value algorithm model.
Further, the step 5 further comprises the following steps: and (4) training and checking results of the neural network, judging whether the training result is close to an ideal effect according to whether the actual calculation result of the solid line in the training result is close to the prediction result of the dotted line in the graph, and retraining until the ideal effect is achieved if the included angle between the actual calculation result of the solid line and the prediction result of the dotted line in the graph is greater than 10 degrees.
In addition, the DCS system in the fourth step is provided with three density deviation indicator lamps of green, yellow and red, wherein,
green indicates deviation of. + -. 10kg/m3Internal;
yellow indicates a deviation of. + -. 15kg/m3；
Red means deviation at. + -. 20kg/m3。
More preferably, when the green indicator light is on: the limestone slurry tank works normally;
when the yellow indicator light is on: PID automatically adjusts the opening of a filtering water adjusting valve of a recirculation tank of the grinding machine, and automatically matches limestone slurry until a green indicator lamp is on;
when the red indicator light is on: the opening degree of a water filtering regulating valve of a recirculation tank of the PID regulating mill can automatically proportion limestone slurry within a short time without reaching a green deviation range, and manual proportion is carried out until a green indicator lamp is on through manual intervention.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
the invention can be used for preparing the limestone slurry according to the original SO of the flue gas2The concentration, the unit load, the raw flue gas flow and the net flue gas flow change, the automatic configuration of the slurry density is realized, the manual intervention is reduced, the pH of the slurry of the absorption tower is ensured to meet the operation under the condition of sudden change of the operation working condition, and the phenomenon that the environmental protection parameters exceed the standard due to the low density of the limestone slurry can be effectively reduced. Meanwhile, DCS sets three warning colors of green, yellow and red, and the personnel on the operation monitoring disc can directly judge the deviation between the calculated value of the limestone slurry density formula and the measured value, so that the operation monitoring disc is clear at a glance and is convenient for adjusting the operation working condition in time. Compared with the prior art, the scheme finds out the optimal value range of the density of the limestone slurry under different working conditions, realizes the automatic configuration of the density of the limestone slurry according to the optimal value, and enables the density of the limestone slurry to approach or reach the optimal value range, thereby achieving the purpose of runningWhen the working condition changes suddenly, the clean flue gas SO is ensured2The concentration does not exceed the standard, has good popularization and practical value, and can generate good economic benefit after wide popularization and application.
Drawings
Fig. 1 is a diagram illustrating the training result of the neural network according to the present invention.
Detailed Description
In order to make the technical means, innovative features, objectives and functions realized by the present invention easy to understand, the present invention is further described below.
The examples described herein are specific embodiments of the present invention, are intended to be illustrative and exemplary in nature, and are not to be construed as limiting the scope of the invention. In addition to the embodiments described herein, those skilled in the art will be able to employ other technical solutions which are obvious based on the disclosure of the claims and the specification of the present application, and these technical solutions include technical solutions which make any obvious replacement or modification for the embodiments described herein.
A method for calculating a limestone slurry density optimal value algorithm model based on Matlab software is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: collecting historical data: leading out raw flue gas SO from DCS system2Historical data of concentration, unit load, raw flue gas flow, pH value and net flue gas flow, wherein the sampling time interval is 1s, and abnormal data are removed;
step two: model training: training by taking a BP neural network model of Matlab software as a practical model to obtain a model example, predicting and comparing actual operation conditions by using the model example, repeatedly training and verifying by changing model parameters until the error between the model example and the actual operation conditions is within an allowable range, and obtaining an optimal value algorithm model;
the method specifically comprises the following steps:
step 1, importing historical data: selecting data to be modeled from DCS historical data, exporting the data to be in a csv format, and uploading the exported data to matlab software;
step 2, software operation: selecting separators, import ranges and str types according to requirements, and then selecting a matrix mode;
step 3, data preprocessing: the neural network uses each column as a sample, each row is a single variable, so that the imported data needs to be transposed, and the following commands are input into a command line window to transpose the data for input and output:
command: data = Assaydatabulian2';
taking 2 to 14 lines as input x, automatically outputting a target variable y, and inputting the following commands in a command line window to select the input data x:
command: x _ raw = data (2: 14:): y _ raw = data (1:);
step 4, normalizing the input data x and the target variable y:
inputting the following commands in a command line window, and normalizing input data x and a target variable y:
command: [ x, inputps ] = mapminmax (x _ raw);
[y,outputps]=mapminmax(y_raw);
the normalized calculation method comprises the following steps: 2 x (x-xmin)/(xmax-xmin) + (-1), xman expressing maximum data for x, xmin expressing minimum data for x;
step 5, training and establishing a neural network model by using the y value: clicking an Import button, generating an input export window, selecting x as input data, importing a target variable y, automatically training a y value by software, simultaneously creating a neural network model, training the neural network and checking the result, judging whether the training result is close to an ideal effect according to whether the actual calculation result of a solid line in the training result is close to the prediction result of a dotted line in the graph, if the included angle between the actual calculation result of the solid line and the prediction result of the dotted line in the training result is greater than 10 degrees, performing nonlinear fitting on the neural network by utilizing matlab software, and determining a model example through repeated training and verification until the ideal effect is achieved.
And 6, performing inverse normalization processing on the target variable y: after the calculation of the neural network model, the target variable y of the output data needs to be subjected to inverse normalization, so that the following commands are input in a command line window by matching the actual output of the system, and the target variable y is subjected to inverse normalization:
command y _ pre = mapminmax ('reverse', y _ tem, outputps);
and y _ pre is the limestone slurry optimal value algorithm model.
Step three: embedding a DCS system: obtaining the authority of the DCS system from a manufacturer, embedding an optimal value algorithm model into the DCS system, and according to the original SO of the flue gas at a certain moment2The density of limestone slurry corresponding to the moment of the optimal value algorithm model is calculated by a DCS (distributed control System) according to the concentration, the unit load, the flow rate of raw flue gas, the pH value and the flow rate of clean flue gas;
step four: adjusting the density of limestone slurry: and (3) introducing the actually measured density of the limestone slurry into a DCS, and adjusting the opening of a filter water adjusting valve of a recirculation tank of the grinding machine by utilizing a PID (proportion integration differentiation) according to the deviation between the calculated value and the actually measured value of the optimal value algorithm model by the DCS, controlling the flow rate of the filter water of the recirculation tank, and adjusting the density of the limestone slurry to finally achieve the purpose that the error between the actually measured value of the density and the calculated value of a formula is within an allowable.
Wherein, the DCS system is provided with three density deviation indicator lights of green, yellow and red, wherein,
green indicates deviation of. + -. 10kg/m3Internal;
yellow indicates a deviation of. + -. 15kg/m3；
Red means deviation at. + -. 20kg/m3。
When the green indicating lamp is on: the limestone slurry tank works normally;
when the yellow indicator light is on: PID automatically adjusts the opening of a filtering water adjusting valve of a recirculation tank of the grinding machine, and automatically matches limestone slurry until a green indicator lamp is on;
when the red indicator light is on: the opening degree of a water filtering regulating valve of a recirculation tank of the PID regulating mill can automatically proportion limestone slurry within a short time without reaching a green deviation range, and manual proportion is carried out until a green indicator lamp is on through manual intervention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for calculating a limestone slurry density optimal value algorithm model based on Matlab software is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: collecting historical data;
step two: training a model;
step three: embedding a DCS system;
step four: adjusting the density of limestone slurry: and adjusting the density of the limestone slurry to finally achieve the error between the measured density value and the calculated value of the formula within an allowable range.
2. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 1, wherein: the first step specifically comprises: leading out raw flue gas SO from DCS system2And (3) historical data of concentration, unit load, raw flue gas flow, pH value and net flue gas flow, wherein the sampling time interval is 1s, and abnormal data are removed.
3. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 1, wherein: the second step specifically comprises: training by taking a BP neural network model of Matlab software as a practical model to obtain a model example, predicting and comparing actual operation conditions by using the model example, repeatedly training and verifying by changing model parameters until the error between the model example and the actual operation conditions is within an allowable range, and obtaining an optimal value algorithm model.
4. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 1, wherein: the third step specifically comprises: obtaining the authority of the DCS system from a manufacturer, embedding an optimal value algorithm model into the DCS system, and according to the original SO of the flue gas at a certain moment2Concentration, unit load, raw flue gas flow, pH value and net flue gas flow, and the DCS system calculates an optimal value algorithm model at the momentAnd marking the corresponding density of limestone slurry.
5. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 1, wherein: the fourth step specifically comprises: and (3) introducing the actually measured limestone slurry density into a DCS, and regulating the opening of a filter water regulating valve of a recirculation tank of the grinding machine by utilizing PID according to the deviation between the calculated value and the actually measured value of the optimal value algorithm model by the DCS, so as to control the flow of the filter water of the recirculation tank.
6. The method for calculating the optimal value algorithm model of the density of the limestone slurry based on the Matlab software as claimed in claim 1, wherein the second step specifically comprises the following steps:
step 1, importing historical data: selecting data to be modeled from DCS historical data, exporting the data to be in a csv format, and uploading the exported data to matlab software;
step 2, software operation: selecting separators, import ranges and str types according to requirements, and then selecting a matrix mode;
step 3, data preprocessing: the neural network uses each column as a sample, each row is a single variable, so that the imported data needs to be transposed, and the following commands are input into a command line window to transpose the data for input and output:
command: data = Assaydatabulian2';
taking 2 to 14 lines as input x, automatically outputting a target variable y, and inputting the following commands in a command line window to select the input data x:
command: x _ raw = data (2: 14:): y _ raw = data (1:);
step 4, normalizing the input data x and the target variable y:
inputting the following commands in a command line window, and normalizing input data x and a target variable y:
command: [ x, inputps ] = mapminmax (x _ raw);
[y,outputps]=mapminmax(y_raw);
the normalized calculation method comprises the following steps: 2 x (x-xmin)/(xmax-xmin) + (-1), xman expressing maximum data for x, xmin expressing minimum data for x;
step 5, training and establishing a neural network model by using the y value: clicking an Import button to generate an input export window, selecting x as input data, importing a target variable y, automatically training a y value by software, and simultaneously creating a neural network model;
and 6, performing inverse normalization processing on the target variable y: after the calculation of the neural network model, the target variable y of the output data needs to be subjected to inverse normalization, so that the following commands are input in a command line window by matching the actual output of the system, and the target variable y is subjected to inverse normalization:
command y _ pre = mapminmax ('reverse', y _ tem, outputps);
and y _ pre is the limestone slurry optimal value algorithm model.
7. The method for calculating the optimal value algorithm model for limestone slurry density based on Matlab software as claimed in claim 6, wherein said step 5 further comprises the steps of: and (4) training the neural network and checking results, and judging whether the training result is close to an ideal effect according to whether the actual calculation result of the solid line in the training result is close to the prediction result of the dotted line in the graph.
8. The method for calculating the optimal value algorithm model for the density of the limestone slurry based on the Matlab software as claimed in claim 7, wherein if the included angle between the two is greater than 10 degrees, the method is retrained until the ideal effect is achieved.
9. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 1, wherein: the DCS system in the fourth step is provided with three density deviation indicator lamps of green, yellow and red, wherein,
green indicates deviation of. + -. 10kg/m3Internal;
yellow indicates a deviation of. + -. 15kg/m3；
Red for biasThe difference is +/-20 kg/m3。
10. The method for calculating the optimal value algorithm model of limestone slurry density based on Matlab software as claimed in claim 4, wherein:
when the green indicating lamp is on: the limestone slurry tank works normally;
when the yellow indicator light is on: PID automatically adjusts the opening of a filtering water adjusting valve of a recirculation tank of the grinding machine, and automatically matches limestone slurry until a green indicator lamp is on;
when the red indicator light is on: the opening degree of a water filtering regulating valve of a recirculation tank of the PID regulating mill can automatically proportion limestone slurry within a short time without reaching a green deviation range, and manual proportion is carried out until a green indicator lamp is on through manual intervention.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020108726341 | 2020-08-26 | ||
| CN202010872634.1A CN112102901A (en) | 2020-08-26 | 2020-08-26 | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112530530A true CN112530530A (en) | 2021-03-19 |
Family
ID=73756761
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010872634.1A Withdrawn CN112102901A (en) | 2020-08-26 | 2020-08-26 | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software |
| CN202011483203.2A Pending CN112530530A (en) | 2020-08-26 | 2020-12-16 | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010872634.1A Withdrawn CN112102901A (en) | 2020-08-26 | 2020-08-26 | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112102901A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113941233A (en) * | 2021-10-19 | 2022-01-18 | 国能神福(石狮)发电有限公司 | Desulfurization control method and device |
| CN116440670A (en) * | 2023-04-12 | 2023-07-18 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113946144A (en) * | 2021-09-18 | 2022-01-18 | 国能龙源环保有限公司 | Optimal control system and control method for gypsum dehydration |
| CN114488775B (en) * | 2021-12-23 | 2024-02-06 | 东北大学 | Control method and device for pulping process of suspension roasting product |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0919623A (en) * | 1995-07-07 | 1997-01-21 | Babcock Hitachi Kk | Wet type waste gas desulfurizing method and device therefor |
| JPH1176749A (en) * | 1997-09-03 | 1999-03-23 | Mitsubishi Heavy Ind Ltd | Exhaust gas desulfurizer and exhaust gas desulfurization method |
| CN105700579A (en) * | 2016-01-26 | 2016-06-22 | 国网山东省电力公司青岛供电公司 | A PH value prediction method and apparatus for a desulphurization solution in a desulphurization system |
| CN107203687A (en) * | 2017-04-17 | 2017-09-26 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | Absorption tower sweetening process multiple target cooperative intelligent optimal control method |
| CN109343367A (en) * | 2018-10-26 | 2019-02-15 | 齐鲁工业大学 | A method of based on network response surface flue gas desulfurization |
| CN109420424A (en) * | 2017-08-22 | 2019-03-05 | 邢台国泰发电有限责任公司 | A kind of wet desulfurization of flue gas by limestone-gypsum method energy saving of system optimization method |
| CN111229010A (en) * | 2020-01-19 | 2020-06-05 | 福建龙净环保股份有限公司 | Opening control system and opening control method of slurry supply regulating valve |
-
2020
- 2020-08-26 CN CN202010872634.1A patent/CN112102901A/en not_active Withdrawn
- 2020-12-16 CN CN202011483203.2A patent/CN112530530A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0919623A (en) * | 1995-07-07 | 1997-01-21 | Babcock Hitachi Kk | Wet type waste gas desulfurizing method and device therefor |
| JPH1176749A (en) * | 1997-09-03 | 1999-03-23 | Mitsubishi Heavy Ind Ltd | Exhaust gas desulfurizer and exhaust gas desulfurization method |
| CN105700579A (en) * | 2016-01-26 | 2016-06-22 | 国网山东省电力公司青岛供电公司 | A PH value prediction method and apparatus for a desulphurization solution in a desulphurization system |
| CN107203687A (en) * | 2017-04-17 | 2017-09-26 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | Absorption tower sweetening process multiple target cooperative intelligent optimal control method |
| CN109420424A (en) * | 2017-08-22 | 2019-03-05 | 邢台国泰发电有限责任公司 | A kind of wet desulfurization of flue gas by limestone-gypsum method energy saving of system optimization method |
| CN109343367A (en) * | 2018-10-26 | 2019-02-15 | 齐鲁工业大学 | A method of based on network response surface flue gas desulfurization |
| CN111229010A (en) * | 2020-01-19 | 2020-06-05 | 福建龙净环保股份有限公司 | Opening control system and opening control method of slurry supply regulating valve |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113941233A (en) * | 2021-10-19 | 2022-01-18 | 国能神福(石狮)发电有限公司 | Desulfurization control method and device |
| CN116440670A (en) * | 2023-04-12 | 2023-07-18 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
| CN116440670B (en) * | 2023-04-12 | 2023-10-31 | 华能伊春热电有限公司 | Limestone slurry density stability control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112102901A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112530530A (en) | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software | |
| CN111340199B (en) | Material balance and deep learning-based energy-saving method for desulfurization system | |
| CN103028480A (en) | Intelligent control system for vertical mill based on fuzzy PID (proportion integration differentiation) algorithm | |
| CN104656441A (en) | Natural gas purification process modeling optimization method based on unscented kalman neural network | |
| CN115309117B (en) | WFGD export SO based on data drive2Concentration prediction and intelligent optimization method | |
| WO2022062339A1 (en) | System and method for controlling air valve of variable air volume cabin unit | |
| CN109847916A (en) | A kind of energy conservation optimizing method of cement raw material vertical mill system | |
| CN105749729A (en) | Ammonification system based on automatic-adjusted pH value | |
| CN107991885A (en) | A kind of coal-burning power plant's denitration spray ammonia autocontrol method and system | |
| CN111675325A (en) | Intelligent anaerobic reactor system and wastewater treatment detection method | |
| CN114510098B (en) | Production environment regulation and control method and system | |
| CN110302888A (en) | Cement mill Optimization of Energy Saving system | |
| CN111408243B (en) | Wet desulfurization pH value control system and method for thermal power generating unit | |
| CN104386727B (en) | A kind of nano-calcium carbonate carburizing reagent device | |
| CN201811207U (en) | High temperature corrosion state diagnosing and preventing system for water wall of boiler | |
| CN116440670B (en) | Limestone slurry density stability control method | |
| CN115193232B (en) | Ca in desulfurization slurry 2+ Method for controlling oxidation state of slurry on line by concentration and pH | |
| CN111841259A (en) | Control system and method for cyclic absorption process of ammonia water absorption tower | |
| CN109813850B (en) | Pretreatment device and pretreatment method for automatic control analyzer | |
| CN208087639U (en) | A kind of syrup stove drying neutralized system detecting feedback automatically with intensity of sulfitation | |
| CN113253618B (en) | Intelligent management and control system for all-dimensional sintering process | |
| CN205650071U (en) | Automatically regulated adds ammonia system based on pH value | |
| CN112947616B (en) | Intelligent constraint control method for pH value of wet desulphurization based on trend prejudgment | |
| CN115487589A (en) | Automatic filtration control management system for water plant filter tank | |
| CN111450694B (en) | Desulfurization system industrial controller based on multi-objective optimization and 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 | ||
| CB02 | Change of applicant information |
Address after: 100039 room 901, 9 / F, building 1, yard 16, West Fourth Ring Middle Road, Haidian District, Beijing Applicant after: Guoneng Longyuan environmental protection Co.,Ltd. Address before: 100039 room 911, 1 building, 16 West Fourth Ring Road, Haidian District, Beijing. Applicant before: BEIJING GUODIAN LONGYUAN ENVIRONMENTAL ENGINEERING Co.,Ltd. |
|
| CB02 | Change of applicant information |