CN111893791A - Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm - Google Patents
Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm Download PDFInfo
- Publication number
- CN111893791A CN111893791A CN202010689269.0A CN202010689269A CN111893791A CN 111893791 A CN111893791 A CN 111893791A CN 202010689269 A CN202010689269 A CN 202010689269A CN 111893791 A CN111893791 A CN 111893791A
- Authority
- CN
- China
- Prior art keywords
- paper
- drying
- temperature
- paper sheet
- air
- 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
- 238000001035 drying Methods 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 33
- 238000004088 simulation Methods 0.000 claims abstract description 79
- 238000005457 optimization Methods 0.000 claims abstract description 35
- 238000005265 energy consumption Methods 0.000 claims abstract description 27
- 238000012937 correction Methods 0.000 claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 16
- 239000000126 substance Substances 0.000 claims description 15
- 238000012546 transfer Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000001704 evaporation Methods 0.000 claims description 3
- 230000008020 evaporation Effects 0.000 claims description 3
- 239000000835 fiber Substances 0.000 claims description 3
- 238000003825 pressing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000001179 sorption measurement Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- D—TEXTILES; PAPER
- D21—PAPER-MAKING; PRODUCTION OF CELLULOSE
- D21F—PAPER-MAKING MACHINES; METHODS OF PRODUCING PAPER THEREON
- D21F5/00—Dryer section of machines for making continuous webs of paper
Landscapes
- Paper (AREA)
Abstract
The invention discloses an intelligent algorithm-based operation optimization method for a drying part of a domestic paper making machine, which comprises the following steps of: s1: establishing a mechanism simulation model of a paper drying process of the household paper based on a paper drying mechanism; s2: establishing a drying process simulation error correction model based on an SVR algorithm; s3: checking the simulation precision of the paper sheet drying process simulation model to the key variable of the drying process; s4: establishing an operation optimization model of a drying part of a domestic paper making machine based on an SLQP algorithm; s5: optimizing historical operating parameters of a drying part of the paper machine by using an optimization model; the problems that key parameters of the household paper drying process cannot be accurately measured and drying energy consumption is large are solved.
Description
Technical Field
The invention relates to the field of operation optimization of a drying part of a paper machine for domestic paper, in particular to an intelligent algorithm-based operation optimization method of the drying part of the paper machine for domestic paper.
Background
Dewatering is the most important part of the papermaking process. In order to achieve the required strength and quality standard, the dryness of the finished household paper is usually controlled to be 92-95%. In the papermaking dewatering link, heating and drying are the most energy-consuming part, and the energy consumption accounts for about 70% of the total energy consumption in the papermaking production process. Therefore, the key point of reducing the energy consumption of the drying part is to reduce the energy consumption and the production cost of the whole papermaking process. In the actual production process, correct adjustment of the operating parameters of the drying section has a great influence on the energy consumption in the paper sheet drying process, but a scientific and reasonable optimization method of the operating parameters of the drying section depends on accurate measurement of key variables in the drying process. Because the structural design of the drying part is very compact, and the inside of the drying part is a high-temperature and high-humidity environment, the existing household paper making machine control system does not accurately measure key process parameters which are most concerned by process personnel such as paper dryness, air supply humidity, air exhaust humidity and the like. Therefore, in actual production, an operator can only control and optimize the operation parameters of the drying part by depending on experience and feedback of product quality inspection results, and the drying part usually does not operate under the optimal working condition due to the lack of scientific calculation as guidance, so that the energy consumption of the paper drying process and the production cost of enterprises are increased. In addition, the new process and the new equipment for drying the household paper enterprise have low iteration speed, so that the process of saving energy and reducing consumption in the paper sheet drying process is slow.
Establishing a paper sheet drying process simulation model and an energy consumption optimization model can realize accurate measurement of key process parameters in the drying process and reduce energy consumption in the drying process on the premise of avoiding high-cost technology or equipment modification. However, the existing drying process models are modeled based on a paper sheet drying mechanism, the simulation precision is poor, and the result given by the optimized model is further unreliable. The problem of large energy consumption in the drying process cannot be effectively solved. The method for optimizing the operation of the drying part of the domestic paper papermaking machine based on the intelligent algorithm can effectively solve the problems of low simulation precision of key parameters in the drying process and high drying energy consumption.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an intelligent algorithm-based method for optimizing the operation of the drying part of the domestic paper machine, and solves the problems of low simulation precision of key variables and high drying energy consumption in the domestic paper drying process.
The invention adopts the technical scheme that the method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm comprises the following steps:
s1: establishing a mechanism simulation model of a paper drying process of the household paper based on a paper drying mechanism;
s2: establishing a drying process simulation error correction model based on an SVR algorithm;
s3: checking the simulation precision of the paper sheet drying process simulation model to the key variable of the drying process;
s4: establishing an operation optimization model of a drying part of a domestic paper making machine based on an SLQP algorithm;
s5: and optimizing historical operating parameters of the drying part of the paper machine by using an optimization model.
Preferably, S1 includes the following sub-steps:
s11: a temperature and humidity model of the paper sheet drying process is established according to the heat and mass transfer mechanism of the paper sheet drying process, and the calculation method of the moisture content change rate of the paper sheet is as follows:
the method for calculating the paper sheet temperature change rate is as follows:
wherein X is the sheet moisture content, i.e. the mass of water carried by the oven dried fibres per mass; t is the temperature of the paper sheet; l is a paper sheet drying distance, namely the distance which the paper sheet passes along the circumferential direction of the cylinder body; kmIs the convective mass transfer coefficient between the paper sheet and the hot air of the air hood; g is the absolute dry gram weight of the paper sheet; v is the linear speed of the drying cylinder, namely the running speed of the paper machine; pSIs the mass fraction of water vapor in the air on the surface of the paper sheet; pAThe mass fraction of the water vapor in the hot air is; pTThe total pressure of hot air is adopted; h isSPIs the overall heat transfer coefficient from the steam in the cylinder to the sheet; t isSIs the temperature of the steam in the drying cylinder; h isAPThe convection heat transfer coefficient between the paper and the hot air is adopted; t isAThe temperature is the temperature of hot air; hOSensible heat for water evaporation in the paper sheet; hsHeat of adsorption for moisture in the sheet;CFis the specific heat of the fiber; cWIs the specific heat of water; r is an ideal gas constant; mWIs the molar mass of water;
s12: the dryness of the paper sheet when the paper sheet is scraped off the drying cylinder by the scraper is the paper forming dryness, and the calculation method comprises the following steps:
wherein, DryoutExpressing the paper dryness; xoutIndicating the moisture content of the sheet as it is scraped off the dryer;
s13: the method for calculating the energy consumption of the drying cylinder comprises the following steps:
wherein the content of the first and second substances,
is the energy consumption of the drying cylinder in unit time; l is the total distance that the paper sheet passes along the circumferential direction of the drying cylinder; h isSCThe total heat transfer coefficient from the steam in the drying cylinder to the surface of the cylinder body; t iscThe surface temperature of the cylinder body; w is the width of the paper sheet;
the heat transferred to the paper sheet at the pressing position by the drying cylinder in unit time;
heat loss of the drying cylinder in unit time;
s14: the energy consumption of the gas hood heater is calculated as follows:
wherein the content of the first and second substances,
the energy consumption of the heater in unit time is;
the flow rate of hot air is adopted; Δ HHChanging the enthalpy of hot air; xHThe humidity of hot air; t ishSupplying air temperature to the air hood; t isEIs ambient temperature;
heat loss of the hood heater per unit time;
s15: deriving production data for different periods of time from the energy management system, the production data including: drying cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHAir hood dry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE；
S16: inputting the production data into a mechanism simulation model, and simulating to obtain the exhaust air humidity X of each group of production dataOAir exhaust temperature T of air hoodODrying section high pressure steam flow FHWith the low pressure steam flow F of the drying sectionLDry with the sheetout；
S17: and calculating a mechanism simulation error, wherein a simulation error calculation formula is as follows:
wherein, ytIn the form of an actual value of the value,
are analog values.
Preferably, S2 includes the following sub-steps:
s21, in order to eliminate the difference of each variable on dimension and improve the operation efficiency of the algorithm, the production data and the mechanism simulation error data obtained in the step S1 are standardized, and the standardization processing formula is as follows:
wherein X is an independent variable, X ═ X1,…xp]n×pY is a dependent variable, Y ═ Y1,…yq]n×qWhere i is 1,2, …, n is the number of samples, j is 1,2, …, p is the dimension of the sample, xjIs the mean value of the samples in the j dimension, xijIs the j-dimensional value of the ith sample,
for the j-dimensional normalized value of the i-th sample, SjIs the standard deviation of the sample in the j dimension, Sj 2The variance in the j dimension for the sample;
s23, introducing relaxation variables based on the principle of minimizing structural risk
And
and introducing a lagrange multiplier alphai，
ηi，
Obtaining a model of a support vector machine, wherein the model of the support vector machine is as follows:
where ω is a weight coefficient and x is an input variable [ x ]1,…xp]n×pB is an offset term, αi，
Is Lagrange multiplier, K (x)i,xj) Is a kernel function;
s24, the kernel function can map linear indivisible low-dimensional feature data to a high-dimensional space, and convert a nonlinear problem into a linear problem, and the common kernel function comprises: linear kernel function Linear, polynomial kernel function Poly, radial basis kernel function RBF and sigmoid kernel function;
the radial basis kernel function RBF is adopted, and the formula is shown as the following formula:
K(xi,x)＝exp(-γ‖xi-x‖2),γ>0
where γ is a kernel function parameter.
Preferably, S3 includes the following sub-steps:
s31, integrating the paper sheet drying process mechanism simulation model and the drying process simulation error correction model into a paper sheet drying process simulation model; the paper sheet drying process mechanism simulation model can perform mechanism simulation on key variables according to input production data; the drying process simulation error correction model can predict mechanism simulation errors under the current production data. The output calculation formula of the paper sheet drying process simulation model is as follows:
wherein the content of the first and second substances,
is the final analog value of the key variable,
is a mechanism simulation value of a key variable,
mechanism simulation error as a key variable;
s32, using the average relative error to measure the simulation effect of the simulation model of the paper drying process on the key variables, wherein the calculation formula is as follows:
where n is the total number of test set samples.
Preferably, S4 includes the following sub-steps:
s41, selecting the drying cylinder pressure P according to the selection of the decision variables and the principle of easy acquisition and controllableCWet side supply air temperature TWHDry side supply air temperature TDHWith exhaust frequency fEAs a decision variable of the energy consumption optimization model, the feasible domain of the decision variable is set according to the limits of the drying cylinder, the air hood heater and the exhaust fan device as follows:
pmin≤PC≤pmax
T1min≤TWH≤T1max
T2min≤TDH≤T2max
fmin≤fE≤fmax
s42, the constraint condition is the constraint of the system state variable, and the constraint condition of the operation optimization method of the drying part of the domestic paper making machine mainly comprises the following two aspects:
s421: restricting the dryness of paper; the main function of the dryer section is to evaporate water from the sheet and dry the wet sheet, usually with certain requirements on the dryness of the sheet leaving the dryer section:
Dryout≥Drysta
wherein, DryoutRepresenting the dryness of the paper sheet in the out-of-dryer section, from a paper sheet drying process simulation model, DrystaExpressing the standard dryness of finished paper;
the dew point constraint, in actual production, in order to prevent the air hood from dripping, the exhaust air temperature must be controlled above the dew point, because the temperature distribution of the air and the air hood shell is not uniform, in order to prevent the local temperature from being lower than the dew point, the exhaust air temperature must be controlled at a higher value, and forms a certain difference with the dew point temperature, according to the practical experience, when the difference is above 20 ℃, no dripping is formed in the air hood:
TO≥TDP+20
POV＝PT·RHO
wherein, TDPIs the dew point temperature, POVFor partial pressure of exhaust steam, RHORelative humidity of the exhaust air. All are obtained by a paper sheet drying process simulation model;
s43, the ton paper drying cost is taken as an objective function, and the calculation method is shown as the following formula:
min Cost＝(UH×FH+UL×FL+UE×PE)/(v*G*W*CR)
wherein Cost is the Cost of paper per ton; u shapeH、ULAnd UERespectively representing a high-pressure steam unit price, a low-pressure steam unit price and an electric unit price; fH、FLAnd PERespectively representing the high-pressure steam flow, the low-pressure steam flow and the electric power of an exhaust fan;
s44, solving the optimization problem of S41-S43 by using a sequence least square programming method,
the calculation formula of the least square programming method is as follows:
wherein the content of the first and second substances,
x representing an objective functionkJacobi matrix of (1), HkRepresenting the objective function at XkHessian matrix of (A), XkThe iterative form of (a) is shown as follows:
h in the solution processkThe iterative form of (a) is shown as follows:
wherein the content of the first and second substances,
ΔXk＝Xk+1-Xk
preferably, S5 includes the following sub-steps:
s51: inputting drying section production data, including cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHAir hood dry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE；
S52: optimizing the historical operating parameters of the drying part of the paper machine by using an optimization model, namely solving the cylinder pressure P when Cost is minimumCWet side air supply temperature TWHDry side air supply temperature TDHWith exhaust frequency fEAnd the constraint condition is satisfied.
The method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm has the following beneficial effects:
1. the paper sheet drying process simulation model can realize accurate simulation of key parameters of the drying process under various operation parameter combinations.
2. The operation optimization model of the drying part of the paper machine for the household paper can be used for solving according to the current production conditions to obtain the global optimal solution of the drying cylinder pressure, the air supply temperature at the dry-wet side and the air exhaust frequency, so that the drying cost of the household paper is effectively reduced.
Drawings
FIG. 1 is a flow chart of the method for optimizing the operation of the drying section of the domestic paper making machine based on an intelligent algorithm.
FIG. 2 is a comparison graph of an actual high-pressure steam flow value and a simulated high-pressure steam flow value of the method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm.
FIG. 3 is a comparison graph of the actual low-pressure steam flow value and the simulated low-pressure steam flow value of the method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm.
FIG. 4 is a comparison graph of the actual air exhaust temperature value and the simulated air exhaust temperature value of the method for optimizing the operation of the drying part of the domestic paper machine based on the intelligent algorithm.
FIG. 5 is a comparison graph of the actual exhaust air humidity value and the simulated exhaust air humidity value of the method for optimizing the operation of the drying section of the domestic paper machine based on the intelligent algorithm.
Fig. 6 is a graph comparing the dry cost of paper before and after the optimization of the method for optimizing the operation of the dry part of the domestic paper machine based on the intelligent algorithm.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in FIG. 1, the method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm comprises the following modeling steps:
s1: establishing a mechanism simulation model of a paper drying process of the household paper based on a paper drying mechanism;
s2: establishing a drying process simulation error correction model based on an SVR algorithm;
s3: checking the simulation precision of the paper sheet drying process simulation model to the key variable of the drying process;
s4: establishing an operation optimization model of a drying part of a domestic paper making machine based on an SLQP algorithm;
s5: and optimizing historical operating parameters of the drying part of the paper machine by using an optimization model.
Firstly, establishing a mechanism simulation model of a paper sheet drying process of the household paper:
establishing a temperature and humidity model in the paper sheet drying process according to the heat and mass transfer mechanism in the paper sheet drying process,
the method for calculating the moisture content change rate of the paper sheet is as follows:
the method for calculating the paper sheet temperature change rate comprises the following steps:
wherein X is the sheet moisture content, i.e. the mass of water carried by the oven dried fibres per mass; t is the temperature of the paper sheet; l is a paper sheet drying distance, namely the distance which the paper sheet passes along the circumferential direction of the cylinder body; kmIs the convective mass transfer coefficient between the paper sheet and the hot air of the air hood; g is the absolute dry gram weight of the paper sheet; v is the linear speed of the drying cylinder, namely the running speed of the paper machine; pSIs the mass fraction of water vapor in the air on the surface of the paper sheet; pAThe mass fraction of the water vapor in the hot air is; pTThe total pressure of hot air is adopted; h isSPIs the overall heat transfer coefficient from the steam in the cylinder to the sheet; t isSIs the temperature of the steam in the drying cylinder; h isAPThe convection heat transfer coefficient between the paper and the hot air is adopted; t isAThe temperature is the temperature of hot air; hOSensible heat for water evaporation in the paper sheet; hsHeat of adsorption for moisture in the sheet; cFIs the specific heat of the fiber; cWIs the specific heat of water; r is an ideal gas constant; mWIs the molar mass of water.
The dryness of the paper sheet when the paper sheet is scraped off the drying cylinder by the scraper is the paper forming dryness, and the calculation method comprises the following steps:
wherein, DryoutExpressing the paper dryness; xoutIndicating the moisture content of the sheet as it is scraped off the dryer;
the method for calculating the energy consumption of the drying cylinder comprises the following steps:
wherein the content of the first and second substances,
is the energy consumption of the drying cylinder in unit time; l is the total distance that the paper sheet passes along the circumferential direction of the drying cylinder; h isSCThe total heat transfer coefficient from the steam in the drying cylinder to the surface of the cylinder body; t iscThe surface temperature of the cylinder body; w is the width of the paper sheet;
the heat transferred to the paper sheet at the pressing position by the drying cylinder in unit time;
heat loss of the drying cylinder in unit time;
the energy consumption of the gas hood heater is calculated as follows:
wherein the content of the first and second substances,
the energy consumption of the heater in unit time is;
the flow rate of hot air is adopted; Δ HHChanging the enthalpy of hot air; xHThe humidity of hot air; t ishSupplying air temperature to the air hood; t isEIs ambient temperature;
is the heat loss per unit time of the hood heater.
After the establishment of the mechanism simulation model of the paper drying process of the household paper is finished, the production data of different time periods are derived from the energy management system, and the method comprises the following steps: drying cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHAir hood dry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE. Inputting the data into a mechanism simulation model, and simulating to obtain the exhaust humidity X of the air hood of each group of production dataOAir exhaust temperature T of air hoodODrying section high pressure steam flow FHWith the low pressure steam flow F of the drying sectionLDry with the sheetout。
And calculating a mechanism simulation error by the following method:
wherein, ytIn the form of an actual value of the value,
are analog values.
Then, establishing a drying process simulation error correction model:
in order to eliminate the difference of each variable in dimension and improve the operation efficiency of the algorithm, the production data obtained in S1 and the mechanism simulation error data need to be normalized, and the normalization processing formula is as follows:
wherein X is an independent variable, X ═ X1,…xp]n×pY is a dependent variable, Y ═ Y1,…yq]n×qI is 1,2, …, n is the number of samples, j is 1,2, …, and p is the dimension of the samples. x is the number ofjIs the mean value of the samples in the j dimension, xijIs the j-dimensional value of the ith sample,
for the j-dimensional normalized value of the i-th sample, SjIs the standard deviation of the sample in the j dimension. Sj 2Is the variance of the sample in the j dimension.
Introducing relaxation variables based on the principle of minimizing structural risk
And
and introducing a lagrange multiplier alphai，
ηi，
And obtaining a model of the support vector machine. As shown in the following formula:
where ω is a weight coefficient and x is an input variable [ x ]1,…xp]n×pB is an offset term, αi，
Is Lagrange multiplier, K (x)i,xj) Is a kernel function.
The kernel function can map linearly indivisible low-dimensional feature data to a high-dimensional space, and convert a nonlinear problem into a linear problem. Common kernels are the Linear kernel (Linear), the polynomial kernel (Poly), the radial basis kernel (RBF) and the sigmoid kernel. The invention adopts the RBF with the most extensive application, and the formula is shown as follows:
K(xi,x)＝exp(-γ‖xi-x‖2),γ>0
where γ is a kernel function parameter.
And integrating the paper sheet drying process mechanism simulation model and the drying process simulation error correction model into a paper sheet drying process simulation model. The paper sheet drying process mechanism simulation model can perform mechanism simulation on key variables according to input production data; the drying process simulation error correction model can predict mechanism simulation errors under the current production data. The output of the sheet drying process simulation model is shown below:
wherein the content of the first and second substances,
is the final analog value of the key variable,
is a mechanism simulation value of a key variable,
is a mechanism simulation error of a key variable.
The Mean Relative Error (MRE) was used to measure the simulation effect of the sheet drying process simulation model on the key variables, and the formula was as follows:
where n is the total number of test set samples.
After the paper sheet drying process simulation model is verified, establishing a domestic paper machine drying part operation optimization model:
selecting the drying cylinder pressure P according to the principle that the selection of the decision variables follows easy acquisition and can be controlledCWet side supply air temperature TWHDry side supply air temperature TDHWith exhaust frequency fEAs a decision variable of the energy consumption optimization model. The feasible domain of decision variables set according to the limits of the drying cylinder, the gas hood heater and the exhaust fan device is as follows:
pmin≤PC≤pmax
T1min≤TWH≤T1max
T2min≤TDH≤T2max
fmin≤fE≤fmax
the constraint is a constraint on a system state variable. The constraint conditions of the operation optimization method of the drying part of the domestic paper making machine mainly comprise the following two aspects:
(1) and (5) restricting the dryness of the paper sheet. The main function of the dryer section is to evaporate water from the sheet and dry the wet sheet, usually with certain requirements on the dryness of the sheet leaving the dryer section:
Dryout≥Drysta
wherein, DryoutRepresenting the dryness of the paper sheet in the out-of-dryer section, from a paper sheet drying process simulation model, DrystaExpressed as the standard dryness of the paper.
(2) And (4) dew point restraint. In actual production, in order to prevent the air hood from dripping, the temperature of the exhaust air must be controlled to be above the dew point. Because the temperature distribution of the air and the air hood shell is not uniform, in order to prevent the local temperature from being lower than the dew point, the exhaust air temperature must be controlled to be a higher value, and a certain difference is formed between the exhaust air temperature and the dew point temperature. According to practical experience, this difference does not form drops of water in the hood above 20 ℃:
TO≥TDP+20
POV＝PT·RHO
wherein, TDPIs the dew point temperature, POVFor partial pressure of exhaust steam, RHORelative humidity of the exhaust air. All derived from a paper drying process simulation model.
The invention takes the drying cost of paper per ton as an objective function, and the calculation method is shown as the following formula:
min Cost＝(UH×FH+UL×FL+UE×PE)/(v*G*W*CR)
wherein Cost is the Cost of paper per ton; u shapeH、ULAnd UERespectively represent the unit price of high-pressure steam,Low-pressure steam unit price and electric unit price; fH、FLAnd PERespectively representing the high-pressure steam flow, the low-pressure steam flow and the electric power of the exhaust fan.
After the establishment of the operation optimization model of the drying part of the domestic paper machine is finished, the model is solved by using a Sequential Least square Programming (SLQP). The slslslqp algorithm is a method for converting a nonlinear programming problem into a simple quadratic programming problem to solve, and is shown in the following formula:
wherein the content of the first and second substances,
x representing an objective functionkJacobi matrix of (1), HkRepresenting the objective function at XkThe Hessian matrix of (c). XkThe iterative form of (a) is shown as follows:
the iteration form in the solving process is shown as the following formula:
wherein the content of the first and second substances,
ΔXk＝Xk+1-Xk
and finally, optimizing the historical operating parameters of the drying part of the paper machine by using an optimization model:
inputting drying section production data, including cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHGas coverDry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE. Optimizing the historical operating parameters of the drying part of the paper machine by using an optimization model, namely solving the cylinder pressure P when Cost is minimumCWet side air supply temperature TWHDry side air supply temperature TDHWith exhaust frequency fEWhile satisfying the constraints.
When the method is implemented, FIG. 2 is a comparison graph of an actual high-pressure steam flow value and a simulated high-pressure steam flow value after the method is applied; FIG. 3 is a graph comparing an actual low pressure steam flow value with a simulated low pressure steam flow value using the present invention; FIG. 4 is a graph comparing actual exhaust air temperature values with simulated exhaust air temperature values after the present invention is applied; FIG. 5 is a graph comparing actual exhaust air humidity values with simulated exhaust air humidity values using the present invention; figure 6 is a graph comparing the dry cost per ton of paper before and after optimization using the present invention.
Claims (6)
1. The method for optimizing the operation of the drying part of the domestic paper making machine based on the intelligent algorithm is characterized by comprising the following steps of:
s1: establishing a mechanism simulation model of a paper drying process of the household paper based on a paper drying mechanism;
s2: establishing a drying process simulation error correction model based on an SVR algorithm;
s3: checking the simulation precision of the paper sheet drying process simulation model to the key variable of the drying process;
s4: establishing an operation optimization model of a drying part of a domestic paper making machine based on an SLQP algorithm;
s5: and optimizing historical operating parameters of the drying part of the paper machine by using an optimization model.
2. An intelligent algorithm based optimization method for the dryer section of a domestic paper machine according to claim 1, characterized in that said S1 comprises the following sub-steps:
s11: a temperature and humidity model of the paper sheet drying process is established according to the heat and mass transfer mechanism of the paper sheet drying process, and the calculation method of the moisture content change rate of the paper sheet is as follows:
the method for calculating the paper sheet temperature change rate is as follows:
wherein X is the sheet moisture content, i.e. the mass of water carried by the oven dried fibres per mass; t is the temperature of the paper sheet; l is a paper sheet drying distance, namely the distance which the paper sheet passes along the circumferential direction of the cylinder body; kmIs the convective mass transfer coefficient between the paper sheet and the hot air of the air hood; g is the absolute dry gram weight of the paper sheet; v is the linear speed of the drying cylinder, namely the running speed of the paper machine; pSIs the mass fraction of water vapor in the air on the surface of the paper sheet; pAThe mass fraction of the water vapor in the hot air is; pTThe total pressure of hot air is adopted; h isSPIs the overall heat transfer coefficient from the steam in the cylinder to the sheet; t isSIs the temperature of the steam in the drying cylinder; h isAPThe convection heat transfer coefficient between the paper and the hot air is adopted; t isAThe temperature is the temperature of hot air; hOSensible heat for water evaporation in the paper sheet; hSHeat of adsorption for moisture in the sheet; cFIs the specific heat of the fiber; cWIs the specific heat of water; r is an ideal gas constant; mWIs the molar mass of water;
s12: the dryness of the paper sheet when the paper sheet is scraped off the drying cylinder by the scraper is the paper forming dryness, and the calculation method comprises the following steps:
wherein, DryoutExpressing the paper dryness; xoutIndicating the moisture content of the sheet as it is scraped off the dryer;
s13: the method for calculating the energy consumption of the drying cylinder comprises the following steps:
wherein the content of the first and second substances,
is the energy consumption of the drying cylinder in unit time; l is the total distance that the paper sheet passes along the circumferential direction of the drying cylinder; h isSCThe total heat transfer coefficient from the steam in the drying cylinder to the surface of the cylinder body; t isCThe surface temperature of the cylinder body; w is the width of the paper sheet;
the heat transferred to the paper sheet at the pressing position by the drying cylinder in unit time;
heat loss of the drying cylinder in unit time;
s14: the energy consumption of the gas hood heater is calculated as follows:
wherein the content of the first and second substances,
the energy consumption of the heater in unit time is;
the flow rate of hot air is adopted; Δ HHChanging the enthalpy of hot air; xHThe humidity of hot air; t ishSupplying air temperature to the air hood; t isEIs ambient temperature;
heat loss of the hood heater per unit time;
s15: deriving production data for different periods of time from the energy management system, the production data including: drying cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHAir hood dry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE；
S16: inputting the production data into a mechanism simulation model, and simulating to obtain the exhaust air humidity X of each group of production dataOAir exhaust temperature T of air hoodODrying section high pressure steam flow FHWith the low pressure steam flow F of the drying sectionLDry with the sheetout；
S17: and calculating a mechanism simulation error, wherein a simulation error calculation formula is as follows:
wherein, ytIn the form of an actual value of the value,
are analog values.
3. An intelligent algorithm based optimization method for the dryer section of a domestic paper machine according to claim 1, characterized in that said S2 comprises the following sub-steps:
s21: in order to eliminate the difference of each variable in dimension and improve the operation efficiency of the algorithm, the production data obtained in step S1 and the mechanism simulation error data are normalized, and the normalization processing formula is as follows:
wherein X is an independent variable, X ═ X1，…xp]n×pY is a dependent variable, Y ═ Y1，…yq]n×qN is the number of samples, j is 1,2jIs the mean value of the samples in the j dimension, xijIs the j-dimensional value of the ith sample,
for the j-dimensional normalized value of the i-th sample, SjIs the standard deviation of the sample in the j dimension, Sj 2The variance in the j dimension for the sample;
s23: introducing relaxation variables based on the principle of minimizing structural risk
And
and introducing a lagrange multiplier alphai，
ηi，
Obtaining a model of a support vector machine, wherein the model of the support vector machine is as follows:
where ω is a weight coefficient and x is an input variable [ x ]1，…xp]n×pB is an offset term, αi，
Is Lagrange multiplier, K (x)i，xj) Is a kernel function;
s24: the kernel function can map linear inseparable low-dimensional feature data to a high-dimensional space and convert a nonlinear problem into a linear problem, and common kernel functions comprise: linear kernel function Linear, polynomial kernel function Poly, radial basis kernel function RBF and sigmoid kernel function;
the radial basis kernel function RBF is adopted, and the formula is shown as the following formula:
K(xi，x)＝exp(-γ||xi-x||2)，γ＞0
where γ is a kernel function parameter.
4. An intelligent algorithm based optimization method for the dryer section of a domestic paper machine according to claim 1, characterized in that said S3 comprises the following sub-steps:
s31: integrating a paper sheet drying process mechanism simulation model and a drying process simulation error correction model into a paper sheet drying process simulation model; the paper sheet drying process mechanism simulation model can perform mechanism simulation on key variables according to input production data; the drying process simulation error correction model can predict mechanism simulation errors under the current production data. The output calculation formula of the paper sheet drying process simulation model is as follows:
wherein the content of the first and second substances,
is the final analog value of the key variable,
is a mechanism simulation value of a key variable,
mechanism simulation error as a key variable;
s32: the average relative error was used to measure the simulation effect of the sheet drying process simulation model on the key variables, and the formula was as follows:
where n is the total number of test set samples.
5. An intelligent algorithm based optimization method for the dryer section of a domestic paper machine according to claim 1, characterized in that said S4 comprises the following sub-steps:
s41: selecting the drying cylinder pressure P according to the principle that the selection of the decision variables follows easy acquisition and can be controlledCWet side supply air temperature TWHDry side supply air temperature TDHWith exhaust frequency fEAs a decision variable of the energy consumption optimization model, the feasible domain of the decision variable is set according to the limits of the drying cylinder, the air hood heater and the exhaust fan device as follows:
pmin≤PC≤pmax
T1min≤TWH≤T1max
T2min≤TDH≤T2max
fmin≤fE≤fmax
s42: the constraint condition is the constraint of system state variables, and the constraint condition of the operation optimization method of the drying part of the domestic paper making machine mainly comprises the following two aspects:
s421: restricting the dryness of paper; the main function of the dryer section is to evaporate water from the sheet and dry the wet sheet, usually with certain requirements on the dryness of the sheet leaving the dryer section:
Dryout≥Drysta
wherein, DryoutRepresenting the dryness of the paper sheet in the out-of-dryer section, from a paper sheet drying process simulation model, DrystaExpressing the standard dryness of finished paper;
the dew point constraint, in actual production, in order to prevent the air hood from dripping, the exhaust air temperature must be controlled above the dew point, because the temperature distribution of the air and the air hood shell is not uniform, in order to prevent the local temperature from being lower than the dew point, the exhaust air temperature must be controlled at a higher value, and forms a certain difference with the dew point temperature, according to the practical experience, when the difference is above 20 ℃, no dripping is formed in the air hood:
TO≥TDP+20
POV＝PT·RHO
wherein, TDPIs the dew point temperature, POVFor partial pressure of exhaust steam, RHORelative humidity of the exhaust air. All are obtained by a paper sheet drying process simulation model;
s43: the ton paper drying cost is taken as an objective function, and the calculation method is shown as the following formula:
min Cost＝(UH×FH+UL×FL+UE×PE)/(v*G*W*CR)
wherein Cost is the Cost of paper per ton; u shapeH、ULAnd UERespectively representing a high-pressure steam unit price, a low-pressure steam unit price and an electric unit price; fH、FLAnd PERespectively representing the high-pressure steam flow, the low-pressure steam flow and the electric power of an exhaust fan;
s44: solving the optimization problem of S41-S43 by using a sequence least squares programming method,
the calculation formula of the least square programming method is as follows:
wherein the content of the first and second substances,
x representing an objective functionkJacobi matrix of (1), HkRepresenting the objective function at XkHessian matrix of (A), XkThe iterative form of (a) is shown as follows:
h in the solution processkThe iterative form of (a) is shown as follows:
wherein the content of the first and second substances,
ΔXk＝Xk+1-Xk
6. an intelligent algorithm based optimization method for the dryer section of a domestic paper machine according to claim 1, characterized in that said S5 comprises the following sub-steps:
s51: inputting drying section production data, including cylinder pressure PCLinear speed v of drying cylinder, gram weight G, coiling rate CR and hot air temperature T at dry side of air hoodDHHot air temperature T at wet side of air hoodWHAir hood dry side fan frequency fDHFrequency f of fan on wet side of gas hoodWHExhaust fan frequency fEAmbient temperature TEAmbient temperature XE；
S52: optimizing the historical operating parameters of the drying part of the paper machine by using an optimization model, namely solving to obtain the drying cylinder pressure P when Cost is minimumCWet side air supply temperature TWHDry side air supply temperature TDHWith exhaust frequency fEAnd the constraint condition is satisfied.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010689269.0A CN111893791A (en) | 2020-07-17 | 2020-07-17 | Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010689269.0A CN111893791A (en) | 2020-07-17 | 2020-07-17 | Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111893791A true CN111893791A (en) | 2020-11-06 |
Family
ID=73189368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010689269.0A Pending CN111893791A (en) | 2020-07-17 | 2020-07-17 | Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111893791A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949162A (en) * | 2021-01-25 | 2021-06-11 | 广州博依特智能信息科技有限公司 | Operation optimization method for drying part energy system of boxboard paper machine based on data driving |
| CN117743772A (en) * | 2023-12-29 | 2024-03-22 | 维达纸业(浙江)有限公司 | Toilet paper drying parameter optimization method and system based on artificial intelligent model |
| CN117743772B (en) * | 2023-12-29 | 2024-05-28 | 维达纸业(浙江)有限公司 | Toilet paper drying parameter optimization method and system based on artificial intelligent model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| CN109577064A (en) * | 2018-12-14 | 2019-04-05 | 华南理工大学 | Mechanism modeling method for predicting energy consumption and evaporation capacity of drying part of toilet paper machine |
| CN111241717A (en) * | 2020-03-11 | 2020-06-05 | 广州博依特智能信息科技有限公司 | Method for optimizing operation parameters of drying part of toilet paper machine based on mechanism model |
| CN111241754A (en) * | 2020-01-17 | 2020-06-05 | 广州博依特智能信息科技有限公司 | Soft measurement method for key process parameters of paper sheet drying |
| CN111400832A (en) * | 2020-03-11 | 2020-07-10 | 广州博依特智能信息科技有限公司 | Hybrid modeling method for predicting key operation parameters of drying part of toilet paper machine |
-
2020
- 2020-07-17 CN CN202010689269.0A patent/CN111893791A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| CN109577064A (en) * | 2018-12-14 | 2019-04-05 | 华南理工大学 | Mechanism modeling method for predicting energy consumption and evaporation capacity of drying part of toilet paper machine |
| CN111241754A (en) * | 2020-01-17 | 2020-06-05 | 广州博依特智能信息科技有限公司 | Soft measurement method for key process parameters of paper sheet drying |
| CN111241717A (en) * | 2020-03-11 | 2020-06-05 | 广州博依特智能信息科技有限公司 | Method for optimizing operation parameters of drying part of toilet paper machine based on mechanism model |
| CN111400832A (en) * | 2020-03-11 | 2020-07-10 | 广州博依特智能信息科技有限公司 | Hybrid modeling method for predicting key operation parameters of drying part of toilet paper machine |
Non-Patent Citations (1)
| Title |
|---|
| 陈仕鸿: "基于SVＲ的广东省台风灾害损失评估", 《海洋环境科学》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949162A (en) * | 2021-01-25 | 2021-06-11 | 广州博依特智能信息科技有限公司 | Operation optimization method for drying part energy system of boxboard paper machine based on data driving |
| CN117743772A (en) * | 2023-12-29 | 2024-03-22 | 维达纸业(浙江)有限公司 | Toilet paper drying parameter optimization method and system based on artificial intelligent model |
| CN117743772B (en) * | 2023-12-29 | 2024-05-28 | 维达纸业(浙江)有限公司 | Toilet paper drying parameter optimization method and system based on artificial intelligent model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109577064B (en) | Mechanism modeling method for predicting energy consumption and evaporation capacity of drying part of toilet paper machine | |
| CN111400832B (en) | Hybrid modeling method for predicting key operation parameters of drying part of toilet paper machine | |
| CN111241717A (en) | Method for optimizing operation parameters of drying part of toilet paper machine based on mechanism model | |
| CN111893791A (en) | Method for optimizing operation of drying part of domestic paper making machine based on intelligent algorithm | |
| CN105783427A (en) | Microwave vacuum drying method achieving staging control | |
| CN112949162B (en) | Method for optimizing operation of energy system of drying part of cardboard paper machine based on data driving | |
| Sivill et al. | Thermodynamic simulation of dryer section heat recovery in paper machines | |
| CN111241754B (en) | Soft measurement method for key process parameters of paper drying | |
| CN104850151A (en) | Temperature control method for airflow type cut tobacco dryer combustion chamber | |
| CN110013044A (en) | A method of barrel temperature is obtained by calculating KLD-2 cut-tobacco drier dehydrating amount | |
| Ghodbanan et al. | Optimization for energy consumption in drying section of fluting paper machine | |
| Kong et al. | Effect of operating parameters on the drying performance of multicylinder paper machine dryer section | |
| Chen et al. | Energy system diagnosis of paper-drying process, Part 2: A model-based estimation of energy-saving potentials | |
| CN113609660A (en) | Numerical simulation method for predicting heat and mass transfer rule of clothes in clothes dryer | |
| CN111291968B (en) | Multi-energy system operation stability calculation method based on big data | |
| CN117494548A (en) | Intelligent adjusting method for oven parameters and computer-readable storage medium | |
| Jankes et al. | Waste heat potentials in the drying section of the paper machine in umka cardboard mill | |
| CN111578690A (en) | Wood moisture content control method based on hidden Markov model and particle swarm optimization | |
| CN114642268B (en) | Intelligent control system and method for drying silk based on volatile moisture content | |
| CN109459928B (en) | Fuzzy fractional order PIDμDDS replacement cooking temperature control method of controller | |
| Wang et al. | Modeling of furnace operation with a new adaptive data echo state network method integrating block recursive partial least squares | |
| CN103616819B (en) | The PID controller design method of calm single-input single-output Systems with Multiple Time-Delays | |
| CN111926606B (en) | Online monitoring method for energy efficiency of drying part of paper machine | |
| Åkesson et al. | Parameter optimization of a paper machine model | |
| Kong et al. | Sequential modeling of paper drying process to reduce thermal energy use, part 1: theoretical model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201106 |