CN113609748A - Cement batching method driven by preferential consumption of solid waste based on bionic algorithm - Google Patents

Cement batching method driven by preferential consumption of solid waste based on bionic algorithm Download PDF

Info

Publication number
CN113609748A
CN113609748A CN202110639138.6A CN202110639138A CN113609748A CN 113609748 A CN113609748 A CN 113609748A CN 202110639138 A CN202110639138 A CN 202110639138A CN 113609748 A CN113609748 A CN 113609748A
Authority
CN
China
Prior art keywords
cement
solid waste
algorithm
raw materials
bionic
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
Application number
CN202110639138.6A
Other languages
Chinese (zh)
Inventor
宋晓玲
胡敬平
徐盼盼
汤建建
梁智霖
罗维
黄东
杨忠
侯慧杰
刘冰川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Xinjiang Tianye Group Co Ltd
Original Assignee
Huazhong University of Science and Technology
Xinjiang Tianye Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology, Xinjiang Tianye Group Co Ltd filed Critical Huazhong University of Science and Technology
Priority to CN202110639138.6A priority Critical patent/CN113609748A/en
Publication of CN113609748A publication Critical patent/CN113609748A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Medical Informatics (AREA)
  • Algebra (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Processing Of Solid Wastes (AREA)

Abstract

The invention relates to a solid waste preferential digestion driven cement batching method based on a bionic algorithm. The method comprises the following steps: integrating the component data of the solid waste raw materials into an attribute matrix; optimal solid waste material ratios are obtained through optimization calculation of a bionic algorithm represented by a non-dominated sorting multi-target evolutionary algorithm; simultaneously, the target of consuming the target waste residue amount to the maximum extent and approaching the expected three-rate value in a balanced manner is realized; and (4) optimizing and calculating by a bionic algorithm to obtain an optimal batching ratio, and guiding actual cement production. In the optimization process, the actual cement production feeding data is randomly used as an initial guess value after being normalized, and the convergence rate is calculated in an accelerated mode. The method meets the requirement of maximally absorbing solid waste raw materials in the process of producing chloroethylene waste residues and firing cement by using a plurality of calcium carbide methods. The method effectively solves the problem of unstable cement production performance caused by large fluctuation of solid waste raw materials in the feeding process in the cement production taking industrial solid waste as the solid waste raw materials, realizes the preferential consumption of the solid waste with large inventory, and is also suitable for the effective utilization of a large amount of solid waste raw materials.

Description

Cement batching method driven by preferential consumption of solid waste based on bionic algorithm
Technical Field
The invention belongs to the field of solid waste resource utilization, and particularly relates to a cement batching method driven by preferential consumption of solid waste based on a bionic algorithm.
Background
In recent years, with the rapid increase of the production of urban solid wastes and bulk industrial solid wastes in China, the solid wastes are paid more and more attention to the cooperative treatment of rotary cement kilns, and the cooperative treatment amount of household wastes, urban sludge and general industrial solid wastes is increased day by day, wherein the cooperative treatment amount of the cement kilns of dangerous solid wastes occupies more than 45% of the incineration treatment amount of dangerous wastes.
Taking the co-processing of the rotary cement kiln with industrial solid wastes as an example, in recent years, by deeply analyzing the raw material components, physical and chemical characteristics of various industrial wastes, it was found that the industrial solid wastes can be used as raw materials for firing cement. A process for preparing waste slag cement from waste polyvinyl chloride dregs includes such steps as calcining the cement clinker from calcium dregs, adding calcium, clay and iron dregs, mixing natural gypsum with desulfurized ash or citric acid dregs, fly ash, coal gangue and lime stone, pre-production test, analog screening, selecting raw materials, homogenizing, classifying storage, effective metering, preparing, routine monitoring and two-grinding-one burning. The raw materials of the whole waste residues are mainly derived from industrial solid wastes generated by upstream industries such as chemical industry, calcium carbide industry, thermoelectric industry, biochemical companies and the like, such as: calcium raw materials such as carbide slag, dust collected by a carbide furnace, lime slag, limestone chips and purified ash, clay raw materials such as fly ash, furnace slag and coal gangue, calibration raw materials such as sulfuric acid slag, copper slag and iron tailings, and retarder raw materials such as desulfurized gypsum and citric acid slag. Compared with the traditional cement process, the full waste slag cement has various raw materials and complex components, and the amount of waste slag greatly fluctuates along with the operation condition of upstream enterprises, so that the produced cement has uneven performance and quality, which is a great challenge for the batching of cement raw materials.
In the field of cement feed proportioning, an Excel manual trial calculation table method is often adopted for cement raw material proportioning, and cement compatibility is mainly calculated by utilizing a constraint condition of a three-rate value; in Excel, a linear/nonlinear programming module can also be used for carrying out optimization solution, but in practical situations, the situation that the optimal solution cannot be obtained by the method is often encountered. Meanwhile, the raw material components and types of the cement process after the solid waste is doped are more complicated than those of common Portland cement, although the practical experience of waste slag cement raw material blending is accumulated after the research of technical personnel for many years, the method for performing compatibility calculation on the cement raw materials by adopting the Excel table has lower efficiency, and the problem that the feeding and blending ratio of waste slag and the quality of cement products are uneven under the condition of large raw material fluctuation cannot be well solved. Although there are reports related to the use of genetic algorithms for optimal control of the proportion of conventional portland cement raw materials, there are still many problems. The genetic algorithm reported heretofore is mostly applied to the optimization of the traditional portland cement batching method, mainly aiming at the traditional cement production process with simple raw materials; in a batch of solutions obtained by Excel linear/nonlinear programming, the consumption of solid waste raw materials with large inventory is sometimes small, and the requirement for maximum consumption of carbide slag and other bulk industrial solid wastes is difficult to meet.
The method is based on an evolutionary algorithm represented by non-dominated sorting multi-objective optimization, the non-dominated sorting multi-objective evolutionary algorithm is commonly used for seeking the optimal solution of a plurality of objective functions, and the selected algorithm is mainly different from a common genetic algorithm in that:
(1) the calculation complexity is greatly reduced by adopting a rapid non-dominated sorting method;
(2) a congestion degree and congestion degree comparison operator is defined to replace a sharing radius required to be specified, so that individuals in the quasi-Pareto domain can be expanded to the whole Pareto domain and are uniformly distributed, and the diversity of the population is kept;
(3) an elite strategy is introduced, the sampling space is enlarged, the loss of the optimal individual is prevented, and the operation speed of the algorithm is improved.
The algorithm is often used for optimizing multi-objective problems, and the optimization effect of the algorithm is greatly improved. The application of the algorithm to the compatibility calculation of industrial solid waste cement raw materials with complex components does not appear before, and the bionic algorithm program is applied to the raw material proportioning optimization problem of the waste residue raw material cement process for the first time. However, there are many technical problems in applying the algorithm to the compatibility calculation of industrial solid waste cement raw materials with more complicated components. Therefore, the invention further improves the program of the bionic algorithm aiming at the characteristics of solid waste raw materials, and successfully realizes the bionic optimization of the raw material proportion of the waste slag-containing cement process.
Disclosure of Invention
The invention provides a bionic algorithm-based cement batching method driven by preferential consumption of solid wastes, and solves the problems of large feeding fluctuation, unstable cement production quality and imperfect calculation method of a three-rate value when industrial waste residues are used as raw materials for producing cement. Specifically, the method comprises the following steps:
step 1, selecting a plurality of groups of solid waste raw materials to produce data of cement, wherein the data comprises the types of the solid waste raw materials, key composition parameters of the solid waste raw materials and five main oxides of CaO and Al2O3、Fe2O3、SiO2And SO3The content ratio of the solid waste raw materials is taken as a vector to be optimized. In particular, all types of feed are matrix blocks a, a being a 5 x n matrix. For example, the first column of matrix a is carbide slag, the second column is admixture, and the following columns are other solid wastes in turn. Vector quantity
Figure DEST_PATH_IMAGE002
Represents the percentage of each raw material in the cement raw material, vector
Figure DEST_PATH_IMAGE004
The total amount of the five oxides in the cement feed is expressed by the following formula:
Figure DEST_PATH_IMAGE006
·
Figure DEST_PATH_IMAGE008
=
Figure DEST_PATH_IMAGE010
A
Figure 779278DEST_PATH_IMAGE002
Figure DEST_PATH_IMAGE012
wherein C1 represents the weight percentage content of CaO in the carbide slag, C2 represents the weight percentage content of CaO in the mixture, and so on; s1 represents SiO in carbide slag2S2 represents SiO in the mixture2The mass percentage of the components is repeated; f1 represents Fe in carbide slag2O3F2 represents Fe in the mixture2O3The mass percentage of the components is repeated; a1 represents Al in carbide slag2O3A2 represents Al in the mixture2O3The mass percentage of the components is repeated; s1 represents SO in carbide slag3S2 represents SO in the mixture3And so on.
Preferably, taking a certain batch of cement feed as an example:
TABLE 1 batch of Cement feed oxides content and proportions
Species (wt%) CaO SiO2 Fe2O3 Al2O3 SO3 Feed ratio
Carbide slag 68.32 3.38 0.51 1.87 0.48 40.27
Mixture material 86.27 3.70 0.70 0.70 0.50 25.10
Fly ash 10.00 49.84 7.70 17.91 1.29 7.28
Slag of furnace 7.90 48.20 7.43 16.00 0.45 4.44
Steel slag 44.61 16.70 18.49 4.43 0.41 6.78
Silicon powder 0.31 94.52 0.24 0.46 0.49 4.15
Silica 7.56 44.89 7.56 15.93 0.21 7.00
Incineration ash 26.03 26.95 8.37 8.96 5.54 4.99
The integration transforms into an attribute matrix, that is:
Figure DEST_PATH_IMAGE014
·
Figure DEST_PATH_IMAGE016
=
Figure DEST_PATH_IMAGE018
by writing historical feeding data of recent years into an attribute matrix, the historical data can be randomly used in the process of solving the optimal solution through iterative calculation of a subsequent algorithm
Figure 398216DEST_PATH_IMAGE002
As the initial guess.
And 2, preferably, selecting a bionic algorithm represented by a non-dominated sorting multi-target genetic algorithm, improving the bionic algorithm according to the characteristics of the solid waste raw materials, and optimally calculating to obtain a plurality of optimal solid waste raw material ratios through the bionic algorithm. In the process of setting the algorithm, the expected three-rate values (lime saturation coefficient KH or LSF, silicon rate SM and aluminum rate IM) of the cement are taken as fitness functions, and the adaptability of the generated solid waste raw material proportioning solution is evaluated according to the fitness functions (namely, the closer the calculated actual three-rate value is to the expected three-rate value, the stronger the adaptability of the corresponding solid waste raw material proportioning solution in the algorithm is). After the expected three-rate value is input, a new round of population growth and screening are carried out by taking the expected three-rate value as a fitness function, and four objective functions for representing the deviation between the expected three-rate value and the actual three-rate value through constraint
Figure DEST_PATH_IMAGE020
，
Figure DEST_PATH_IMAGE022
，
Figure DEST_PATH_IMAGE024
，
Figure DEST_PATH_IMAGE026
And solving a batch of optimal solutions meeting the four objective functions. Wherein KH (or LSF), SM and IM are expected three values, and KH (or LSF), SM and IM are actual three values.
The three-rate value in the waste slag cement process adopts a calculation formula as follows:
Figure DEST_PATH_IMAGE028
Figure DEST_PATH_IMAGE030
Figure DEST_PATH_IMAGE032
Figure DEST_PATH_IMAGE034
taking the deviation between the expected three-rate value and the actual three-rate value calculated by the three-rate value formula according to the feeding ratio of the solid waste slag obtained by the final optimization solution as an objective function
Figure 907781DEST_PATH_IMAGE020
，
Figure DEST_PATH_IMAGE035
，
Figure DEST_PATH_IMAGE036
，
Figure 975094DEST_PATH_IMAGE026
The objective function is written as:
Figure DEST_PATH_IMAGE038
Figure DEST_PATH_IMAGE040
Figure DEST_PATH_IMAGE042
Figure DEST_PATH_IMAGE044
Figure DEST_PATH_IMAGE046
or
Figure DEST_PATH_IMAGE048
Wherein
Figure DEST_PATH_IMAGE050
，
Figure DEST_PATH_IMAGE052
，
Figure DEST_PATH_IMAGE054
，
Figure DEST_PATH_IMAGE056
Are respectively an objective function
Figure 304313DEST_PATH_IMAGE020
，
Figure 330038DEST_PATH_IMAGE035
，
Figure 862650DEST_PATH_IMAGE036
，
Figure 264813DEST_PATH_IMAGE026
A weight factor of, and
Figure DEST_PATH_IMAGE057
far greater than
Figure 402533DEST_PATH_IMAGE050
，
Figure 661476DEST_PATH_IMAGE052
，
Figure 117603DEST_PATH_IMAGE054
. To constrain the three-rate values evenly, it is preferable to set
Figure DEST_PATH_IMAGE059
，
Figure DEST_PATH_IMAGE061
，
Figure DEST_PATH_IMAGE063
，
Figure DEST_PATH_IMAGE065
Guarantee y1，y2，y3And y4All tend to 0. In satisfying
Figure DEST_PATH_IMAGE067
，
Figure DEST_PATH_IMAGE069
，
Figure DEST_PATH_IMAGE071
，
Figure DEST_PATH_IMAGE073
On the premise of (A) under the condition of (B),
Figure 995560DEST_PATH_IMAGE026
weight factor
Figure 722208DEST_PATH_IMAGE056
May be further increased so that
Figure 417632DEST_PATH_IMAGE020
，
Figure 862519DEST_PATH_IMAGE035
，
Figure 403222DEST_PATH_IMAGE036
It is possible to approach 0 more uniformly and, preferably,
Figure 249955DEST_PATH_IMAGE056
is that
Figure DEST_PATH_IMAGE075
、
Figure DEST_PATH_IMAGE076
、
Figure 818078DEST_PATH_IMAGE054
5 to 15 times of the total amount of the active carbon,
Figure 750262DEST_PATH_IMAGE075
、
Figure 94655DEST_PATH_IMAGE052
、
Figure DEST_PATH_IMAGE077
the ratio of the three is 0.5-3, and the ratio is increased
Figure 61474DEST_PATH_IMAGE056
So that the overall three-rate value is equally close to the desired three-rate value. In the actual production of cement, when the performance of cement is sensitive to the influence of a certain three-rate value, the weight factor before the constraint function of the three-rate value can be modified in the algorithm setting
Figure DEST_PATH_IMAGE079
To dynamically measure the influence on the cement ratio. Compared with the constraint condition of calculating three values in the traditional cement batching method (taking the square sum of the difference of the three values), the method can lead the actual three values KH (or LSF), SM and IM to be infinitely close to the expected three values KH (or LSF), SM and IM, and can scientifically measure the influence of a certain sensitive value on the cement proportioning.
Introducing the historical data and the expected ternary value into an algorithm, encoding the historical data and the expected ternary value into a bit string to generate an initial population, and generating a sub-population through non-dominated sorting, bionic operation and genetic variationQnMerging the offspring population and the parent population into RnAnd generating a new father population through non-dominated sorting and congestion calculation, continuing genetic evolution to generate a new offspring population, adopting an optimal individual retention mechanism until an evolution algebra reaches a maximum set value or a fitness function is smaller than a threshold value, and obtaining a batch of optimal solutions by setting an optimal front-end individual coefficient, preferably 0.2-0.5.
Step 3, satisfying the objective function obtained in the step 2
Figure 301963DEST_PATH_IMAGE020
，
Figure 455864DEST_PATH_IMAGE035
，
Figure 603948DEST_PATH_IMAGE036
，
Figure 159694DEST_PATH_IMAGE026
According to a target function of maximum consumption of a certain waste residue
Figure DEST_PATH_IMAGE081
To sort, take the top set of solutions. And setting a proper optimal front-end individual coefficient for the generated new generation qualified population, preferably setting the optimal front-end individual coefficient to be 0.2-0.5, so as to obtain a batch of Pareto optimal solutions. The Pareto optimal solutions are sequentially ordered from high to low according to the amount of certain solid waste residues with the maximum consumption requirement (such as the preferential consumption of carbide slag), and the top group of optimal solutions are taken as the sought final solutions which finally meet the objective function.
Preferably, the steps of the process for solving the cement batching method of the present invention are described in detail by taking the feed composition (table 2) of the solid waste residue of a certain batch of cement plant mentioned in step 1 as an example.
TABLE 2 batch of Cement feed oxides content and proportions
Species (wt%) CaO SiO2 Fe2O3 Al2O3 SO3 Feed ratio
Carbide slag 68.32 3.38 0.51 1.87 0.48 40.27
Mixture material 86.27 3.70 0.70 0.70 0.50 25.10
Fly ash 10.00 49.84 7.70 17.91 1.29 7.28
Slag of furnace 7.90 48.20 7.43 16.00 0.45 4.44
Steel slag 44.61 16.70 18.49 4.43 0.41 6.78
Silicon powder 0.31 94.52 0.24 0.46 0.49 4.15
Silica 7.56 44.89 7.56 15.93 0.21 7.00
Incineration ash 26.03 26.95 8.37 8.96 5.54 4.99
The three desired values to be met are KH =0.88, SM =2.15, IM =1.45 in sequence, and the cement batching is carried out with the carbide slag as the target of maximum slag consumption.
The optimal solution of the feeding proportion of each solid waste residue is obtained by the non-dominated sorting multi-target evolutionary algorithm based on the bionic algorithm, and the optimal solution is as follows:
carbide slag: 50.0576%, mixture: 16.0989%, fly ash: 2.4237%, slag: 3.5862%, steel slag: 5.8345%, silicon powder: 4.6222%, silica: 11.4113%, incineration ash: 6.0386 percent.
The corresponding three values are KH =0.88187, SM =2.1506, IM =1.4451, very close to the desired three values KH =0.88, SM =2.15, IM = 1.45.
And 4, guiding the raw material ratio of the actual waste slag cement process by using the obtained optimal solution. The cement feeding and batching method is not only suitable for the raw material proportioning of the solid waste residue cement, but also suitable for the raw material proportioning optimization of the traditional cement production process such as portland cement production and the like.
Under the background, the method combines the industrial solid waste cement raw material feeding proportioning data accumulated in the practical operation process of a cement enterprise in the past few years as an initial guess value, establishes a waste slag cement process raw material feeding proportioning model by using a bionic algorithm represented by a non-dominated sorting multi-target evolutionary algorithm, solves the balanced approach expectation three-rate value by using the bionic algorithm optimization model, and simultaneously realizes the preferential consumption of solid waste raw materials with higher stock pressure represented by carbide slag so as to realize the optimal cement waste slag-containing raw material proportioning.
The invention optimizes the whole waste slag cement proportioning based on a bionic algorithm and a multi-target evolutionary algorithm of non-dominated sorting driven by solid waste consumption, the obtained cement raw material proportioning can meet the expected three-rate value as much as possible, and can meet the aim of consuming solid waste slag with larger stock pressure as much as possible.
Drawings
FIG. 1 is a flow chart of a solid waste preferential digestion driven cement batching algorithm based on a biomimetic algorithm; FIG. 2 is a schematic view showing a user interaction interface and an optimization result of a solid waste preferential absorption driven cement ingredient optimization system based on a biomimetic algorithm; FIG. 3 is a schematic diagram of a non-dominated ranking hierarchy, corresponding to a Rank histogram of an intermediate graph; FIG. 4 is a schematic view of a Pareto front surface (top first graph); the algorithm steps of the first step, the second step and the third step in the figure 1 correspond to the functional areas and the control buttons of the first step, the second step and the third step in the software interface in the figure 2 one by one.
Detailed Description
Referring to the drawings of the specification and figure 1, a solid waste preferential digestion driven cement batching method based on a biomimetic algorithm preferably takes as an example the composition of the waste slag cement raw meal feed in table 2.
The composition of the raw waste sludge cement feed material in table 2, i.e. the attribute matrix mentioned in step 1 of the summary of the invention, was selected.
Preferably, algorithm parameter setting is performed, and a target lime saturation coefficient KH =0.89, a target silicon rate SM =2.1, and a target aluminum rate IM =1.4 are set, and specific implementation examples are as follows.
(1) The detailed calculation process for solving the cement proportion by the bionic algorithm
Starting a cement batching program, and initializing initial parameters:
the oxide content data of the individual components of the cement feed introduced, for example:
TABLE 3 oxide content of the Cement feed Components
Species (wt%) CaO SiO2 Fe2O3 Al2O3 SO3
Carbide slag 68.32 3.38 0.51 1.87 0.48
Mixture material 86.27 3.70 0.70 0.70 0.50
Fly ash 10.00 49.84 7.70 17.91 1.29
Slag of furnace 7.90 48.20 7.43 16.00 0.45
Steel slag 44.61 16.70 18.49 4.43 0.41
Silicon powder 0.31 94.52 0.24 0.46 0.49
Silica 7.56 44.89 7.56 15.93 0.21
Incineration ash 26.03 26.95 8.37 8.96 5.54
Integrating the attribute matrix into an attribute matrix after algorithm processing:
by compiling historical feed data over recent years into a matrix of attributes, where Table 4 is a listing of portions of historical feed
Figure 571084DEST_PATH_IMAGE002
(percentage of waste residue fed), these historical data will be used randomly in the process of solving the optimal solution by iterative calculation of the subsequent algorithm
Figure 274598DEST_PATH_IMAGE002
As the initial guess.
Figure 898477DEST_PATH_IMAGE014
·
Figure 636626DEST_PATH_IMAGE016
=
Figure 451873DEST_PATH_IMAGE018
TABLE 4 part of the historical feed data of the ingredients of cement raw meal
Species of Feed ratio historical data 1 (wt%) Feed specific historical data 2 (wt%) Feed fraction historical data 3 (wt%) Feed fraction historical data 4 (wt%) Feed fraction historical data 5 (wt%)
Carbide slag 40.27 39.71 40.87 39.17 37.34
Mixture material 25.10 25.42 26.93 25.61 28.73
Fly ash 7.28 7.34 8.13 7.34 6.09
Slag of furnace 4.44 4.51 4.10 4.82 5.29
Steel slag 6.78 6.61 7.07 6.62 6.69
Silicon powder 4.15 4.23 3.91 4.52 4.27
Silica 7.00 6.70 6.59 7.05 7.87
Incineration ash 4.99 4.93 4.25 4.62 5.24
Desired values of the three values of the introduced cement (lime saturation coefficient KH or LSF, silicon ratio SM and aluminium ratio IM): KH =0.88, SM =2.15, IM =1.45 as fitness function.
Various properties of the coal introduced: the heat consumption of firing is 3014 kJ/kg, the calorific value of coal is 27010 kJ/kg, and the coal ash content is 12.28%.
Setting the parameters of the appropriate genetic algorithm: the method comprises the following steps of 0.3 (namely 30%) of optimal individual proportion, 200% of population size, 300 generations of evolution, 3 times of repeated genetic algorithm simulation, and taking the first raw material (carbide slag) as a preferential digestion object and 0.03 (namely 3%) of maximum allowable variance between the first raw material and an expected value.
Thirdly, the algorithm converts the attribute matrix into binary character strings, the character strings are combined into an initial population P, the population size is set to be 200, and partial individual codes are listed as follows:
L1=1001 0101 L2=0100 1011 L3=0101 1001 L4=1010 0001
…… …… …… ……
L197=0110 1101 L198=1011 0000 L199=0011 1000 L200=1111 0000
fourthly, performing non-dominated sorting and congestion degree calculation on the population P with the size of 200, namely performing congestion degree calculation after layering the P through a non-dominated sorting algorithm, as shown in the attached figure 3 of the specification:
the population P is divided into 9 levels, the number of first-level non-dominant layers is 60, the number of second-level non-dominant layers is 30, and the number of third-level non-dominant layers is 25, … …, and the number of ninth-level non-dominant layers is 7. Therefore, the whole population is layered, and the algorithm performs distance sum calculation, namely congestion degree calculation, on each individual, so that each individual has two attributes of non-dominant layer and congestion degree. Thus reducing the complexity of the algorithm calculation.
Performing bionic operation, selection, crossing, variation and the like on the population P, wherein the bionic operation comprises the following steps:
through elite strategy carried by the bionic algorithm, non-inferior individuals with higher crowding degree and better quality are selected, the optimal leading edge coefficient is set to be 0.3, and then 60 individuals are selected, and the description of crossing and variation of the first 4 individuals is exemplified below.
L1=1001 0101 L2=0100 1011 L3=0101 1001 L4=1010 0001
The new possible populations obtained after crossing are:
1001 1011 1001 1001 1001 0001
0100 0101 0100 1001 0100 0001
0101 0101 0101 1011 0101 0001
1010 0101 1010 1011 1010 1001
after mutation (some sites are 1 → 0 or 0 → 1), the new possible sub-population Qn is obtained as follows:
1001 1011 1001 1001 1001 0001
1101 1011 0001 1001 1010 0001
…… …… ……
0100 0101 0100 1001 0100 0001
1100 0101 0000 1001 0100 1001
…… …… ……
0101 0101 0101 1011 0101 0001
0101 1101 1101 1011 0101 0011
…… …… ……
1010 0101 1010 1011 1010 1001
1010 1101 1110 1011 1000 1001
…… …… ……
combining P and Qn into Rn, repeating the fourth and fifth bionic operation until reaching the iteration number or meeting the end threshold.
Seventhly, sequencing the accommodating quantity and the accommodating quantity according to the requirement of preferentially accommodating certain solid wastes (Pareto front surface drawing, see attached figure 4 of the specification) of a batch of optimal solutions (Pareto front surface drawing, see attached figure 4 of the specification) meeting the expected three rate values, selecting the optimal solutions by an algorithm, outputting the optimal solutions as the proportion of the waste residues, and listing part of the Pareto optimal solutions as shown in a table 5:
TABLE 5 bionic Algorithm Cement proportioning solution
Figure DEST_PATH_IMAGE085
The optimal solutions of Pareto listed in table 5 are sorted from (r) to (v) in order of the consumption of the carbide slag from high to low, and (r) is selected to meet the goal of preferential consumption of the carbide slag.
And solving the optimal solution of the feeding proportion of each solid waste residue by using the non-dominated sorting multi-target evolutionary algorithm based on the bionic algorithm as follows:
TABLE 6 optimal solution of bionic algorithm for cement proportioning
Figure DEST_PATH_IMAGE087
The corresponding actual three rate values are KH =0.88187, SM =2.1506, IM =1.4451, very close to the desired three rate values KH × =0.88, SM × =2.15, IM × = 1.45.
(2) And the artificial trial and error method, the Excel linear/nonlinear programming calculation algorithm and the bionic algorithm solve the cement proportioning case comparison.
Calculating the cement proportion by a manual trial-and-error method:
the constraints are listed, i.e.,
Figure DEST_PATH_IMAGE089
Figure DEST_PATH_IMAGE091
Figure DEST_PATH_IMAGE093
solving this system of equations in quinary form, there are numerous solutions, one set of solutions is taken, as shown in table 7:
TABLE 7 Cement compounding solution by manual trial and error method
Figure DEST_PATH_IMAGE095
The manual trial and error method is a process for solving the five-element equation set, but the process is very complicated and not simple enough, and the situation of no solution often occurs.
Secondly, the Excel table linear/nonlinear programming module is used for restraining the expected three-rate value and the actual three-rate value to be equal, a three-rate value calculation formula is used for solving, and a plurality of solutions meeting the constraint condition are found, wherein the solutions are randomly exemplified as shown in a table 8:
TABLE 8 Excel Linear/non-Linear programming Cement batching solution 1
Figure DEST_PATH_IMAGE097
In the embodiment, constraint conditions that the expected three-rate value is equal to the actual three-rate value are set through an Excel table, and the obtained cement ingredient proportion part is shown in the table, wherein the listed solutions of the first, the second and the third can meet the conditions, and the solution of the first can meet the consumption requirement of the waste residue pile amount based on a cement plant; the second and third steps both contain the condition that the ingredient of a certain raw material is 0, and the consumption of the carbide slag is too small to meet the actual requirement.
And thirdly, when the feeding component of the waste residue raw material is changed, the solution obtained by Excel linear/nonlinear programming can also have the situation of no solution.
Preferably, the feed ingredients of table 9 are taken as examples:
TABLE 9 batch Cement feed oxide content
Species (wt%) CaO SiO2 Fe2O3 Al2O3 SO3
Carbide slag 58.32 3.38 0.51 1.87 0.48
Mixture material 62.21 21.02 0.70 0.70 0.50
Fly ash 11.00 52.84 7.70 14.21 2.10
Slag of furnace 7.90 56.25 9.41 15.87 1.48
Steel slag 15.21 13.63 55.24 5.68 0.61
Silicon powder 0.11 95.21 0.15 0.46 0.21
Silica 3.26 62.12 4.21 8.25 0.36
Incineration ash 26.03 26.95 8.37 8.96 5.54
Preferably, the desired three-rate values KH =0.89, SM =2.1, IM =1.4 are set, and the cement ratio is solved in this way, see table 10.
TABLE 10 Excel Linear/non-Linear programming Cement batching solution 2
Figure DEST_PATH_IMAGE099
From the above examples, it is expected that the three values of the feed composition in table 9 can only satisfy two of them, wherein KH =0.89, SM =2.1, IM =1.35 ≠ 1.4= IM, and it can be seen that in the process of solving the cement mix ratio by Excel, some feed composition data can make the solved solution invalid, and all the constraints (i.e. the solution can not be found) can not be satisfied, and moreover, the content of the carbide slag in the feed mix ratio is up to 69.58%, which is not in accordance with the actual situation.
The proportion of cement feeding is carried out on the waste residue taking the carbide slag as the maximum consumption under the feeding component of the table 9 by the bionic algorithm, and the proportion is shown in a table 11.
TABLE 11 bionic Algorithm Cement batching solution
Figure DEST_PATH_IMAGE101
From the above example, in the case of the feed in table 9, no solution was found for solving the cement mix using Excel linear/non-linear programming. The bionic algorithm can solve the problem that three values KH, SM and IM are close to KH, SM and IM when the Excel linear/nonlinear programming method is used for solving cement batching, and a reasonable waste residue feeding proportion can be obtained.
(3) And the traditional genetic algorithm is compared with the bionic algorithm for solving the cement raw material proportioning case.
Cement compounding calculated by common genetic algorithm (without setting some solid waste slag to consume target first)
The solution generated by using the ordinary genetic algorithm is a possible solution after the algorithm system is optimized from a random initial value, a plurality of approximate solutions are often provided, for example, after expected three-rate values are input into a calculation model, the proportioning ratio of 8 industrial residues is obtained, and some typical solutions are shown in a table 12.
TABLE 12 genetic Algorithm Cement batch solution
Figure DEST_PATH_IMAGE103
From the above embodiment, the target of KH, SM, and IM =1.4 can be satisfied approximately by KH × = KH =0.89, SM × = SM =2.1, and IM × = IM of each solution. In the solution I and the solution II, the difference of the feeding ratio of the carbide slag and the mixture is very large, and the difference of the incineration ash slag and the silica is also large, so that the optimal proportioning data required by stable production is difficult to obtain.
Two cement proportioning solutions with large carbide slag feeding condition fluctuation obtained by the traditional genetic algorithm are listed, and are shown in a table 13.
TABLE 13 genetic Algorithm Cement batch solution
Figure DEST_PATH_IMAGE105
According to the implementation case, the proportion difference of all the feeding items is large in the first solution and the second solution, and the proportion fluctuation of all the solid waste raw materials is large when the cement proportion is calculated by the method. For the waste residue cement production process, the prior consumption target and stable production of waste residues with high stock pressure in a cement raw material yard cannot be realized.
Preferably, the cement feeding proportion of the total industrial waste residue is optimized by taking the maximum consumption of the carbide slag as a consumption amount. The only optimal solution which gives consideration to the approaching expected three-rate value and the maximum storage waste residue consumption is obtained by the non-dominated sorting multi-objective evolutionary algorithm based on the bionic algorithm, and the table 14 shows.
TABLE 14 bionic Algorithm Cement batching solution
Figure DEST_PATH_IMAGE107
From the above example, it is true that the actually calculated three-rate values KH =0.89076, SM =2.0998, IM =1.3985 and the desired three-rate value KH =0.89, SM =2.1, IM =1.4 have a small error, and each slag charge does not have 0%. Compared with the feeding of each waste residue raw material in the table 4 obtained by the calculation of the traditional simple genetic algorithm, the historical feeding data can be used as the initial guess value, the feeding range is stable, the actual situation of the waste residue stacking amount is met, and the batching target of taking the carbide slag as the main waste residue consumption can be realized in the case.
(4) And the traditional genetic algorithm is compared with the bionic algorithm for solving the cement raw material ratio calculation process.
Calculating cases by using a traditional genetic algorithm.
Preferably, with the feed components of table 2 as the attribute matrix, the desired ternary values KH =0.89, SM =2.1, IM =1.4 are set, and the maximum number of iterations of the genetic algorithm is set to 300.
The cement ingredient ratio calculated by the conventional genetic algorithm, the calculation time and the number of iterations in convergence are shown in table 15.
TABLE 15 genetic Algorithm Cement batch solution and solution time
Figure DEST_PATH_IMAGE109
In the above embodiment, the cement ratios KH =0.88994, SM =2.1001, IM =1.4002 and the desired ternary values KH =0.89, SM =2.1, IM =1.4, which are derived by the conventional genetic algorithm, are substantially equal, 118s are consumed in the whole calculation process, the set maximum number of genetic iterations is reached to 300 times, but is still less than the convergence condition, the calculation is ended, and the calculation is converged.
② the invention relates to a bionic algorithm calculation case.
Preferably, the feed components in table 2 are taken as examples.
Preferably, the desired three-rate values KH =0.89, SM =2.1, IM =1.4 are set, and the maximum number of iterations of the biomimetic algorithm is set to 300.
The cement ingredient ratio calculated by the bionic algorithm of the invention, the calculation time and the iteration times during convergence are shown in table 16.
TABLE 16 bionic Algorithm Cement batch solution and solution time
Figure DEST_PATH_IMAGE111
In the above example, the cement mix ratio KH =0.89021, SM =2.99007, IM =1.39913 and the desired ternary value KH =0.89, SM =2.1, IM =1.4 are substantially equal by conventional genetic algorithm, and the resulting optimal solution cement mix ratio is the mix ratio of the historical feed data. The whole calculation process consumes 30.8s, the iteration is carried out for 80 times, and the calculation reaches the convergence condition.
Compared with the traditional genetic algorithm and the bionic algorithm, the traditional genetic algorithm adopts random data as an initial guess value, and the data table 14 shows that the convergence is achieved only after the calculation time and the iteration times are longer. The algorithm of the invention adopts the historical feeding data as the initial population, and when the expected three-rate value is similar to the three-rate value calculated by the feeding data, the historical feeding data can be used as an initial guess value, so that the calculation time can be greatly reduced, and the convergence of the fitness function iteration can be completed in fewer iteration times.
(5) The bionic algorithm of the invention is used for calculating the feeding proportioning case of the sludge and the incineration fly ash which are treated by the conventional portland cement and cement in a synergic manner.
The calculation case of the traditional portland cement raw material proportioning method by using the algorithm program of the invention is as follows:
desired three values KH =0.89, SM =2.5, IM =1.5 were set, and the resulting optimal solution is shown in table 17.
TABLE 17 bionic Algorithm conventional Cement batching solution
Number/type (%) Limestone Clay Sandstone Iron ore slag Incineration ash KH SM IM
① 80.05 12.02 6.55 1.38 2.12 0.88961 2.50123 1.50014
It can be seen from the above examples that KH, SM and IM are very close to KH, SM and IM values, indicating that the same applies to the configuration of conventional portland cement raw materials.
Secondly, the following calculation cases of the ingredients of the tannery sludge co-processed by the cement are calculated by using the algorithm:
in certain tannery sludge, the proportion of each oxide is CaO: 12.81% of Al2O3：5.69%，Fe2O3：4.51%，SiO2：3.85%，SO3：0.35%。
The desired cement preparation after incorporation of tannery sludge into the conventional portland cement raw material has three values KH =0.89, SM =2.1, IM =1.4 in the formulation scheme shown in table 18.
TABLE 18 bionic algorithm leather sludge-doped cement ingredient decomposition
Number/type (%) Limestone Clay Sandstone Copper slag Tanning sludge KH SM IM
① 86.82 2.74 9.12 0.82 0.5 0.89024 2.10232 1.49987
As can be seen from the above embodiment, KH, SM and IM are very close to KH, SM and IM values, and the cement batching method based on the bionic algorithm in the invention is also suitable for the cement co-processing sludge.
The calculation case of the ingredients of the incineration fly ash in the cooperative treatment of the cement by using the algorithm is as follows:
incineration fly ash belongs to one of hazardous wastes, and one of the disposal modes is to mix the incineration fly ash into a cement raw material for cooperative disposal. Preferably, in the fly ash from incineration of household garbage, the proportion of each oxide is CaO: 10.95% of Al2O3：23.19%，Fe2O3：6.62%，SiO2：42.22%，SO3：4.22%。
The desired three rate values for conventional portland cement raw material incorporation into tannery sludge are KH =0.89, SM =2.1, and IM =1.4 for the formulation shown in table 19.
TABLE 19 bionic algorithm for cement ingredient decomposition by doping fly ash from incineration of domestic garbage
Number/type (%) Limestone Quartz sand Shale Copper slag Incineration fly ash of household garbage KH SM IM
① 82.90 9.99 0.00 2.10 5.01 0.89064 2.09957 1.50002
As can be seen from the above embodiment, KH, SM and IM are very close to KH, SM and IM values, and the cement batching method based on the bionic algorithm in the invention is also suitable for the cement synergistic treatment of the municipal solid waste incineration fly ash (hazardous waste).
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (8)

1. A solid waste preferential digestion driven cement batching method based on a bionic algorithm is characterized by comprising the following steps: the method integrates the component data of the solid waste raw materials into an attribute matrix, the mixture ratio of a plurality of solid waste raw materials is used as a vector to be optimized, the goal of maximally absorbing target waste residues and infinitely approaching an expected three-rate value is realized, the optimal mixture ratio is obtained by optimizing and calculating a bionic optimization algorithm represented by a non-dominated sorting multi-objective evolutionary algorithm, and the solid waste raw material ratio of the cement production raw material is realized.
2. A solid waste preferential consumption driven cement batching method based on biomimetic algorithm as recited in claim 1, characterized in that the attribute matrix is a matrix block a, a being a 5 x n matrix;
the first column of the matrix A is carbide slag, the second column is mixture, and the subsequent columns are other solid waste raw materials in turn, and vector quantity
Figure 143392DEST_PATH_IMAGE001
Represents the feeding percentage and vector quantity of each solid waste raw material in the cement raw material
Figure 861949DEST_PATH_IMAGE002
The total amount of five oxides in the cement raw material is shown, and the concrete form is as follows:
Figure 581644DEST_PATH_IMAGE003
·
Figure 625823DEST_PATH_IMAGE004
=
Figure 663924DEST_PATH_IMAGE005
A
Figure 451751DEST_PATH_IMAGE001
Figure 25952DEST_PATH_IMAGE006
wherein A is the chemical component data of a plurality of groups of cement raw materials, C1 represents the mass percentage content of CaO in the carbide slag, C2 represents the mass percentage content of CaO in the mixture, and so on; s1 represents SiO in carbide slag2S2 represents the mass percentage of the mixtureSiO2The mass percentage of the components is repeated; f1 represents Fe in carbide slag2O3F2 represents Fe in the mixture2O3The mass percentage of the components is repeated; a1 represents Al in carbide slag2O3A2 represents Al in the mixture2O3The mass percentage of the components is repeated; s1 represents SO in carbide slag3S2 represents SO in the mixture3And so on.
3. The method for cement blending driven by preferential consumption of solid wastes based on the biomimetic algorithm as recited in claim 1, wherein the expected three-rate value is calculated according to the feeding data of solid waste raw materials used in the existing cement production, i.e. the feeding type, the feeding percentage and the data corresponding to the properties of the fired cement clinker; the method comprises the following specific steps:
KH or LSF, SM and IM are expected three values;
estimating actual three-value KH or LSF, SM and IM of the total content of Y1, Y2 and … Yn oxides obtained by calculating the proportion of solid waste raw materials in the attribute matrix;
using the following function
Figure 241033DEST_PATH_IMAGE007
Or
Figure 267895DEST_PATH_IMAGE008
，
Figure 859413DEST_PATH_IMAGE009
，
Figure 288120DEST_PATH_IMAGE010
，
Figure 674102DEST_PATH_IMAGE011
As constraints, where KH or LSF, SM and IM are desired three-rate values, KH or LSF, SM and IM are actual three-rate values:
Figure 453840DEST_PATH_IMAGE012
Figure 583470DEST_PATH_IMAGE013
Figure 866683DEST_PATH_IMAGE014
Figure 689146DEST_PATH_IMAGE015
Figure 690600DEST_PATH_IMAGE016
or
Figure 358342DEST_PATH_IMAGE017
。
4. A solid waste preferential consumption driven cement batching method based on biomimetic algorithm as recited in claim 1, characterized in that the objective function characterizing the deviation of the three values
Figure 761641DEST_PATH_IMAGE007
，
Figure 20584DEST_PATH_IMAGE018
，
Figure 476711DEST_PATH_IMAGE019
，
Figure 213723DEST_PATH_IMAGE020
Are respectively provided with
Figure 471529DEST_PATH_IMAGE021
)，
Figure 635794DEST_PATH_IMAGE022
，
Figure 611840DEST_PATH_IMAGE023
，
Figure 886964DEST_PATH_IMAGE024
Is a target weight factor, wherein
Figure 999276DEST_PATH_IMAGE024
Far greater than
Figure 334443DEST_PATH_IMAGE025
)、
Figure 532206DEST_PATH_IMAGE026
、
Figure 611020DEST_PATH_IMAGE027
，
Figure 843419DEST_PATH_IMAGE028
Is that
Figure 83907DEST_PATH_IMAGE029
、
Figure 768966DEST_PATH_IMAGE022
、
Figure 385892DEST_PATH_IMAGE023
5 to 15 times of the total amount of the active carbon,
Figure 472797DEST_PATH_IMAGE029
、
Figure 884187DEST_PATH_IMAGE022
、
Figure 555077DEST_PATH_IMAGE023
the proportion of the three components is 0.5-3;
in ensuring
Figure 975694DEST_PATH_IMAGE030
，
Figure 651526DEST_PATH_IMAGE031
，
Figure 499397DEST_PATH_IMAGE032
，
Figure 159048DEST_PATH_IMAGE033
On the premise of (A) under the condition of (B),
Figure 117777DEST_PATH_IMAGE020
the increase of the weight factor causes
Figure 179274DEST_PATH_IMAGE007
，
Figure 198045DEST_PATH_IMAGE009
，
Figure 79414DEST_PATH_IMAGE019
It is possible to approach 0 more evenly, thereby ensuring that the actual three-rate value approaches the desired three-rate value indefinitely.
5. A biomimetic algorithm based solid waste preferential digestion driven cement batching method as recited in any one of claims 1 to 4, wherein the fifth objective function is an objective function of maximum solid waste raw material digestion represented by carbide slag
Figure 841833DEST_PATH_IMAGE034
；
Generating an initial population P after inputting historical feeding data, and generating a sub population Q through non-dominated sorting, bionic operation and genetic variationnMerging the offspring population and the parent population into RnGenerating a new father population through non-dominated sorting and congestion calculation, continuing genetic evolution to generate a new offspring population until an evolution algebra reaches a maximum set value or a fitness function is smaller than a threshold value, and obtaining a batch of optimal solutions by setting an optimal front-end individual coefficient, preferably 0.1-0.5; the optimal solutions are according to the consumption of carbide slag, namely an objective function
Figure 757837DEST_PATH_IMAGE034
And sequentially ordering from high to low, and taking the group which is arranged at the front as an optimal solution, namely the optimal solution which finally satisfies each objective function in a balanced manner.
6. The method for cement batching driven by preferential consumption of solid waste based on bionic algorithm as claimed in claim 1, characterized in that the batching ratio of several solid waste raw materials is written into attribute matrix, and when subsequently solving the optimal solution, these historical data can be randomly used as initial guess values, thereby accelerating the calculation of convergence speed.
7. The cement batching method driven by preferential consumption of solid wastes based on the bionic algorithm as recited in claim 1 is not only suitable for the proportioning optimization of solid waste raw materials of which part of solid waste raw materials are industrial solid wastes, household garbage or dangerous waste co-fired cement, but also suitable for the proportioning optimization of raw materials for the production of non-solid waste raw materials such as traditional portland cement.
8. The method for cement blending based on preferential consumption of solid wastes driven by a biomimetic algorithm as recited in claim 1, wherein the solid waste material comprises several of carbide slag, mixture, fly ash, slag, steel slag, silica powder, silica, incineration ash.
CN202110639138.6A 2021-06-08 2021-06-08 Cement batching method driven by preferential consumption of solid waste based on bionic algorithm Pending CN113609748A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110639138.6A CN113609748A (en) 2021-06-08 2021-06-08 Cement batching method driven by preferential consumption of solid waste based on bionic algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110639138.6A CN113609748A (en) 2021-06-08 2021-06-08 Cement batching method driven by preferential consumption of solid waste based on bionic algorithm

Publications (1)

Publication Number Publication Date
CN113609748A true CN113609748A (en) 2021-11-05

Family

ID=78303499

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110639138.6A Pending CN113609748A (en) 2021-06-08 2021-06-08 Cement batching method driven by preferential consumption of solid waste based on bionic algorithm

Country Status (1)

Country Link
CN (1) CN113609748A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117148810A (en) * 2023-11-01 2023-12-01 一夫科技股份有限公司 Beta-type building gypsum process regulation and control method and system combining application requirements
CN117299754A (en) * 2023-09-01 2023-12-29 北京科技大学 Multi-source solid waste recycling method based on calcium-silicon-aluminum-magnesium oxide allocation

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117299754A (en) * 2023-09-01 2023-12-29 北京科技大学 Multi-source solid waste recycling method based on calcium-silicon-aluminum-magnesium oxide allocation
CN117299754B (en) * 2023-09-01 2024-05-10 北京科技大学 Multi-source solid waste recycling method based on calcium-silicon-aluminum-magnesium oxide allocation
CN117148810A (en) * 2023-11-01 2023-12-01 一夫科技股份有限公司 Beta-type building gypsum process regulation and control method and system combining application requirements
CN117148810B (en) * 2023-11-01 2024-01-23 一夫科技股份有限公司 Beta-type building gypsum process regulation and control method and system combining application requirements

Similar Documents

Publication Publication Date Title
Shamsabadi et al. Machine learning-based compressive strength modelling of concrete incorporating waste marble powder
Mohammed et al. Soft computing techniques: systematic multiscale models to predict the compressive strength of HVFA concrete based on mix proportions and curing times
Alderete et al. Effective and sustainable use of municipal solid waste incineration bottom ash in concrete regarding strength and durability
CN113609748A (en) Cement batching method driven by preferential consumption of solid waste based on bionic algorithm
AU2004234122B2 (en) Cementitious material
Jin et al. Non-linear and mixed regression models in predicting sustainable concrete strength
Shamsabadi et al. Data-driven multicollinearity-aware multi-objective optimisation of green concrete mixes
Agor et al. Evaluation of sisal fiber and aluminum waste concrete blend for sustainable construction using adaptive neuro-fuzzy inference system
CN113033923B (en) Method for predicting, evaluating and optimizing cement clinker performance, device and system thereof
CN113160899A (en) NSGA-II algorithm-based sintering material multi-objective optimization method
Bisikirske et al. Multicriteria analysis of glass waste application
US20230104043A1 (en) Cement kiln modeling for improved operation
Ogbonna et al. Effects of cassava-peel-ash on mechanical properties of concrete
Hafez et al. Data-driven optimization tool for the functional, economic, and environmental properties of blended cement concrete using supplementary cementitious materials
Babajanzadeh et al. Compressive strength prediction of self-compacting concrete incorporating silica fume using artificial intelligence methods
CN101775868B (en) Method for sintering and curing industrial waste residue
Chandra Paul et al. An artificial intelligence model for computing optimum fly ash content for structural-grade concrete
CN114912712A (en) Solid waste co-processing cement ingredient control method coupled with feedforward artificial neural network and evolutionary algorithm
CN117172116A (en) Concrete compressive strength prediction method based on PSO-BP combined model
Özgür Deneme Modelling of compressive strength of self-compacting concrete containing fly ash by gene expression programming
Ziaei-Nia et al. Dynamic cost optimization method of concrete mix design
Omran et al. Prediction of Compressive Strength of ‘Green’Concrete Using Artificial Neural Networks
Jin et al. A Statistical Approach to Predicting Fresh State Properties of Sustainable Concrete
CN216837715U (en) System for utilize hot-blast cooperation of cement kiln to activate coal gangue
Rusna et al. Using Artificial Neural Networks for the Prediction of the Compressive Strength of Geopolymer Fly Ash

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