CN111814400A - Air compressor model selection method based on genetic algorithm - Google Patents

Air compressor model selection method based on genetic algorithm Download PDF

Info

Publication number
CN111814400A
CN111814400A CN202010657800.6A CN202010657800A CN111814400A CN 111814400 A CN111814400 A CN 111814400A CN 202010657800 A CN202010657800 A CN 202010657800A CN 111814400 A CN111814400 A CN 111814400A
Authority
CN
China
Prior art keywords
air
fitness
genetic algorithm
function
compressor
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.)
Granted
Application number
CN202010657800.6A
Other languages
Chinese (zh)
Other versions
CN111814400B (en
Inventor
宋印东
徐静雅
马旭
徐毅煜
沈九兵
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.)
Jiangsu University of Science and Technology
Original Assignee
Jiangsu University of Science and Technology
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 Jiangsu University of Science and Technology filed Critical Jiangsu University of Science and Technology
Priority to CN202010657800.6A priority Critical patent/CN111814400B/en
Publication of CN111814400A publication Critical patent/CN111814400A/en
Application granted granted Critical
Publication of CN111814400B publication Critical patent/CN111814400B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Applications Or Details Of Rotary Compressors (AREA)

Abstract

The invention discloses an air compressor type selection method based on a genetic algorithm, which comprises the steps of preliminarily selecting the type and the maximum number of air compressors according to air consumption and rated working pressure; acquiring an objective function of a genetic algorithm according to the preliminarily selected air compressor parameters, and acquiring a fitness function of the genetic algorithm according to a conversion rule of the objective function and an optimization problem; acquiring a fitness optimization function of the genetic algorithm according to the exponential penalty factor and the fitness function; and performing optimization calculation on the fitness optimization function by using the genetic algorithm to obtain each variable parameter of the corresponding objective function under the optimal fitness optimization function. The invention has the beneficial effects that: the minimum cost is optimized through a genetic algorithm, and the corresponding variable parameter in the minimum cost is quickly and accurately obtained, so that the aim of saving the cost is fulfilled, and the defects in the existing method are overcome.

Description

Air compressor model selection method based on genetic algorithm
Technical Field
The invention relates to the technical field of air compressor model selection, in particular to an air compressor model selection method based on a genetic algorithm.
Background
In recent years, with the increasing demand for energy and the decreasing available energy, energy conservation has become an irreversible trend. The air compressor, one of the indispensable devices in the industry, consumes a large amount of electric energy every day, and when the air compressor is in a partial load or no-load condition for a long time, the air compressor consumes a large amount of electric energy, so avoiding the partial load or no-load condition of the air compressor is one of the most important energy-saving ways in the operation process of the air compressor.
Different types and numbers of air compressors can be adopted to meet certain air consumption. The cost required for different types and numbers of air compressors may vary throughout the service life. In order to minimize the overall cost while meeting the gas usage requirements, a specific assortment of compressor types and numbers is required. In order to find out the specific collocation, the most commonly used methods at present are an estimation method and an exhaustive method, wherein the estimation method is to estimate the most suitable type and number in a plurality of air compressors according to the air consumption and the working pressure, but the method saves time, but the randomness is too high, and the most probable method cannot find the type selection scheme with the lowest cost; the exhaustion method is characterized in that a plurality of air compressors are sequentially matched according to air consumption and working pressure, then the total cost is respectively calculated, and finally the type and the number of the corresponding air compressors with the lowest cost are selected. Therefore, how to efficiently and accurately find the air compressor with the lowest total cost is the direction of research. Aiming at the defects of the existing method, a new air compressor model selection method is needed to be provided, and an air compressor with low cost and good effect can be quickly and accurately selected.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the technical problem solved by the invention is as follows: the air compressor model selection method based on the genetic algorithm is provided, and the air compressor with the optimal cost can be quickly and accurately selected.
In order to solve the technical problems, the invention provides the following technical scheme: a genetic algorithm-based air compressor model selection method comprises the steps of preliminarily selecting the type and the maximum number of air compressors according to air consumption and rated working pressure; acquiring an objective function of a genetic algorithm according to the preliminarily selected air compressor parameters, and acquiring a fitness function of the genetic algorithm according to a conversion rule of the objective function and an optimization problem; acquiring a fitness optimization function of the genetic algorithm according to the exponential penalty factor and the fitness function; and performing optimization calculation on the fitness optimization function by using the genetic algorithm to obtain each variable parameter of the corresponding objective function under the optimal fitness optimization function.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the preliminarily selected air compressor comprises an air centrifugal compressor A and an air screw compressor B, and the types of the air centrifugal compressor A and the air screw compressor B are AiAnd BjAnd of the kind AiAnd BjThe corresponding number of the units is XiAnd YjAnd (4) a table.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the objective function is defined as the function of the target,
Figure BDA0002577383070000021
whereinF (X, Y) denotes an objective function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like.
The fitness function is:
F(X,Y)＝-f(X,Y)
where F (X, Y) represents a fitness function.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the fitness optimization function is as follows,
F′(X,Y)＝F(X,Y)×10max{0,-g(X,Y)}
wherein F' (X, Y) represents a fitness optimization function, 10max{0,-g(X,Y)}For the exponential penalty factor, g (X, Y) is the gas difference function.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the expression of the gas difference function g (X, Y) is,
Figure BDA0002577383070000022
wherein Q isAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjThe rated air displacement of the air-like screw compressor, Q is the air consumption.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the optimizing calculation by utilizing the genetic algorithm further comprises the following steps of coding; generating an initial population; calculating individual fitness according to a fitness optimization function; judging whether constraint conditions are met; and judging whether the termination condition is met, if so, outputting a result, otherwise, carrying out selection, intersection and variation algorithms and repeatedly calculating until the termination condition is met.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the genetic algorithm is coded by adopting a multi-parameter binary coding mode.
As a preferable embodiment of the air compressor model selection method based on the genetic algorithm according to the present invention, wherein: the termination condition is whether the fitness and the group fitness of the optimal individual rise or not, if the fitness and the group fitness of the optimal individual do not rise any more, the termination condition is met, and the algorithm is ended; if the fitness and the population fitness of the optimal individual are increased, the terminal condition is not met, selection, crossing and mutation algorithms need to be carried out, the evolutionary algebra memory is updated, the population is used as a new next-generation population, repeated circulation is carried out until the terminal condition is met, the corresponding result is output, and the algorithm is ended.
The invention has the beneficial effects that: the invention optimizes the minimum cost through a genetic algorithm to obtain the corresponding variable parameter at the minimum cost, thereby achieving the purpose of saving the cost. The method overcomes the defects of low accuracy or low efficiency in the prior method and has better practicability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a schematic overall flow chart of a genetic algorithm-based air compressor model selection method according to this embodiment;
fig. 2 is a schematic flow chart of the genetic algorithm performing optimization calculation on the fitness optimization function in this embodiment.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to the schematic diagram of fig. 1, the schematic diagram shows a genetic algorithm-based air compressor model selection method proposed in this embodiment, which is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
s1: preliminarily selecting the type and the maximum number of the air compressors according to the air consumption and the rated working pressure;
specifically, the preliminarily selected air compressors comprise an air centrifugal compressor A and an air screw compressor B, the types of the air centrifugal compressor A and the air screw compressor B are preliminarily selected according to the known air consumption Q and the rated working pressure P required by a user, the types of the selected air centrifugal compressor and the air screw compressor are required to be close to the known air consumption Q, and the pressure is equal to the rated working pressure P.
The preliminarily selected air centrifugal compressor A and the air screw compressor B are respectively AiAnd BjAnd of the kind AiAnd BjThe corresponding number of the units is XiAnd YjAnd (4) a table. Wherein i ∈ [1, a ]]I is the type code of the air centrifugal compressor A, and a corresponds to the total number of the types of the centrifugal machine A; j is an element of [1, b ]]B is the total number of the types of the air screw compressors B, and i, j, a and B are integers which are more than or equal to 1. Air centrifugal compressor A of each kindiThe number of the units is XiPlatform, air screw compressor B of each kindjThe number of the units is YjStage, XiAnd YjThe numerical value of (a) is a natural number, and is used as a variable parameter in the genetic algorithm of the present embodiment.
Determining the maximum number c of the air compressors according to the air consumption Q and the preliminarily selected minimum rated air displacement of the air centrifugal compressor A and the air screw compressor B, wherein c is a positive integer, and understanding that X isi∈[0,c]，Yj∈[0,c]The maximum number c is determined by dividing the gas consumption Q by the minimum rated gas displacement and taking the minimum positive integer greater than or equal to the quotient as the maximum number c.
S2: acquiring an objective function of the genetic algorithm according to the preliminarily selected air compressor parameters, and acquiring a fitness function of the genetic algorithm according to a conversion rule of the objective function and an optimization problem;
specifically, the objective function is the total cost of the selected air compressor, and the calculation formula of the objective function is,
Figure BDA0002577383070000051
wherein f (X, Y) represents an objective function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like. In this example, SAiAnd SBjRespectively, are as follows,
SAi＝GAi+YAi+WAi+DAi
SBj＝GBj+YBj+WBj+DBj
wherein G isAiAnd GBjAre respectively AiAir centrifugal compressor and BjPurchase costs for seed air screw compressors; y isAiAnd YBjAre respectively AiAir centrifugal compressor and BjThe running cost of the air screw compressor can be obtained by multiplying the matching power of the air compressor by the service time by the electric charge; wAiAnd WBjAre respectively AiAir centrifugal compressor and BjMaintenance costs for air screw compressors; dAiAnd DBjAre respectively AiAir centrifugal compressor and BjThe unit of the electric energy loss is element when the air screw compressor is partially loaded or unloaded.
Since the minimum value of the total cost, that is, the minimum value of the objective function, needs to be obtained in this embodiment, the objective function needs to be converted into a fitness function, which is calculated by the following formula,
F(X,Y)＝-f(X,Y)
where F (X, Y) represents a fitness function.
S3: acquiring a fitness optimization function of the algorithm according to the exponential penalty factor and the fitness function;
wherein, inequality constraint needs to be converted into penalty function, in this embodiment, an exponential penalty factor is introduced to reduce the fitness of the corresponding individual, and then the fitness optimization function can be converted into,
F′(X,Y)＝F(X,Y)×10max{0,-g(X,Y)}
wherein F' (X, Y) represents a fitness optimization function, 10max{0,-g(X,Y)}For an exponential penalty factor, g (X, Y) is the gas difference function.
Specifically, in the air compressor model selection, the constraint condition that the total rated displacement of the air compressor after the model selection is greater than or equal to the gas consumption is satisfied, that is, the value of the gas difference function g (X, Y) should be greater than or equal to 0, wherein the expression of the gas difference function g (X, Y) is,
Figure BDA0002577383070000061
wherein Q isAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjThe rated air displacement of the air-like screw compressor, Q is the air consumption.
S4: and optimizing and calculating the fitness optimization function by using a genetic algorithm to obtain each variable parameter of the corresponding objective function under the optimal fitness optimization function.
Referring to the schematic of fig. 2, which is an interactive flow diagram of an optimization calculation using a genetic algorithm, the process further comprises the following steps,
s4-1: coding; the solution data of the variable parameter solution space is expressed as genotype string structure data of the genetic space, and the algorithm adopts a multi-parameter binary coding mode. Because the number of the types of the air centrifugal compressor A and the air screw compressor B is a and B respectively, the number of the air centrifugal compressor A and the number of the air screw compressor B can be regarded as a group a and a group B respectively, and the range of the number of the air centrifugal compressor A and the air screw compressor B in each group is [0, c ], namely the problem of optimization of the type selection of the compressor at the level of (a + B) factor c is solved.
S4-2: generating an initial population;
specifically, M initial string structure data, that is, M individuals, are randomly generated to form an initial population, and iteration is started with this as an initial point, and an evolution algebra counter t is set to 1.
S4-3: calculating individual fitness according to a fitness optimization function; from the foregoing steps, the fitness optimization function in the present embodiment is F' (X, Y).
S4-4: and judging whether the constraint condition is met. Wherein the constraint condition is
Figure BDA0002577383070000071
Wherein g (X, Y) is a gas difference function determined from the total rated displacement and gas usage of the selected air compressor, QAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjThe rated air displacement of the air-like screw compressor, Q is the air consumption.
The gas difference function g (X, Y) is determined according to the total rated exhaust gas quantity and gas consumption quantity of the selected air compressor, when g (X, Y) is more than or equal to 0, the constraint condition is met, and F' (X, Y) is more than or equal to F (X, Y); when g (X, Y)<When 0, if the constraint condition is not satisfied, passing through an exponential penalty factor of 10max{0,-g(X,Y)}After multiplication, the solution of the fitness optimization function F' (X, Y) will be reduced to a small number and thus be rejected under the action of the optimization operator.
S4-5: and judging whether the termination condition is met. Wherein, the termination condition is that when the fitness of the optimal individual and the population fitness do not rise any more, the algorithm is terminated.
Specifically, the termination condition is whether the fitness and the group fitness of the optimal individual rise, if the fitness and the group fitness of the optimal individual do not rise any more, the termination condition is met, and the algorithm is ended; if the fitness and the population fitness of the optimal individual are increased, the terminal condition is not met, selection, crossing and mutation algorithms need to be carried out, the evolutionary algebra memory t +1 is updated, the population is used as a new next generation population, the circulation is repeated until the terminal condition is met, the corresponding result is output, and the algorithm is ended.
The selection operator adopted by the selection algorithm in the embodiment is a proportion selection operator, that is, the probability of the fitness of each individual is used to determine the legacy possibility of the descendants of the individual, and the probability of each individual being selected is in direct proportion to the fitness of the individual, that is, the higher the fitness is, the higher the probability of the individual being selected is, and the lower the probability of the individual being selected is, otherwise, the lower the probability of the individual being selected is. In the algorithm, each individual is subjected to descending order arrangement according to the fitness of the individual, the first N individuals are recorded and are copied into M individuals according to a certain proportion to obtain a population P' (t), wherein N is less than M.
The cross algorithm adopts a random pairing method, namely M individuals in a group are paired in pairs in a random mode to form an M/2 paired individual group, and the cross operation is performed among the paired individuals. The crossover operator used in the crossover algorithm in this embodiment is a single-point crossover operator, that is, only one crossover point is randomly set in the structure of the individual genotype string, and then the genotypes of the two parents are exchanged from this point to obtain the population P "(t).
The mutation operator adopted by the mutation algorithm is a basic mutation operator, namely, one or more gene values are randomly selected from the individual genotype string structure by using the mutation probability Pm to perform mutation operation, so as to obtain a population P' (t).
When the termination condition is not met, the selection, crossing and mutation algorithms are required to be carried out, the evolutionary algebra memory t +1 is updated, the population is used as a new next generation population, the circulation is repeated until the termination condition is met, and finally, the corresponding result is output and the algorithm is ended. Wherein, the output result is the type A of the air centrifugal compressor A and the air screw compressor B corresponding to the maximum fitnessiAnd BjAnd their respectively corresponding number XiAnd Yj。
Scene one:
in order to verify the advantages of the air compressor model selection method proposed in this embodiment in practical application relative to the conventional method, the following experiment was performed:
suppose that the maximum gas usage required by a user is 420m3Min, rated working pressure 0.8 MPa. The air compressor is thus type-selected.
1. By the method of the invention
S1: preliminarily selecting the type and the maximum number of the air compressors according to the air consumption and the rated working pressure;
specifically, the gas consumption Q is 420m3The type A of the air centrifugal compressor A and the air screw compressor B is preliminarily selected according to the min and the rated working pressure P which is 0.8MPaiAnd Bj. The initial selection result is
Ai，i∈[1,3]：A1：QA1＝150m3/min,PA1＝0.8MPa；A2：QA2＝180m3/min,PA2＝0.8MPa；A3：QA3＝210m3/min,PA3＝0.8MPa；
Bj，j∈[1,3]：B1：QB1＝20m3/min,PB1＝0.8MPa；B2：QB2＝40m3/min,PB2＝0.8MPa；B3：QB3＝60m3/min,PB3＝0.8MPa。
Air centrifugal compressor A with initial selectioniAnd air screw compressor BjThe corresponding number of the units is XiAnd Yj，XiAnd YjThe numerical value of (a) is a natural number, and is used as a variable parameter in the genetic algorithm of the present embodiment.
According to the gas consumption Q being 420m3Min, and the initially selected minimum rated displacement Q of the air centrifugal compressor A and the air screw compressor BB1＝20m3The maximum number of air compressors c, 420/20, 21 is determined by/min, it being understood that X isi∈[0,21]，Yj∈[0,21]。
S2: acquiring an objective function of a genetic algorithm according to the preliminarily selected air compressor parameters, and acquiring a fitness function of the algorithm according to a conversion rule of the objective function and an optimization problem;
specifically, the objective function is the total cost of the selected air compressor, and the calculation formula of the objective function is,
Figure BDA0002577383070000081
wherein f (X, Y) represents an objective function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like. In this example, SAiAnd SBjRespectively, are as follows,
SAi＝GAi+YAi+WAi+DAi
SBj＝GBj+YBj+WBj+DBj
wherein G isAiAnd GBjAre respectively AiAir centrifugal compressor and BjPurchase costs for seed air screw compressors; y isAiAnd YBjAre respectively AiAir centrifugal compressor and BjThe running cost of the air screw compressor can be obtained by multiplying the matching power of the air compressor by the service time by the electric charge; wAiAnd WBjAre respectively AiAir centrifugal compressor and BjMaintenance costs for air screw compressors; dAiAnd DBjAre respectively AiAir centrifugal compressor and BjThe unit of the electric energy loss is element when the air screw compressor is partially loaded or unloaded.
Since the minimum value of the total cost, that is, the minimum value of the objective function, needs to be obtained in this embodiment, the objective function needs to be converted into a fitness function, which is calculated by the following formula,
F(X,Y)＝-f(X,Y)
where F (X, Y) represents a fitness function.
S3: acquiring a fitness optimization function of the algorithm according to the exponential penalty factor and the fitness function;
wherein, inequality constraint needs to be converted into penalty function, in this embodiment, an exponential penalty factor is introduced to reduce the fitness of the corresponding individual, and then the fitness optimization function can be converted into,
F′(X,Y)＝F(X,Y)×10max{0,-g(X,Y)}
wherein F' (X, Y) represents a fitness optimization function, 10max{0,-g(X,Y)}For an exponential penalty factor, g (X, Y) is the gas difference function.
Specifically, in the air compressor model selection, the constraint condition that the total rated displacement of the air compressor after the model selection is greater than or equal to the gas consumption is satisfied, that is, the value of the gas difference function g (X, Y) should be greater than or equal to 0, wherein the expression of the gas difference function g (X, Y) is,
Figure BDA0002577383070000091
wherein Q isAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjRated displacement of air screw compressor.
S4: and optimizing and calculating the fitness optimization function by using a genetic algorithm to obtain each variable parameter of the corresponding objective function under the optimal fitness optimization function.
Referring to the schematic of fig. 2, there is shown an interactive flow diagram of an optimization calculation using a genetic algorithm, the process comprising the steps of,
s4-1: coding; the solution data of the variable parameter solution space is expressed as genotype string structure data of the genetic space, and the algorithm adopts a multi-parameter binary coding mode. Because the number of the types of the air centrifugal compressor A and the air screw compressor B is 3, the number of the air centrifugal compressor A and the number of the air screw compressor B can be regarded as 3 groups, and the range of the number of each group of the air centrifugal compressor A and the air screw compressor B is [0,21], namely the model selection optimization problem of the compressor with the level of 6 factors 21 is solved.
S4-2: generating an initial population;
specifically, 100 initial string structure data, that is, 100 individuals, are randomly generated to form an initial population, and iteration is started with this as an initial point, and an evolution algebra counter t is set to 1.
S4-3: calculating individual fitness according to a fitness optimization function; from the foregoing steps, the fitness optimization function in the present embodiment is F' (X, Y).
S4-4: and judging whether the constraint condition is met. Wherein the constraint condition is
Figure BDA0002577383070000101
Wherein g (X, Y) is a gas difference function determined from the total rated displacement and gas usage of the selected air compressor, QAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjRated displacement of air screw compressor.
The gas difference function g (X, Y) is determined according to the total rated exhaust gas quantity and gas consumption quantity of the selected air compressor, when g (X, Y) is more than or equal to 0, the constraint condition is met, and F' (X, Y) is more than or equal to F (X, Y); when g (X, Y)<When 0, if the constraint condition is not satisfied, passing through an exponential penalty factor of 10max{0,-g(X,Y)}After multiplication, the solution of the fitness optimization function F' (X, Y) will be reduced to a small number and thus be rejected under the action of the optimization operator.
S4-5: and judging whether the termination condition is met. Wherein, the termination condition is that when the fitness of the optimal individual and the population fitness do not rise any more, the algorithm is terminated.
Specifically, if the end conditions that the fitness of the optimal individual and the population fitness do not rise any more are met, the algorithm is ended; if the termination condition is not met, selection, crossing and mutation algorithms need to be carried out, the evolutionary algebra memory t +1 is updated, the population is used as a new next generation population, the circulation is repeated until the termination condition is met, the corresponding result is output, and the algorithm is ended.
The selection operator adopted by the selection algorithm in the embodiment is a proportion selection operator, that is, the probability of the fitness of each individual is used to determine the legacy possibility of the descendants of the individual, and the probability of each individual being selected is in direct proportion to the fitness of the individual, that is, the higher the fitness is, the higher the probability of the individual being selected is, and the lower the probability of the individual being selected is, otherwise, the lower the probability of the individual being selected is. In the algorithm, each individual is subjected to descending order arrangement according to the fitness of the individual, the first 30 individuals are recorded and are copied into 100 individuals according to a certain proportion to obtain a population P' (t).
The cross algorithm adopts a random pairing method, namely 100 individuals in the group are paired in pairs in a random mode to form a 50-pair paired individual group, and the cross operation is performed among the paired individuals. The crossover operator used in the crossover algorithm in this embodiment is a single-point crossover operator, that is, only one crossover point is randomly set in the structure of the individual genotype string, and then the genotypes of the two parents are exchanged from this point to obtain the population P "(t).
The mutation operator adopted by the mutation algorithm is a basic mutation operator, namely one or more gene values are randomly selected from the individual genotype string structure by using the mutation probability of 0.005 to perform mutation operation, so as to obtain a population P' (t).
When the termination condition is not met, the selection, crossing and mutation algorithms are required to be carried out, the evolutionary algebra memory t +1 is updated, the population is used as a new next generation population, the circulation is repeated until the termination condition is met, and finally, the corresponding result is output and the algorithm is ended. Wherein, the output corresponding result is the type A of the air centrifugal compressor A and the air screw compressor B corresponding to the maximum fitnessiAnd BjAnd their respectively corresponding number XiAnd Yj。
2. By conventional exhaustion methods
Firstly, according to the maximum gas consumption Q being 420m3The type A of the air centrifugal compressor A and the air screw compressor B is preliminarily selected according to the min and the rated working pressure P which is 0.8MPaiAnd Bj. The initial selection result is
Ai，i∈[1,3]：A1：QA1＝150m3/min,PA1＝0.8MPa；A2：QA2＝180m3/min,PA2＝0.8MPa；A3：QA3＝210m3/min,PA3＝0.8MPa；
Bj，j∈[1,3]：B1：QB1＝20m3/min,PB1＝0.8MPa；B2：QB2＝40m3/min,PB2＝0.8MPa；B3：QB3＝60m3/min,PB3＝0.8MPa。
Air centrifugal compressor A with initial selectioniAnd air screw compressor BjThe corresponding number of the units is XiAnd Yj，XiAnd YjThe numerical value of (1) is a natural number.
According to the maximum gas consumption Q of 420m3Min, and the initially selected minimum rated displacement Q of the air centrifugal compressor A and the air screw compressor BB1＝20m3Min determines the maximum number of air compressors c, c 420/20 21, Xi∈[0,21]，Yj∈[0,21]。
Then all possibilities are arranged for all selected air compressors, e.g. the first combination is X1＝1，X2＝0，X3＝0，Y1＝0，Y2＝0，Y30, the last combination being X1＝21，X2＝21，X3＝21，Y1＝21，Y2＝21，Y321. This, in total, amounts to 621≈2.19×1016And (4) a combination mode.
Respectively calculating the required cost corresponding to each combination mode, wherein the cost function is
Figure BDA0002577383070000111
Wherein f (X, Y) represents a cost function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like. In this example, SAiAnd SBjRespectively, are as follows,
SAi＝GAi+YAi+WAi+DAi
SBj＝GBj+YBj+WBj+DBj
wherein G isAiAnd GBjAre respectively AiAir centrifugal compressor and BjPurchase costs for seed air screw compressors; y isAiAnd YBjAre respectively AiAir centrifugal compressor and BjThe running cost of the air screw compressor can be obtained by multiplying the matching power of the air compressor by the service time by the electric charge; wAiAnd WBjAre respectively AiAir centrifugal compressor and BjMaintenance costs for air screw compressors; dAiAnd DBjAre respectively AiAir centrifugal compressor and BjThe unit of the electric energy loss is element when the air screw compressor is partially loaded or unloaded.
In the air compressor model selection, the constraint condition which must be satisfied is that the total rated displacement of the air compressor after the model selection is greater than or equal to the gas consumption, namely the value of a gas difference function g (X, Y) should be greater than or equal to 0, wherein the expression of the gas difference function g (X, Y) is,
Figure BDA0002577383070000121
wherein Q isAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjRated displacement of air screw compressor.
If g (X, Y) is more than or equal to 0, the constraint condition is met, and corresponding combined data are reserved; and when g (X, Y) <0, the constraint condition is not satisfied, and corresponding combined data is removed.
Finally, the combination corresponding to the type A of the air centrifugal compressor A and the air screw compressor B is selected from the reserved combinations, wherein the corresponding combination has the minimum cost function valueiAnd BjAnd their respectively corresponding number XiAnd Yj。
Comparing the method of the present invention with the traditional exhaustion method, firstly, the method adopted by the present invention only needs to select 100 initial selection groups, the subsequent type selection process only needs to calculate the type selection by the genetic algorithm, and all the results do not need to be calculated one by one, the general genetic algorithm calculates 1000 generations to be convergent, so the calculation of 100 × 1000 to 10 in the experiment will be carried out5Convergence after the second time; while the traditional exhaustion method needs to calculate 2.19 multiplied by 1016In combination, it is obvious that the model selection speed of the method adopted by the invention is far greater than that of an exhaustive method. Secondly, although the result obtained by the traditional exhaustion method is an accurate optimal value; however, the calculation termination condition of the method is that the fitness of the optimal individual and the population fitness do not rise any more, so that the difference between the obtained result and the actual optimal value is very small or even the actual optimal value, and the difference between the results obtained by the two methods is very small or even no difference. In conclusion, the method adopted by the invention is greatly superior to the traditional exhaustive method.
3. Using conventional estimation methods
According to the maximum gas consumption Q of 420m3Selecting the type A of the air centrifugal compressor A and the air screw compressor B according to the rated working pressure P of 0.8MPaiAnd BjRecording the selected air centrifugal compressor AiAnd air screw compressor BjThe corresponding number of the units is XiAnd Yj，XiAnd YjThe numerical value of (1) is a natural number.
The final result selected by the estimation method is
Ai，i＝1：A1：QA1＝210m3/min,PA1＝0.8MPa，X1＝2
A1：QA1＝210m3/min,PA1The matched power of 0.8MPa is 1200kW, and the exhaust gas quantity adjusting range is 100-60%.
Calculating the required cost corresponding to the combination mode, wherein the cost function is
Figure BDA0002577383070000131
Wherein f (X, Y) represents a cost function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like. In this example, SAiAnd SBjRespectively, are as follows,
SAi＝GAi+YAi+WAi+DAi
SBj＝GBj+YBj+WBj+DBj
wherein G isAiAnd GBjAre respectively AiAir centrifugal compressor and BjPurchase costs for seed air screw compressors; y isAiAnd YBjAre respectively AiAir centrifugal compressor and BjThe running cost of the air screw compressor can be obtained by multiplying the matching power of the air compressor by the service time by the electric charge; wAiAnd WBjAre respectively AiAir centrifugal compressor and BjMaintenance costs for air screw compressors; dAiAnd DBjAre respectively AiAir centrifugal compressor and BjThe unit of the electric energy loss is element when the air screw compressor is partially loaded or unloaded.
The average gas consumption of the air compressor in one year is 60% of full load operation, namely 0.60 multiplied by 420 to 252m3And/min. A centrifuge A is required1Operating at full capacity, another centrifuge A1Run at partial load of 60% full load. Queried, A running at full load1：QA1＝210m3/min,PA1When the machine works for 16 hours every day under the pressure of 0.8MPa, the cost corresponding to one year is GA1＝10000,YA1＝1200×365×16×0.5＝3504000,WA1＝60000,DA10; partial load operation at 60% full load A1：QA1＝210m3/min,PA1When the machine works for 16 hours every day under the pressure of 0.8MPa, the cost corresponding to one year is GA1＝10000,YA1＝0,WA1＝60000,DA1The final cost is f (X, Y) 10000+3504000+60000+10000+60000+ 3500 +2102400 ═ 5746400 dollars, 0.6 × 3504000 ═ 2102400.
The end result selected by the method of the invention is
Ai，i＝1：A1：QA1＝150m3/min,PA1＝0.8MPa，X1＝2；
Bj，j＝1：B1：QB1＝60m3/min,PB1＝0.8Mpa，Y1＝2。
A1：QA1＝150m3/min,PA1The matched power is 900kW under 0.8MPa, and the exhaust gas quantity adjusting range is 100-80%;
B1：QB1＝60m3/min,PB1the matched power of 0.8Mpa is 320kW, and the exhaust gas quantity adjusting range is 100-30%.
The average gas consumption of the air compressor in one year is 60% of full load operation, namely 0.60 multiplied by 420 to 252m3And/min. A centrifuge A is required1Two screw machines B operating at full load1Run at a partial load of 85% full load. Through inquiry, D A is operated according to full load1：QA1＝150m3/min,PA1When the machine works for 16 hours every day under the pressure of 0.8MPa, the cost corresponding to one year is GA1＝9000,YA1＝900×365×16×0.5＝2628000,WA1＝60000,DA10; b operating at partial load of 85% full load1：QB1＝60m3/min,PB1The cost of each year is G when the work is carried out for 16 hours every day under 0.8MpaB1＝8100,YB1＝0,WB1＝50000,DB1When the cost is 0.85 × 320 × 365 × 16 × 0.5 ═ 794240, the final cost is 2 × 9000+2628000+60000+2 × (8100+50000+794240) ═ 4410680 dollars.
Comparing the method of the present invention with the conventional estimation method, the one-year cost of the final model selection result using the method of the present invention is 4410680 yuan, and the method of the present invention is usedThe cost of the final model selection result of the traditional estimation method is 5746400 yuan, and the model selection result adopting the method of the invention saves more than the model selection result adopting the traditional estimation method
Figure BDA0002577383070000141
The model selection of the air compressor is carried out by adopting an estimation method, and the actual optimal value cannot be selected at a high probability, so that great financial resources are wasted in the using process. In conclusion, the method adopted by the invention is greatly superior to the traditional estimation method.
Compared with the traditional exhaustion method and the traditional estimation method, the method has the advantages that the calculation speed is greatly superior to that of the exhaustion method, the accuracy of type selection is greatly superior to that of the estimation method, the advantages of high accuracy of the exhaustion method and high calculation speed of the estimation method are achieved, and the defects of low calculation speed of the exhaustion method and low accuracy of the estimation method are overcome. In conclusion, the method adopted by the invention is greatly superior to the traditional method.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.

Claims (8)

1. A genetic algorithm-based air compressor model selection method is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
preliminarily selecting the type and the maximum number of the air compressors according to the air consumption and the rated working pressure;
acquiring an objective function of a genetic algorithm according to the preliminarily selected air compressor parameters, and acquiring a fitness function of the genetic algorithm according to a conversion rule of the objective function and an optimization problem;
acquiring a fitness optimization function of the genetic algorithm according to the exponential penalty factor and the fitness function;
and performing optimization calculation on the fitness optimization function by using the genetic algorithm to obtain each variable parameter of the corresponding objective function under the optimal fitness optimization function.
2. The genetic algorithm-based air compressor typing method of claim 1, wherein: the preliminarily selected air compressor comprises an air centrifugal compressor A and an air screw compressor B, and the types of the air centrifugal compressor A and the air screw compressor B are AiAnd BjAnd of the kind AiAnd BjThe corresponding number of the units is XiAnd YjAnd (4) a table.
3. The genetic algorithm-based air compressor model selection method of claim 1 or 2, wherein: the objective function is defined as the function of the target,
Figure FDA0002577383060000011
wherein f (X, Y) represents an objective function, SAiIs A atiThe required cost of the air-like centrifugal compressor, SBjIs the number BjThe required cost of air screw compressor-like.
The fitness function is:
F(X,Y)＝-f(X,Y)
where F (X, Y) represents a fitness function.
4. The genetic algorithm-based air compressor typing method of claim 3, wherein: the fitness optimization function is as follows,
F′(X,Y)＝F(X,Y)×10max{0,-g(X,Y)}
wherein F' (X, Y) represents a fitness optimization function, 10max{0,-g(X,Y)}For the exponential penalty factor, g (X, Y) is the gas difference function.
5. The genetic algorithm-based air compressor typing method of claim 4, wherein: the expression of the gas difference function g (X, Y) is,
Figure FDA0002577383060000021
wherein Q isAiIs A atiRated displacement, Q, of air-like centrifugal compressorBjIs the number BjThe rated air displacement of the air-like screw compressor, Q is the air consumption.
6. The genetic algorithm-based air compressor model selection method of claim 4 or 5, wherein: the optimizing calculation using the genetic algorithm further comprises the steps of,
coding; generating an initial population; calculating individual fitness according to a fitness optimization function; judging whether constraint conditions are met; and judging whether the termination condition is met, if so, outputting a result, otherwise, carrying out selection, intersection and variation algorithms and repeatedly calculating until the termination condition is met.
7. The genetic algorithm-based air compressor typing method of claim 6, wherein: the genetic algorithm is coded by adopting a multi-parameter binary coding mode.
8. The genetic algorithm-based air compressor selection method of any one of claims 4, 5 or 7, wherein: the termination condition is whether the fitness of the optimal individual and the population fitness rise or not,
if the fitness of the optimal individual and the group fitness do not rise any more, the termination condition is met, and the algorithm is ended; if the fitness and the population fitness of the optimal individual are increased, the terminal condition is not met, selection, crossing and mutation algorithms need to be carried out, the evolutionary algebra memory is updated, the population is used as a new next-generation population, repeated circulation is carried out until the terminal condition is met, the corresponding result is output, and the algorithm is ended.
CN202010657800.6A 2020-07-09 2020-07-09 Air compressor model selection method based on genetic algorithm Active CN111814400B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010657800.6A CN111814400B (en) 2020-07-09 2020-07-09 Air compressor model selection method based on genetic algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010657800.6A CN111814400B (en) 2020-07-09 2020-07-09 Air compressor model selection method based on genetic algorithm

Publications (2)

Publication Number Publication Date
CN111814400A true CN111814400A (en) 2020-10-23
CN111814400B CN111814400B (en) 2021-11-26

Family

ID=72842124

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010657800.6A Active CN111814400B (en) 2020-07-09 2020-07-09 Air compressor model selection method based on genetic algorithm

Country Status (1)

Country Link
CN (1) CN111814400B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112365101A (en) * 2020-12-09 2021-02-12 国网山东省电力公司电力科学研究院 Thermal power generating unit peak regulation combined total coal consumption optimization method and system based on genetic algorithm
CN113807015A (en) * 2021-09-17 2021-12-17 南方电网科学研究院有限责任公司 Parameter optimization method, device, equipment and storage medium for compressed air energy storage system
TWI833604B (en) * 2023-03-15 2024-02-21 緯創資通股份有限公司 Equipment parameter recommendation method, electronic device and non-transitory computer readable recording medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103107963A (en) * 2013-01-09 2013-05-15 王少夫 Broadband matching network optimization method based on hybrid genetic algorithm
CN103177185A (en) * 2013-03-13 2013-06-26 中国石油大学(北京) Method and device for polycrystalline diamond compact bit (PDC) drilling parameter multi-objective optimization
CN104184170A (en) * 2014-07-18 2014-12-03 国网上海市电力公司 Independent microgrid configuration optimization method based on improved adaptive genetic algorithm

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103107963A (en) * 2013-01-09 2013-05-15 王少夫 Broadband matching network optimization method based on hybrid genetic algorithm
CN103177185A (en) * 2013-03-13 2013-06-26 中国石油大学(北京) Method and device for polycrystalline diamond compact bit (PDC) drilling parameter multi-objective optimization
CN104184170A (en) * 2014-07-18 2014-12-03 国网上海市电力公司 Independent microgrid configuration optimization method based on improved adaptive genetic algorithm

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
YI-BO HU 等: "《A new penalty based genetic algorithm for constrained optimization problems》", 《2005 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS》 *
俞倩 等: "《基于遗传算法的中央空调水系统变流量节能优化研究》", 《低温与超导》 *
李洪 等: "《基于MATLAB遗传算法的优化断路器温控工艺》", 《计算机科学》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112365101A (en) * 2020-12-09 2021-02-12 国网山东省电力公司电力科学研究院 Thermal power generating unit peak regulation combined total coal consumption optimization method and system based on genetic algorithm
CN113807015A (en) * 2021-09-17 2021-12-17 南方电网科学研究院有限责任公司 Parameter optimization method, device, equipment and storage medium for compressed air energy storage system
CN113807015B (en) * 2021-09-17 2023-12-26 南方电网科学研究院有限责任公司 Parameter optimization method, device, equipment and storage medium for compressed air energy storage system
TWI833604B (en) * 2023-03-15 2024-02-21 緯創資通股份有限公司 Equipment parameter recommendation method, electronic device and non-transitory computer readable recording medium

Also Published As

Publication number Publication date
CN111814400B (en) 2021-11-26

Similar Documents

Publication Publication Date Title
CN111814400B (en) Air compressor model selection method based on genetic algorithm
CN112032032B (en) Optimization method for frequency conversion operation mode of open type circulating water pump of wet cooling unit
CN110110349B (en) Multi-working-condition optimization design method for space guide vane of rotary vane type mixed flow pump
CN109428602A (en) A kind of data-encoding scheme, device and storage medium
CN112901449A (en) Air compressor system energy consumption optimization method based on machine learning
JP4383013B2 (en) Calculation method of characteristic curve of centrifugal fluid machine by computer
CN113361047B (en) Impeller high-dimensional optimization and model selection method for multilayer sensing structure
CN116680269A (en) Time sequence data coding and compressing method, system, equipment and medium
Zhang et al. Performance improvement of a pump as turbine in storage mode by optimization design based on genetic algorithm and fuzzy logic
CN112018822B (en) Demand side comprehensive flexible load regulation and control optimization method and system
CN108446452A (en) A kind of mixed-flow pump impeller Robust Optimal Design
CN111859242A (en) Household power energy efficiency optimization method and system
CN116610731A (en) Big data distributed storage method and device, electronic equipment and storage medium
CN116595874A (en) Impeller mechanical performance prediction model parameter optimization method and device and storage medium
CN116305953A (en) System day-ahead multi-objective optimization method based on cogeneration unit characteristic equation and constraint thereof
CN115263467A (en) Method and system for determining upper and lower limits of operating power of single-extraction cogeneration extraction condensing unit
CN115293056A (en) Modelica model-oriented multi-objective optimization algorithm
CN114065621A (en) Gas compressor characteristic equation coefficient fitting method based on genetic algorithm
JP2003106298A (en) Method and system for designing turbo type fluid machinery
CN112613654A (en) Comprehensive energy system flexibility evaluation method based on multi-type energy storage
CN116341762B (en) Optimal energy flow solving method and system for high-altitude wind power supply system
CN113344073A (en) Daily load curve clustering method and system based on fusion evolution algorithm
CN115992814A (en) Method and device for scheduling air compression system
CN117273280A (en) Genetic algorithm-based multi-well combined injection and production optimization method for gas storage
Fialho et al. A multi-objective approach to balance buildings construction cost and energy efficiency

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant