CN115221736B - Method for constructing prediction model of yarn splicing strength - Google Patents

Method for constructing prediction model of yarn splicing strength Download PDF

Info

Publication number
CN115221736B
CN115221736B CN202211140893.0A CN202211140893A CN115221736B CN 115221736 B CN115221736 B CN 115221736B CN 202211140893 A CN202211140893 A CN 202211140893A CN 115221736 B CN115221736 B CN 115221736B
Authority
CN
China
Prior art keywords
yarn
splicing strength
yarn splicing
fiber
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211140893.0A
Other languages
Chinese (zh)
Other versions
CN115221736A (en
Inventor
季霞
王顺国
王丽霞
贾坤
闫红霞
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.)
Donghua University
Qingdao Hongda Textile Machinery Co Ltd
Original Assignee
Donghua University
Qingdao Hongda Textile Machinery 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 Donghua University, Qingdao Hongda Textile Machinery Co Ltd filed Critical Donghua University
Priority to CN202211140893.0A priority Critical patent/CN115221736B/en
Publication of CN115221736A publication Critical patent/CN115221736A/en
Application granted granted Critical
Publication of CN115221736B publication Critical patent/CN115221736B/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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Geometry (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Hardware Design (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Spinning Or Twisting Of Yarns (AREA)

Abstract

The invention relates to the field of intelligent parameter prediction of an air yarn twister in the textile industry, in particular to a method for constructing a prediction model of yarn splicing strength, which comprises the following steps: obtaining structural parameters of the yarn; constructing a yarn splicing strength basic model by using the structural parameters; constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn; parameterizing the yarn splicing strength prediction initial model; optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model. The absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength prediction model and the actual value of the yarn splicing strength is the minimum, and the yarn splicing strength prediction model provides a theoretical basis for researching the relationship between the yarn strength and parameters such as fiber performance, process parameters, tensile strain and the like and also provides a guide for the optimization of the modern spinning process.

Description

Method for constructing prediction model of yarn splicing strength
Technical Field
The invention relates to the field of intelligent parameter setting of air yarn twisters in textile industry, in particular to a method for constructing a prediction model of yarn splicing strength.
Background
With the continuous improvement of the concepts of intellectualization, modernization and science and technology, the modernization modification process of the machinery in the textile industry is also continuously promoted. At present, automatic yarn splicing by using an air yarn twister is an indispensable step in the current automatic textile industry. When the yarn is spliced, the splicing strength of the yarn is an important index of the yarn quality, and the splicing strength directly influences the spinning efficiency, the subsequent process of spinning and even the performance of final textiles. The yarn splicing strength is influenced by various factors such as fiber performance, yarn structure parameters, process parameters and the like. For new fiber materials, the experience of workers and splicing equipment are mainly relied on. In addition, the testing of splice strength is destructive and requires the production process to be stopped, which can affect the efficient and high quality production of the enterprise, thereby reducing the market competitiveness of the enterprise. Therefore, a fast and accurate method for predicting the yarn splicing strength based on fiber performance, yarn structure and yarn process parameters needs to be found. Meanwhile, due to errors caused by various uncertain factors in the air twister, some errors exist between the established prediction model and the actual value, and along with the arrival of a machine learning method along with the network big data era and the development progress of related hardware, the problems can be solved by using a corresponding solution of the machine learning method, but no corresponding solution exists at present.
Disclosure of Invention
Aiming at the defects of the prior art and the requirements of practical engineering, the invention provides a method for constructing a yarn splicing strength prediction model, which comprises the following steps: obtaining structural parameters of the yarn, wherein the structural parameters comprise the cross section area of the yarn, the tensile modulus of the yarn and the axial strain capacity of the yarn; constructing a yarn splicing strength base model by using the structural parameters, wherein the yarn splicing strength base model expresses a functional relation between the yarn splicing strength and the structural parameters; constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn; parameterizing the yarn splicing strength prediction initial model; optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model, wherein the absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength prediction model and the actual value of the yarn splicing strength is the minimum. The method comprises the steps of establishing a yarn splicing strength prediction model by combining characteristic parameters of the yarn with fiber performance of the yarn, and optimizing the yarn splicing strength prediction model by a particle optimization algorithm in a machine learning method, so that the absolute value of the difference between a predicted value of the yarn splicing strength and an actual value of the yarn splicing strength is minimum. The particle optimization algorithm greatly reduces the dependence on the experiment times on the premise of ensuring that the experiment data is enough, simultaneously meets the condition that a plurality of influence factors act simultaneously, and can search the implicit relation between the influence factors and the yarn splicing strength under the condition of ensuring the precision of a high-cycle range; meanwhile, the yarn splicing strength prediction model provides a theoretical basis for researching the relationship between the yarn strength and the parameters such as fiber performance, process parameters, tensile strain and the like, and also provides a guide for the optimization of the modern spinning process.
Optionally, the yarn splicing strength base model satisfies the following formula:
Figure 295009DEST_PATH_IMAGE001
，
wherein the content of the first and second substances,
Figure 665948DEST_PATH_IMAGE003
which represents the strength of the yarn splice,
Figure 287553DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 111153DEST_PATH_IMAGE005
the tensile modulus of the yarn is expressed,
Figure 374775DEST_PATH_IMAGE006
indicating the amount of axial strain in the yarn.
Optionally, the constructing an initial model of yarn splicing strength prediction by combining the yarn splicing strength basic model and the fiber performance of the yarn comprises the following steps:
obtaining the fiber performance of the yarn when the yarn is twisted, wherein the fiber performance meets the following formula:
Figure 334641DEST_PATH_IMAGE007
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 517360DEST_PATH_IMAGE009
which represents the total stress of the fiber,
Figure 969201DEST_PATH_IMAGE010
representing the cross-directional tension of the fiber under tension,
Figure 629990DEST_PATH_IMAGE011
representing the angle of a single yarn with the axis of the yarn;
constructing a yarn splicing strength prediction initial model by combining the fiber performance with the yarn splicing strength basic model, wherein the yarn splicing strength prediction initial model meets the following formula:
Figure 585308DEST_PATH_IMAGE012
，
wherein the content of the first and second substances,
Figure 938928DEST_PATH_IMAGE003
which represents the strength of the yarn splice,
Figure 737120DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 76966DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 11424DEST_PATH_IMAGE014
which represents the total strain force of the yarn,
Figure 676891DEST_PATH_IMAGE011
representing the angle of an individual yarn from the yarn axis.
Optionally, the parameterizing the initial model for yarn splicing strength prediction comprises the following steps:
obtaining yarn twist
Figure 696800DEST_PATH_IMAGE016
And the length to diameter ratio s of the fiber;
by using yarn twist
Figure 699391DEST_PATH_IMAGE016
And the ratio s of the length to the diameter, respectively, to obtain the volume fraction of the fiber
Figure 626371DEST_PATH_IMAGE017
Adhesion factor n and slip ratio
Figure 587374DEST_PATH_IMAGE019
；
By the ratio of length to diameter s, the sticking factor n and the slip ratio
Figure 969945DEST_PATH_IMAGE019
Obtaining effective fiber length of yarn
Figure 776227DEST_PATH_IMAGE021
；
Using volume fraction
Figure 685277DEST_PATH_IMAGE017
And effective fiber length
Figure 426968DEST_PATH_IMAGE021
And parameterizing variables in the initial model for predicting the splicing strength of the yarns.
Optionally, the volume fraction of the fibers
Figure 687048DEST_PATH_IMAGE017
The following formula is satisfied:
Figure 31442DEST_PATH_IMAGE022
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 935944DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of length to diameter of the fiber.
Optionally, the adhesion factor n satisfies the following formula:
Figure 707591DEST_PATH_IMAGE023
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 330333DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of length to diameter of the fiber.
Optionally, the slip ratio
Figure 478418DEST_PATH_IMAGE019
The following formula is satisfied:
Figure 362060DEST_PATH_IMAGE024
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 445554DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of the length to the diameter of the fiber.
Optionally, the effective fiber length
Figure 414647DEST_PATH_IMAGE026
The following formula is satisfied:
Figure 241789DEST_PATH_IMAGE027
wherein n represents an adhesion factor of the fiber,
Figure 979937DEST_PATH_IMAGE019
which represents the slip rate of the fiber and,
Figure 93387DEST_PATH_IMAGE029
is the length of one helical period of the fiber,
Figure 425142DEST_PATH_IMAGE031
denotes the coefficient of friction of the fibre and s denotes the ratio of the length to the diameter of the fibre.
Optionally, the parameterized initial model for predicting yarn splicing strength satisfies the following formula:
Figure 180609DEST_PATH_IMAGE032
，
wherein the content of the first and second substances,
Figure 773264DEST_PATH_IMAGE003
which represents the strength of the yarn splice,
Figure 461210DEST_PATH_IMAGE033
，
Figure 139316DEST_PATH_IMAGE035
indicating the number of layers of fibers in the cross-section of the yarn,
Figure 308260DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 755422DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 741833DEST_PATH_IMAGE036
denotes the tensile modulus of the fiber of
Figure 782601DEST_PATH_IMAGE013
The tensile modulus of the yarn is measured as,
Figure 879870DEST_PATH_IMAGE037
representing the angle of the fibers that spiral coaxially with the yarn with the axial direction of the yarn,
Figure 322484DEST_PATH_IMAGE026
which represents the effective fiber length of the yarn,
Figure 214216DEST_PATH_IMAGE038
，
Figure DEST_PATH_IMAGE040
representing the ratio of the radial strain to the axial strain of the yarn,
Figure 273439DEST_PATH_IMAGE006
indicating the amount of axial strain in the yarn.
Optionally, the optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model includes the following steps:
predicting the number of constant parameters in an initial model according to the yarn splicing strength, and setting a search space dimension for particle optimization;
different constant parameters are analogized to particles in the population, and the optimization process is analogized to a particle iterative optimization process;
constructing a particle iterative optimization fitness function;
calculating the fitness of each group of constant parameters after the position is updated, comparing the fitness of each group of constant parameters with the historical optimal value of each group, and updating the historical optimal value of each group if the predicted value of the splicing strength of the yarn is closer to the actual value of the splicing strength of the yarn due to the current constant parameters of each group;
calculating the fitness of the whole group of constant parameters after position updating, comparing the fitness of the whole group of constant parameters with the whole group of historical optimal values, and updating the whole group of historical optimal values if the predicted value of the yarn splicing strength is closer to the actual value of the yarn splicing strength due to the current whole group of constant parameters;
setting iteration times;
and acquiring a whole set of constant parameters after iteration is finished, optimizing the parameterized yarn splicing strength prediction initial model by using the whole set of constant parameters, and acquiring a yarn splicing strength prediction model.
Optionally, the iterative fitness function of the particle satisfies the following formula:
Figure 908820DEST_PATH_IMAGE041
，
wherein the content of the first and second substances,
Figure 330574DEST_PATH_IMAGE042
represents the actual value of the yarn splicing strength during the iterative optimization of the particles,
Figure DEST_PATH_IMAGE043
，
Figure 799733DEST_PATH_IMAGE035
indicating the number of layers of fibers in the cross-section of the yarn,
Figure 815093DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 519744DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 796004DEST_PATH_IMAGE036
denotes a tensile modulus of the fiber of
Figure 170485DEST_PATH_IMAGE013
The tensile modulus of the yarn is measured as,
Figure 532196DEST_PATH_IMAGE037
representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,
Figure 381816DEST_PATH_IMAGE006
indicating the amount of axial strain in the yarn.
In a second aspect, the present invention further provides a system for building a yarn splicing strength prediction model, including: the yarn twisting data acquisition module is used for acquiring the structural parameters of the yarn; a base model construction module for constructing a yarn splicing strength base model using the structural parameters; the initial model building module is used for building a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn; a model parameterization module for parameterizing the yarn splicing strength prediction initial model; and the prediction model optimization module is used for optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model, and the absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength prediction model and the actual value of the yarn splicing strength is minimum. The system for constructing the model for predicting the yarn splicing strength is suitable for the method for constructing the model for predicting the yarn splicing strength in the first aspect, stably realizes the prediction and optimization of the yarn splicing strength through the interaction of a plurality of modules, provides an actual carrier capable of being actually operated and completing the method for constructing the model for predicting the yarn splicing strength while ensuring the stable operation and the accuracy of prediction data, and improves the actual engineering applicability of the invention.
Drawings
FIG. 1 is a flow chart of a method for constructing a model for predicting the splicing strength of yarns according to the present invention;
FIG. 2 is a real image of an air twister according to the present invention;
FIG. 3 is a flow chart of an alternative embodiment of the present invention for parameterizing the initial model for yarn splice strength prediction;
fig. 4 is a schematic diagram of a system module for constructing a prediction model of yarn splicing strength according to the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are merely illustrative and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail in order to avoid obscuring the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
Referring to fig. 1, in an embodiment, a method for constructing a yarn splicing strength prediction model provided by the present invention includes the following steps:
s1, obtaining structural parameters of the yarn.
In an alternative embodiment, the structural parameters in step S1 include the cross-sectional area of the yarn, the tensile modulus of the yarn, and the axial strain of the yarn.
And S2, constructing a yarn splicing strength basic model by using the structural parameters.
Referring to fig. 2, in an alternative embodiment, the construction of the yarn splicing strength base model using the structural parameters in step S2 is implemented by using solid forceFrom the theory of science, the external force provided by the air yarn twister under the action of air can be known
Figure 43742DEST_PATH_IMAGE045
I.e. the strength of the twist-on of the yarn
Figure 448178DEST_PATH_IMAGE045
The following basic relationship is provided with the cross-sectional area of the yarn, the tensile modulus of the yarn and the axial strain of the yarn:
Figure 438131DEST_PATH_IMAGE001
this basic relationship can be set as the yarn splicing strength basic model of the present invention, in which,
Figure 953426DEST_PATH_IMAGE045
which represents the strength of the yarn splice,
Figure 345224DEST_PATH_IMAGE004
the cross-sectional area is shown,
Figure 920562DEST_PATH_IMAGE005
the tensile modulus is expressed in terms of the modulus,
Figure 522445DEST_PATH_IMAGE046
the axial strain is shown. The yarn splicing strength basic model can be used as a basis for constructing a yarn splicing strength prediction initial model and a yarn splicing strength prediction model in subsequent steps, and expresses the functional relationship between the yarn splicing strength and structural parameters.
S3, constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn;
in an alternative embodiment, the step S3 of constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model and the fiber performance of the yarn comprises the following steps:
and S31, obtaining the fiber performance of the yarn during yarn twisting. Assuming that the fibres are fully elastic elements, they cannot withstand any pressureForce, under the tension of the yarn, the fibres only producing tension
Figure 982376DEST_PATH_IMAGE010
Pulling force
Figure 87735DEST_PATH_IMAGE010
Becomes the only stress acting on the fiber. Due to the pulling force
Figure 974920DEST_PATH_IMAGE010
Parallel to the direction of the yarn axis, thus describing the total stress to which the yarn is subjected
Figure 532940DEST_PATH_IMAGE009
I.e. the fiber properties satisfy the following formula:
Figure 921196DEST_PATH_IMAGE007
，
wherein the content of the first and second substances,
Figure 22007DEST_PATH_IMAGE009
which represents the total stress of the fiber,
Figure 939148DEST_PATH_IMAGE010
representing the cross-directional tension of the fiber under tension,
Figure 390989DEST_PATH_IMAGE011
indicating the angle of an individual yarn from the yarn axis.
And S32, constructing a yarn splicing strength prediction initial model by combining the fiber performance with the yarn splicing strength basic model. The initial model for predicting the yarn splicing strength meets the following formula:
Figure 51777DEST_PATH_IMAGE012
，
wherein the content of the first and second substances,
Figure 131729DEST_PATH_IMAGE003
the strength of the yarn splicing is expressed,
Figure 360716DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 158907DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 357808DEST_PATH_IMAGE014
which represents the total strain force of the yarn,
Figure 430281DEST_PATH_IMAGE011
representing the angle of an individual yarn from the yarn axis.
And S4, parameterizing the yarn splicing strength prediction initial model.
Referring to fig. 3, in an alternative embodiment, the parameterization of the initial model for predicting the yarn splicing strength in step S4 includes the following steps:
s41, obtaining yarn twist
Figure 220383DEST_PATH_IMAGE016
And the length to diameter ratio s of the fiber.
In an alternative embodiment, the corresponding yarn twist is obtained by referring to the equipment standard of the air twister
Figure 850078DEST_PATH_IMAGE016
The length-to-diameter ratio s of the fiber is obtained by referring to the fiber standards of the constituent yarns of the air twister.
S42, utilizing the twist of the yarn
Figure 383828DEST_PATH_IMAGE016
And the ratio s of the length to the diameter, respectively, to obtain the volume fraction of the fiber
Figure 172792DEST_PATH_IMAGE047
Adhesion factor n and slip ratio
Figure 743582DEST_PATH_IMAGE019
。
Through yarn twist
Figure 250787DEST_PATH_IMAGE016
And the volume fraction of the fiber of the length to diameter ratio s
Figure 198014DEST_PATH_IMAGE017
Adhesion factor n of fiber and slip ratio of fiber
Figure 107064DEST_PATH_IMAGE019
Is the basis of the initial model for parameterizing the yarn splicing strength prediction in volume fraction
Figure 973389DEST_PATH_IMAGE017
Adhesion factor n and slip ratio
Figure 577677DEST_PATH_IMAGE019
In the expression, a plurality of constant parameters exist, and the constant parameters can be influenced by various factors such as the size of a splicing cavity of the air yarn splicer, compressed air at an inlet and the like, so that the accuracy of the prediction of the splicing strength of the yarn is influenced, and the volume fractions are respectively determined by the current equipment
Figure 453229DEST_PATH_IMAGE017
Adhesion factor n and slip ratio
Figure 216786DEST_PATH_IMAGE019
The initial model for predicting the yarn splicing strength is constructed by the formulas, and the constant parameters contained in the initial model for predicting the yarn splicing strength are optimized through the subsequent steps, so that the prediction model for the yarn splicing strength with higher accuracy can be obtained.
In an alternative embodiment, the volume fraction of the fibers
Figure 129378DEST_PATH_IMAGE017
The following formula is satisfied:
Figure 876754DEST_PATH_IMAGE022
，
wherein the content of the first and second substances,
Figure 900205DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of length to diameter of the fiber.
In yet another alternative embodiment, the adhesion factor n satisfies the following equation:
Figure 783848DEST_PATH_IMAGE023
，
wherein the content of the first and second substances,
Figure 726396DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of length to diameter of the fiber. The adhesion factor n expresses the amount of friction and adhesion of the individual fibers, which is twisted with the yarn
Figure 570855DEST_PATH_IMAGE016
In inverse proportion, the greater the yarn twist T, the greater the adhesion factor.
In yet another alternative embodiment, the slip ratio
Figure 788210DEST_PATH_IMAGE019
The following formula is satisfied:
Figure 855521DEST_PATH_IMAGE024
，
wherein the content of the first and second substances,
Figure 234550DEST_PATH_IMAGE016
representing the yarn twist and s representing the ratio of the length to the diameter of the fiber.
S43, ratio of passage length to diameter S, adhesion factor n, and slip ratio
Figure 566305DEST_PATH_IMAGE019
Obtaining effective fiber length of yarn
Figure 321772DEST_PATH_IMAGE026
。
In yet another alternative embodiment, the effective fiber length
Figure 55372DEST_PATH_IMAGE026
The following formula is satisfied:
Figure 605302DEST_PATH_IMAGE048
，
wherein n represents an adhesion factor of the fiber,
Figure 17829DEST_PATH_IMAGE019
which represents the slip rate of the fiber,
Figure 452353DEST_PATH_IMAGE029
is the length of one helical period of the fiber,
Figure 899515DEST_PATH_IMAGE031
representing the coefficient of friction of the fiber and s the ratio of the length to the diameter of the fiber.
S44, utilizing volume fraction
Figure 885925DEST_PATH_IMAGE047
And effective fiber length
Figure 192273DEST_PATH_IMAGE026
Parameterizing variables in the initial model of yarn splice strength prediction.
In an alternative embodiment, the number of fibers per layer in the yarn is selected
Figure 23962DEST_PATH_IMAGE049
The following formula is satisfied:
Figure 466576DEST_PATH_IMAGE050
，
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE052
indicating the number of layers of fiber in the cross-section of the yarn. Assuming that the path of the single fiber in the yarn is a Tongzhou spiral, the angle between the single fiber and the axial direction of the yarn is relatively large
Figure 889467DEST_PATH_IMAGE053
The following formula is satisfied:
Figure 417532DEST_PATH_IMAGE054
=
Figure 52912DEST_PATH_IMAGE055
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 612682DEST_PATH_IMAGE016
which is indicative of the twist of the yarn,
Figure 940895DEST_PATH_IMAGE056
is the radius of the fiber. When the yarn has a total of
Figure 815311DEST_PATH_IMAGE035
When the fiber is layered, the tensile modulus of the fiber is
Figure 129748DEST_PATH_IMAGE013
And the force of the yarn in the axial direction of the yarn is the cosine value of the self force of the yarn under the action of the twisting strength of the yarn, so the total strength of the twisted yarn𝐹The following formula is satisfied:
Figure 406009DEST_PATH_IMAGE057
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 780490DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 142201DEST_PATH_IMAGE036
denotes the tensile modulus of the fiber of
Figure 525909DEST_PATH_IMAGE013
The tensile modulus of the yarn is measured as,
Figure 922255DEST_PATH_IMAGE053
representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn. According to the correlation formulas obtained in the steps S41 to S42, parameterization may be performed on variables in the initial yarn splicing strength prediction model, where the parameterized initial yarn splicing strength prediction model satisfies the following formula:
Figure 326692DEST_PATH_IMAGE032
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 51065DEST_PATH_IMAGE003
the strength of the yarn splicing is expressed,
Figure 97518DEST_PATH_IMAGE033
，
Figure 348371DEST_PATH_IMAGE035
indicating the number of layers of fibers in the cross-section of the yarn,
Figure 64654DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 135379DEST_PATH_IMAGE026
which represents the effective fiber length of the yarn,
Figure 595310DEST_PATH_IMAGE038
，
Figure 966248DEST_PATH_IMAGE040
representing the ratio of the radial strain to the axial strain of the yarn,
Figure 712488DEST_PATH_IMAGE006
indicating the amount of axial strain in the yarn.
And S5, optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model.
In an optional embodiment, the optimizing the parameterized initial model for predicting yarn splicing strength in step S5 to obtain the model for predicting yarn splicing strength includes the following steps: predicting the number of constant parameters in an initial model according to the yarn splicing strength, setting a search space dimension for particle optimization, and simulating different constant parameters into particles in a population, wherein the optimization process is simulated into a particle iterative optimization process; constructing a particle iteration optimizing fitness function; calculating the fitness of each group of constant parameters after position updating, comparing the fitness of each group of constant parameters with the historical optimal value of each group, and updating the historical optimal value of each group if the predicted value of the yarn splicing strength is closer to the actual value of the yarn splicing strength due to the current constant parameters of each group; calculating the fitness of the whole group of constant parameters after the position is updated, comparing the fitness of the whole group of constant parameters with the whole group of historical optimal values, and updating the whole group of historical optimal values if the predicted value of the yarn splicing strength is closer to the actual value of the yarn splicing strength due to the current whole group of constant parameters; setting iteration times; and acquiring a whole set of constant parameters after iteration is finished, and optimizing the parameterized yarn splicing strength prediction initial model by using the whole set of constant parameters to obtain a yarn splicing strength prediction model. The step of setting the number of iterations may be selected such that the optimization process is considered to be achieved when the iteration update reaches a range where the predicted value of the yarn splicing strength and the actual value of the yarn splicing strength have reached the predicted requirement. If the requirement is not met, continuing to iteratively update; the step of setting the iteration times can also be selected as that when the updating of the iterative constant parameter is stopped and is not changed any more, the constant parameter is considered to enable the absolute value of the difference between the predicted value of the yarn splicing strength and the actual value of the yarn splicing strength to be minimum, namely, the optimization process is considered to be achieved, and if the requirement is not met, the iterative updating is continued. Specifically, in this embodiment, the particle iterative optimization fitness function satisfies the following formula:
Figure 677033DEST_PATH_IMAGE041
，
wherein the content of the first and second substances,
Figure 534130DEST_PATH_IMAGE042
representing the actual value of the yarn splicing strength when the particles are iteratively optimized,
Figure 897591DEST_PATH_IMAGE033
，
Figure 80310DEST_PATH_IMAGE035
indicating the number of layers of fibers in the cross-section of the yarn,
Figure 125627DEST_PATH_IMAGE004
the cross-sectional area of the yarn is shown,
Figure 927361DEST_PATH_IMAGE013
which represents the tensile modulus of the fiber,
Figure 7312DEST_PATH_IMAGE036
denotes a tensile modulus of the fiber of
Figure 236299DEST_PATH_IMAGE013
The tensile modulus of the yarn is measured as,
Figure 768912DEST_PATH_IMAGE037
representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,
Figure 498971DEST_PATH_IMAGE006
indicating the amount of axial strain in the yarn.
In yet another alternative embodiment, the optimizing the parameterized yarn splicing strength predicting initial model in step S5 to obtain the yarn splicing strength predicting model may be implemented by using a particle optimization algorithm in the prior art, and the absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength predicting model and the actual value of the yarn splicing strength is minimized by adaptively rewriting the prior algorithm for optimizing the constant parameter in the yarn splicing strength predicting initial model.
The method comprises the steps of establishing a yarn splicing strength prediction model by combining characteristic parameters of the yarn with fiber performance of the yarn, and optimizing the yarn splicing strength prediction model by a particle optimization algorithm in a machine learning method, so that the absolute value of the difference between a predicted value of the yarn splicing strength and an actual value of the yarn splicing strength is minimum. The particle optimization algorithm is used for greatly reducing the dependence on the experiment times on the premise of ensuring that the experiment data is enough, simultaneously meeting the condition that a plurality of influence factors act simultaneously, and being capable of searching the implicit relation between the influence factors and the yarn splicing strength under the condition of ensuring the precision of a high-cycle range; meanwhile, the yarn splicing strength prediction model provides a theoretical basis for researching the relationship between the yarn strength and the parameters such as fiber performance, process parameters, tensile strain and the like, and also provides a guide for the optimization of the modern spinning process.
In still another alternative embodiment, referring to fig. 4, the present invention further provides a system for constructing a yarn splicing strength prediction model, including: the yarn twisting data acquisition module is used for acquiring the structural parameters of the yarn; a base model construction module for constructing a yarn splicing strength base model using the structural parameters; the initial model building module is used for building a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn; a model parameterization module for parameterizing the yarn splicing strength prediction initial model; and the prediction model optimization module is used for optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model, and the absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength prediction model and the actual value of the yarn splicing strength is minimum.
The system for constructing the yarn splicing strength prediction model is suitable for the method for constructing the yarn splicing strength prediction model, stably realizes the prediction and optimization of the yarn splicing strength through the interaction of a plurality of modules, provides an actual carrier which can be actually operated and can complete the method for constructing the yarn splicing strength prediction model while ensuring the stable operation and the accuracy of prediction data, and improves the actual engineering applicability of the invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.

Claims (9)

1. A method for constructing a prediction model of yarn splicing strength is characterized by comprising the following steps:
obtaining structural parameters of the yarn, wherein the structural parameters comprise the cross section area of the yarn, the tensile modulus of the yarn and the axial strain capacity of the yarn;
constructing a yarn splicing strength base model by using the structural parameters, wherein the yarn splicing strength base model expresses a functional relation between the yarn splicing strength and the structural parameters;
constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn;
parameterizing the initial model for predicting the splicing strength of the yarns, wherein the parameterized initial model for predicting the splicing strength of the yarns meets the following formula:
Figure 647937DEST_PATH_IMAGE001
，
wherein the content of the first and second substances,
Figure 906880DEST_PATH_IMAGE002
which represents the strength of the yarn splice,
Figure 67734DEST_PATH_IMAGE003
，
Figure 601483DEST_PATH_IMAGE004
representing the number of layers of fibers in the cross-section of the yarn,
Figure 265814DEST_PATH_IMAGE005
the cross-sectional area of the yarn is shown,
Figure 961237DEST_PATH_IMAGE006
which represents the tensile modulus of the fiber,
Figure 468442DEST_PATH_IMAGE007
denotes the tensile modulus of the fiber of
Figure 412740DEST_PATH_IMAGE006
The tensile modulus of the yarn is measured as,
Figure 321790DEST_PATH_IMAGE008
representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,
Figure 63481DEST_PATH_IMAGE009
which represents the effective fiber length of the yarn,
Figure 57982DEST_PATH_IMAGE010
，
Figure 667955DEST_PATH_IMAGE011
representing the ratio of the radial strain to the axial strain of the yarn,
Figure 306878DEST_PATH_IMAGE012
the amount of axial strain of the yarn is indicated,
Figure 344104DEST_PATH_IMAGE013
the volume fraction of the fibers is expressed,
Figure 701267DEST_PATH_IMAGE014
representing the total strain force of the yarn;
optimizing the parameterized yarn splicing strength prediction initial model to obtain a yarn splicing strength prediction model, wherein the absolute value of the difference between the predicted value of the yarn splicing strength predicted by the yarn splicing strength prediction model and the actual value of the yarn splicing strength is the minimum.
2. The method for constructing the yarn splicing strength prediction model according to claim 1, wherein the yarn splicing strength basic model satisfies the following formula:
Figure 114931DEST_PATH_IMAGE015
，
wherein the content of the first and second substances,
Figure 732994DEST_PATH_IMAGE002
which represents the strength of the yarn splice,
Figure 816487DEST_PATH_IMAGE005
the cross-sectional area of the yarn is shown,
Figure 785580DEST_PATH_IMAGE016
the tensile modulus of the yarn is expressed,
Figure 878301DEST_PATH_IMAGE012
indicating the amount of axial strain in the yarn.
3. The method for constructing the yarn splicing strength prediction model according to claim 1, wherein the step of constructing a yarn splicing strength prediction initial model by combining the yarn splicing strength basic model with the fiber performance of the yarn comprises the following steps:
obtaining the fiber performance of the yarn when the yarn is twisted, wherein the fiber performance meets the following formula:
Figure 350871DEST_PATH_IMAGE017
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 995479DEST_PATH_IMAGE018
which represents the total stress of the fiber,
Figure 61655DEST_PATH_IMAGE019
representing the cross-directional tension of the fiber under tension,
Figure 817122DEST_PATH_IMAGE020
representing the angle of a single yarn with the axis of the yarn;
constructing a yarn splicing strength prediction initial model by combining the fiber performance with the yarn splicing strength basic model, wherein the yarn splicing strength prediction initial model meets the following formula:
Figure 550722DEST_PATH_IMAGE021
，
wherein the content of the first and second substances,
Figure 835073DEST_PATH_IMAGE002
which represents the strength of the yarn splice,
Figure 778758DEST_PATH_IMAGE005
the cross-sectional area of the yarn is shown,
Figure 944773DEST_PATH_IMAGE006
which represents the tensile modulus of the fiber,
Figure 657514DEST_PATH_IMAGE014
which represents the total strain force of the yarn,
Figure 378345DEST_PATH_IMAGE020
representing the angle of an individual yarn from the yarn axis.
4. The method for constructing a model for predicting yarn splicing strength according to claim 1, wherein the parameterizing of the initial model for predicting yarn splicing strength comprises the following steps:
obtaining yarn twist
Figure 419114DEST_PATH_IMAGE022
And the length to diameter ratio s of the fiber;
by using yarn twist
Figure 516383DEST_PATH_IMAGE022
And the ratio s of the length to the diameter respectively obtain the volume fraction of the fiber
Figure 958996DEST_PATH_IMAGE013
Adhesion factor n and slip ratio
Figure 116308DEST_PATH_IMAGE023
；
By the ratio s of length to diameter, the adhesion factor n and the slip ratio
Figure 503427DEST_PATH_IMAGE023
Obtaining effective fiber length of yarn
Figure 279753DEST_PATH_IMAGE009
；
Using volume fraction
Figure 701508DEST_PATH_IMAGE013
And effective fiber length
Figure 905087DEST_PATH_IMAGE009
And parameterizing variables in the initial model for predicting the splicing strength of the yarns.
5. The method for constructing a model for predicting yarn splicing strength according to claim 4, wherein the volume fraction of the fibers
Figure 45081DEST_PATH_IMAGE013
The following formula is satisfied:
Figure 218574DEST_PATH_IMAGE024
，
wherein the content of the first and second substances,
Figure 635780DEST_PATH_IMAGE022
representing the yarn twist and s representing the ratio of the length to the diameter of the fiber.
6. The method for constructing a yarn splicing strength prediction model according to claim 5, wherein the adhesion factor n satisfies the following formula:
Figure 869315DEST_PATH_IMAGE025
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 371971DEST_PATH_IMAGE022
representing the yarn twist and s representing the ratio of length to diameter of the fiber.
7. The method for constructing a model for predicting yarn splicing strength according to claim 6, wherein the slip ratio is determined by a numerical value
Figure 614734DEST_PATH_IMAGE023
The following formula is satisfied:
Figure 745501DEST_PATH_IMAGE026
，
wherein the content of the first and second substances,
Figure 25304DEST_PATH_IMAGE022
representing the yarn twist and s representing the ratio of length to diameter of the fiber.
8. The method for constructing the yarn splicing strength prediction model according to claim 1, wherein the optimizing the parameterized yarn splicing strength prediction initial model to obtain the yarn splicing strength prediction model comprises the following steps:
predicting the number of constant parameters in an initial model according to the yarn splicing strength, and setting a search space dimension for particle optimization;
different constant parameters are analogized to particles in the population, and the optimization process is analogized to a particle iterative optimization process;
constructing a particle iterative optimization fitness function;
calculating the fitness of each group of constant parameters after position updating, comparing the fitness of each group of constant parameters with the historical optimal value of each group, and updating the historical optimal value of each group if the predicted value of the yarn splicing strength is closer to the actual value of the yarn splicing strength due to the current constant parameters of each group;
calculating the fitness of the whole group of constant parameters after the position is updated, comparing the fitness of the whole group of constant parameters with the whole group of historical optimal values, and updating the whole group of historical optimal values if the predicted value of the yarn splicing strength is closer to the actual value of the yarn splicing strength due to the current whole group of constant parameters;
setting iteration times;
and acquiring a whole set of constant parameters after iteration is finished, optimizing the parameterized yarn splicing strength prediction initial model by using the whole set of constant parameters, and acquiring a yarn splicing strength prediction model.
9. The method for constructing a yarn splicing strength prediction model according to claim 8, wherein the particle iterative optimization fitness function satisfies the following formula:
Figure 139890DEST_PATH_IMAGE027
，
wherein, the first and the second end of the pipe are connected with each other,
Figure 920764DEST_PATH_IMAGE028
representing the actual value of the yarn splicing strength when the particles are iteratively optimized,
Figure 309633DEST_PATH_IMAGE003
，
Figure 884971DEST_PATH_IMAGE004
indicating the number of layers of fibers in the cross-section of the yarn,
Figure 96640DEST_PATH_IMAGE005
the cross-sectional area of the yarn is shown,
Figure 681206DEST_PATH_IMAGE006
which represents the tensile modulus of the fiber,
Figure 927510DEST_PATH_IMAGE007
denotes the tensile modulus of the fiber of
Figure 673749DEST_PATH_IMAGE006
The tensile modulus of the yarn is measured as,
Figure 762928DEST_PATH_IMAGE008
representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,
Figure 495392DEST_PATH_IMAGE012
indicating the amount of axial strain in the yarn.
CN202211140893.0A 2022-09-20 2022-09-20 Method for constructing prediction model of yarn splicing strength Active CN115221736B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211140893.0A CN115221736B (en) 2022-09-20 2022-09-20 Method for constructing prediction model of yarn splicing strength

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211140893.0A CN115221736B (en) 2022-09-20 2022-09-20 Method for constructing prediction model of yarn splicing strength

Publications (2)

Publication Number Publication Date
CN115221736A CN115221736A (en) 2022-10-21
CN115221736B true CN115221736B (en) 2022-12-09

Family

ID=83616802

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211140893.0A Active CN115221736B (en) 2022-09-20 2022-09-20 Method for constructing prediction model of yarn splicing strength

Country Status (1)

Country Link
CN (1) CN115221736B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858171A (en) * 2019-02-14 2019-06-07 南京航空航天大学 Weave the prediction technique of ceramic matric composite stress-strain response and intensity
CN113536687A (en) * 2021-07-26 2021-10-22 上海大学 Construction method of monochrome cotton fabric color and dye concentration prediction model based on PSO-LSSVM
CN114707219A (en) * 2022-04-12 2022-07-05 中国矿业大学 Method and system for constructing tear strength model of fabric membrane material and application method of model
CN114994289A (en) * 2022-08-01 2022-09-02 江苏卓鹏智能机电有限公司 Spinning product quality detection method and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115516146A (en) * 2020-05-06 2022-12-23 立达Cz有限公司 Method for detecting structural defects of a wrapped yarn comprising cores from parallel fibres bound together by wrapping fibres and wild fibres, a device for performing the method, a computer program for the device and a computer readable medium with the computer program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858171A (en) * 2019-02-14 2019-06-07 南京航空航天大学 Weave the prediction technique of ceramic matric composite stress-strain response and intensity
CN113536687A (en) * 2021-07-26 2021-10-22 上海大学 Construction method of monochrome cotton fabric color and dye concentration prediction model based on PSO-LSSVM
CN114707219A (en) * 2022-04-12 2022-07-05 中国矿业大学 Method and system for constructing tear strength model of fabric membrane material and application method of model
CN114994289A (en) * 2022-08-01 2022-09-02 江苏卓鹏智能机电有限公司 Spinning product quality detection method and system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
喷气涡流纺纱线拉伸断裂强力预测模型构建与验证;姚江薇等;《纺织学报》;20181015(第10期);全文 *
基于有限单元法的平纹织物复合材料强度预测:1.RVE的有限元模型;左中鹅等;《纺织学报》;20091215(第12期);全文 *
立体织机开口机构和纬纱***的优化设计;闫红霞;《中国优秀硕士论文》;20151203;全文 *

Also Published As

Publication number Publication date
CN115221736A (en) 2022-10-21

Similar Documents

Publication Publication Date Title
Jay An overview of macrobending and microbending of optical fibers
Chen et al. Experimental research on bending performance of structural cable
CN109241649B (en) Fiber yarn performance detection method and system based on decision tree model
Fallahpour et al. Evaluating applicability of VIKOR method of multi-criteria decision making for parameters selection problem in rotor spinning
CN111080408A (en) Order information processing method based on deep reinforcement learning
CN106116138A (en) A kind of wire drawing coating processes of minor diameter low-loss bend-insensitive single-mode optical fiber
CN115221736B (en) Method for constructing prediction model of yarn splicing strength
Liu et al. Bond behavior of basalt fiber-reinforced polymer bars embedded in concrete under mono-tensile and cyclic loads
WO2022135075A1 (en) Optical cable
Li et al. Dynamic stiffness of braided HMPE ropes under long-term cyclic loads: A full-scale experimental investigation
US8644659B2 (en) Methods and systems for predicting an optical fiber performance parameter
Liu et al. Numerical analysis of fibers tensions in the siro-spinning triangle using finite element method
Wang et al. Complex structure of braid in fiber art creation with multisensor IoT technology
CN115874321B (en) Self-adaptive management method and system for improving yarn quality
CN106383391A (en) Low-friction optical fiber cable and manufacturing method thereof
Azzam An optimum design for composite helical springs
Liu et al. Theoretical study of effect of ring spinning triangle division on fiber tension distribution
CN113108985B (en) Core wire embedded grating intelligent steel strand tension value correction calculation method
CN203259699U (en) Novel covered wire wiring cable
CN1250470C (en) Method of characterizing one or more properties of optical fibres
CN113313430B (en) Integrated BOM system for whole process of manufacturing steel wire rope and construction method
CN1988420B (en) Method for detecting optic fiber polarization mode dispersion
Beltran et al. Mill specific prediction of worsted yarn performance
JPS6265006A (en) Loose type optical fiber cable
Wang et al. Method for deriving twisting process parameters of large package E-glass yarn by measuring physical properties of bobbin yarn

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