CN115221736B - Method for constructing prediction model of yarn splicing strength - Google Patents
Method for constructing prediction model of yarn splicing strength Download PDFInfo
- 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
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
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:
wherein the content of the first and second substances,which represents the strength of the yarn splice,the cross-sectional area of the yarn is shown,the tensile modulus of the yarn is expressed,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:
wherein, the first and the second end of the pipe are connected with each other,which represents the total stress of the fiber,representing the cross-directional tension of the fiber under tension,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:
wherein the content of the first and second substances,which represents the strength of the yarn splice,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,which represents the total strain force of the yarn,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:
by using yarn twistAnd the ratio s of the length to the diameter, respectively, to obtain the volume fraction of the fiberAdhesion factor n and slip ratio;
By the ratio of length to diameter s, the sticking factor n and the slip ratioObtaining effective fiber length of yarn;
Using volume fractionAnd effective fiber lengthAnd parameterizing variables in the initial model for predicting the splicing strength of the yarns.
wherein, the first and the second end of the pipe are connected with each other,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:
wherein, the first and the second end of the pipe are connected with each other,representing the yarn twist and s representing the ratio of length to diameter of the fiber.
wherein, the first and the second end of the pipe are connected with each other,representing the yarn twist and s representing the ratio of the length to the diameter of the fiber.
wherein n represents an adhesion factor of the fiber,which represents the slip rate of the fiber and,is the length of one helical period of the fiber,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:
wherein the content of the first and second substances,which represents the strength of the yarn splice,,indicating the number of layers of fibers in the cross-section of the yarn,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,denotes the tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,representing the angle of the fibers that spiral coaxially with the yarn with the axial direction of the yarn,which represents the effective fiber length of the yarn,,representing the ratio of the radial strain to the axial strain of the yarn,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:
wherein the content of the first and second substances,represents the actual value of the yarn splicing strength during the iterative optimization of the particles,,indicating the number of layers of fibers in the cross-section of the yarn,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,denotes a tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,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 knownI.e. the strength of the twist-on of the yarnThe 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:this basic relationship can be set as the yarn splicing strength basic model of the present invention, in which,which represents the strength of the yarn splice,the cross-sectional area is shown,the tensile modulus is expressed in terms of the modulus,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 tensionPulling forceBecomes the only stress acting on the fiber. Due to the pulling forceParallel to the direction of the yarn axis, thus describing the total stress to which the yarn is subjectedI.e. the fiber properties satisfy the following formula:
wherein the content of the first and second substances,which represents the total stress of the fiber,representing the cross-directional tension of the fiber under tension,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:
wherein the content of the first and second substances,the strength of the yarn splicing is expressed,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,which represents the total strain force of the yarn,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:
In an alternative embodiment, the corresponding yarn twist is obtained by referring to the equipment standard of the air twisterThe 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 yarnAnd the ratio s of the length to the diameter, respectively, to obtain the volume fraction of the fiberAdhesion factor n and slip ratio。
Through yarn twistAnd the volume fraction of the fiber of the length to diameter ratio sAdhesion factor n of fiber and slip ratio of fiberIs the basis of the initial model for parameterizing the yarn splicing strength prediction in volume fractionAdhesion factor n and slip ratioIn 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 equipmentAdhesion factor n and slip ratioThe 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.
wherein the content of the first and second substances,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:
wherein the content of the first and second substances,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 yarnIn inverse proportion, the greater the yarn twist T, the greater the adhesion factor.
wherein the content of the first and second substances,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 ratioObtaining effective fiber length of yarn。
In yet another alternative embodiment, the effective fiber lengthThe following formula is satisfied:
wherein n represents an adhesion factor of the fiber,which represents the slip rate of the fiber,is the length of one helical period of the fiber,representing the coefficient of friction of the fiber and s the ratio of the length to the diameter of the fiber.
S44, utilizing volume fractionAnd effective fiber lengthParameterizing variables in the initial model of yarn splice strength prediction.
In an alternative embodiment, the number of fibers per layer in the yarn is selectedThe following formula is satisfied:
wherein the content of the first and second substances,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 largeThe following formula is satisfied:
wherein, the first and the second end of the pipe are connected with each other,which is indicative of the twist of the yarn,is the radius of the fiber. When the yarn has a total ofWhen the fiber is layered, the tensile modulus of the fiber isAnd 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:
wherein, the first and the second end of the pipe are connected with each other,the cross-sectional area of the yarn is shown,denotes the tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,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:
wherein, the first and the second end of the pipe are connected with each other,the strength of the yarn splicing is expressed,,indicating the number of layers of fibers in the cross-section of the yarn,which represents the tensile modulus of the fiber,which represents the effective fiber length of the yarn,,representing the ratio of the radial strain to the axial strain of the yarn,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:
wherein the content of the first and second substances,representing the actual value of the yarn splicing strength when the particles are iteratively optimized,,indicating the number of layers of fibers in the cross-section of the yarn,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,denotes a tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,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:
wherein the content of the first and second substances,which represents the strength of the yarn splice,,representing the number of layers of fibers in the cross-section of the yarn,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,denotes the tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,which represents the effective fiber length of the yarn,,representing the ratio of the radial strain to the axial strain of the yarn,the amount of axial strain of the yarn is indicated,the volume fraction of the fibers is expressed,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:
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:
wherein, the first and the second end of the pipe are connected with each other,which represents the total stress of the fiber,representing the cross-directional tension of the fiber under tension,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:
wherein the content of the first and second substances,which represents the strength of the yarn splice,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,which represents the total strain force of the yarn,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:
by using yarn twistAnd the ratio s of the length to the diameter respectively obtain the volume fraction of the fiberAdhesion factor n and slip ratio;
By the ratio s of length to diameter, the adhesion factor n and the slip ratioObtaining effective fiber length of yarn;
5. The method for constructing a model for predicting yarn splicing strength according to claim 4, wherein the volume fraction of the fibersThe following formula is satisfied:
6. The method for constructing a yarn splicing strength prediction model according to claim 5, wherein the adhesion factor n satisfies the following formula:
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 valueThe following formula is satisfied:
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:
wherein, the first and the second end of the pipe are connected with each other,representing the actual value of the yarn splicing strength when the particles are iteratively optimized,,indicating the number of layers of fibers in the cross-section of the yarn,the cross-sectional area of the yarn is shown,which represents the tensile modulus of the fiber,denotes the tensile modulus of the fiber ofThe tensile modulus of the yarn is measured as,representing the angle of the fiber spiraling co-axially with the yarn with the axial direction of the yarn,indicating the amount of axial strain in the yarn.
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)
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)
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 |
-
2022
- 2022-09-20 CN CN202211140893.0A patent/CN115221736B/en active Active
Patent Citations (4)
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)
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 |