Method, device, equipment and medium for optimizing pre-oxidation time parameters

Abstract

The present disclosure relates to a method, device, computer equipment and storage medium for optimizing pre-oxidation time parameters. The optimization method includes: obtaining the first temperature of each temperature zone of the first pre-oxidation production line under each environment, and the second temperature of each temperature zone of the second pre-oxidation production line under each environment, as well as the number of multiple environments; according to the multiple first temperatures, the multiple second temperatures and the number of multiple environments, deriving the first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and the second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line. The first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are both solutions with the largest survival time in their corresponding solution sets, and can enable the corresponding production lines to have the lowest energy consumption and the highest pre-oxidation silk modulus while satisfying dynamic constraints. The simultaneous optimization of the pre-oxidation time parameters of the two pre-oxidation production lines is achieved, and the frequent switching of the pre-oxidation time parameters is avoided.

Description

Technical Field

[0001] The present disclosure relates to the technical field of carbon fiber production, and in particular to a method, device, computer equipment, and storage medium for optimizing pre-oxidation time parameters. Background Art

[0002] The preoxidation process is one of the most time-consuming and energy-intensive steps in carbon fiber production. To improve carbon fiber production efficiency and reduce production costs, while simultaneously producing high-quality preoxidized yarns and minimizing energy consumption, it is necessary to optimize process parameters such as the temperature and preoxidation time in each temperature zone of the preoxidation line, the drafting force applied by the drafting rollers on the fiber, the heating medium, and the heating rate. Currently, reducing the preoxidation time of polyacrylonitrile precursor in each temperature zone of the preoxidation line is the most commonly used approach. However, insufficient preoxidation time can lead to the formation of a skin-core structure, which affects the mechanical properties of the carbon fiber. While lowering the temperature in each temperature zone of the preoxidation line while extending the preoxidation time can improve the preoxidation effect to a certain extent, it also leads to reduced production efficiency. Therefore, while rationally setting the temperature in each temperature zone of the preoxidation line to ensure the preoxidized yarn's physical properties, such as modulus and tensile strength, it is crucial to rationally set the preoxidation time in each temperature zone of the preoxidation line to improve production efficiency and reduce production costs. Summary of the Invention

[0003] To overcome the problems existing in the related art, the present disclosure provides a method, apparatus, computer equipment and storage medium for optimizing pre-oxidation time parameters.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter is provided, the method comprising:

[0005] Obtaining a first temperature of each temperature zone of the first pre-oxidation line under each environment, a second temperature of each temperature zone of the second pre-oxidation line under each environment, and the number of the multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation line and the second pre-oxidation line, the first pre-oxidation line and the second pre-oxidation line both include multiple environments, and the multiple environments of the first pre-oxidation line correspond one-to-one to and are the same as the multiple environments of the second pre-oxidation line;

[0006] According to the plurality of first temperatures, the plurality of second temperatures and the number of the plurality of environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line are obtained, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first highest pre-oxidation silk modulus while satisfying dynamic constraints, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second highest pre-oxidation silk modulus while satisfying the dynamic constraints.

[0007] In some exemplary embodiments of the present disclosure, the step of deriving, based on the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line includes:

[0008] When the number of multiple environments is less than the total number of environments, and the current environment has ended, perform the following actions:

[0009] If both the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have not ended, using the first pre-oxidation time parameter as the first optimized pre-oxidation time parameter, and using the second pre-oxidation time parameter as the second optimized pre-oxidation time parameter, wherein the first pre-oxidation time parameter is the pre-oxidation time parameter currently used by the first pre-oxidation production line, and the second pre-oxidation time parameter is the pre-oxidation time parameter currently used by the second pre-oxidation production line;

[0010] If the survival time of the first pre-oxidation time parameter has not ended and the survival time of the second pre-oxidation time parameter has ended, the first pre-oxidation time parameter is used as the first optimized pre-oxidation time parameter, and the second optimized pre-oxidation time parameter is obtained by solving a pre-oxidation time parameter optimization model, wherein the pre-oxidation time parameter optimization model includes a first task and a second task, the first task is to solve the first optimized pre-oxidation time parameter, and the second task is to solve the second optimized pre-oxidation time parameter;

[0011] If the survival time of the first pre-oxidation time parameter has expired and the survival time of the second pre-oxidation time parameter has not expired, obtaining the first optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model, and using the second pre-oxidation time parameter as the second optimized pre-oxidation time parameter;

[0012] If the survival time of the first pre-oxidation time parameter and the second pre-oxidation time parameter has expired, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are obtained by solving the pre-oxidation time parameter optimization model.

[0013] In some exemplary embodiments of the present disclosure, the optimization method further includes:

[0014] When the number of the multiple environments is greater than or equal to the total number of environments, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are output.

[0015] In some exemplary embodiments of the present disclosure, obtaining the first optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model includes:

[0016] Using an explicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model to obtain a first solution set;

[0017] taking the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter;

[0018] The step of obtaining the second optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model includes:

[0019] Solving the pre-oxidation time parameter optimization model using the explicit genetic knowledge transfer method to obtain a second solution set;

[0020] The solution with the largest survival time in the second solution set is used as the second optimized pre-oxidation time parameter.

[0021] In some exemplary embodiments of the present disclosure, the optimization method further includes:

[0022] If there are multiple solutions with the longest survival time in the first solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the first solution set is used as the first optimized pre-oxidation time parameter;

[0023] If there are multiple solutions with the longest survival time in the second solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the second solution set is used as the second optimized pre-oxidation time parameter.

[0024] In some exemplary embodiments of the present disclosure, obtaining the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model includes:

[0025] Using an implicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model, a third solution set and a fourth solution set are obtained;

[0026] taking the solution with the largest survival time in the third solution set as the first optimized pre-oxidation time parameter;

[0027] The solution with the largest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

[0028] In some exemplary embodiments of the present disclosure, the optimization method further includes:

[0029] If there are multiple solutions with the longest survival time in the third solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the third solution set is used as the first optimized pre-oxidation time parameter;

[0030] If there are multiple solutions with the longest survival time in the fourth solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

[0031] According to a second aspect of an embodiment of the present disclosure, a device for optimizing a pre-oxidation time parameter is provided, the device comprising:

[0032] a data acquisition module configured to acquire a first temperature of each temperature zone of the first pre-oxidation production line under each environment, a second temperature of each temperature zone of the second pre-oxidation production line under each environment, and a number of the multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation production line and the second pre-oxidation production line, the first pre-oxidation production line and the second pre-oxidation production line both include multiple environments, and the multiple environments of the first pre-oxidation production line correspond one-to-one to and are identical to the multiple environments of the second pre-oxidation production line;

[0033] The parameter optimization module is configured to obtain a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line based on multiple first temperatures, multiple second temperatures and the number of multiple environments, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first maximum pre-oxidation silk modulus while satisfying dynamic constraints, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second maximum pre-oxidation silk modulus while satisfying the dynamic constraints.

[0034] According to a third aspect of an embodiment of the present disclosure, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the optimization method described in the first aspect when executing the computer program.

[0035] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the optimization method described in the first aspect are implemented.

[0036] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: based on multiple first temperatures, multiple second temperatures, and the number of multiple environments, a first optimized pre-oxidation time parameter and a second optimized pre-oxidation time parameter can be obtained, the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have the first lowest energy consumption and the first highest pre-oxidation silk modulus while satisfying dynamic constraints, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have the second lowest energy consumption and the second highest pre-oxidation silk modulus while satisfying dynamic constraints, thereby achieving simultaneous optimization of the pre-oxidation time parameters of the two pre-oxidation production lines, which can enable the two pre-oxidation production lines to obtain high-quality pre-oxidation silk while reducing the energy consumption of the pre-oxidation process. At the same time, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are respectively the solutions with the largest survival time in their corresponding solution sets, thereby avoiding frequent switching of the pre-oxidation time parameters.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0039] Figure 1 4 is a flow chart of a method for optimizing pre-oxidation time parameters according to an exemplary embodiment of the present disclosure.

[0040] Figure 2 According to the exemplary embodiment of the present disclosure Figure 1 Flowchart of step S102 in FIG.

[0041] Figure 3 It is a flow chart showing how to obtain a first optimized pre-oxidation time parameter by solving a pre-oxidation time parameter optimization model according to an exemplary embodiment of the present disclosure.

[0042] Figure 4 FIG. 4 is a flowchart of a knowledge transfer method of explicit inheritance according to an exemplary embodiment of the present disclosure.

[0043] Figure 5 According to the exemplary embodiment of the present disclosure Figure 4 Flowchart of step S405 in FIG.

[0044] Figure 6 3 is a flow chart of obtaining a second optimized pre-oxidation time parameter by solving a pre-oxidation time parameter optimization model according to an exemplary embodiment of the present disclosure.

[0045] Figure 7 According to the exemplary embodiment of the present disclosure Figure 2 Flowchart of step S102-9 in FIG.

[0046] Figure 8 4 is a flowchart of a knowledge transfer method of implicit inheritance according to an exemplary embodiment of the present disclosure.

[0047] Figure 9 The flowchart of allocating skill factors to offspring individuals using a skill factor inheritance strategy according to an exemplary embodiment of the present disclosure is shown.

[0048] Figure 10 According to the exemplary embodiment of the present disclosure Figure 8 Flowchart of step S807 in FIG.

[0049] Figure 11 4 is a flow chart of a method for optimizing pre-oxidation time parameters according to an exemplary embodiment of the present disclosure.

[0050] Figure 12 It is a block diagram of a device for optimizing pre-oxidation time parameters according to an exemplary embodiment of the present disclosure.

[0051] Figure 13 is a block diagram of a computer device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0053] The preoxidation process is one of the most time-consuming and energy-intensive steps in carbon fiber production. To improve carbon fiber production efficiency and reduce production costs while simultaneously producing high-quality preoxidized yarns and minimizing energy consumption, it is necessary to optimize process parameters such as the temperature and preoxidation time in each temperature zone of the preoxidation line, the drafting force applied by the drafting rollers on the fiber, the heating medium, and the heating rate. Reducing the preoxidation time of polyacrylonitrile precursor in each temperature zone of the preoxidation line is currently the most commonly used method. However, insufficient preoxidation time can lead to the formation of a skin-core structure, which affects the mechanical properties of the carbon fiber. While lowering the temperature in each temperature zone of the preoxidation line while extending the preoxidation time can improve the preoxidation effect to a certain extent, it also leads to reduced production efficiency. Therefore, while rationally setting the temperature in each temperature zone of the preoxidation line to ensure the preoxidized yarn maintains physical properties such as modulus and tensile strength, it is crucial to rationally set the preoxidation time in each temperature zone of the preoxidation line to improve production efficiency and reduce production costs. Current parameter optimization methods are only applicable to the parameter optimization of a single preoxidation line and often require frequent switching between deployment solutions.

[0054] In order to solve the above technical problems, the present disclosure provides a method, device, computer equipment and storage medium for optimizing pre-oxidation time parameters. The first temperature of each temperature zone of the first pre-oxidation production line under each environment, the second temperature of each temperature zone of the second pre-oxidation production line under each environment, and the number of multiple environments are obtained. Based on the multiple first temperatures, the multiple second temperatures and the number of multiple environments, the first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and the second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line are obtained. The first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have the first lowest energy consumption and the first highest pre-oxidation silk modulus while satisfying the dynamic constraint conditions, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have the second lowest energy consumption and the second highest pre-oxidation silk modulus while satisfying the dynamic constraint conditions. The pre-oxidation time parameters of the two pre-oxidation production lines are optimized simultaneously, so that the two pre-oxidation production lines can obtain high-quality pre-oxidation silk while reducing the energy consumption of the pre-oxidation process. At the same time, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are respectively the solutions with the largest survival time in their corresponding solution sets, thereby avoiding frequent switching of the pre-oxidation time parameters.

[0055] The exemplary embodiment of the present disclosure provides a method for optimizing the pre-oxidation time parameters, such as Figure 1 As shown, the optimization method of the pre-oxidation time parameters shown in this exemplary embodiment includes:

[0056] S101. Obtain the first temperature of each temperature zone of the first pre-oxidation production line under each environment, and the second temperature of each temperature zone of the second pre-oxidation production line under each environment, as well as the number of multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation production line and the second pre-oxidation production line, and the first pre-oxidation production line and the second pre-oxidation production line both include multiple environments, and the multiple environments of the first pre-oxidation production line correspond one-to-one to and are the same as the multiple environments of the second pre-oxidation production line.

[0057] A pre-oxidation period of the pre-oxidation line is referred to as an environment. The first pre-oxidation line and the second pre-oxidation line both include multiple environments, and the multiple environments of the first pre-oxidation line correspond to and are identical to the multiple environments of the second pre-oxidation line.

[0058] In step S101 , the pre-oxidation temperature of each temperature zone of the first pre-oxidation production line and each temperature zone of the second pre-oxidation production line in each environment, as well as the number of multiple environments, are respectively obtained.

[0059] For example, the first pre-oxidation line includes 10 temperature zones, and the second pre-oxidation line includes 10 temperature zones. By the time data is acquired, the first and second pre-oxidation lines have experienced six identical, one-to-one environments. The first temperature of each of the 10 temperature zones of the first pre-oxidation line under each of the six environments is acquired, and the second temperature of each of the 10 temperature zones of the second pre-oxidation line under each of the six environments is acquired. The number of acquired environments is six.

[0060] S102. According to the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line are obtained, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first maximum pre-oxidation silk modulus while satisfying dynamic constraints, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second maximum pre-oxidation silk modulus while satisfying dynamic constraints.

[0061] The modulus of pre-oxidized yarn refers to the ratio of stress to strain per unit length when the pre-oxidized yarn is subjected to external force within the elastic range. The modulus of pre-oxidized yarn reflects the ability of pre-oxidized yarn to resist deformation when subjected to external force and is one of the important indicators for evaluating the performance of pre-oxidized yarn.

[0062] In step S102, based on the multiple first temperatures, multiple second temperatures, and the number of multiple environments obtained in step S101, a first optimized pre-oxidation time parameter is obtained that enables the first pre-oxidation production line to have the lowest energy consumption and the highest pre-oxidation fiber modulus while satisfying the dynamic constraint conditions, and a second optimized pre-oxidation time parameter is obtained that enables the second pre-oxidation production line to have the lowest energy consumption and the highest pre-oxidation fiber modulus while satisfying the dynamic constraint conditions. The pre-oxidation time parameters of the two pre-oxidation production lines can be optimized simultaneously, thereby improving the production efficiency of the two pre-oxidation production lines.

[0063] For example, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are derived based on the first temperature of each of the 10 temperature zones of the first pre-oxidation production line in each of the 6 environments, the second temperature of each of the 10 temperature zones of the second pre-oxidation production line in each of the 6 environments, and the number of multiple environments being 6.

[0064] In an exemplary embodiment of the present disclosure, Figure 2 As shown, according to the number of the multiple first temperatures, the multiple second temperatures and the multiple environments, the first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and the second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line are obtained, which may specifically include:

[0065] S102-1. Determine whether the number of the multiple environments is less than the total number of environments. If so, execute step S102-2.

[0066] In step S102-1, it is determined whether the number of multiple environments obtained in step S101 is less than the total number of environments. For example, if the total number of environments is 10, and the number of multiple environments obtained in step S101 is 6, which is less than the total number of environments 10, then step S102-2 is executed.

[0067] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: when the number of multiple environments is greater than or equal to the total number of environments, outputting a first optimized pre-oxidation time parameter and a second optimized pre-oxidation time parameter. For example, if the total number of environments is set to 10, and the number of multiple environments obtained is also 10, which is equal to the total number of environments, then outputting the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter. The output first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter may be the most recent first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter stored in the computer.

[0068] S102-2: Determine whether the current environment has ended. If so, execute step S102-3; if not, return to step S102-1.

[0069] S102-3. Determine whether the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have not ended, wherein the first pre-oxidation time parameter is the pre-oxidation time parameter currently used by the first pre-oxidation production line, and the second pre-oxidation time parameter is the pre-oxidation time parameter currently used by the second pre-oxidation production line. If so, execute step S102-4; if not, execute step S102-5.

[0070] The lifetime of the first pre-oxidation time parameter may be a feasible time length of the first pre-oxidation time parameter in the time domain. The lifetime of the second pre-oxidation time parameter may be a feasible time length of the second pre-oxidation time parameter in the time domain.

[0071] S102-4: Using the first pre-oxidation time parameter as a first optimized pre-oxidation time parameter, and using the second pre-oxidation time parameter as a second optimized pre-oxidation time parameter.

[0072] In step S102-4, when the survival time of the first pre-oxidation time parameter and the second pre-oxidation time parameter has not ended, the first pre-oxidation time parameter and the second pre-oxidation time parameter can continue to be used, with the first pre-oxidation time parameter being used as the first optimized pre-oxidation time parameter and the second pre-oxidation time parameter being used as the second optimized pre-oxidation time parameter.

[0073] S102-5: Determine whether the lifetime of the first pre-oxidation time parameter and the lifetime of the second pre-oxidation time parameter have both expired. If not, execute step S102-6; if so, execute step S102-9.

[0074] S102-6: Determine whether the lifetime of the first pre-oxidation time parameter has expired and the lifetime of the second pre-oxidation time parameter has not expired. If so, execute step S102-7; if not, execute step S102-8.

[0075] S102-7. Obtain a first optimized pre-oxidation time parameter by solving a pre-oxidation time parameter optimization model, and use the second pre-oxidation time parameter as a second optimized pre-oxidation time parameter; wherein the pre-oxidation time parameter optimization model includes a first task and a second task, the first task is to solve the first optimized pre-oxidation time parameter, and the second task is to solve the second optimized pre-oxidation time parameter.

[0076] In an exemplary embodiment of the present disclosure, a pre-oxidation time parameter optimization model may be established in the following manner.

[0077] Dynamic constraints can be set as shown in the following formula.

[0078]

[0079] Among them, xi is the pre-oxidation time of the ith temperature zone of the pre-oxidation production line, T i (t) is the temperature of the ith temperature zone of the pre-oxidation production line under the environment t.

[0080] The minimum energy consumption of the pre-oxidation production line can be obtained using the following formula while satisfying the above dynamic constraints.

[0081]

[0082] Among them, x i is the pre-oxidation time of the ith temperature zone of the pre-oxidation production line; T i is the temperature variable of the ith temperature zone of the pre-oxidation production line; t is the number of the environment; T i (t) is the temperature of the ith temperature zone of the pre-oxidation production line under the environment t; T0 is the room temperature, for example, 25°C; c a is the specific heat capacity of air, for example, 1.01 kJ / kg℃; V a is the air flow rate, for example 10m 3 / min; ρ is the air density, for example, 1.29kg / m 3 η is the heater efficiency, for example, 75%; U is the three-phase voltage, for example, 380V; I E is the exhaust fan current, for example 1.5A; I R is the circulating fan current, for example 5A; I D is the driving motor current, for example, 0.4A; θ is the phase difference, for example, 120°.

[0083] The maximum pre-oxidation silk modulus of the pre-oxidation production line can be obtained using the following formula while satisfying the above dynamic constraints.

[0084]

[0085] Among them, x i is the pre-oxidation time of the ith temperature zone of the pre-oxidation production line; T i is the temperature variable of the i-th temperature zone of the pre-oxidation production line; t is the number of the environment; w1 is the weighting coefficient, which can be determined according to the actual situation; x1+x2 is the sum of the pre-oxidation time of all temperature zones of the pre-oxidation production line; E is the Young's modulus, for example, 230N / m 2 ; S is the cross-sectional area of ​​the original fiber, for example, 38.48 μm 2τ is the drafting rate, for example, 5%; F0 is the initial tension of the raw yarn, which can be determined according to the material properties of the raw yarn or the process requirements; ν1 is the speed of the drafting roller, for example, 0.5 m / s; dx is the contribution of the raw yarn in a certain small interval during the drafting process; L is the distance between the drafting rollers, for example, 50 m; w2 is the weighting coefficient, which can be determined according to the actual situation; A is the pre-exponential factor, for example, 4.15×10 5 ; e is the base of natural logarithm, for example 2.718; E a is the activation energy, for example, 124.7 kJ / mol; R is the molar gas constant, for example, 8.314 J / mol K; T i (t) is the temperature of the ith temperature zone of the pre-oxidation production line under the environment t.

[0086] The established pre-oxidation time parameter optimization model can be expressed using the following formula: In step S102-7, the first optimized pre-oxidation time parameter can be obtained by solving the following pre-oxidation time parameter optimization model.

[0087]

[0088] Among them, Task1 is the first task, Task2 is the second task, EC1 is the energy consumption of the first pre-oxidation production line, EC2 is the energy consumption of the second pre-oxidation production line, M1 is the pre-oxidation silk modulus of the first pre-oxidation production line, and M2 is the pre-oxidation silk modulus of the second pre-oxidation production line.

[0089] The optimized pre-oxidation time parameters obtained by solving the above pre-oxidation time parameter optimization model can enable the corresponding pre-oxidation production line to have the lowest energy consumption and the highest pre-oxidation yarn modulus while meeting the dynamic constraints. This can save energy consumption and improve production efficiency while ensuring the quality of the pre-oxidation yarn.

[0090] In an exemplary embodiment of the present disclosure, Figure 3 As shown, obtaining the first optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model may include:

[0091] S301. Use the knowledge transfer method of explicit genetics to solve the pre-oxidation time parameter optimization model to obtain a first solution set.

[0092] like Figure 4 As shown, the explicit genetic knowledge transfer method may specifically include:

[0093] S401. The pre-oxidation time of each temperature zone of the pre-oxidation production line is used as a decision variable, and constraints are set for the decision variables.

[0094] For example, the constraints set for the decision variables are that the upper limit of the pre-oxidation time in each temperature zone is 9 minutes and the lower limit is 3 minutes.

[0095] S402: Set the population size, number of iterations, crossover probability, mutation probability, migration mutation probability, robust threshold, time window, and robust solution library size, and randomly generate an initial population according to the constraints of the decision variables.

[0096] For example, set the population size to 100, the number of iterations to 500, the crossover probability to 0.9, the mutation probability to 0.1, the migration mutation probability to 0.1, the robust thresholds to 0.1, 0.2, 0.3, 0.4, the time window to 2, and the robust solution size to 10.

[0097] An initial population is randomly generated according to the constraints of the decision variables, and the initial population may include 100 individuals with a time period of more than 3 minutes and less than 9 minutes.

[0098] S403: Update the Pareto solution set, feasible solution ratio, and non-dominated solution ratio of the current task.

[0099] The Pareto solution set can include individuals in the current population that cannot be simultaneously surpassed by other solutions on all objectives. The proportion of feasible solutions can be the proportion of individuals in the current population that meet the constraints. The proportion of non-dominated solutions can be the percentage of individuals in the entire current population that belong to the Pareto solution set. The Pareto solution set, the proportion of feasible solutions, and the proportion of non-dominated solutions can be automatically calculated and updated using algorithms well known to those skilled in the art and will not be described in detail here.

[0100] S404. Perform crossover and mutation operations on the parent population to obtain the offspring population, and calculate the survival time of the offspring individuals.

[0101] In step S402, the number of iterations is set. For the 0th iteration, the initial population is the parent population. For the other iterations, the child population obtained in the previous iteration is the parent population.

[0102] The survival time of offspring individuals can be calculated by an algorithm well known to those skilled in the art, which will not be described in detail here.

[0103] S405. Use the migration mutation probability adaptive strategy to obtain a set of positive migration individuals.

[0104] like Figure 5 As shown, step S405 may specifically include:

[0105] S405-1. Traverse the robust solution library of the current task.

[0106] S405-2. Generate a random number r between [0, 1].

[0107] S405-3. If r is less than the migration mutation probability, mutate the current individual and determine whether the mutated individual is non-dominated in the population of another task. If not, execute step S405-4. If so, execute step S405-5.

[0108] S405-4. Determine whether the survival time of the mutant individual is greater than that of the majority of individuals in the population of another task. If so, execute step S405-5; if not, execute step S405-6.

[0109] The order of determining whether the mutant is non-dominant in the population of the other task in step S405-3 and determining whether the mutant's survival time is greater than that of the majority of individuals in the population of the other task in step S405-4 can be interchanged. Specifically, after generating a mutant, first determine whether its survival time is greater than that of the majority of individuals in the population of the other task. If so, proceed to step S405-5. If not, then determine whether the mutant is non-dominant in the population of the other task. If so, proceed to step S405-5; otherwise, proceed to step S405-6.

[0110] S405-5. Update the number of positive migrations and add the mutant individual to the positive migration individual set.

[0111] Updating the number of positive migrations may be performed by adding 1 to the number of positive migrations.

[0112] S405-6: Determine whether the robust solution library of the current task has been traversed. If so, execute step S405-7; if not, repeat steps S405-2 to S405-3.

[0113] S405-7. Use the ratio of the number of positive migrations to the number of mutations to update the migration mutation probability, and output the set of positive migration individuals.

[0114] S406: Merge the parent population, the child population, and the set of migrating individuals, update the factor rankings of all individuals in the parent population, and update the parent population to individuals ranked higher according to different skill factors.

[0115] S407: Update the Pareto solution set, feasible solution ratio, and non-dominated solution ratio of the current task.

[0116] S408: Determine whether the maximum number of iterations has been reached. If so, execute step S409; if not, repeat steps S404 to S407.

[0117] S409: Output the robust Pareto optimal solution set and update the robust solution library of the current task.

[0118] In step S301, the pre-oxidation time of each temperature zone of the first pre-oxidation production line can be used as a decision variable, the first task can be used as the current task, and the second task can be used as another task. The output robust Pareto optimal solution set can be the first solution set.

[0119] The knowledge transfer method of explicit genetics is applied to solving the pre-oxidation time parameter optimization model. Through the unidirectional transfer of knowledge between the two tasks and the reuse of useful knowledge, the ability to solve the pre-oxidation time parameter optimization model is enhanced.

[0120] S302 : Taking the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter.

[0121] Selecting the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter can make the first optimized pre-oxidation time parameter have better robustness and avoid frequent switching of the pre-oxidation time parameter of the first pre-oxidation production line.

[0122] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the first solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the first solution set as the first optimized pre-oxidation time parameter.

[0123] The switching cost may be the time and resources consumed when switching parameters. Using the solution with the lowest switching cost among the multiple solutions with the longest survival times in the first solution set as the first optimized pre-oxidation time parameter can reduce the time and resources consumed when the first pre-oxidation production line switches from the currently used pre-oxidation time parameter to the first optimized pre-oxidation time parameter.

[0124] S102-8. Using the first pre-oxidation time parameter as a first optimized pre-oxidation time parameter, and obtaining a second optimized pre-oxidation time parameter by solving a pre-oxidation time parameter optimization model.

[0125] If the judgment results of steps S102-3, S102-5, and S102-6 are all negative, it can be determined that the lifetime of the first pre-oxidation time parameter has not expired, but the generation time of the second pre-oxidation time parameter has expired. In this case, step S102-8 is executed, and the first pre-oxidation time parameter is used as the first optimized pre-oxidation time parameter. The second optimized pre-oxidation time parameter is obtained by solving the pre-oxidation time parameter optimization model.

[0126] The pre-oxidation time parameter optimization model in step S102 - 8 is the same as the pre-oxidation time parameter optimization model in step S102 - 7 , and will not be described again here.

[0127] In an exemplary embodiment of the present disclosure, Figure 6As shown, obtaining the second optimized pre-oxidation time parameter by solving the pre-oxidation time parameter optimization model may include:

[0128] S601. Use the knowledge transfer method of explicit genetics to solve the pre-oxidation time parameter optimization model to obtain a second solution set.

[0129] The knowledge transfer method of explicit inheritance in step S601 is the same as the knowledge transfer method of explicit inheritance in step S301 and will not be described in detail here.

[0130] In step S601, the pre-oxidation time of each temperature zone of the second pre-oxidation production line can be used as a decision variable, the second task can be used as the current task, and the first task can be used as another task. The output robust Pareto optimal solution set can be the second solution set.

[0131] The knowledge transfer method of explicit genetics is applied to solving the pre-oxidation time parameter optimization model. Through the unidirectional transfer of knowledge between the two tasks and the reuse of useful knowledge, the ability to solve the pre-oxidation time parameter optimization model is enhanced.

[0132] S602: Taking the solution with the largest survival time in the second solution set as the second optimized pre-oxidation time parameter.

[0133] Selecting the solution with the largest survival time in the second solution set as the second optimized pre-oxidation time parameter can make the second optimized pre-oxidation time parameter have better robustness and avoid frequent switching of the pre-oxidation time parameter of the second pre-oxidation production line.

[0134] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the second solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the second solution set as the second optimized pre-oxidation time parameter.

[0135] By using the solution with the smallest switching cost among the multiple solutions with the largest survival times in the second solution set as the second optimized pre-oxidation time parameter, the time and resources required to switch the second pre-oxidation production line from the currently used pre-oxidation time parameter to the second optimized pre-oxidation time parameter can be reduced.

[0136] S102-9. Obtain a first optimized pre-oxidation time parameter and a second optimized pre-oxidation time parameter by solving a pre-oxidation time parameter optimization model.

[0137] In step S102-9, when the survival times of the first pre-oxidation time parameter and the second pre-oxidation time parameter have both expired, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are obtained by solving the pre-oxidation time parameter optimization model.

[0138] The pre-oxidation time parameter optimization model in step S102 - 9 is the same as the pre-oxidation time parameter optimization model in step S102 - 7 , and will not be described again here.

[0139] In an exemplary embodiment of the present disclosure, Figure 7 As shown, step S102-9 may include:

[0140] S102-9-1. Use the implicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model to obtain the third solution set and the fourth solution set.

[0141] like Figure 8 As shown, the implicit inheritance knowledge transfer method may specifically include:

[0142] S801. The pre-oxidation time of each temperature zone of the pre-oxidation production line is used as a decision variable, and constraints are set for each decision variable.

[0143] For example, the constraints set for the decision variables are that the upper limit of the pre-oxidation time in each temperature zone is 9 minutes and the lower limit is 3 minutes.

[0144] S802. Set the population size, number of iterations, crossover probability, mutation probability, knowledge transfer probability, robust threshold, time window, and robust solution library size, randomly generate the initial population according to the constraints of the decision variables, assign a skill factor to each individual in the initial population, and calculate its survival time.

[0145] For example, set the population size to 100, the number of iterations to 500, the crossover probability to 0.9, the mutation probability to 0.1, the knowledge transfer probability to 0.1, the robust thresholds to 0.1, 0.2, 0.3, 0.4, the time window to 2, and the robust solution size to 10.

[0146] An initial population is randomly generated according to the constraints of the decision variables, and the initial population may include 100 individuals with a time period of more than 3 minutes and less than 9 minutes.

[0147] The skill factor is used to identify the task to which an individual belongs in multi-task optimization. The skill factor of an individual is the index of the task for which the individual performs best among all tasks. The skill factor can be assigned to each individual in the initial population by randomly assigning the skill factor to each individual in the initial population.

[0148] The survival time of an individual refers to the length of time that the individual is feasible in the time domain. The survival time of each individual in the initial population can be calculated by an algorithm well known to those skilled in the art, and will not be described in detail here.

[0149] S803: Update the Pareto solution set, feasible solution ratio, and non-dominated solution ratio of each task.

[0150] The Pareto solution set can include individuals in the current population that cannot be simultaneously surpassed by other solutions on all objectives. The proportion of feasible solutions can be the proportion of individuals in the current population that meet the constraints. The proportion of non-dominated solutions can be the percentage of individuals in the entire current population that belong to the Pareto solution set. The Pareto solution set, the proportion of feasible solutions, and the proportion of non-dominated solutions can be automatically calculated and updated using algorithms well known to those skilled in the art and will not be described in detail here.

[0151] S804. Randomly select two parent individuals from the parent population, perform crossover and mutation operations to generate offspring individuals, and use the skill factor inheritance strategy to assign skill factors to the offspring individuals, calculate their survival time, and then add them to the offspring population.

[0152] In step S802, the number of iterations is set. For the 0th iteration, the initial population is the parent population. For the other iterations, the child population obtained in the previous iteration is the parent population.

[0153] The survival time of offspring individuals can be calculated by an algorithm well known to those skilled in the art, which will not be described in detail here.

[0154] like Figure 9 As shown in the figure, skill factors are assigned to offspring individuals using the skill factor inheritance strategy, which may include:

[0155] S901. Determine whether the skill factors of the two parent individuals are the same. If so, execute step S902; if not, execute step S903.

[0156] S902. Offspring individuals c1 and c2 inherit the skill factors of parent individuals p1 and p2 respectively.

[0157] S903. Generate two random numbers r1 and r2 between [0, 1].

[0158] S904 , determine whether r1 is smaller than the knowledge transfer probability rmp1 and r2 is smaller than the knowledge transfer probability rmp2 , if so, execute step S905 , if not, execute step S906 .

[0159] S905. Offspring individuals c1 and c2 inherit the skill factors of parent individuals p2 and p1 respectively.

[0160] S906. Determine whether r1 is less than rmp1 and r2 is greater than or equal to rmp2. If so, execute step S907; if not, execute step S908.

[0161] S907, offspring individuals c1 and c2 both inherit the skill factor of parent individual p1.

[0162] S908. Determine whether r1 is greater than or equal to rmp1 and r2 is less than rmp2. If so, execute step S909; if not, execute step S902.

[0163] S909, the offspring individuals c1 and c2 both inherit the skill factor of the parent individual p2.

[0164] S910: Update the number of knowledge transfers between two tasks.

[0165] S805: Determine whether the offspring population has reached the parent population size. If so, execute step S806; if not, repeat step S804.

[0166] Determining whether the offspring population has reached the size of the parent population may be determining whether the number of individuals in the offspring population has reached the number of individuals in the parent population.

[0167] S806: Merge the parent population and the child population, update the factor rankings of all individuals in the parent population, and update the parent population to individuals ranked higher according to different skill factors.

[0168] S807: Update the knowledge transfer probability using the knowledge transfer probability adaptive strategy.

[0169] like Figure 10 As shown, step S807 may specifically include:

[0170] S807-1. Traverse the offspring population.

[0171] The offspring population here may be the offspring population generated in step S802.

[0172] S807-2. Determine whether the offspring individual is obtained by cross-task and whether its performance in the corresponding task is better than that of its parent. If so, execute step S807-3; if not, execute step S807-4.

[0173] The skill factor of the offspring can be used to determine whether it is obtained across tasks. Specifically, the skill factors of the two parent individuals usually correspond to different tasks. When the skill factor of the offspring individual does not match the skill factor of one of the parents, it can be considered to be obtained across tasks.

[0174] By comparing the pre-oxidation time and other parameters of the offspring individuals with those of the parent population, it can be determined whether the offspring individuals are superior to the parent population. Other parameters can also be compared to make this judgment.

[0175] S807-3. Update the number of positive migrations.

[0176] Updating the number of positive migrations may be performed by adding 1 to the number of positive migrations.

[0177] S807-4. Determine whether the offspring population has been traversed. If so, execute step S807-5. If not, repeat step S807-2.

[0178] S807-5. Update the knowledge transfer probability between the two tasks using the ratio of the number of positive transfers to the number of knowledge transfers.

[0179] The number of knowledge transfers represents the total number of cross-task offspring individuals generated during the entire optimization process. The number of positive transfers refers to the number of times a cross-task offspring individual performs better than its parent individual in the new task. The positive transfer rate, calculated as the ratio of the number of positive transfers to the number of knowledge transfers, is used to assess the success rate of cross-task knowledge transfer.

[0180] S808. Update the Pareto solution set, feasible solution ratio, and non-dominated solution ratio of each task.

[0181] S809: Determine whether the maximum number of iterations has been reached. If so, execute step S810; if not, repeat steps S804 to S808.

[0182] S810: Output the robust Pareto optimal solution set and update the robust solution library of each task.

[0183] In step S102-9-1, the pre-oxidation time for each temperature zone of the first pre-oxidation line and the pre-oxidation time for each temperature zone of the second pre-oxidation line can be used as decision variables. Each task can include a first task and a second task. The output robust Pareto optimal solution set can include a third solution set and a fourth solution set.

[0184] The knowledge transfer method of implicit genetics is applied to solving the pre-oxidation time parameter optimization model. Through the bidirectional transfer of knowledge between the two tasks and the reuse of useful knowledge, the ability to solve the pre-oxidation time parameter optimization model is enhanced.

[0185] S102-9-2. The solution with the largest survival time in the third solution set is used as the first optimized pre-oxidation time parameter.

[0186] Selecting the solution with the largest survival time in the third solution set as the first optimized pre-oxidation time parameter can make the first optimized pre-oxidation time parameter have better robustness and avoid frequent switching of the pre-oxidation time parameter of the first pre-oxidation production line.

[0187] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the third solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the third solution set as the first optimized pre-oxidation time parameter.

[0188] By using the solution with the smallest switching cost among the multiple solutions with the largest survival times in the third solution set as the first optimized pre-oxidation time parameter, the time and resources required to switch the first pre-oxidation production line from the currently used pre-oxidation time parameter to the first optimized pre-oxidation time parameter can be reduced.

[0189] S102-9-3. The solution with the largest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

[0190] Selecting the solution with the largest survival time in the fourth solution set as the second optimized pre-oxidation time parameter can make the second optimized pre-oxidation time parameter have better robustness and avoid frequent switching of the pre-oxidation time parameter of the second pre-oxidation production line.

[0191] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the fourth solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the fourth solution set as the second optimized pre-oxidation time parameter.

[0192] By using the solution with the smallest switching cost among the multiple solutions with the largest survival times in the fourth solution set as the second optimized pre-oxidation time parameter, the time and resources required to switch the second pre-oxidation production line from the currently used pre-oxidation time parameter to the second optimized pre-oxidation time parameter can be reduced.

[0193] In this exemplary embodiment, the pre-oxidation time parameters of two pre-oxidation production lines are simultaneously optimized, enabling both lines to produce high-quality pre-oxidized yarn while reducing energy consumption during the pre-oxidation process. Furthermore, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are the solutions with the longest survival time in their respective solution sets, thereby avoiding frequent switching of the pre-oxidation time parameters.

[0194] The exemplary embodiment of the present disclosure provides a method for optimizing the pre-oxidation time parameters. Figure 11 As shown, the optimization method of the pre-oxidation time parameters shown in this exemplary embodiment includes:

[0195] S1101. Obtain a first temperature of each temperature zone of a first pre-oxidation production line under each environment, a second temperature of each temperature zone of a second pre-oxidation production line under each environment, and the number of the multiple environments.

[0196] S1102. Determine whether the number of multiple environments is less than the total number of environments. If so, execute step S1104; if not, execute step S1103.

[0197] S1103 , outputting a first optimized pre-oxidation time parameter and a second optimized pre-oxidation time parameter.

[0198] S1104: Determine whether the current environment has ended. If so, execute step S1105; if not, return to step S1102.

[0199] S1105 , determining whether the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have not yet ended; if so, executing step S1106 ; if not, executing step S1107 .

[0200] S1106: Use the first pre-oxidation time parameter as a first optimized pre-oxidation time parameter, and use the second pre-oxidation time parameter as a second optimized pre-oxidation time parameter.

[0201] S1107 , determining whether the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have both ended; if not, executing step S1108 ; if so, executing step S1111 .

[0202] S1108. Determine whether the lifetime of the first pre-oxidation time parameter has expired and the lifetime of the second pre-oxidation time parameter has not expired. If so, execute step S1109; if not, execute step S1110.

[0203] S1109. Use the knowledge transfer method of explicit genetics to solve the pre-oxidation time parameter optimization model to obtain a first solution set, and use the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter, and use the second pre-oxidation time parameter as the second optimized pre-oxidation time parameter.

[0204] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the first solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the first solution set as the first optimized pre-oxidation time parameter.

[0205] S1110. Use the first pre-oxidation time parameter as the first optimized pre-oxidation time parameter, use the explicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model, obtain a second solution set, and use the solution with the largest survival time in the second solution set as the second optimized pre-oxidation time parameter.

[0206] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the second solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the second solution set as the second optimized pre-oxidation time parameter.

[0207] S1111. Use the knowledge transfer method of implicit genetics to solve the pre-oxidation time parameter optimization model to obtain the third solution set and the fourth solution set. The solution with the largest survival time in the third solution set is used as the first optimized pre-oxidation time parameter, and the solution with the largest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

[0208] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the third solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the third solution set as the first optimized pre-oxidation time parameter.

[0209] In an exemplary embodiment of the present disclosure, a method for optimizing a pre-oxidation time parameter may further include: if there are multiple solutions with the longest survival time in the fourth solution set, taking the solution with the smallest switching cost among the multiple solutions with the longest survival time in the fourth solution set as the second optimized pre-oxidation time parameter.

[0210] In this exemplary embodiment, the pre-oxidation time parameters of two pre-oxidation production lines are simultaneously optimized, enabling both lines to produce high-quality pre-oxidized yarn while reducing energy consumption during the pre-oxidation process. Furthermore, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are the solutions with the longest survival time in their respective solution sets, thereby avoiding frequent switching of the pre-oxidation time parameters.

[0211] The exemplary embodiment of the present disclosure provides a device for optimizing the pre-oxidation time parameters. Figure 12 As shown, the device for optimizing the pre-oxidation time parameters includes a data acquisition module 1201 and a parameter optimization module 1202 .

[0212] The data acquisition module 1201 is configured to obtain the first temperature of each temperature zone of the first pre-oxidation production line under each environment, the second temperature of each temperature zone of the second pre-oxidation production line under each environment, and the number of multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation production line and the second pre-oxidation production line, the first pre-oxidation production line and the second pre-oxidation production line both include multiple environments, and the multiple environments of the first pre-oxidation production line correspond one-to-one to and are the same as the multiple environments of the second pre-oxidation production line.

[0213] The parameter optimization module 1202 is configured to obtain a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line based on the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first maximum pre-oxidation silk modulus while satisfying dynamic constraints, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second maximum pre-oxidation silk modulus while satisfying dynamic constraints.

[0214] In this exemplary embodiment, the pre-oxidation time parameters of the two pre-oxidation production lines are optimized simultaneously, so that the two pre-oxidation production lines can obtain high-quality pre-oxidation yarns while reducing the energy consumption of the pre-oxidation process.

[0215] In an exemplary embodiment of the present disclosure, the parameter optimization module 1202 is further configured to:

[0216] When the number of multiple environments is less than the total number of environments and the current environment has ended, perform the following operations:

[0217] If both the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have not ended, the first pre-oxidation time parameter is used as the first optimized pre-oxidation time parameter, and the second pre-oxidation time parameter is used as the second optimized pre-oxidation time parameter, wherein the first pre-oxidation time parameter is the pre-oxidation time parameter currently used by the first pre-oxidation production line, and the second pre-oxidation time parameter is the pre-oxidation time parameter currently used by the second pre-oxidation production line;

[0218] If the survival time of the first pre-oxidation time parameter has not ended and the survival time of the second pre-oxidation time parameter has ended, the first pre-oxidation time parameter is used as the first optimized pre-oxidation time parameter, and the second optimized pre-oxidation time parameter is obtained by solving the pre-oxidation time parameter optimization model, wherein the pre-oxidation time parameter optimization model includes a first task and a second task, the first task is to solve the first optimized pre-oxidation time parameter, and the second task is to solve the second optimized pre-oxidation time parameter;

[0219] If the survival time of the first pre-oxidation time parameter has expired and the survival time of the second pre-oxidation time parameter has not expired, the first optimized pre-oxidation time parameter is obtained by solving the pre-oxidation time parameter optimization model, and the second pre-oxidation time parameter is used as the second optimized pre-oxidation time parameter;

[0220] If the survival times of the first pre-oxidation time parameter and the second pre-oxidation time parameter have both expired, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are obtained by solving the pre-oxidation time parameter optimization model.

[0221] In an exemplary embodiment of the present disclosure, the device for optimizing pre-oxidation time parameters further includes a parameter output module, which is configured to output a first optimized pre-oxidation time parameter and a second optimized pre-oxidation time parameter when the number of multiple environments is greater than or equal to the total number of environments.

[0222] In an exemplary embodiment of the present disclosure, the parameter optimization module 1202 is further configured to:

[0223] The knowledge transfer method of explicit genetics is used to solve the pre-oxidation time parameter optimization model and obtain the first solution set.

[0224] The solution with the largest survival time in the first solution set is used as the first optimized pre-oxidation time parameter;

[0225] The knowledge transfer method of explicit genetics is used to solve the pre-oxidation time parameter optimization model and obtain the second solution set;

[0226] The solution with the largest survival time in the second solution set is taken as the second optimized pre-oxidation time parameter.

[0227] In an exemplary embodiment of the present disclosure, the parameter optimization module 1202 is further configured to:

[0228] If there are multiple solutions with the longest survival time in the first solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the first solution set is used as the first optimized pre-oxidation time parameter;

[0229] If there are multiple solutions with the longest survival time in the second solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the second solution set is used as the second optimized pre-oxidation time parameter.

[0230] In an exemplary embodiment of the present disclosure, the parameter optimization module 1202 is further configured to:

[0231] The knowledge transfer method of implicit genetics is used to solve the pre-oxidation time parameter optimization model and obtain the third and fourth solution sets.

[0232] The solution with the largest survival time in the third solution set is used as the first optimized pre-oxidation time parameter;

[0233] The solution with the largest survival time in the fourth solution set is taken as the second optimized pre-oxidation time parameter.

[0234] In an exemplary embodiment of the present disclosure, the parameter optimization module 1202 is further configured to:

[0235] If there are multiple solutions with the longest survival time in the third solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the third solution set is used as the first optimized pre-oxidation time parameter;

[0236] If there are multiple solutions with the longest survival time in the fourth solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

[0237] In an exemplary embodiment of the present disclosure, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are respectively solutions with the largest survival time in their corresponding solution sets, thereby avoiding frequent switching of the pre-oxidation time parameters.

[0238] Each module in the above-mentioned pre-oxidation time parameter optimization device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the form of software in a memory in the computer device so that the processor can call and execute the corresponding operations of each module.

[0239] In an exemplary embodiment, a computer device is provided, including a processor and a memory, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for optimizing any pre-oxidation time parameter are implemented.

[0240] In one exemplary embodiment, a computer-readable storage medium is provided, having a computer program stored thereon. When executed by a processor, the computer program implements the steps of any of the above-described methods for optimizing pre-oxidation time parameters. The computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0241] In an exemplary embodiment, a computer program product is provided, comprising a computer program, which implements the steps of any of the above-mentioned methods for optimizing pre-oxidation time parameters when executed by a processor.

[0242] refer to Figure 13 , a block diagram of a structure of a computer device that can be used as the present disclosure will now be described. The computer device includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a random access memory (RAM) 1303. Various programs and data required for the operation of the computer device 1300 can also be stored in the RAM 1303. The computing unit 1301, ROM 1302, and RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0243] Multiple components in the computer device 1300 are connected to the I / O interface 1305, including: an input unit 1306, an output unit 1307, a storage unit 1308, and a communication unit 1309. The input unit 1306 can be any type of device that can input information to the computer device 1300. The input unit 1306 can receive input digital or character information and generate key signal input related to user settings and / or function control of the computer device 1300, and can include but is not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and / or a remote control. The output unit 1307 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1308 can include but is not limited to a magnetic disk and an optical disk. The communication unit 1309 allows the computer device 1300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device and / or the like.

[0244] The computing unit 1301 can be a variety of general and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1301 performs the various methods and processes described above, such as the optimization method for the pre-oxidation time parameters. For example, in some embodiments, the optimization method for the pre-oxidation time parameters can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 1308. In some embodiments, part or all of the computer program can be loaded and / or installed on the computer device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the optimization method for the pre-oxidation time parameters described above can be performed. Alternatively, in other embodiments, the computing unit 1301 may be configured to execute the optimization method of the pre-oxidation time parameters in any other appropriate manner (for example, by means of firmware).

[0245] The computer device 1300 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned method for optimizing the pre-oxidation time parameters.

[0246] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0247] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for optimizing pre-oxidation time parameters, characterized in that: The optimization method comprises: Obtaining a first temperature of each temperature zone of the first pre-oxidation line under each environment, a second temperature of each temperature zone of the second pre-oxidation line under each environment, and the number of the multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation line and the second pre-oxidation line, the first pre-oxidation line and the second pre-oxidation line both include multiple environments, and the multiple environments of the first pre-oxidation line correspond one-to-one to and are the same as the multiple environments of the second pre-oxidation line; According to the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line are obtained, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first maximum pre-oxidation silk modulus while satisfying a dynamic constraint condition, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second maximum pre-oxidation silk modulus while satisfying the dynamic constraint condition; The step of obtaining, based on the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line includes: When the number of multiple environments is less than the total number of environments, and the current environment has ended, perform the following actions: If the survival time of the first pre-oxidation time parameter has ended, and the survival time of the second pre-oxidation time parameter has not ended, use the explicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model to obtain a first solution set; use the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter; use the second pre-oxidation time parameter as the second optimized pre-oxidation time parameter; wherein, the first pre-oxidation time parameter is the pre-oxidation time parameter currently used by the first pre-oxidation production line, and the second pre-oxidation time parameter is the pre-oxidation time parameter currently used by the second pre-oxidation production line, and the pre-oxidation time parameter optimization model includes a first task and a second task, the first task is to solve the first optimized pre-oxidation time parameter, and the second task is to solve the second optimized pre-oxidation time parameter; If the survival time of the first pre-oxidation time parameter has not expired and the survival time of the second pre-oxidation time parameter has expired, solving the pre-oxidation time parameter optimization model using the explicit genetic knowledge transfer method to obtain a second solution set; using the solution with the largest survival time in the second solution set as the second optimized pre-oxidation time parameter; and using the first pre-oxidation time parameter as the first optimized pre-oxidation time parameter; If the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have both expired, the pre-oxidation time parameter optimization model is solved using an implicit genetic knowledge transfer method to obtain a third solution set and a fourth solution set; the solution with the largest survival time in the third solution set is used as the first optimized pre-oxidation time parameter; and the solution with the largest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

2. The method for optimizing the pre-oxidation time parameters according to claim 1, wherein The step of obtaining a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line based on the plurality of first temperatures, the plurality of second temperatures, and the number of the plurality of environments further includes: When the number of the multiple environments is less than the total number of environments and the current environment has ended, perform the following operations: If both the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have not ended, the first pre-oxidation time parameter is used as the first optimized pre-oxidation time parameter, and the second pre-oxidation time parameter is used as the second optimized pre-oxidation time parameter.

3. The method for optimizing the pre-oxidation time parameters according to claim 2, wherein: The optimization method further comprises: When the number of the multiple environments is greater than or equal to the total number of environments, the first optimized pre-oxidation time parameter and the second optimized pre-oxidation time parameter are output.

4. The method for optimizing the pre-oxidation time parameters according to claim 1, wherein The optimization method further comprises: If there are multiple solutions with the longest survival time in the first solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the first solution set is used as the first optimized pre-oxidation time parameter; If there are multiple solutions with the longest survival time in the second solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the second solution set is used as the second optimized pre-oxidation time parameter.

5. The method for optimizing the pre-oxidation time parameters according to claim 1, wherein: The optimization method further comprises: If there are multiple solutions with the longest survival time in the third solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the third solution set is used as the first optimized pre-oxidation time parameter; If there are multiple solutions with the longest survival time in the fourth solution set, the solution with the smallest switching cost among the multiple solutions with the longest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

6. A device for optimizing pre-oxidation time parameters, characterized in that: The optimization device comprises: a data acquisition module configured to acquire a first temperature of each temperature zone of the first pre-oxidation production line under each environment, a second temperature of each temperature zone of the second pre-oxidation production line under each environment, and a number of the multiple environments, wherein each environment is a pre-oxidation time period of the first pre-oxidation production line and the second pre-oxidation production line, the first pre-oxidation production line and the second pre-oxidation production line both include multiple environments, and the multiple environments of the first pre-oxidation production line correspond one-to-one to and are identical to the multiple environments of the second pre-oxidation production line; a parameter optimization module configured to derive, based on a plurality of the first temperatures, a plurality of the second temperatures, and a plurality of the number of the environments, a first optimized pre-oxidation time parameter corresponding to the first pre-oxidation production line and a second optimized pre-oxidation time parameter corresponding to the second pre-oxidation production line, wherein the first optimized pre-oxidation time parameter enables the first pre-oxidation production line to have a first minimum energy consumption and a first maximum pre-oxidation silk modulus while satisfying a dynamic constraint condition, and the second optimized pre-oxidation time parameter enables the second pre-oxidation production line to have a second minimum energy consumption and a second maximum pre-oxidation silk modulus while satisfying the dynamic constraint condition; The parameter optimization module is further configured to: When the number of multiple environments is less than the total number of environments, and the current environment has ended, perform the following actions: If the survival time of the first pre-oxidation time parameter has ended, and the survival time of the second pre-oxidation time parameter has not ended, use the explicit genetic knowledge transfer method to solve the pre-oxidation time parameter optimization model to obtain a first solution set; use the solution with the largest survival time in the first solution set as the first optimized pre-oxidation time parameter; use the second pre-oxidation time parameter as the second optimized pre-oxidation time parameter; wherein, the first pre-oxidation time parameter is the pre-oxidation time parameter currently used by the first pre-oxidation production line, and the second pre-oxidation time parameter is the pre-oxidation time parameter currently used by the second pre-oxidation production line, and the pre-oxidation time parameter optimization model includes a first task and a second task, the first task is to solve the first optimized pre-oxidation time parameter, and the second task is to solve the second optimized pre-oxidation time parameter; If the survival time of the first pre-oxidation time parameter has not expired and the survival time of the second pre-oxidation time parameter has expired, solving the pre-oxidation time parameter optimization model using the explicit genetic knowledge transfer method to obtain a second solution set; using the solution with the largest survival time in the second solution set as the second optimized pre-oxidation time parameter; and using the first pre-oxidation time parameter as the first optimized pre-oxidation time parameter; If the survival time of the first pre-oxidation time parameter and the survival time of the second pre-oxidation time parameter have both expired, the pre-oxidation time parameter optimization model is solved using an implicit genetic knowledge transfer method to obtain a third solution set and a fourth solution set; the solution with the largest survival time in the third solution set is used as the first optimized pre-oxidation time parameter; and the solution with the largest survival time in the fourth solution set is used as the second optimized pre-oxidation time parameter.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the optimization method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the optimization method according to any one of claims 1 to 5 are implemented.

Images