CN118013864B - Viscose fiber yellowing optimization method based on whale algorithm - Google Patents
Viscose fiber yellowing optimization method based on whale algorithm Download PDFInfo
- Publication number
- CN118013864B CN118013864B CN202410418196.XA CN202410418196A CN118013864B CN 118013864 B CN118013864 B CN 118013864B CN 202410418196 A CN202410418196 A CN 202410418196A CN 118013864 B CN118013864 B CN 118013864B
- Authority
- CN
- China
- Prior art keywords
- whale
- yellowing
- individual
- optimal
- current
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/50—Manufacturing or production processes characterised by the final manufactured product
- Y02P70/62—Manufacturing or production processes characterised by the final manufactured product related technologies for production or treatment of textile or flexible materials or products thereof, including footwear
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Polysaccharides And Polysaccharide Derivatives (AREA)
Abstract
The invention discloses a viscose fiber yellowing optimization method based on a whale algorithm, and particularly relates to the field of electric digital data processing. Torque data on a yellowing reaction stirrer are collected, a mathematical model is established to calculate the output power of the optimal stirrer, relevant data and parameters of the viscose fiber yellowing reaction are obtained, the using amount of carbon disulfide, the esterification degree of cellulose xanthate and the yellowing reaction time are introduced as constraint conditions, a multi-objective optimization model of the yellowing parameters is constructed, an improved whale algorithm is used for iterative calculation, and optimal parameter configuration is output.
Description
Technical Field
The invention relates to the technical field of viscose fiber production, in particular to a viscose fiber yellowing optimization method based on whale algorithm.
Background
In the preparation process of spinning dope of viscose fiber, yellowing is an important process step, and the process is that alkali cellulose reacts with carbon disulfide and sodium hydroxide to generate cellulose xanthate, and after certain standing and ripening, viscose with spinnability is generated. The quality of the viscose is the key for determining the quality of the fiber product, and the control of the yellowing process is the function for determining the quality of the viscose.
The stirring rotation speed of the yellowing reaction kettle is closely related to the yellowing reaction of alkali cellulose, the stirring rotation speed is too high or too low, the yellowing of the viscose fiber is adversely affected, the rotation speed of the stirrer can be greatly reduced even under high-power operation for a long time, the stirrer needs to be frequently replaced, and the production cost is increased.
The period of yellowing and the control of temperature in the yellowing process are all key problems for determining the quality of the viscose. At present, the yellowing glue preparation is cyclic production, one yellowing period is ended, the next yellowing period is started, and cyclic execution is performed, so that the yellowing temperature fluctuation is large, the yellowing parameter control is controlled by virtue of worker experience, the yellowing reaction cannot reach the optimal state, the production of viscose fibers is greatly influenced, the yellowing reaction is uneven, and the viscose quality is poor.
Disclosure of Invention
In order to solve the technical problems, the invention provides a viscose fiber yellowing optimization method based on a whale algorithm, which adopts an improved multi-objective whale algorithm to iteratively find an optimal solution by performing optimal parameters on a yellowing parameter model.
The viscose fiber yellowing optimization method based on whale algorithm comprises the following steps:
S1: mixing cellulose with alkali liquor, placing the mixture in a yellowing reaction kettle, and adding carbon disulfide into the alkalized cellulose;
S2: a torque sensor is arranged on a stirrer in a yellowing reaction kettle, zero calibration is carried out under the condition that alkali cellulose does not flow, torque data on the stirrer are collected by using the torque sensor after the yellowing reaction starts, a mathematical model is constructed based on the torque data on the stirrer and the output power of the stirrer, and the optimal output power of the stirrer when the torque data of the stirrer is currently detected is calculated through the model;
S3: collecting historical parameters and operation parameters of the viscose fiber yellowing reaction, comprising: the A fiber amount, the yellowing temperature, the pH value and the vacuum degree of a yellowing machine of the alkali cellulose; and introducing the use amount of carbon disulfide, the esterification degree of cellulose xanthate and the yellowing reaction time as constraint conditions;
S4: constructing a multi-target optimization model of the parameters of the yellowing process of the viscose, carrying out iterative computation on the parameter model of the yellowing process by using a multi-target whale algorithm, solving an optimal solution of the multi-target optimization model of the parameters of the yellowing process, and providing a configuration scheme of the optimization parameters, wherein the iterative computation comprises the following steps:
S41: generating d-dimensional space according to the target parameters to be solved, generating N whale positions, and obtaining the current optimal whale individual The position is%) Position of whale individualTo achieve%) Whale individualIn the best whale individualNext position under influence of (a)The calculation formula of (2) is as follows:
，
，
，
，
Wherein the method comprises the steps of Representing spatial coordinatesThe (k) th component is used to determine,For the distance between the current individual and the random individual,AndFor the coefficient vector, a is a convergence factor, decreasing linearly from 2 to 0 as the number of iterations increases,AndAre random numbers between 0 and 1;
S42: the current whale individual approaches the current optimal whale individual in a spiral mode to update the position;
S43: introducing adaptive inertial weight w as adaptive parameter in iterative calculation process, and adapting individual whale Sorting according to ascending order, dividing all whales into two parts and respectively averaging fitnessAndWherein<The adaptation degree of the current whale individual is respectively matched with that ofAndComparing, the inertial weights are classified as follows:
（1）< This means that the fitness of the individual is low, near the edges of the optimal solution or the locally optimal solution; to increase the search capability of an individual, the weight w varies over a large range, i.e. a random number between (0.8, 1.2) is taken;
（2） This means that the fitness of the individual is high, possibly in the center of the optimal solution or near the global optimal solution; to preserve the diversity of the global search, the weights w take random numbers between (0.3, 0.6) or (1.3, 1.6) with 50% probability, respectively; the smaller or larger weight range is selected with 50% probability, so that the diversity of the algorithm in the searching process can be kept, and the method is beneficial to jumping out of a local optimal solution;
（3）< < this represents a transition region where the fitness of the individual is at a moderate level, possibly at an optimal solution; in order to maintain stability, the weight w takes a fixed value of 1, i.e. no additional inertial adjustment is performed;
S44: introducing a Levy flight strategy in iterative computation to enhance global searching capability of whale individuals;
s45: a secondary interpolation method is introduced to enhance the local search method of whale individuals;
S5: calculating final optimal parameter configuration according to the method of the step S4, and checking whether the output parameter configuration meets the constraint conditions of the carbon disulfide usage amount, the esterification degree of cellulose xanthate and the yellowing reaction time in the step S3; if not, repeating the step S4 to carry out iterative calculation again.
As a further aspect of the present invention, the basic parameter data in the viscose fiber yellowing process in step S3 includes: the A fiber amount, the yellowing temperature, the pH value and the vacuum degree of a yellowing machine of the alkali cellulose; the parameters of the yellowing reactor include: the feeding amount, the rotation speed of the stirrer and the corresponding power.
As a further aspect of the present invention, the main steps of constructing the mathematical model related to the stirring rotation speed in step S2 are as follows:
S21: data collection and processing: data of relevant parameters and flow rate of alkali cellulose and stirring rotation speed of a yellowing reaction kettle in the historical viscose fiber yellowing reaction are collected, wherein the relevant parameters of the alkali cellulose comprise: fiber diameter, fiber length, fiber hygroscopicity; preprocessing the collected data, including data cleaning, missing value processing and feature scaling. The quality and consistency of the data are ensured so that the neural network model can learn better.
S22: and (3) constructing a model: the neural network model is constructed using a multi-layer perceptron that is made up of a plurality of fully connected hidden layers, each hidden layer containing a plurality of neurons. The data collected in step S21 are divided into a data set and a verification set, and the training set trains the model. During training, the weights and biases of the model are updated by a back-propagation algorithm to minimize the loss function. And evaluating the trained model by using a verification set, wherein an evaluation index is mean square error, and adjusting the hyper-parameters or the model structure of the model according to an evaluation result.
S23: and applying the trained model to actual order production, predicting the optimal stirring rotation speed of the yellowing reaction kettle by using the model according to the input relevant parameters of the alkali cellulose and the detected liquid flow rate, and carrying out actual production verification.
As a further aspect of the present invention, the calculation formula of a in step S41 is:，
Where λ is a constant coefficient, θ is a random number between intervals 0,1, t is the current number of iterations, The maximum iteration number, e is Euler constant, the convergence factor a is in nonlinear decrease along with the increase of the iteration number, the attenuation degree of the whale at the initial stage a is low, the attenuation degree of the whale at the later stage a is high, and the whale is moved at the smaller step to search the optimal solution.
As a further aspect of the present invention, the whale individual in step S41 performs contraction of the surrounding ring and updates the position in a spiral motion during the process of capturing the hunting, and the calculation formula is as follows:
，
Where b is the logarithmic spiral shape constant, Is a random number between-1 and 1,、、、The same meaning as in the formula in step S41.
As a further aspect of the present invention, the individual whale described in step S44The formula for enhancing global search capability update location using Levy flight strategy is as follows:
，
Wherein the method comprises the steps of Is of whale individualThe location of the update is then updated and,The point-of-view is indicated,Representing randomly selected whale individuals in the current population, step represents a random step size, generated by the Mantegna method, and the formula is as follows: ；
Wherein the method comprises the steps of （，，…，) And（，，…，) Is a d-dimensional space vector and has=1.5，AndIs subject to the following normal distribution:
~（0，），~（0，），
，=1。
as a further aspect of the present invention, the individual whale described in step S45 The formula for enhancing the update position of the local searching capability by adopting the quadratic interpolation method is as follows:
，
Wherein the method comprises the steps of For the next updated position of individuals of the whale population in d-dimensional space,For randomly selected individual positions in the current whale population in d-dimensional space,For the global optimal individual position of the current whale population in d-dimensional space,The fitness of the optimal individual position for the current whale population,For the fitness of random individual positions in the current whale population,The fitness of the location for the next update of whale population individuals.
The invention has the beneficial effects that: according to the optimization method for the viscose fiber yellowing parameters based on the whale algorithm, in the viscose short fiber yellowing reaction, the output power of the stirrer is dynamically adjusted by collecting the torque on the yellowing stirrer, so that the stirrer operates in an optimal state under different working conditions, the stirring efficiency is improved, and the production time is reduced; the motor power is adjusted according to the torque change monitored in real time, so that overload or overheat of equipment can be avoided, the service life of the equipment is prolonged, and the maintenance cost is reduced; and (3) iteratively calculating the optimal configuration of the yellowing parameters by using a multi-target whale algorithm, so that the yellowing reaction reaches the optimal state under the constraint condition, the yellowing reaction rate is improved, the reaction time is reduced, and the viscose staple fibers are produced with stable quality.
Drawings
FIG. 1 is a graph showing the comparison of the iterative process with the weight w within the range (0.8,1.2) in the example;
FIG. 2 is a graph showing the comparison of the iterative process with the weight w in the range of (0.3, 0.6) or (1.3,1.6) in the example;
fig. 3 is a comparison graph of the iterative process when the weight w takes a value of 1 in the embodiment.
Detailed Description
The following description of the technical solution in the embodiment of the present invention is clear and complete.
The invention discloses a method for optimizing viscose fiber yellowing parameters based on whale algorithm, which comprises the following steps:
S1: mixing cellulose with alkali liquor, placing the mixture in a yellowing reaction kettle, and adding carbon disulfide into the alkalized cellulose;
S2: a torque sensor is arranged on a stirrer in a yellowing reaction kettle, zero calibration is carried out under the condition that alkali cellulose does not flow, torque data on the stirrer are collected by using the torque sensor after the yellowing reaction starts, a mathematical model is constructed based on the torque data on the stirrer and the rotating speed of the stirrer, and the optimal output power of the stirrer when the torque data of the stirrer is currently detected is given out through the model; the stirring speed of the yellowing reaction kettle is closely related to the yellowing reaction of the alkali cellulose, the stirring speed is insufficient, the added carbon disulfide cannot be fully mixed with the alkali cellulose, and the reaction rate is reduced; the stirring speed is too high, so that alkali cellulose can be damaged, the consistency of cellulose products is poor, and a stirrer in a reaction kettle can be damaged;
s3: other relevant data and parameters of the viscose fiber yellowing reaction are obtained, including: the A fiber amount, the yellowing temperature, the pH value and the vacuum degree of a yellowing machine of the alkali cellulose; and introducing the use amount of carbon disulfide, the esterification degree of cellulose xanthate and the yellowing reaction time as constraint conditions;
S4: constructing a multi-target optimization model of the parameters of the yellowing process of the viscose, carrying out iterative computation on the parameter model of the yellowing process by using a multi-target whale algorithm, solving an optimal solution of the multi-target optimization model of the parameters of the yellowing process, and providing a configuration scheme of the optimization parameters, wherein the iterative computation comprises the following steps:
S41: generating d-dimensional space according to the target parameters to be solved, generating N whale positions, and obtaining the current optimal whale individual The position is%) Position of whale individualTo achieve%) The next position of the whale individual under the influence of the best whale individualThe calculation formula of (2) is as follows:
，
，
，
，
Wherein the method comprises the steps of Representing spatial coordinatesThe (k) th component is used to determine,For the distance between the current individual and the random individual,AndFor the coefficient vector, a is a convergence factor, decreasing linearly from 2 to 0 as the number of iterations increases,AndAre random numbers between 0 and 1;
S42: the current whale individual approaches the current optimal whale individual in a spiral mode to update the position;
S43: introducing adaptive inertial weight w as adaptive parameter in iterative calculation process, and adapting individual whale Sorting according to ascending order, dividing all whales into two parts and respectively averaging fitnessAndWherein<The adaptation degree of the current whale individual is respectively matched with that ofAndComparing, the inertial weights are classified as follows:
（1）< This means that the fitness of the individual is low, near the edges of the optimal solution or the locally optimal solution; to increase the search capability of an individual, the weight w varies over a large range, i.e. a random number between (0.8, 1.2) is taken; referring to fig. 1, an iterative process comparison graph of the weight w within the range (0.8,1.2) is shown;
（2）This means that the fitness of the individual is high, possibly in the center of the optimal solution or near the globally optimal solution. To preserve the diversity of the global search, the weights w take random numbers between (0.3, 0.6) or (1.3, 1.6) with 50% probability, respectively; the smaller or larger weight range is selected with 50% probability, so that the diversity of the algorithm in the searching process can be kept, and the method is beneficial to jumping out of a local optimal solution; referring to fig. 2, a comparison graph of iterative processes with weights w within the range of (0.3, 0.6) or (1.3,1.6) is shown;
（3）< < This represents a transition region where the fitness of the individual is at a medium level, possibly at an optimal solution. In order to maintain stability, the weight w takes a fixed value of 1, i.e. no additional inertial adjustment is performed; please refer to fig. 3, which is a comparison graph of iterative process when the weight w is 1;
Under different conditions, the value range of the weight w is obtained by the history data obtained by actual production; comparing the graphs through an iteration process, the data convergence is fastest under the condition that the iteration times are the same in the value range of the weight w;
S44: introducing a Levy flight strategy in iterative computation to enhance global searching capability of whale individuals;
s45: a secondary interpolation method is introduced to enhance the local search method of whale individuals;
S5: calculating final optimal parameter configuration according to the method of the step S4, and checking whether the output parameter configuration meets the constraint conditions of the carbon disulfide usage amount, the esterification degree of cellulose xanthate and the yellowing reaction time in the step S3; if not, repeating the step S4 to carry out iterative calculation again.
Further, the basic parameter data in the viscose fiber yellowing process in step S3 includes: the A fiber amount, the yellowing temperature, the pH value and the vacuum degree of a yellowing machine of the alkali cellulose; the parameters of the yellowing reactor include: the feeding amount, the rotation speed of the stirrer and the corresponding power.
Further, the calculation formula of a in step S41 is:，
Where λ is a constant coefficient, θ is a random number between intervals 0,1, t is the current number of iterations, The maximum iteration number, e is Euler constant, the convergence factor a is in nonlinear decrease along with the increase of the iteration number, the attenuation degree of the whale at the initial stage a is low, the attenuation degree of the whale at the later stage a is high, and the whale is moved at the smaller step to search the optimal solution.
Further, the whale individual in step S41 performs contraction of the surrounding ring and updates the position in a spiral motion during the process of capturing the hunting object, and the calculation formula is as follows:
，
Where b is the logarithmic spiral shape constant, Is a random number between-1 and 1,、、、The same meaning as in the formula in step S41.
Further, the individual whales described in step S44The formula for enhancing global search capability update location using Levy flight strategy is as follows:
，
Wherein the method comprises the steps of Is of whale individualThe location of the update is then updated and,The point-of-view is indicated,Representing randomly selected whale individuals in the current population, step represents a random step size, generated by the Mantegna method, and the formula is as follows: ；
Wherein the method comprises the steps of （，，…，) And（，，…，) Is a d-dimensional space vector and has=1.5，AndIs subject to the following normal distribution:
~（0，），~（0，），
，=1。
Further, the individual whales described in step S45 The formula for enhancing the update position of the local searching capability by adopting the quadratic interpolation method is as follows:
，
Wherein the method comprises the steps of For the next updated position of individuals of the whale population in d-dimensional space,For randomly selected individual positions in the current whale population in d-dimensional space,For the global optimal individual position of the current whale population in d-dimensional space,The fitness of the optimal individual position for the current whale population,For the fitness of random individual positions in the current whale population,The fitness of the location for the next update of whale population individuals.
The embodiments of the present invention are disclosed as preferred embodiments, but not limited thereto, and those skilled in the art will readily appreciate from the foregoing description that various extensions and modifications can be made without departing from the spirit of the present invention.
Claims (5)
1. The viscose fiber yellowing optimization method based on whale algorithm is characterized by comprising the following steps of:
S1: mixing cellulose with alkali liquor, placing the mixture in a yellowing reaction kettle, and adding carbon disulfide into the alkalized cellulose;
S2: a torque sensor is arranged on a stirrer in a yellowing reaction kettle, zero calibration is carried out under the condition that alkali cellulose does not flow, torque data on the stirrer are collected by using the torque sensor after the yellowing reaction starts, a mathematical model is constructed based on the torque data on the stirrer and the output power of the stirrer, and the optimal output power of the stirrer when the torque data of the stirrer is currently detected is calculated through the model; the main steps of constructing the mathematical model related to the stirring rotation speed are as follows:
s21: and (3) data collection: data of relevant parameters and flow rate of alkali cellulose and stirring rotation speed of a yellowing reaction kettle in the historical viscose fiber yellowing reaction are collected, wherein the relevant parameters of the alkali cellulose comprise: fiber diameter, fiber length, fiber hygroscopicity;
S22: and (3) constructing a model: selecting a neural network model, dividing the collected data into a data set and a verification set, training the data set and the stirring rotating speed of the optimal yellowing reaction kettle produced by an actual order, and evaluating the model by using the verification set to ensure that the model achieves the preset accuracy;
S23: inputting relevant parameters of alkali cellulose and the detected liquid flow rate according to the production requirement of a real order, and giving the optimal stirring rotating speed corresponding to the yellowing reaction kettle;
S3: collecting historical parameters and operation parameters of the viscose fiber yellowing reaction, comprising: the A fiber amount, the yellowing temperature, the pH value and the vacuum degree of a yellowing machine of the alkali cellulose; and introducing the use amount of carbon disulfide, the esterification degree of cellulose xanthate and the yellowing reaction time as constraint conditions;
S4: constructing a multi-target optimization model of the parameters of the yellowing process of the viscose, carrying out iterative computation on the parameter model of the yellowing process by using a multi-target whale algorithm, solving an optimal solution of the multi-target optimization model of the parameters of the yellowing process, and providing a configuration scheme of the optimization parameters, wherein the iterative computation comprises the following steps:
S41: generating d-dimensional space according to the target parameters to be solved, generating N whale positions, and obtaining the current optimal whale individual The position is%) Position of whale individualTo achieve%) Whale individualIn the best whale individualNext position under influence of (a)The calculation formula of (2) is as follows:
，
，
，
，
Wherein the method comprises the steps of Representing spatial coordinatesThe (k) th component is used to determine,For the distance between the current individual and the random individual,AndFor the coefficient vector, a is a convergence factor, decreasing linearly from 2 to 0 as the number of iterations increases,AndAre random numbers between 0 and 1;
S42: the current whale individual approaches the current optimal whale individual in a spiral mode to update the position;
S43: introducing adaptive inertial weight w as adaptive parameter in iterative calculation process, and adapting individual whale Sorting according to ascending order, dividing all whales into two parts and respectively averaging fitnessAndWherein<The adaptation degree of the current whale individual is respectively matched with that ofAndComparing, the inertial weights are classified as follows:
（1）< w is a random number between (0.8,1.2);
（2） w is taken as a random number between (0.3, 0.6) or (1.3,1.6) with a probability of 50%;
（3）< < w takes a value of 1;
S44: introducing a Levy flight strategy in iterative computation to enhance global searching capability of whale individuals;
s45: a secondary interpolation method is introduced to enhance the local search method of whale individuals;
S5: calculating final optimal parameter configuration according to the method of the step S4, and checking whether the output parameter configuration meets the constraint conditions of the carbon disulfide usage amount, the esterification degree of cellulose xanthate and the yellowing reaction time in the step S3; if not, repeating the step S4 to carry out iterative calculation again.
2. The optimization method of viscose fiber yellowing based on whale algorithm according to claim 1, wherein the calculation formula of a in step S41 is: ，
Where λ is a constant coefficient, θ is a random number between intervals 0,1, t is the current number of iterations, E is Euler constant, convergence factor a decreases nonlinearly with the increase of iteration number, the attenuation degree of a is low in the initial stage, whale moves in larger step length, the attenuation degree of a is high in the later stage, and whale moves in smaller step length to find the optimal solution.
3. The optimization method of viscose fiber yellowing according to claim 1, wherein the whale individual in step S41 performs shrinkage of the surrounding ring and updates the position in spiral motion during the process of hunting, and the calculation formula is:
；
Where b is the logarithmic spiral shape constant, Is a random number between-1 and 1,、、、The same meaning as in the formula in step S41.
4. The method of claim 1, wherein the individual whales in step S44The formula for enhancing global search capability update location using Levy flight strategy is as follows:
，
Wherein the method comprises the steps of Is of whale individualThe location of the update is then updated and,The point-of-view is indicated,Representing randomly selected whale individuals in the current population, step represents a random step size, generated by the Mantegna method, and the formula is as follows: ；
Wherein the method comprises the steps of （，，…，) And（，，…，) Is a d-dimensional space vector and has=1.5，AndIs subject to the following normal distribution:
~（0，），~（0，）
，=1。
5. The method for optimizing the yellowing of viscose fiber based on whale algorithm as claimed in claim 1, wherein the step S45 is characterized in that the quadratic interpolation method is adopted for whale individuals The updated formula of (c) is as follows:
，
Wherein the method comprises the steps of For the next updated position of individuals of the whale population in d-dimensional space,For randomly selected individual positions in the current whale population in d-dimensional space,For the global optimal individual position of the current whale population in d-dimensional space,The fitness of the optimal individual position for the current whale population,For the fitness of random individual positions in the current whale population,The adaptation to the next updated position of the whale population.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410418196.XA CN118013864B (en) | 2024-04-09 | 2024-04-09 | Viscose fiber yellowing optimization method based on whale algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410418196.XA CN118013864B (en) | 2024-04-09 | 2024-04-09 | Viscose fiber yellowing optimization method based on whale algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118013864A CN118013864A (en) | 2024-05-10 |
| CN118013864B true CN118013864B (en) | 2024-06-28 |
Family
ID=90948770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410418196.XA Active CN118013864B (en) | 2024-04-09 | 2024-04-09 | Viscose fiber yellowing optimization method based on whale algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118013864B (en) |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2710054A1 (en) * | 2011-05-20 | 2014-03-26 | Innovia Films Limited | Process for processing cellulose films or shaped articles |
| CN102393694B (en) * | 2011-09-27 | 2014-08-20 | 宜宾海丝特纤维有限责任公司 | Yellowing automatic control system in production of short fiber stock solution viscose |
| CN104831392A (en) * | 2015-05-27 | 2015-08-12 | 宜宾丝丽雅集团有限公司 | High-strength low-elongation viscose fiber and preparation method thereof |
| CN109886589B (en) * | 2019-02-28 | 2024-01-05 | 长安大学 | Method for solving low-carbon workshop scheduling based on improved whale optimization algorithm |
| CN110728021B (en) * | 2019-09-05 | 2024-03-01 | 杭州电子科技大学 | Microstrip filter antenna design method based on improved binary whale optimization algorithm |
| AU2020103826A4 (en) * | 2020-12-01 | 2021-02-11 | Dalian University | Whale dna sequence optimization method based on harmony search (hs) |
| CN112653142B (en) * | 2020-12-18 | 2022-09-02 | 武汉大学 | Wind power prediction method and system for optimizing depth transform network |
| CN113962070A (en) * | 2021-10-12 | 2022-01-21 | 河北工程大学 | Reliability optimization design method and optimal laminated structure of glass fiber reinforced plastic sand-filled pipe and culvert |
| CN114595565B (en) * | 2022-02-28 | 2024-05-31 | 湖北工业大学 | Parameter optimization method for solving wireless power transmission system by improving whale algorithm |
| CN116015967B (en) * | 2023-01-06 | 2024-05-31 | 重庆软江图灵人工智能科技有限公司 | Industrial Internet intrusion detection method based on improved whale algorithm optimization DELM |
| CN116544974A (en) * | 2023-04-28 | 2023-08-04 | 三峡大学 | Method for optimally configuring capacity of hybrid energy storage system based on whale optimization algorithm of global search strategy |
-
2024
- 2024-04-09 CN CN202410418196.XA patent/CN118013864B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| "基于鲸鱼-粒子群耦合算法的轨迹规划研究";程万里等;《淮阴工学院学报》;20221015;第31卷(第05期);第60-65、80页 * |
| "求解大规模优化问题的改进鲸鱼优化算法";龙文等;《系统工程理论与实践》;20171125;第233-244页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118013864A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103778482B (en) | Aquaculture dissolved oxygen short term prediction method based on multiscale analysis | |
| CN114362175B (en) | Wind power prediction method and system based on depth certainty strategy gradient algorithm | |
| CN113544599A (en) | Method for executing a process and optimizing a control signal used in the process | |
| CN110555548B (en) | ICS-ELM ultra-short-term wind power prediction method based on data mining original error correction | |
| CN117592819B (en) | Dynamic supervision method and device for land-sea complex oriented to ocean pasture | |
| CN112561139A (en) | Short-term photovoltaic power generation power prediction method and system | |
| CN111144663A (en) | Ultra-short-term wind power prediction method for offshore wind farm considering output fluctuation process | |
| CN116028822B (en) | Electric energy meter error state evaluation method, system, equipment and storage medium | |
| CN112819238A (en) | Short-term wind power prediction method based on chaotic chicken flock optimization algorithm | |
| CN113138555A (en) | GRNN electric spindle thermal error modeling method based on genetic algorithm optimization | |
| CN113221447A (en) | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm | |
| US20240095535A1 (en) | Executing a genetic algorithm on a low-power controller | |
| CN116108975A (en) | Method for establishing short-term load prediction model of power distribution network based on BR-SOM clustering algorithm | |
| CN115271237A (en) | An Industrial Data Quality Prediction Method Based on Improved PSO-GA and SVM | |
| CN108594793A (en) | A kind of improved RBF flight control systems fault diagnosis network training method | |
| CN109886488B (en) | Distributed wind power plant layered hybrid short-term prediction method considering wind speed time lag | |
| CN117828403A (en) | Water pump fault prediction and diagnosis method based on machine learning | |
| CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
| CN115755589B (en) | An optimization method for reactor fuzzy control system based on genetic algorithm | |
| CN117507365A (en) | Artificial intelligent control method based on dynamic self-adaptive parameter adjustment of materials and environment | |
| CN118013864B (en) | Viscose fiber yellowing optimization method based on whale algorithm | |
| CN119397914A (en) | New material production process parameter optimization method and system based on artificial intelligence | |
| CN118070675B (en) | Soil nitrogen mineralization rate prediction system based on machine learning | |
| CN118199053A (en) | A wind power prediction method, system and storage medium | |
| CN117828387A (en) | A data enhancement method for polyester polymerization process |
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 |