CN115238961A - Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network - Google Patents
Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network Download PDFInfo
- Publication number
- CN115238961A CN115238961A CN202210719847.XA CN202210719847A CN115238961A CN 115238961 A CN115238961 A CN 115238961A CN 202210719847 A CN202210719847 A CN 202210719847A CN 115238961 A CN115238961 A CN 115238961A
- Authority
- CN
- China
- Prior art keywords
- neural network
- whale
- prey
- network model
- individual
- 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.)
- Pending
Links
- 241000283153 Cetacea Species 0.000 title claims abstract description 170
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 100
- 238000004073 vulcanization Methods 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 63
- 238000005457 optimization Methods 0.000 title claims abstract description 46
- 238000003062 neural network model Methods 0.000 claims description 63
- 238000012549 training Methods 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 244000144992 flock Species 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 25
- 238000002474 experimental method Methods 0.000 abstract description 7
- 238000012800 visualization Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009182 swimming Effects 0.000 description 2
- 241000282461 Canis lupus Species 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012803 optimization experiment Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Heating, Cooling, Or Curing Plastics Or The Like In General (AREA)
Abstract
The invention provides a tire vulcanization quality prediction method based on whale algorithm optimization BP neural network, and relates to the technical field of neural network prediction. The method adopts the neural network to predict the performance quality of the vulcanized tire, is quicker and more efficient than the analysis and prediction of the traditional vulcanization experiment data, can provide a model foundation for the subsequent optimization process, and can realize the visualization of the vulcanization result. Meanwhile, the initial weight and the threshold value of the whale algorithm BP neural network are utilized, so that the improved and optimized neural network has higher-precision prediction capability, and the tire vulcanization quality prediction precision is improved.
Description
Technical Field
The invention relates to the technical field of neural network prediction, in particular to a tire vulcanization quality prediction method, a tire vulcanization quality prediction system, a tire vulcanization quality storage medium and electronic equipment based on whale algorithm optimization BP neural network.
Background
With the increasing demand for automobiles in the market, the tire industry has been rapidly developed as one of the main supporting industries of the automobile industry, and in order to not affect the handling stability and driving safety of vehicles, while ensuring high production efficiency, the performance and quality of tires are also emphasized at the same time, and vulcanization is one of the important processes of tire production, which is also the last process, and the purpose is to crosslink and vulcanize unvulcanized rubber, so that the tires have the required physical properties, and the use requirements are met. However, the coupling of various factors causes the quality of the vulcanized tire to deteriorate, resulting in a low yield. Therefore, much work has been done to predict the quality of the vulcanized tire through experimental, theoretical, and machine learning methods.
Compared with the conventional tire vulcanization experimental method, the machine learning method has the advantages of high efficiency, economy and accuracy, and thus is widely applied in the industry. At present, a BP neural network is commonly adopted to establish a network model of vulcanization process parameters and performance indexes, a solving method taking performance output predicted by the neural network as an objective function is adopted, and a genetic algorithm is taken as an optimization method of the vulcanization process parameters to predict and optimize the vulcanization process parameters.
However, when the genetic algorithm optimizes the BP neural network, the selection of the initial population has certain dependence and is easy to fall into local optimization, so that the accuracy of the prediction result is unstable, and the tire vulcanization quality is unstable.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides the tire vulcanization quality prediction method based on whale algorithm optimization BP neural network, and solves the technical problem that the tire vulcanization quality prediction method based on BP neural network is easy to fall into local optimum.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, the invention provides a tire vulcanization quality prediction method based on whale algorithm optimization BP neural network, which comprises the following steps:
s1, obtaining historical data, wherein the historical data comprises tire vulcanization process parameters and quality index data measured by a testing machine;
s2, normalizing the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
s3, initializing parameters of a BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
s4, traversing by taking the individual position of the whale as the initial weight and the threshold of the BP neural network model and taking the training error value of the BP neural network model as a fitness function;
s5, searching for prey, surrounding prey or driving prey and updating the position of the whale, meeting the given precision requirement or reaching the maximum iteration number, stopping iteration optimization and outputting the optimal position of the whale, and otherwise, returning to the step S4 to execute again;
and S6, assigning the optimal position to the optimal weight and the threshold value of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
Preferably, the initializing parameters of the BP neural network model for the tire vulcanization quality prediction scenario based on the whale algorithm includes:
setting whale number N and iteration number T according to the execution parameters of the initialization model under the scene of tire vulcanization quality prediction max In combination with the network topology structure initialization optimization dimension D and initialization parameters A, a and C, and improving the definition formula of the convergence factor parameter a, the calculation formula is as follows:
a=2-2*(t 2 /T max 2 )
A=2ar 1 -a
C=2r 2
wherein a is a convergence factor, the convergence factor is decreased from 2 to 0 along with the iteration number, T is the current iteration number, and T is the convergence factor max Is the maximum iteration number; a and C are co-operative coefficient vectors, r 1 And r 2 Random numbers of (0, 1) are used.
Preferably, the traversing by taking the individual position of the whale as the initial weight and the threshold of the BP neural network model and the training error value of the BP neural network model as the fitness function includes:
taking the training error value error as a whale population fitness value, calculating a minimum fitness value of a whale population and an optimal whale individual position, taking the optimal whale individual position as an initial weight and a threshold of a BP neural network model, updating the weight and the threshold according to a gradient descent method, and updating the formula as follows:
wherein: mu is the learning rate of BP neural network, omega 1 、b 1 Weight and threshold, omega, between input layer and hidden layer in BP neural network 2 、b 2 Weight and threshold value, omega ', between a hidden layer and an output layer in the BP neural network respectively' 1 、b’ 1 Are respectively omega 1 、b 1 Updated weights and threshold, ω' 2 、b’ 2 Are respectively omega 2 、b 2 The updated weights and thresholds.
Preferably, the whale is searched for prey, surrounded by prey or driven and location updated, including:
s501, generating a random number P from 0 to 1 to decide whether whales choose to search and surround prey or catch up by using an air bubble net, if P <0.5, executing step S502, and otherwise, executing step S503.
S502, driving a prey by a whale shoal in a mode of manufacturing a bubble net, swimming around the prey in a continuously reduced circle, and meanwhile swimming along a spiral path and updating the position;
s503, when the absolute value A is larger than 1, the whale searches for a prey globally and updates the position; when | a | <1, the whale performs a local search for a prey and updates the location.
Preferably, in S502, the updating manner for moving along the spiral path and updating the position includes:
wherein the content of the first and second substances,indicating the distance between individual whales and prey,is the position of the prey at time t,is the position of the individual whale at the moment t,is the updated position, l is [ -1,1]A random number in between.
Preferably, in S503, when | a | >1, the whale performs a global search for the prey and updates the location, including:
when the absolute value of A is larger than 1, the whale colony can carry out a random hunting stage, namely the whale colony can randomly select a whale individual and update the position of the whale colony to the current random whale individual;
wherein the content of the first and second substances,denoted as the current selection at time tSelecting the distance between random whale individuals and other whale individuals,is the position of a whale individual at the moment t at random,is the position of other individual whales at the moment t,is the position of the location after the update,is a random vector.
Preferably, in S503, when | a | <1, the whale performs a local search for a prey and updates the location, including:
when | A | <1, the whale shoal can carry out a prey surrounding stage, namely the whale shoal can carry out local searching on prey from the current optimal whale individual and update the position;
wherein the content of the first and second substances,expressed as the distance between the currently optimal individual whale and other individual whales at the moment t,is the position of the optimal whale individual at the moment t,is the position of other individual whales at the moment t,is the position of the location after the update,is a random vector.
In a second aspect, a tire vulcanization quality prediction system based on whale algorithm optimization BP neural network comprises:
the data acquisition module is used for acquiring historical data, wherein the historical data comprises tire vulcanization process parameters and quality index data measured by the testing machine;
the model structure determining module is used for carrying out normalization processing on the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
the initialization parameter module is used for initializing parameters of the BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
the traversal module is used for traversing the whale individual positions as the initial weight and the threshold of the BP neural network model and the training error values of the BP neural network model as fitness functions;
the optimizing module is used for searching prey, surrounding prey or driving prey for whales, updating positions, meeting given precision requirements or reaching the maximum iteration number, stopping iteration optimizing and outputting the optimal position of the whales, and otherwise, returning to the step S4 to execute again;
and the prediction module is used for assigning the optimal position to the optimal weight and the threshold of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
In a third aspect, the present invention provides a computer-readable storage medium storing a computer program for optimizing tire cure quality prediction for a BP neural network based on a whale algorithm, wherein the computer program causes a computer to execute the tire cure quality prediction method for optimizing the BP neural network based on the whale algorithm as described above.
In a fourth aspect, the present invention provides an electronic device comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing a tire cure quality prediction method based on whale algorithm optimized BP neural network as described above.
(III) advantageous effects
The invention provides a tire vulcanization quality prediction method based on whale algorithm optimization BP neural network. Compared with the prior art, the method has the following beneficial effects:
the method adopts the neural network to predict the performance quality of the vulcanized tire, is quicker and more efficient than the analysis and prediction of the traditional vulcanization experiment data, can provide a model foundation for the subsequent optimization process, and can realize the visualization of the vulcanization result. Meanwhile, the initial weight and the threshold of the whale algorithm BP neural network are utilized, so that the improved and optimized neural network has higher-precision prediction capability, and the tire vulcanization quality prediction precision is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a block diagram of a tire vulcanization quality prediction method based on whale algorithm optimization BP neural network in the embodiment of the invention;
FIG. 2 is a schematic flow chart of an improved whale algorithm in an embodiment of the invention;
fig. 3 is a comparison chart of the method and the optimization experimental fitness of different algorithms according to the embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The tire vulcanization quality prediction method based on whale algorithm optimization BP neural network provided by the embodiment of the application solves the technical problem that the tire vulcanization quality prediction method based on BP neural network is prone to get into local optimization, the initial weight and the threshold value of the BP neural network are optimized by the improved whale algorithm, the defect that the whale algorithm gets into local optimization in the optimization process is overcome, the accuracy of prediction results is improved, and therefore the tire yield is improved.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
compared with the traditional tire vulcanization experimental method, the machine learning method has the advantages of high efficiency, economy and accuracy, and is widely applied in the industry. Aiming at the problem of tire vulcanization quality prediction, a network model of vulcanization process parameters and performance indexes is established by adopting a BP neural network. However, when the genetic algorithm optimizes the BP neural network, the selection of the initial population has certain dependence and is easy to fall into local optimum, so that the accuracy of the prediction result is unstable, and the tire vulcanization quality is unstable. In order to solve the problems, the embodiment of the invention optimizes the initial weight and the threshold of the BP neural network by using the improved whale algorithm, overcomes the defect that the whale algorithm is trapped into local optimization in the optimization process, realizes the coordination local search in the optimization process, improves the local development capability, and enables the improved and optimized neural network to have higher-precision prediction capability.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
The embodiment of the invention provides a tire vulcanization quality prediction method based on whale algorithm optimization BP neural network, as shown in figure 1, the method comprises the following steps:
s1, obtaining historical data of tire vulcanization quality;
s2, normalizing the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
s3, initializing parameters of a BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
s4, traversing by taking the individual position of the whale as the initial weight and the threshold of the BP neural network model and taking the training error value of the BP neural network model as a fitness function;
s5, searching for prey, surrounding prey or driving prey and updating the position of the whale, meeting the given precision requirement or reaching the maximum iteration number, stopping iteration optimization and outputting the optimal position of the whale, and otherwise, returning to the step S4 to execute again;
and S6, assigning the optimal position to the optimal weight and the threshold of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
The performance quality prediction of the vulcanized tire is carried out by adopting the neural network, compared with the traditional vulcanization experiment data analysis prediction, the performance quality prediction method is quicker and more efficient, a model basis can be provided for a subsequent optimization process, and the visualization of the vulcanization result can be realized. Meanwhile, the initial weight and the threshold value of the whale algorithm BP neural network are utilized, so that the improved and optimized neural network has higher-precision prediction capability, and the tire vulcanization quality prediction precision is improved.
The following describes each step in detail:
in step S1, history data of the tire vulcanization quality is acquired. The specific implementation process is as follows:
and collecting historical data of the tire vulcanization quality to obtain tire vulcanization process parameters (such as vulcanization temperature T, vulcanization time T and vulcanization pressure F) and quality index data measured by the testing machine.
In step S2, normalization processing is performed on the history data; and training the neural network by combining an empirical formula and the processed historical data to obtain the minimum value of the error of the neural network, and determining the topological structure of the BP neural network model based on the minimum value of the error of the neural network. The specific implementation process is as follows:
s201, normalizing the historical data, wherein a formula of the normalization processing is as follows;
wherein: x is a variable before normalization in historical data; max (X) and min (X) are respectively the maximum value and the minimum value of the historical data; and Y is a normalized variable.
It should be noted that each type of data is normalized separately.
S202, calculating the number of hidden layer nodes of the BP neural network according to the error minimum value of the neural network, and determining the topological structure of the BP neural network model. The specific implementation process is as follows:
and (3) according to the node number interval calculated by an empirical formula, combining network training to calculate the error minimum value of the neural network to determine the hidden layer node number of the BP neural network, wherein the empirical formula is as follows:
wherein n isTo hide the number of nodes, n 1 For the number of nodes of the input layer, n 2 Is the number of nodes in the output layer, and c is the interval [1, 10 ]]Is constant. This gives that the hidden layer n is taken to be [3, 12 ]]The integer in (3) is calculated, and when the number of hidden layers n =6 is taken, the error value of the neural network is minimum, so that a 3 × 6 × 4 BP neural network structure is established. In the specific implementation process, n is taken as [3, 12 ]]Each number in the number is respectively substituted into a BP neural network for training to obtain an error value corresponding to the number, and the n value corresponding to the minimum error value is taken as the number of the hidden layers, which is omitted and directly obtained, and the parameter values are used later. It should be noted that, in the training process, the vulcanization temperature T, the vulcanization time T, and the vulcanization pressure F are used as the inputs of the BP neural network model, and the quality index data is used as the output of the BP neural network model.
In step S3, parameters of the BP neural network model are initialized for the tire cure quality prediction scenario based on the whale algorithm. The specific implementation process is as follows:
aiming at initialization model execution parameters under a tire vulcanization quality prediction scene, the whale number N is set, the iteration number is Tmax, the optimization dimensionality is initialized by combining a network topological structure to be D, and parameters A, a and C are initialized, so that a definition formula of a convergence factor parameter a is improved. The calculation formula is as follows:
a=2-2*(t 2 /Tmax 2 )
A=2ar 1 -a
C=2r 2
wherein a is a convergence factor, the convergence factor is decreased to 0 from 2 along with the iteration times, t is the current iteration times, and Tmax is the maximum iteration times; a and C are co-operative coefficient vectors, r 1 And r 2 Random numbers of (0, 1) are used.
In step S4, traversing by using the whale individual position as the initial weight and the threshold of the BP neural network model, and using the training error value error of the BP neural network model as the fitness function value fitness. The specific implementation process is as follows:
taking the training error value error as a whale population fitness value, calculating a minimum fitness value of a whale population and an optimal whale individual position, taking the optimal whale individual position as an initial weight and a threshold of a BP neural network model, updating the weight and the threshold according to a gradient descent method, and updating the formula as follows:
wherein: mu is the learning rate of BP neural network, omega 1 、b 1 Weights and thresholds, ω, between input and hidden layers in BP neural networks, respectively 2 、b 2 Weights and thresholds, ω 'between the hidden layer and the output layer in the BP neural network, respectively' 1 、b’ 1 Are respectively omega 1 、b 1 Updated weight and threshold, ω' 2 、b’ 2 Are respectively omega 2 、b 2 The updated weights and thresholds.
The flow of the improved whale algorithm is shown in fig. 2.
In step S5, the whale is searched for prey, surrounded by prey or driven away and position updating is carried out, given precision requirements are met or the maximum iteration number is reached, iteration optimization is stopped, the optimal position of the whale is output, and otherwise, the step S4 is returned to be executed again.
It should be noted that whales in the embodiments of the present invention are whales with improved parameter definition formulas.
S501, generating a random number P from 0 to 1 to decide whether whales choose to search and surround prey or catch up by using an air bubble net, if P <0.5, executing step S502, and otherwise, executing step S503.
S502, the whale shoal drives the prey in a mode of manufacturing an air bubble net, moves around the prey in a circle which is continuously reduced, moves along a spiral path and updates the position.
Wherein, the first and the second end of the pipe are connected with each other,representing the distance between individual whales and prey (the current optimal solution),is the position of the prey at time t,is the position of the individual whale at the moment t, and l is [ -1,1]A random number in between.
S503, when the | A | is >1, the whale searches for a prey globally and updates the position; when | a | <1, the whale performs a local search for a prey and updates the location. The method specifically comprises the following steps:
when | A | >1, the whale swarm can carry out a random hunting stage, namely the whale swarm can randomly select a whale individual and update the position of the whale swarm to the current random whale individual;
wherein the content of the first and second substances,expressed as the distance between the currently selected random individual whale and other individual whales at time t,is the position of a whale individual at the moment t at random,is the position of other individual whales at the moment t,is a random vector.
When | A | <1, the whale colony can carry out a prey surrounding stage, namely the whale colony can carry out local searching on prey and update the position to the current optimal whale individual;
wherein the content of the first and second substances,expressed as the distance between the current optimal individual whale and other individual whales at the moment t,is the position of the optimal whale individual at the moment t,is the position of other individual whales at the moment t,is a random vector.
In step S6, the optimal position is assigned to the optimal weight and the threshold of the BP neural network model, network training is performed to obtain an optimized BP neural network model, and a quality index prediction result is obtained through the optimized BP neural network model. The specific implementation process is as follows:
and assigning the optimal position obtained in the step S5 to the optimal weight and the threshold value of the BP neural network, carrying out network training to obtain an optimized BP neural network model, inputting the vulcanization temperature T, the vulcanization time T and the vulcanization pressure F within a reasonable range into the optimized BP neural network model, and outputting a quality index prediction result.
FIG. 3 shows a comparison of the improved whale algorithm and the fitness of the optimization experiments of different algorithms in the embodiment of the invention. Wherein WOA-BP is the optimized BP neural network of the existing whale optimization algorithm, IWOA-BP is the method of the embodiment of the invention, and GWOO-BP is the optimized BP neural network of the wolf optimization algorithm. As can be seen from fig. 3, the method according to the embodiment of the present invention has the best optimization effect.
The embodiment of the invention also provides a tire vulcanization quality prediction system based on whale algorithm optimization BP neural network, which comprises:
the data acquisition module is used for acquiring historical data, wherein the historical data comprises tire vulcanization process parameters and quality index data measured by the testing machine;
the model structure determining module is used for carrying out normalization processing on the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
the initialization parameter module is used for initializing parameters of the BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
the traversal module is used for traversing the whale individual positions as the initial weight and the threshold of the BP neural network model and the training error values of the BP neural network model as fitness functions;
the optimizing module is used for searching prey, surrounding prey or driving prey for whales, updating positions, meeting the given precision requirement or reaching the maximum iteration number, stopping iterative optimization and outputting the optimal positions of the whales, and otherwise, returning to the step S4 to execute again;
and the prediction module is used for assigning the optimal position to the optimal weight and the threshold value of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
It can be understood that the tire vulcanization quality prediction system based on whale algorithm optimized BP neural network provided by the embodiment of the invention corresponds to the tire vulcanization quality prediction method based on whale algorithm optimized BP neural network, and the explanation, examples, beneficial effects and the like of the relevant contents can refer to the corresponding contents in the tire vulcanization quality prediction method based on whale algorithm optimized BP neural network, and the details are not repeated here.
Embodiments of the present invention also provide a computer-readable storage medium storing a tire vulcanization quality prediction computer program for optimizing a BP neural network based on a whale algorithm, wherein the computer program causes a computer to execute the tire vulcanization quality prediction method for optimizing a BP neural network based on a whale algorithm as described above.
An embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing a tire cure quality prediction method based on whale algorithm optimized BP neural network as described above.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the performance quality prediction of the vulcanized tire is carried out by adopting the neural network, compared with the traditional vulcanization experiment data analysis prediction, the performance quality prediction method is quicker and more efficient, a model basis can be provided for a subsequent optimization process, and the visualization of the vulcanization result can be realized. Meanwhile, the initial weight and the threshold of the whale algorithm BP neural network are utilized, so that the improved and optimized neural network has higher-precision prediction capability, and the tire vulcanization quality prediction precision is improved.
2. The calculation formula of the convergence factor a in the whale algorithm is improved, the improved whale algorithm is used for optimizing the initial weight and the threshold of the BP neural network, the defect that the whale algorithm is trapped into local optimization in the optimization process is overcome, local search is coordinated in the optimization process, the local development capacity is improved, and the tire vulcanization quality prediction accuracy is further improved.
1. According to the embodiment of the invention, the initial weight and the threshold of the BP neural network are optimized by using the improved whale algorithm, so that the defect that the whale algorithm is trapped into local optimization in the optimization process is overcome, local search is coordinated in the optimization process, the local development capability is improved, and the improved and optimized neural network has high-precision prediction capability. Meanwhile, the performance quality prediction of the vulcanized tire is carried out by adopting the neural network, compared with the traditional vulcanization experiment data analysis prediction, the method is quicker and more efficient, a model basis is provided for the subsequent optimization of process parameters, and the visualization of the vulcanization result can be realized.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A tire vulcanization quality prediction method based on whale algorithm optimization BP neural network is characterized by comprising the following steps:
s1, obtaining historical data, wherein the historical data comprises tire vulcanization process parameters and quality index data measured by a testing machine;
s2, normalizing the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
s3, initializing parameters of a BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
s4, traversing by taking the individual position of the whale as the initial weight and the threshold of the BP neural network model and taking the training error value of the BP neural network model as a fitness function;
s5, searching for prey, surrounding prey or driving prey and updating the position of the whale, meeting the given precision requirement or reaching the maximum iteration number, stopping iteration optimization and outputting the optimal position of the whale, and otherwise, returning to the step S4 to execute again;
and S6, assigning the optimal position to the optimal weight and the threshold value of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
2. The whale algorithm-based tire vulcanization quality prediction method for optimizing the BP neural network according to claim 1, wherein the initializing parameters of the BP neural network model for a tire vulcanization quality prediction scenario based on the whale algorithm comprises:
setting whale number N and iteration number T according to the execution parameters of the initialization model under the scene of tire vulcanization quality prediction max In combination with the network topology structure initialization optimization dimension D and the initialization parameters a, a and C, to improve the definition formula of the convergence factor parameter a, the calculation formula is as follows:
a=2-2*(t 2 /T max 2 )
A=2ar 1 -a
C=2r 2
wherein a is a convergence factor, the convergence factor is decreased from 2 to 0 along with the iteration number, T is the current iteration number, and T is the convergence factor max Is the maximum iteration number; a and C are co-operative coefficient vectors, r 1 And r 2 Both are random numbers of (0, 1).
3. The method for predicting tire vulcanization quality based on whale algorithm optimized BP neural network as claimed in claim 1, wherein the step of traversing the training error values of the BP neural network model as fitness functions by using whale individual positions as initial weights and threshold values of the BP neural network model comprises the steps of:
taking the training error value error as a whale population fitness value, calculating a minimum fitness value of a whale population and an optimal whale individual position, taking the optimal whale individual position as an initial weight and a threshold of a BP neural network model, updating the weight and the threshold according to a gradient descent method, and updating the formula as follows:
wherein: mu is the learning rate of BP neural network, omega 1 、b 1 Weights and thresholds, ω, between input and hidden layers in BP neural networks, respectively 2 、b 2 Weight and threshold value, omega ', between a hidden layer and an output layer in the BP neural network respectively' 1 、b′ 1 Are respectively omega 1 、b 1 Updated weight and threshold, ω' 2 、b' 2 Are respectively omega 2 、b 2 The updated weights and thresholds.
4. The method for tire vulcanization quality prediction based on whale algorithm optimized BP neural network of claim 1, wherein the whale searching for, enclosing or driving prey and performing location update comprises:
s501, generating a random number P from 0 to 1 to decide whether whales select to search and surround prey or catch up by using an air bubble net, if P is less than 0.5, executing a step S502, and if not, executing a step S503;
s502, driving a prey by a whale flock in a mode of manufacturing a bubble net, moving around the prey in a continuously reduced circle, moving along a spiral path and updating the position;
s503, when the absolute value of A is larger than 1, the whale searches for a prey globally and updates the position; when | A | <1, whale performs local search for prey and updates location.
5. The method for predicting tire vulcanization quality based on whale algorithm optimized BP neural network as claimed in claim 4, wherein in S502, the updating mode of walking along the spiral path and updating the position comprises:
6. The method for predicting tire vulcanization quality based on whale algorithm optimized BP neural network as claimed in claim 4, wherein in S503, when | A | >1, whale searches prey globally and updates location, including:
when the absolute value of A is more than 1, the whale swarm can carry out a random hunting stage, namely the whale swarm can randomly select a whale individual and update the position of the whale swarm to the current random whale individual;
wherein the content of the first and second substances,expressed as the distance between the currently selected random individual whale and other individual whales at time t,is the position of a whale individual at the moment t at random,is the position of other whale individuals at the time t,is the position after the update and is,is a random vector.
7. The method for predicting tire vulcanization quality based on optimized BP neural network by whale algorithm as claimed in claim 4, wherein in S503, when | A | <1, whale searches for prey locally and updates location, including:
when | A | is less than 1, the whale colony can carry out a prey surrounding stage, namely the whale colony can carry out local searching on prey and update the position to the current optimal whale individual;
wherein the content of the first and second substances,expressed as the distance between the currently optimal individual whale and other individual whales at the moment t,is the position of the optimal whale individual at the moment t,is the position of other whale individuals at the time t,is the position of the location after the update,is a random vector.
8. A tire vulcanization quality prediction system based on whale algorithm optimization BP neural network is characterized in that the system comprises:
the data acquisition module is used for acquiring historical data, wherein the historical data comprises tire vulcanization process parameters and quality index data measured by the testing machine;
the model structure determining module is used for carrying out normalization processing on the historical data; training the neural network through the processed historical data by combining an empirical formula to obtain a minimum neural network error value, and determining the topological structure of the BP neural network model based on the minimum neural network error value;
the initialization parameter module is used for initializing parameters of the BP neural network model aiming at a tire vulcanization quality prediction scene based on a whale algorithm;
the traversal module is used for traversing the whale individual positions serving as the initial weight and the threshold of the BP neural network model and the training error value of the BP neural network model serving as a fitness function;
the optimizing module is used for searching prey, surrounding prey or driving prey for whales, updating positions, meeting the given precision requirement or reaching the maximum iteration number, stopping iterative optimization and outputting the optimal positions of the whales, and otherwise, returning to the step S4 to execute again;
and the prediction module is used for assigning the optimal position to the optimal weight and the threshold value of the BP neural network model, carrying out network training to obtain the optimized BP neural network model, and obtaining a quality index prediction result through the optimized BP neural network model.
9. A computer-readable storage medium, characterized in that it stores a computer program for optimizing tire cure quality prediction of a BP neural network based on a whale algorithm, wherein the computer program causes a computer to execute the whale algorithm-optimized BP neural network-based tire cure quality prediction method as claimed in any one of claims 1 to 7.
10. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the whale algorithm-based optimized BP neural network tire cure quality prediction method as recited in any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210719847.XA CN115238961A (en) | 2022-06-23 | 2022-06-23 | Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210719847.XA CN115238961A (en) | 2022-06-23 | 2022-06-23 | Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115238961A true CN115238961A (en) | 2022-10-25 |
Family
ID=83668572
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210719847.XA Pending CN115238961A (en) | 2022-06-23 | 2022-06-23 | Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115238961A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115796707A (en) * | 2023-02-02 | 2023-03-14 | 浪潮通用软件有限公司 | PVB resin product quality index prediction method and device |
CN116292245A (en) * | 2023-02-27 | 2023-06-23 | 安徽云磬科技产业发展有限公司 | Piston pump voiceprint fault detection method |
CN116594353A (en) * | 2023-07-13 | 2023-08-15 | 湖北工业大学 | Machine tool positioning error compensation modeling method and system based on CWP-BPNN |
CN117241376A (en) * | 2023-09-14 | 2023-12-15 | 兰州理工大学 | WSN node positioning method for multi-strategy improved BP neural network |
CN117236202A (en) * | 2023-11-16 | 2023-12-15 | 中国海洋大学 | Tread extrusion temperature prediction method combining intelligent algorithm and deep learning technology |
-
2022
- 2022-06-23 CN CN202210719847.XA patent/CN115238961A/en active Pending
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115796707A (en) * | 2023-02-02 | 2023-03-14 | 浪潮通用软件有限公司 | PVB resin product quality index prediction method and device |
CN116292245A (en) * | 2023-02-27 | 2023-06-23 | 安徽云磬科技产业发展有限公司 | Piston pump voiceprint fault detection method |
CN116594353A (en) * | 2023-07-13 | 2023-08-15 | 湖北工业大学 | Machine tool positioning error compensation modeling method and system based on CWP-BPNN |
CN116594353B (en) * | 2023-07-13 | 2023-11-07 | 湖北工业大学 | Machine tool positioning error compensation modeling method and system based on CWP-BPNN |
CN117241376A (en) * | 2023-09-14 | 2023-12-15 | 兰州理工大学 | WSN node positioning method for multi-strategy improved BP neural network |
CN117241376B (en) * | 2023-09-14 | 2024-04-19 | 兰州理工大学 | WSN node positioning method for multi-strategy improved BP neural network |
CN117236202A (en) * | 2023-11-16 | 2023-12-15 | 中国海洋大学 | Tread extrusion temperature prediction method combining intelligent algorithm and deep learning technology |
CN117236202B (en) * | 2023-11-16 | 2024-01-30 | 中国海洋大学 | Tread extrusion temperature prediction method combining intelligent algorithm and deep learning technology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115238961A (en) | Tire vulcanization quality prediction method based on whale algorithm optimization BP neural network | |
CN115271167B (en) | BP neural network-based tire vulcanization quality RFV index prediction method and system | |
CN110794832B (en) | Mobile robot path planning method based on reinforcement learning | |
CN112101530B (en) | Neural network training method, device, equipment and storage medium | |
CN112560914A (en) | Rolling bearing fault diagnosis method based on improved LSSVM | |
CN116242383B (en) | Unmanned vehicle path planning method based on reinforced Harris eagle algorithm | |
CN111191785B (en) | Structure searching method based on expansion search space for named entity recognition | |
WO2023071592A1 (en) | Network structure search method for ultra-large search space, system and medium | |
Huang et al. | Ponas: Progressive one-shot neural architecture search for very efficient deployment | |
CN114755586B (en) | Lithium ion battery residual life prediction method | |
CN113688565B (en) | Supercritical CO based on optimal trade-offs 2 Bayes optimizing method for centrifugal compressor | |
CN113376541B (en) | Lithium ion battery health state prediction method based on CRJ network | |
CN114547964A (en) | Improved HHO (Hilbert-Huang-Quadrature-order) optimization DELM (Del-enhanced dead mass) based debutanizer soft measurement modeling method | |
CN114637881A (en) | Image retrieval method based on multi-agent metric learning | |
CN111294922B (en) | Method and device for accurately positioning wireless sensor network nodes in grading and rapid mode | |
CN117371320A (en) | Photonic crystal fiber prediction method and system based on reinforced gray wolf optimization algorithm | |
CN114936413B (en) | Ship body appearance optimization neural network modeling method and ship body appearance optimization method | |
CN111291193A (en) | Application method of knowledge graph in zero-time learning | |
CN115639799A (en) | Tire vulcanizer hydraulic system fault diagnosis method based on improved BP-HMM hybrid model | |
CN114239826A (en) | Neural network pruning method, medium and electronic device | |
CN114925190B (en) | Mixed reasoning method based on rule reasoning and GRU neural network reasoning | |
CN112819075B (en) | Balanced small sample task classification method based on transduction type reasoning | |
Liang et al. | Spatial-temporal alignment of time series with different sampling rates based on cellular multi-objective whale optimization | |
CN114781614B (en) | Lithium ion battery health state prediction method | |
JP4308641B2 (en) | Pipeline evaluation method |
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 |