CN115983099A - Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data - Google Patents
Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data Download PDFInfo
- Publication number
- CN115983099A CN115983099A CN202211565745.3A CN202211565745A CN115983099A CN 115983099 A CN115983099 A CN 115983099A CN 202211565745 A CN202211565745 A CN 202211565745A CN 115983099 A CN115983099 A CN 115983099A
- Authority
- CN
- China
- Prior art keywords
- carbon fiber
- fiber composite
- strength
- parallel
- deep learning
- 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
Images
Classifications
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The application relates to the technical field of materials, in particular to a method and a device for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data, wherein the method comprises the following steps: the method comprises the steps of obtaining a multi-source test data result of the carbon fiber composite parallel cable, solving a standard length strength characteristic of the carbon fiber composite parallel cable according to the multi-source test data result and corresponding weight based on a preset genetic algorithm and a preset deep learning algorithm, and estimating the strength characteristic of the carbon fiber composite parallel cable according to the standard length strength characteristic to obtain an estimated strength characteristic of the carbon fiber composite parallel cable. According to the method and the device, the multi-scale prediction of the carbon fiber parallel cables can be realized according to multi-source data integration, the prediction result is more real and reliable, the application range of strength estimation is expanded by a deep learning algorithm, the estimation efficiency and the estimation precision of the strength value are improved, and the obtained estimation result is more accurate.
Description
Technical Field
The application relates to the technical field of materials, in particular to a method and a device for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data.
Background
The carbon fiber composite material has the advantages of light weight, high strength, corrosion resistance, fatigue resistance and the like, and the application form of the carbon fiber composite material cable in engineering mainly comprises a parallel rod cable, a parallel plate cable, a stranded cable, a pull rod cable and the like.
In the related art, the ultimate bearing capacity of the carbon fiber composite parallel cables cannot be obtained by directly superposing the bearing capacity of each cable, and the actual bearing capacity of the parallel cables is lower than the sum of the bearing capacity of each cable. In actual engineering, the strength distribution of a single cable is usually obtained through material property tests, and the design bearing capacity of a plurality of parallel cables needs to be theoretically deduced according to the strength distribution rule of the single cable, wherein the method comprises a series system calculation method and a Monte Carlo method.
However, in the related art, the serial system calculation method has a large error of the calculation result for the parallel cables with a large number, and the calculation amount is heavy when the monte carlo method is used to estimate the strength characteristics of the target cable, so that the calculation efficiency and the calculation accuracy of the carbon fiber composite parallel cable strength are reduced, and the accuracy and the reliability of the calculation result are insufficient, which needs to be solved.
Disclosure of Invention
The application provides a method and a device for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data, and aims to solve the technical problems that in the related technology, the error of an obtained calculation result is large for a series system calculation method for a plurality of parallel cables, and the calculation amount is heavy when a Monte Carlo method is used for estimating the strength characteristic of a target cable, so that the calculation efficiency and the calculation precision of the strength of the parallel cable of the carbon fiber composite material are reduced, and the accuracy and the reliability of the calculation result are insufficient.
The embodiment of the first aspect of the application provides a method for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data, which comprises the following steps: obtaining a multi-source test data result of the carbon fiber composite parallel cable; based on a preset genetic algorithm and a preset deep learning algorithm, solving the standard length strength characteristic of the parallel cable of the carbon fiber composite material according to the multi-source test data result and the corresponding weight; and estimating the strength characteristic of the parallel cable of the carbon fiber composite material according to the standard length strength characteristic to obtain the estimated strength characteristic of the parallel cable of the carbon fiber composite material.
In one embodiment of the present application, the multiple experimental data sources of the multiple experimental data results include at least 2 samples with the same or different lengths, parallel numbers, installation errors and anchoring errors.
Optionally, in an embodiment of the present application, the solving the standard length strength characteristics of the parallel cables of the carbon fiber composite material according to the multi-source test data results and the corresponding weights based on a preset genetic algorithm and a preset deep learning algorithm includes: selecting a material variation coefficient, a parallel connection number, a length, a mounting error and an anchoring error; generating a deep learning sample by using a Monte Carlo method based on the material variation coefficient, the number of parallel-connected roots, the length, the installation error and the anchoring error; establishing a deep learning neural network, inputting the deep learning sample to the carbon fiber composite material parallel cables and the preset standard length strength characteristics, and obtaining the strength characteristics through the deep learning neural network.
In addition, in an embodiment of the present application, the solving the standard length strength characteristics of the parallel cables of the carbon fiber composite material according to the multi-source test data results and the corresponding weights based on a preset genetic algorithm and a preset deep learning algorithm includes: selecting tensile strength test values of the same material and the same single cable diameter; selecting a corresponding standard length according to the tensile strength test value; determining weights of different samples of the multi-source test data; and estimating the intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value which are used as input parameters for genetic algorithm estimation.
The embodiment of the second aspect of the application provides a device for estimating the strength of a parallel cable made of a carbon fiber composite material under multi-source data, which comprises: the acquisition module is used for acquiring multi-source test data results of the carbon fiber composite parallel cable; the solving module is used for solving the standard length strength characteristic of the carbon fiber composite parallel cable according to the multi-source test data result and the corresponding weight based on a preset genetic algorithm and a preset deep learning algorithm; and the estimation module is used for estimating the strength characteristic of the carbon fiber composite parallel cable according to the standard length strength characteristic to obtain the estimated strength characteristic of the carbon fiber composite parallel cable.
Wherein, in one embodiment of the present application, the multiple experimental data sources of the multiple-source experimental data results comprise at least 2 samples of the same or different lengths, number of parallel connections, mounting errors, and anchoring errors.
Optionally, in an embodiment of the present application, the solving module includes: the first selecting unit is used for selecting a material variation coefficient, the number of parallel connection, the length, a mounting error and an anchoring error; a generating unit for generating a deep learning sample with a monte carlo device based on the material variation coefficient, the number of parallel connections, the length, the installation error, and the anchoring error; and the acquisition unit is used for establishing a deep learning neural network, inputting the deep learning sample to the parallel cables of the carbon fiber composite material and the preset standard length strength characteristics, and acquiring the strength characteristics through the deep learning neural network.
Additionally, in an embodiment of the present application, the solving module further includes: the second selecting unit is used for selecting tensile strength test values of the same material and the same single cable diameter; the selecting unit is used for selecting the corresponding standard length according to the tensile strength test value; the determining unit is used for determining the weights of different samples of the multi-source test data; and the estimating unit is used for estimating the intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value which are used as input parameters for genetic algorithm estimation.
An embodiment of a third aspect of the present application provides an electronic device, including: the strength estimation method comprises the steps of storing a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the strength estimation method of the carbon fiber composite parallel cable under the multi-source data according to the embodiment.
An embodiment of a fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, the method for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data is implemented.
According to the embodiment of the application, the standard length strength characteristic of the carbon fiber composite parallel cable can be solved according to the multi-source test data result and the corresponding weight based on the preset genetic algorithm and the preset deep learning algorithm by obtaining the multi-source test data result of the carbon fiber composite parallel cable, and the estimated strength characteristic of the carbon fiber composite parallel cable is obtained by estimating the strength characteristic of the carbon fiber composite parallel cable according to the standard length strength characteristic. Therefore, the problems that in the related technology, the error of the obtained calculation result is large for the parallel cables with a large number in the series system calculation method, and the calculation amount is heavy when the Monte Carlo method is used for estimating the strength characteristics of the target cable, so that the calculation efficiency and the calculation precision of the carbon fiber composite material parallel cable strength are reduced, the accuracy and the reliability of the calculation result are insufficient, and the like are solved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a method for estimating strength of parallel cables of a carbon fiber composite material under multi-source data according to an embodiment of the present application;
FIG. 2 is a process diagram of predicting strength characteristics of a parallel cable of a carbon fiber composite material by a preset deep learning algorithm according to an embodiment of the present application;
FIG. 3 is a process diagram of estimating the standard length strength characteristics of parallel cables of carbon fiber composite material under multi-source data by using a preset genetic algorithm according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an iterative process of estimating the standard length strength characteristics of the parallel cables of the carbon fiber composite material under multi-source data by using a preset genetic algorithm according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of a device for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.
The method and the device for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data of the embodiment of the application are described below with reference to the accompanying drawings. In order to solve the problems that in the related art mentioned in the background technology center, the error of the obtained calculation result is large for the parallel cables with a large number, and the calculation amount is heavy when the Monte Carlo method is used for estimating the strength characteristic of the target cable, so that the calculation efficiency and the calculation precision of the strength of the parallel cables of the carbon fiber composite material are reduced, and the accuracy and the reliability of the calculation result are insufficient, the method for estimating the strength of the parallel cables of the carbon fiber composite material under the multi-source data is provided. Therefore, the problems that in the related technology, the error of the obtained calculation result is large for the parallel cables with a large number in the series system calculation method, and the calculation amount is heavy when the Monte Carlo method is used for estimating the strength characteristics of the target cable, so that the calculation efficiency and the calculation accuracy of the strength of the parallel cables made of the carbon fiber composite material are reduced, the accuracy and the reliability of the calculation result are insufficient, and the like are solved.
Specifically, fig. 1 is a schematic flow chart of a method for estimating strength of a parallel cable of a carbon fiber composite material under multi-source data according to an embodiment of the present application.
As shown in fig. 1, the method for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data comprises the following steps:
in step S101, a multi-source test data result of the carbon fiber composite parallel cable is obtained.
It can be understood that the multi-source test data results in the embodiment of the application can be integrated by aiming at different multi-source test data, so that the final multi-source test data result is obtained.
According to the method and the device, the multi-source test data result of the carbon fiber composite material parallel cable can be obtained, and the prediction precision of the carbon fiber composite material parallel cable estimation is improved by regulating the relevant data required by the solving process in the following steps.
Wherein, in one embodiment of the present application, the multiple experimental data sources of the multiple-source experimental data results comprise at least 2 samples of the same or different lengths, number of parallel connections, mounting errors, and anchoring errors.
It will be appreciated that in embodiments of the present application, multiple sources of experimental data may include, but are not limited to, at least 2 specimens of the same or different lengths, numbers of parallels, installation errors, and anchoring errors.
The multiple experimental data source of multisource experimental data result of this application embodiment obtains multisource experimental data result through introducing many-sided experimental data including inequality or different length, parallelly connected radical, installation error and 2 at least samples of anchor error, has improved the authenticity and the comprehensiveness of data source, makes the estimation more accurate.
In step S102, based on a preset genetic algorithm and a preset deep learning algorithm, the standard length strength characteristics of the parallel cable of the carbon fiber composite material are solved according to the multi-source test data results and the corresponding weights.
It can be understood that in the embodiment of the application, the preset deep learning algorithm and the preset genetic algorithm can be fused and used through the result of the multi-source test data and the corresponding weight, and the standard length strength characteristic of the carbon fiber composite parallel cable under the multi-source data is estimated.
It should be noted that the preset genetic algorithm and the preset deep learning algorithm are set by those skilled in the art according to actual situations, and are not specifically limited herein.
In the actual execution process, in the process of solving the standard length strength characteristics of the carbon fiber composite parallel cable based on the preset genetic algorithm and the preset deep learning algorithm, if the sample type is larger than 1, the preset deep learning algorithm can be introduced into the preset genetic algorithm for operation, then the data obtained by the preset deep learning algorithm are continuously processed through the preset genetic algorithm, and finally the standard length strength characteristics of the carbon fiber composite parallel cable under the multi-source data are obtained.
According to the embodiment of the application, the standard length strength characteristic of the parallel cable made of the carbon fiber composite material can be solved according to the multi-source test data result and the corresponding weight based on the preset genetic algorithm and the preset deep learning algorithm, and the prediction speed of the large-scale cable can be remarkably increased by combining the deep learning prediction method and the genetic algorithm, so that the estimation process is more efficient.
Optionally, in an embodiment of the present application, based on a preset genetic algorithm and a preset deep learning algorithm, solving a standard length strength characteristic of a parallel cable of a carbon fiber composite material according to a multi-source test data result and a corresponding weight includes: selecting a material variation coefficient, a parallel connection number, a length, a mounting error and an anchoring error; generating a deep learning sample by utilizing a Monte Carlo method based on the material variation coefficient, the number of parallel connection, the length, the installation error and the anchoring error; establishing a deep learning neural network, inputting a deep learning sample for the parallel cables of the carbon fiber composite material and the preset standard length strength characteristics, and obtaining the strength characteristics through the deep learning neural network.
It is understood that, in the embodiment of the present application, the above steps may be used to implement a pre-designed deep learning algorithm, wherein the coefficient of variation of the material may be defined by combining the mean and the standard deviation of the intensity of the material into one parameter, i.e. the coefficient of variation of the material,
the coefficient of variation of the material = standard deviation of the material strength of the standard length sample/mean value of the strength of the standard length sample, the number of parallel cables may be the number of single cables included in the cross section of the parallel cables, the length may be defined as,
length = length of parallel cords/standard length,
the installation error may be derived from an uneven error in the installation of the parallel cables, where the error is assumed to be evenly distributed, the installation error is defined as,
mounting error = mean value of strength of stress generated by maximum mounting error/standard length sample,
the anchoring error can be caused by that in the process of pulling the parallel cable anchorage, the adhesive generates outward protrusion on the free surface, the outer cable of the parallel cable extends more than the inner cable, so that the inner cable and the outer cable generate stress difference, further the integral strength of the parallel cable is reduced, the anchoring error is defined as,
anchoring error = mean value of error stress generated by the guy cable at the center position of the anchorage/strength of standard length sample,
namely, 5 dimensionless parameters are selected as main prediction parameters to carry out a preset deep learning algorithm.
In the actual execution process, firstly, the prediction parameters of the preset deep learning algorithm are selected.
As shown in Table 1, a reference index meaning table for predicting the strength of the parallel cables of the carbon fiber composite material for a preset deep learning algorithm is provided. In the preset deep learning algorithm, after a material variation coefficient, a parallel root number, a length, an installation error and an anchoring error are selected as prediction parameters, input data processing is carried out, input algorithm data are converted into values between 0 and 1 in an equal proportion mode so as to facilitate value estimation, and reference indexes for carrying out data conversion on the material variation coefficient, the parallel root number, the length, the installation error and the anchoring error are sequentially arranged in a graph.
TABLE 1
| Parameter(s) | Value range | Adjusting the ratio | Input range |
| Coefficient of variation of |
0～0.2 | ×5 | 0～1 |
| Number of parallel connection | 1～1000 | ×0.001 | 0.001～1 |
| Length of | 1～10000 | ×0.0001 | 0.0001～1 |
| |
0～0.025 | ×40 | 0～1 |
| Error of anchoring | 0～0.05 | ×20 | 0～1 |
Secondly, a deep learning sample is established, and the deep learning sample can be generated by utilizing a Monte Carlo method according to the selected prediction parameters.
For example, 1210 samples may be randomly generated with a uniform distribution, each sample being subjected to 2000 monte carlo calculations, wherein the output data for each sample includes: intensity mean, intensity standard value of 95% assurance rate. And the sample set is: 1000 training samples, 200 test samples, and 10 test samples.
And finally, establishing a deep learning neural network, and performing deep learning prediction to obtain the strength characteristics.
For example, in the deep learning neural network establishment, the input layer comprises 5 nodes, the output layer comprises 2 nodes, the middle layer comprises 2 dense layers, the activation function adopts relu and linear layers, the relu and linear layers respectively comprise 256 nodes and 16 nodes, and the learning parameters Epochs =10000 and batch size =8, so that the learning efficiency is reduced by 20% every 1000 steps. The test proves that the average absolute error of the verification set is 0.0010, the design precision can be met, wherein the error range of the strength average value of the test sample is-0.32% -0.18%, the error range of the strength standard value of the 95% guarantee rate is-0.29% -0.18%, and the strength characteristic of the parallel cable can be well predicted.
For the target carbon fiber composite parallel cable and the given standard length strength characteristic, 5 selected dimensionless independent parameter values are input, namely the material variation coefficient, the number of parallel connection roots, the length, the installation error and the anchoring error value of the target carbon fiber composite parallel cable are input, and through the established deep learning neural network, the strength standard value of the corresponding strength mean value and 95% guarantee rate can be obtained, namely the strength mean value and the standard deviation are considered to be obtained.
As shown in fig. 2, the working contents of the pre-set deep learning algorithm are explained in detail in a specific embodiment.
Firstly, selecting prediction parameters, inputting material variation coefficient, parallel root number, length, installation error and anchoring error data, then processing the input data, converting the input data into numerical values between 0 and 1 in an equal proportion, secondly, generating a deep learning sample by a Monte Carlo method, establishing a deep learning network, inputting the material variation coefficient, parallel root number, length, installation error and anchoring error data of a target parallel cable, performing deep learning prediction, and finally obtaining a strength prediction result.
According to the method and the device, the material variation coefficient, the number of parallel connection, the length, the installation error and the anchoring error can be selected, the deep learning sample is generated by using the Monte Carlo method, the deep learning neural network is established, the standard length strength characteristic is estimated by integrating test data of samples with any length, and the prediction range of the length of the inhaul cable is further expanded.
In addition, in an embodiment of the present application, based on a preset genetic algorithm and a preset deep learning algorithm, solving a standard length strength characteristic of the parallel cable made of the carbon fiber composite material according to a multi-source test data result and a corresponding weight includes: selecting tensile strength test values of the same material and the same single cable diameter; selecting a corresponding standard length according to the tensile strength test value; determining weights of different samples of the multi-source test data; and estimating intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value, and the intensity mean value and the intensity standard value are used as input parameters for genetic algorithm estimation.
It is understood that, in the embodiment of the present application, the above steps may be used to implement a preset genetic algorithm, and estimate the standard length strength characteristic of the parallel cable of the carbon fiber composite material under the multi-source data, so as to obtain the strength characteristic of the parallel cable of the carbon fiber composite material targeted in the following steps.
In the actual execution process, the preset genetic algorithm can firstly prepare test data, select tensile strength test values of the strength of the same material and the same single cable diameter, select single cable test data, multi-cable test data, actual measurement data of the whole cable and the like, wherein the total number of samples of each data source is more than 1.
And secondly, selecting a corresponding standard length according to the tensile strength test value, and selecting a proper standard length which is equal to or slightly smaller than the minimum test sample length according to the test data.
And then, determining the weights of different samples of the multi-source test data, and selecting different weights for different samples according to the precision, reliability, sample quantity, target cable scale and the like of the multi-source test data. The higher the weight is, the higher the reliability and the truth of test data are represented, and the higher the dependence of the strength characteristic of the parallel cable of the target carbon fiber composite material on the data is.
And finally, estimating the intensity characteristics of the corresponding standard length, and performing auxiliary calculation by combining a preset genetic algorithm and a preset deep learning algorithm, wherein the intensity characteristics comprise 2 parameters of an intensity mean value and an intensity standard deviation so as to input the parameters.
As shown in fig. 3, a process diagram for estimating the standard length strength characteristic of the parallel cable of the carbon fiber composite material under multi-source data for the preset genetic algorithm according to an embodiment of the present application is provided. In the running process of the preset genetic algorithm, initialization is firstly carried out, an initial mean value and a standard deviation are obtained, reasonable upper and lower limit values are respectively selected for the mean value and the standard deviation of the standard length stay cable strength to serve as search ranges, each parameter value corresponds to one chromosome, the chromosomes can cover a preset cable force range, and the maximum evolution algebra T is set. N individuals are randomly generated as an initial population P (0), where binary gray coding is used as the chromosome coding.
Secondly, the intensity characteristics of all patterns are calculated, and a Monte Carlo method or deep learning prediction can be adopted according to the sample calculation cost.
Secondly, likelihood function values are calculated, and fitness is obtained. And performing individual evaluation to obtain likelihood function values corresponding to all samples to obtain individual fitness in the t-th generation population P (t), wherein the evaluation function is to calculate the likelihood function values corresponding to all samples according to a maximum likelihood estimation method by inputting parameter values and to enable the fitness value of a better solution to be larger. In the process of calculating the likelihood function value, different sample weights need to be added.
And secondly, carrying out selection operation, enabling the next generation genetic probability of excellent individuals to be larger according to the individual fitness in the t generation population P (t), randomly selecting the individuals inherited to the next generation, wherein a roulette selection mode is adopted, namely the selected probability of each individual is in direct proportion to the fitness of the individual, and ensuring that the more excellent individuals have larger selected probability.
And secondly, performing cross operation, wherein a cross operator acts on the population, and the cross operator determines the chromosome cross position and the cross probability of each selected individual.
And secondly, carrying out mutation operation, and applying a mutation operator to the population, wherein the mutation operator determines the probability of mutation at different positions in each individual chromosome.
Finally, a termination operation is performed. Referring to a schematic diagram of an iteration process of estimating the standard length strength characteristic of the parallel cable of the carbon fiber composite material under multi-source data by using a preset genetic algorithm shown in fig. 4. At this time, if the maximum evolution algebra i does not reach T, the genetic algorithm is continued to iterate, if the maximum evolution algebra i reaches T, the evolution is terminated, the individual with the highest fitness of the final population is output, and the chromosome of the individual is decoded, so that an optimized numerical solution is obtained.
According to the embodiment of the application, the standard length strength characteristic of the parallel cable of the carbon fiber composite material under the multi-source data can be estimated through the preset genetic algorithm, and the accuracy of the estimation result is comprehensively improved by fully considering the source of the multiple test data.
In step S103, the strength characteristic of the parallel cable of the carbon fiber composite material is estimated according to the standard length strength characteristic, so as to obtain the estimated strength characteristic of the parallel cable of the carbon fiber composite material.
It can be understood that in the embodiment of the application, the standard length strength characteristic estimation of the strength characteristic of the parallel cable of the carbon fiber composite material can be performed by using a preset deep learning method, and the estimated strength characteristic of the parallel cable of the carbon fiber composite material is obtained by implementing the preset deep learning method in the above steps, so that the prediction speed of the large-scale cable and the corresponding structure design and optimization speed are remarkably improved.
According to the method for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data, the standard length strength characteristic of the parallel cable of the carbon fiber composite material can be solved according to the multi-source test data result and the corresponding weight based on the preset genetic algorithm and the preset deep learning algorithm by obtaining the multi-source test data result of the parallel cable of the carbon fiber composite material, and the estimated strength characteristic of the parallel cable of the carbon fiber composite material can be obtained by estimating the strength characteristic of the parallel cable of the carbon fiber composite material according to the standard length strength characteristic. Therefore, the problems that in the related technology, the error of the obtained calculation result is large for the parallel cables with a large number in the series system calculation method, and the calculation amount is heavy when the Monte Carlo method is used for estimating the strength characteristics of the target cable, so that the calculation efficiency and the calculation precision of the carbon fiber composite material parallel cable strength are reduced, the accuracy and the reliability of the calculation result are insufficient, and the like are solved.
Next, a carbon fiber composite material parallel cord strength estimation device under multi-source data according to an embodiment of the present application will be described with reference to the drawings.
Fig. 5 is a block diagram of a carbon fiber composite parallel cable strength estimation device under multi-source data according to an embodiment of the present application.
As shown in fig. 5, the apparatus 10 for estimating the strength of a parallel carbon fiber composite rope under the multi-source data includes: an acquisition module 100, a solving module 200 and an estimation module 300.
The obtaining module 100 is used for obtaining a multi-source test data result of the carbon fiber composite parallel cable.
And the solving module 200 is used for solving the standard length strength characteristic of the parallel cable of the carbon fiber composite material according to the multi-source test data result and the corresponding weight based on a preset genetic algorithm and a preset deep learning algorithm.
The estimating module 300 is configured to estimate strength characteristics of the carbon fiber composite parallel cables according to the standard length strength characteristics, so as to obtain estimated strength characteristics of the carbon fiber composite parallel cables.
Wherein, in one embodiment of the present application, the multiple experimental data sources of the multiple-source experimental data results comprise at least 2 samples of the same or different lengths, number of parallel connections, mounting errors, and anchoring errors.
Optionally, in an embodiment of the present application, the solving module 200 includes: the device comprises a first selecting unit, a generating unit and an acquiring unit.
The first selecting unit is used for selecting a material variation coefficient, the number of parallel connection, the length, a mounting error and an anchoring error.
And the generating unit is used for generating a deep learning sample by utilizing a Monte Carlo device based on the material variation coefficient, the number of parallel connection, the length, the installation error and the anchoring error.
And the acquisition unit is used for establishing a deep learning neural network, inputting a deep learning sample to the carbon fiber composite material parallel cable and the preset standard length strength characteristic, and acquiring the strength characteristic through the deep learning neural network.
Additionally, in one embodiment of the present application, the solving module 200 further comprises: the device comprises a second selecting unit, a determining unit and an estimating unit.
And the second selecting unit is used for selecting tensile strength test values of the strength of the same material and the same single cable diameter.
And the selecting unit is used for selecting the corresponding standard length according to the tensile strength test value.
And the determining unit is used for determining the weights of different samples of the multi-source test data.
And the estimating unit is used for estimating the intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value, and are used as input parameters for genetic algorithm estimation.
It should be noted that the explanation of the embodiment of the method for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data is also applicable to the device for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data of the embodiment, and details are not repeated here.
According to the device for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data, the standard length strength characteristic of the parallel cable of the carbon fiber composite material can be solved according to the multi-source test data result and the corresponding weight based on the preset genetic algorithm and the preset deep learning algorithm by obtaining the multi-source test data result of the parallel cable of the carbon fiber composite material, and the estimated strength characteristic of the parallel cable of the carbon fiber composite material can be obtained by estimating the strength characteristic of the parallel cable of the carbon fiber composite material according to the standard length strength characteristic. Therefore, the problems that in the related technology, the error of the obtained calculation result is large for the parallel cables with a large number in the series system calculation method, and the calculation amount is heavy when the Monte Carlo method is used for estimating the strength characteristics of the target cable, so that the calculation efficiency and the calculation accuracy of the strength of the parallel cables made of the carbon fiber composite material are reduced, the accuracy and the reliability of the calculation result are insufficient, and the like are solved.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
a memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.
The processor 602 executes the program to implement the method for estimating the strength of the parallel carbon fiber composite cords under the multi-source data provided in the above embodiments.
Further, the electronic device further includes:
a communication interface 603 for communication between the memory 601 and the processor 602.
The memory 601 is used for storing computer programs that can be run on the processor 602.
If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.
Alternatively, in practical implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 may complete communication with each other through an internal interface.
The processor 602 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
The embodiment also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method for estimating the strength of the parallel cable of the carbon fiber composite material under the multi-source data.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for estimating strength of a carbon fiber composite parallel cable under multi-source data is characterized by comprising the following steps:
obtaining a multi-source test data result of the carbon fiber composite parallel cable;
based on a preset genetic algorithm and a preset deep learning algorithm, solving the standard length strength characteristic of the carbon fiber composite parallel cable according to the multi-source test data result and the corresponding weight; and
and estimating the strength characteristic of the parallel cable of the carbon fiber composite material according to the standard length strength characteristic to obtain the estimated strength characteristic of the parallel cable of the carbon fiber composite material.
2. The method of claim 1, wherein the multiple experimental data sources of the multiple-source experimental data results comprise at least 2 specimens of the same or different lengths, number of parallels, installation errors, and anchoring errors.
3. The method of claim 1, wherein solving the standard length strength characteristics of the carbon fiber composite parallel cables according to the multi-source test data results and corresponding weights based on a preset genetic algorithm and a preset deep learning algorithm comprises:
selecting a material variation coefficient, a parallel connection number, a length, a mounting error and an anchoring error;
generating a deep learning sample by using a Monte Carlo method based on the material variation coefficient, the number of parallel-connected elements, the length, the installation error and the anchoring error;
establishing a deep learning neural network, inputting the deep learning sample to the carbon fiber composite material parallel cables and the preset standard length strength characteristics, and obtaining the strength characteristics through the deep learning neural network.
4. The method of claim 1, wherein solving the standard length strength characteristics of the carbon fiber composite parallel cables according to the multi-source test data results and corresponding weights based on a preset genetic algorithm and a preset deep learning algorithm comprises:
selecting tensile strength test values of the same material and the same single cable diameter;
selecting a corresponding standard length according to the tensile strength test value;
determining weights of different samples of the multi-source test data;
and estimating intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value, and the intensity characteristics are used as input parameters for genetic algorithm estimation.
5. The utility model provides a parallel cable intensity estimation device of carbon-fibre composite under multisource data which characterized in that includes:
the acquisition module is used for acquiring multi-source test data results of the carbon fiber composite parallel cable;
the solving module is used for solving the standard length strength characteristic of the carbon fiber composite parallel cable according to the multi-source test data result and the corresponding weight based on a preset genetic algorithm and a preset deep learning algorithm; and
and the estimation module is used for estimating the strength characteristic of the parallel cable of the carbon fiber composite material according to the standard length strength characteristic to obtain the estimated strength characteristic of the parallel cable of the carbon fiber composite material.
6. The apparatus of claim 5, wherein the multiple experimental data sources of the multiple-source experimental data results comprise at least 2 specimens of the same or different lengths, numbers in parallel, installation errors, and anchoring errors.
7. The apparatus of claim 5, wherein the solving module comprises:
the first selection unit is used for selecting the coefficient of variation of the material, the number of parallel connection, the length, the installation error and the anchoring error;
a generating unit for generating a deep learning sample with a monte carlo device based on the material variation coefficient, the number of parallel connections, the length, the installation error, and the anchoring error;
and the acquisition unit is used for establishing a deep learning neural network, inputting the deep learning samples to the carbon fiber composite material parallel cables and the preset standard length strength characteristics, and acquiring the strength characteristics through the deep learning neural network.
8. The apparatus of claim 5, wherein the solving module further comprises:
the second selecting unit is used for selecting tensile strength test values of the same material and the same single cable diameter;
the selecting unit is used for selecting the corresponding standard length according to the tensile strength test value;
the determining unit is used for determining the weights of different samples of the multi-source test data;
and the estimating unit is used for estimating the intensity characteristics of the corresponding standard length, wherein the intensity characteristics comprise an intensity mean value and an intensity standard value, and are used as input parameters for genetic algorithm estimation.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the carbon fiber composite parallel cable strength estimation method under multi-source data according to any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, the program being executed by a processor for implementing the method for estimating the strength of a parallel cable of carbon fiber composite material under multi-source data according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211565745.3A CN115983099A (en) | 2022-12-07 | 2022-12-07 | Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211565745.3A CN115983099A (en) | 2022-12-07 | 2022-12-07 | Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115983099A true CN115983099A (en) | 2023-04-18 |
Family
ID=85960350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211565745.3A Pending CN115983099A (en) | 2022-12-07 | 2022-12-07 | Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983099A (en) |
-
2022
- 2022-12-07 CN CN202211565745.3A patent/CN115983099A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110544011B (en) | Intelligent system combat effectiveness evaluation and optimization method | |
| CN1916791A (en) | Method of soft measuring fusion index of producing propylene through polymerization in industrialization | |
| CN111611748B (en) | Data-driven material reverse design method and system | |
| Tsai | Improved differential evolution algorithm for nonlinear programming and engineering design problems | |
| CN103294729B (en) | Process, predict the seasonal effect in time series method and apparatus comprising sample point | |
| US20090265291A1 (en) | Information Processing Device and Method, and Program | |
| CN116913435B (en) | High-strength engineering plastic evaluation method and system based on component analysis | |
| Khayat et al. | Adaptive techniques used for lifetime estimation of lithium-ion batteries | |
| CN111369000A (en) | High-dimensional multi-target evolution method based on decomposition | |
| CN114302418A (en) | Method and device for detecting network element equipment performance and computer readable medium | |
| CN112765743A (en) | Multi-objective collaborative optimization method and device for complete machine integrated design of wind turbine generator | |
| CN114004008B (en) | Airplane assembly line resource configuration optimization method based on neural network and genetic algorithm | |
| CN109389517B (en) | Analysis method and device for quantifying line loss influence factors | |
| CN115983099A (en) | Method and device for estimating strength of parallel cable of carbon fiber composite material under multi-source data | |
| CN114154762A (en) | Metal corrosion rate prediction method, device, computer equipment and storage medium | |
| CN110210072B (en) | Method for solving high-dimensional optimization problem based on approximate model and differential evolution algorithm | |
| WO2021213649A1 (en) | Method and system for generating a predictive model | |
| CN117149615A (en) | Method and corresponding device for generating test case execution path | |
| CN115730432A (en) | Scheduling method, system, equipment and storage medium for data processing tasks of Internet of things | |
| Ding et al. | Redundancy optimization for multi-performance multi-state series-parallel systems considering reliability requirements | |
| CN113743003B (en) | Method for calculating intensity of high-voltage line to ground electric field by considering influence of temperature and humidity | |
| Paunović et al. | Integrated fuzzy system and multi-expression programming techniques for supplier selection | |
| CN108920415A (en) | A kind of power-line patrolling figure block weight choosing method based on improved grey system theory | |
| CN111859807A (en) | Initial pressure optimizing method, device, equipment and storage medium for steam turbine | |
| CN113807019A (en) | MCMC wind power simulation method based on improved scene classification and coarse grain removal |
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 |