Method and device for efficiently testing broken filament amount of carbon fiber

Abstract

The invention relates to an efficient testing method and device for the broken filament amount of carbon fibers, and relates to the field of detection of the broken filament amount of the carbon fibers, and the method comprises the following steps: backtracking carbon fiber preparation data of a test sample, extracting raw material defects, a process mismatch parameter time sequence value and an equipment mismatch parameter time sequence value, and carrying out crack simulation generation and hairiness simulation generation for several times; obtaining a crack distribution scale and a hairiness distribution scale; performing broken filament quantity simulation generation according to the crack distribution scale and the hairiness distribution scale to obtain a predicted broken filament quantity; and obtaining a broken filament amount confidence interval, receiving a tested broken filament amount when the broken filament amount confidence interval belongs to the broken filament amount confidence interval, and if the deviation between the tested broken filament amount and the predicted broken filament amount is smaller than a deviation threshold value, carrying out credible identification and feeding back to a broken filament amount indirect testing end. The technical problems that in the prior art, due to the fact that direct measurement is high in cost, indirect measurement needs multiple times of measurement, accidental risks cannot be completely avoided, stability is poor, and detection efficiency is low are solved.

Description

Technical Field

[0001] The invention relates to the field of carbon fiber fuzz amount detection, and in particular to a high-efficiency testing method and device for carbon fiber fuzz amount. Background Art

[0002] Traditional carbon fiber lint testing includes direct measurement and indirect measurement. Direct measurement methods include observing the fiber surface through a high-resolution microscope or electron microscope, and using image processing software to count the number and distribution of lint. Indirect measurement methods include monitoring the break point during fiber stretching, indirectly evaluating the density of lint defects through break frequency and intensity, and using laser to irradiate the fiber surface and analyze the length and density of lint through scattered light signals. There are also standard detection processes such as calculating the residual lint by combing and weighing the fibers under specific tension.

[0003] The direct measurement method has higher accuracy, but its disadvantage is that it is costly to implement. The indirect measurement method has lower implementation cost, but it relies on parameters that are highly correlated with the amount of hair for testing. Its disadvantage is that when the correlated parameters fluctuate, it will lead to larger errors in the calculation results of the amount of hair. Therefore, multiple tests are usually required. Even so, there is still a risk that the retrieved data are all accidental values, which leads to poor stability and low efficiency of the test results. Summary of the invention

[0004] The present invention aims to solve the technical problems in the prior art that direct measurement has high cost, indirect measurement requires multiple measurements, and cannot completely avoid accidental risks, resulting in poor stability and low detection efficiency. An efficient testing method and device for the amount of carbon fiber filaments are provided to solve the problems.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides an efficient method for testing the amount of carbon fiber filaments, comprising: Back-test the carbon fiber preparation data of the sample to extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; Performing crack simulation generation and hairiness simulation generation several times according to the raw material defects, the process mismatch parameter timing values, and the equipment misalignment parameter timing values ​​to obtain a crack distribution scale and a hairiness distribution scale; Simulating and generating the amount of hairiness according to the crack distribution scale and the hairiness distribution scale to obtain a predicted amount of hairiness; Retrieving carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale, performing confidence analysis, and obtaining a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; When the predicted hair amount belongs to the hair amount confidence interval, the tested hair amount is received from the hair amount indirect testing end. If the deviation from the predicted hair amount is less than the deviation threshold, a credible mark is performed and fed back to the hair amount indirect testing end.

[0006] In a second aspect, the present invention provides an efficient testing device for the amount of carbon fiber filaments, comprising: Preparation data module, used to trace back the carbon fiber preparation data of the test sample, extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; A crack and hairiness generation simulation module, used to perform several crack simulations and hairiness simulations according to the raw material defects, the process mismatch parameter timing values ​​and the equipment misalignment parameter timing values, to obtain crack distribution scales and hairiness distribution scales; A hair quantity simulation generation module is used to simulate and generate the hair quantity according to the crack distribution scale and the hair distribution scale to obtain a predicted hair quantity; A confidence interval configuration module is used to retrieve the same type and same location produced carbon fiber in a preset time zone that meets the crack distribution scale and the hairiness distribution scale to perform confidence analysis and obtain a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; The trusted identification module is used to receive the tested hair amount from the hair amount indirect testing end when the predicted hair amount belongs to the hair amount confidence interval, and if the deviation from the predicted hair amount is less than the deviation threshold, perform a trusted identification and feedback to the hair amount indirect testing end.

[0007] The beneficial effects of the present invention are as follows: by back-testing the preparation data of the test sample, the raw material defects, the timing values ​​of the process mismatch parameters and the timing values ​​of the equipment misalignment parameters related to the amount of hair are determined, and then based on the stage characteristics of the amount of hair, the generation simulation of cracks and hairiness in the first stage is first performed, and then the simulation of the amount of hair in the second stage is performed to obtain the predicted amount of hair; further, a confidence interval is constructed using recent detection data to perform a primary verification on the predicted amount of hair, and when it meets the confidence interval, the predicted amount of hair is used to verify the test result, and if the verification passes, a reliable mark is generated, and the mark test result is directly available without the need for multiple tests, and because the predicted amount of hair is a characteristic value that meets the long-term and short-term characteristics, the probability of accidental risk of the test amount of hair with a reliable mark is reduced, thereby achieving the technical effect of improving efficiency and taking into account the realization of cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of a process flow of an efficient method for testing the amount of carbon fiber fuzz provided by the present invention; Figure 2 A schematic structural diagram of a highly efficient testing device for carbon fiber fuzz content provided by the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0010] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0011] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0012] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides an efficient method for testing the amount of carbon fiber filaments, comprising the steps of: S10: Back-test the carbon fiber preparation data of the sample to extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; Specifically, the test sample is a sample cut from a carbon fiber product that needs to be tested for fuzz content; the carbon fiber preparation data refers to the monitoring data during the test sample preparation process, including raw material inspection data before production, from which raw material defect data can be extracted. Specifically, the parameters in the raw material defect data that are most closely correlated with fuzz content are impurities, bubbles, and the shrinkage ratio of the cortex to the core layer.

[0013] The embodiments of the present application use impurity scale characterization for impurities, and the impurity scale is quantitatively calculated by the impurity weight per unit weight of raw materials. The embodiments of the present application use bubble scale characterization for bubbles; the bubble scale is quantitatively calculated by the number of bubbles per unit area; the ratio of the shrinkage rate of the skin layer to the core layer is the ratio of the shrinkage rate of the skin layer to the shrinkage rate of the core layer, which is an existing concept and will not be elaborated in detail.

[0014] Furthermore, the carbon fiber preparation data also includes process mismatch parameter timing values, which are timing record values ​​of process parameters in the generation process that are closer to the user's preset process parameters. In detail, among the process mismatch parameter timing values, the embodiment of the present application selects the drawing ratio mismatch timing values ​​and the heat setting temperature mismatch timing values ​​that are strongly correlated with the amount of hair for calculation.

[0015] Furthermore, the carbon fiber preparation data also includes equipment misalignment parameter timing values, which are equipment control deviation timing record values. Specifically, among the equipment misalignment parameter timing values, the embodiment of the present application selects carbonization furnace gas flow rate distribution misalignment timing values ​​and wire drawing tension misalignment timing values ​​that are strongly correlated with the amount of hair for calculation.

[0016] For the remaining parameters, which are either related to the aforementioned selected parameters or have a weak correlation with the amount of hair, the embodiments of the present application do not select them to avoid increasing redundant calculations.

[0017] By using the test sample parameters, the generation state of its hair quantity can be simulated, which can be used as the final verification data. Compared with the traditional manual experience evaluation, it has higher stability and objectivity.

[0018] Furthermore, in order to ensure accurate prediction of the amount of hair, the embodiment of the present application combines historical data to build a multi-stage simulator. The traditional data-driven model usually collects mapped causal data and then directly builds the corresponding simulator. However, in the actual production process, there are often multiple stages of transition between causal data. Especially in the production process of carbon fiber, the amount of hair is generated gradually. When training the simulator, if the multi-stage process of hair generation is not considered, the result obtained is bound to be inaccurate. Therefore, the embodiment of the present application generates a path based on the stage characteristics of the hair amount as follows: Phase 1: A[raw material defects]-->B(defects magnified during spinning stage); C[process parameter mismatch]-->D(pre-oxidation / carbonization structural defects); E[Equipment wear / operation error]-->F(Mechanical damage accumulation); Phase 2: B-->G [surface cracks / hairiness]; D -> G; F -> G; Phase 3: G-->H[The amount of hair exceeds the standard].

[0019] It can be seen that the generation of the amount of hair is divided into three stages, and the best simulator should be three stages. However, since the characteristic data of stages A [raw material defects] -> B (defect amplification in the spinning stage), C [process parameter mismatch] -> D (pre-oxidation / carbonization structural defects), and E [equipment wear / operation error] -> F (mechanical damage accumulation) are difficult to collect and quantify, the embodiment of the present application temporarily builds a two-stage simulator, namely: Phase 1: A[Raw material defects]-->G[Surface cracks / hairiness]; C[process parameter mismatch]-->G[surface cracks / hairiness]; E[Equipment wear / operation error]-->G[Surface cracks / hairiness]; Phase 2: G-->H[The amount of hair exceeds the standard].

[0020] It can be seen that in the first stage, it is necessary to train simulators of A[raw material defects]-->G[surface cracks / hairiness], C[process parameter mismatch]-->G[surface cracks / hairiness], and E[equipment wear / operation error]-->G[surface cracks / hairiness]. The embodiment of the present application chooses to build three groups of simulators for the three mapping relationships, and each group of simulators includes a crack simulation generator and a hairiness simulation generator; in the second stage, it is necessary to train a simulator of G-->H[excessive hairiness].

[0021] In detail, the training method of any mapping relationship simulator in the first stage is the same. The embodiment of the present application uses the training process of A[raw material defect]->G[surface crack / hairiness] as an example, and the other two can be implemented with reference to the training process of A[raw material defect]->G[surface crack / hairiness].

[0022] Details are as follows: Further, according to the impurity scale, bubble scale, and skin-to-core shrinkage ratio of the raw material defects, several crack simulations and hairiness simulations are performed to obtain several first crack distribution scales and several first hairiness distribution scales, including the steps of: S11: limited to the production process, production equipment model and carbon fiber model, collect carbon fiber preparation record data with impurity scale, bubble scale and skin layer to core layer shrinkage ratio as unique variables, extract multiple groups of data, any one of the multiple groups of data includes impurity scale record parameters, bubble scale record parameters, skin layer to core layer shrinkage ratio record parameters, crack distribution scale detection value and hairiness distribution scale detection value; S12: Supervise and train a crack simulation generator according to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and crack distribution scale detection values ​​of the multiple sets of data; S13: Supervise and train a hairiness simulation generator according to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and hairiness distribution scale detection values ​​of the plurality of data sets.

[0023] Specifically, since slight deviations in chemical production processes will cause larger deviations, the embodiments of the present application build models for limited scenarios for production processes, production equipment models, and carbon fiber models, and only have generalization capabilities in limited scenarios, and are not adaptable to other scenarios. In the training process of A[raw material defects]->G[surface cracks / hairiness], the impurity scale, bubble scale, and skin-to-core shrinkage ratio are input data, so it is required to limit other influencing parameters to be kept within the standard range, collect carbon fiber preparation record data with impurity scale, bubble scale, and skin-to-core shrinkage ratio as unique variables, and extract multiple groups of data, any group of which includes impurity scale record parameters, bubble scale record parameters, skin-to-core shrinkage ratio record parameters, crack distribution scale detection value, and hairiness distribution scale detection value. The crack distribution scale detection value of each group of data in the embodiments of the present application is preferably characterized by the mean value of the number of cracks distributed in a number of unit areas of carbon fiber products, and the hairiness distribution scale detection value is preferably characterized by the weight mean value of the hairiness of a number of unit weights of carbon fiber products.

[0024] Furthermore, the model architectures of the crack simulation generator and the hairiness simulation generator are configured as follows: Input layer [impurity scale, bubble scale, skin layer and core layer shrinkage ratio] --> shared feature extraction layer (the embodiment of the present application is preferably a convolutional fully connected neural network); Shared feature extraction layer --> crack branch: fully connected layer + ReLU; Shared feature extraction layer-->Feather branch: fully connected layer + Sigmoid; Crack branching-->crack distribution scale; Hairiness branch-->hairness distribution scale.

[0025] Among them, the crack branch is the crack simulation generator of the embodiment of the present application, preferably using a deep neural network (DNN), the hidden layer structure is 256-128-64, the activation function is LeakyReLU (α=0.01), the feather branch is the feather simulation generator of the embodiment of the present application, preferably introducing an attention mechanism (AttentionLayer), which can focus on the interaction between bubbles and shrinkage rate, the crack branch loss function selects the mean square error loss function, the convergence error threshold is set to 0.15, the determination coefficient is set to 0.85, the feather branch selects the mean absolute percentage error, and the convergence error threshold is set to 8%.

[0026] During specific training, multiple groups of data are divided into 8:2 ratios, and 8 ratios of data are selected as training data, and 2 ratios of data are selected as verification data. First, the 8 ratios of training data are retrieved and the impurity scale, bubble scale, and skin-to-core shrinkage ratio are used as input data of the input layer. The crack distribution scale detection value and the hairiness distribution scale detection value are used as supervision. Then the mean square error and the mean absolute percentage error are calculated through the loss function. If at least 85% of the output errors have a mean square error of less than or equal to 0.15 and an average absolute percentage error of less than or equal to 8% after a preset number of consecutive trainings, then 2 ratios of data are retrieved to continue training. If at least 85% of the output errors have a mean square error of less than or equal to 0.15 and an average absolute percentage error of less than or equal to 8% after a preset number of consecutive trainings, then it is considered to have converged, and a crack simulation generator and a hairiness simulation generator are obtained.

[0027] The simulators for the other two mapping relationships are trained in the same way.

[0028] Furthermore, the process of training the simulator for the second stage G->H [hair excess] is as follows: Further, simulating and generating the amount of hairiness according to the crack distribution scale and the hairiness distribution scale to obtain the predicted amount of hairiness includes the steps of: S14: collecting carbon fiber preparation record data based on the production process, production equipment model and carbon fiber model, wherein multiple groups of data are extracted, and any group of data of the multiple groups of data includes a crack distribution scale identification value, a hairiness distribution scale identification value and a hairiness amount detection true value; S15: According to the crack distribution scale identification values, hairiness distribution scale identification values ​​and hairiness amount detection true values ​​of the plurality of groups of data, supervised training of a hairiness amount generation simulator; S16: training the crack distribution scale and the hairiness distribution scale according to the hairiness amount generation simulator to obtain the predicted hairiness amount.

[0029] Specifically, the preferred model architecture of the embodiment of the present application is as follows: Input layer [first crack distribution scale, second crack distribution scale, third crack distribution scale] --> crack feature branch, 1D convolution layer; Input layer [first hairiness distribution scale, second hairiness distribution scale, third hairiness distribution scale] --> hairiness feature branch, 1D convolution layer; Crack feature branch-->feature splicing layer; Hairiness feature branch --> feature splicing layer; Feature concatenation layer --> fully connected layer, 256 nodes; Fully connected layer, 256 nodes-->Dropout layer, rate=0.2, to prevent overfitting-->I [output layer: hair amount prediction].

[0030] The loss function is preferably a mean square error loss function, and the convergence error threshold is 0.1, which is stricter than before. The true value of the hair quantity detection is used as the supervision data, and the crack distribution scale identification value and the hairiness distribution scale identification value are used to train the aforementioned model architecture to obtain a hair quantity generation simulator. The convergence and training process are the same as the convergence conditions of the aforementioned crack simulation generator and the hairiness simulation generator. Preferably, the crack distribution scale identification value and the hairiness distribution scale identification value implemented in the present application are generated by processing the data corresponding to the true value of the hair quantity detection through the aforementioned first stage simulator.

[0031] Furthermore, after the training is completed, in order to ensure stability during specific use, the embodiment of the present application reduces the probability of accidental errors by repeating the generation several times, as detailed below: S20: performing crack simulation generation and hairiness simulation generation several times according to the raw material defects, the process mismatch parameter timing value and the equipment misalignment parameter timing value to obtain a crack distribution scale and a hairiness distribution scale; S30: simulating and generating the amount of hairiness according to the crack distribution scale and the hairiness distribution scale to obtain a predicted amount of hairiness; Further, performing several crack simulations and hairiness simulations according to the raw material defects, the process mismatch parameter timing values, and the equipment misalignment parameter timing values ​​to obtain the crack distribution scale and the hairiness distribution scale comprises the steps of: S21: performing several crack simulations and hairiness simulations according to the impurity scale, bubble scale, and skin-to-core shrinkage ratio of the raw material defects to obtain several first crack distribution scales and several first hairiness distribution scales; S22: performing several crack simulation generation and hairiness simulation generation according to the draft ratio mismatch timing value and the heat setting temperature mismatch timing value of the process mismatch parameter timing value, to obtain several second crack distribution scales and several second hairiness distribution scales; S23: performing several crack simulations and hairiness simulations according to the carbonization furnace gas velocity distribution misalignment timing values ​​and the wire drawing tension misalignment timing values ​​of the equipment misalignment parameter timing values, and obtaining several third crack distribution scales and several third hairiness distribution scales; S24: respectively calculating the average of the plurality of first crack distribution scales, the plurality of second crack distribution scales and the plurality of third crack distribution scales, setting them as the crack distribution scale, respectively calculating the average of the plurality of first hairiness distribution scales, the plurality of second hairiness distribution scales and the plurality of third hairiness distribution scales, and obtaining the hairiness distribution scale.

[0032] Preferably, in specific use, each output parameter is cycled at least 20 times, so that 20 first crack distribution scales and 20 first hairiness distribution scales can be obtained, and then the average of the 20 first crack distribution scales is calculated as the first crack distribution scale, and the average of the 20 first hairiness distribution scales is calculated as the first hairiness distribution scale, and the second crack distribution scale and the second hairiness distribution scale, as well as the third crack distribution scale and the third hairiness distribution scale are calculated in the same way, and the first crack distribution scale, the second crack distribution scale and the third crack distribution scale are added to the crack distribution scale, and the first hairiness distribution scale, the second hairiness distribution scale and the third hairiness distribution scale are added to the hairiness distribution scale, and then input into the hairiness amount generation simulator to obtain the predicted hairiness amount.

[0033] S40: retrieving carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale, and performing confidence analysis to obtain a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; Specifically, the predicted hair amount generated by the aforementioned simulation generator is obtained based on the fitting of long-term data patterns, but the actual hair amount value is also affected by the service life of the equipment and the workshop environment. Therefore, it is necessary to refer to the short-term characteristic hair amount to verify the credibility of the predicted hair amount. Preferably, the model of the carbon fiber product and the position number of the production line of the test sample are limited, and a set of reliable hair amount detection record values ​​of carbon fiber products produced in the history of a preset time zone and verified by experts are collected. The LOF outlier factor analysis is used to delete outliers from the hair amount detection record value set, and then the distribution interval of the remaining data is statistically analyzed and set as the hair amount confidence interval.

[0034] S50: When the predicted hair amount belongs to the hair amount confidence interval, receiving the tested hair amount from the hair amount indirect testing terminal, and if the deviation from the predicted hair amount is less than the deviation threshold, performing a credible mark and feeding back to the hair amount indirect testing terminal.

[0035] Specifically, when the predicted hair amount belongs to the hair amount confidence interval, it means that the predicted hair amount is not only applicable to the long term but also to the short term. Then, the test hair amount is received from the hair amount indirect test end. If the deviation from the predicted hair amount is less than the deviation threshold preset by the user, a credible mark is made and fed back to the hair amount indirect test end. If the deviation is greater than or equal to the deviation threshold preset by the user, a suspicious mark is made and fed back to the hair amount indirect test end. Subsequently, the data for the suspicious mark is deleted, and only the mean calculation is performed on the data for the credible mark. The obtained test hair amount will be more accurate. Moreover, due to the credible mark, the tester can reduce the number of tests, thereby improving the test efficiency.

[0036] Furthermore, it also includes: When the predicted hair amount does not belong to the hair amount confidence interval, obtaining a hair amount concentration value of the hair amount confidence interval; Calculating a first deviation distance between the predicted amount of hair and the confidence interval of the amount of hair; When the first deviation distance is less than the deviation threshold, average calculation is performed on the predicted hair amount and the concentrated value of the hair amount to obtain a corrected hair amount, and the predicted hair amount is updated; When the first deviation distance is greater than or equal to the deviation threshold, the process returns to the step of simulating and generating the amount of hair and executes a loop.

[0037] In detail, the concentrated value of the hair amount refers to the mode value or mean of the hair amount, the first deviation distance refers to the distance between the predicted hair amount and the nearest boundary of the hair amount confidence interval, and the deviation threshold is the aforementioned deviation threshold preset by the user. When the first deviation distance is less than the deviation threshold, it means that although there is a deviation, it is still at a reference level. Therefore, the predicted hair amount and the concentrated value of the hair amount are averaged to obtain the corrected hair amount and update the predicted hair amount. When the first deviation distance is greater than or equal to the deviation threshold, return to the hair amount simulation generation step to execute the loop. If the generation results of the preset number of times are all greater than or equal to the deviation threshold, the concentrated value of the hair amount is output as the predicted hair amount.

[0038] Further, when the first deviation distance is less than the deviation threshold, the predicted hair amount and the hair amount concentration value are averaged to obtain the corrected hair amount, including: Calculating a ratio of the first deviation distance to the deviation threshold, and setting the ratio as a first fitting weight; Subtracting the first fitting weight from 1 to obtain a second fitting weight; The concentrated value of the hair amount is weighted according to the first fitting weight, and the predicted hair amount is weighted according to the second fitting weight to obtain the corrected hair amount.

[0039] When the predicted hair amount can be used as a reference, the farther it deviates, the less usable it is, and the smaller the weight should be. Therefore, the ratio of the first deviation distance to the deviation threshold is calculated and set as the first fitting weight; 1 is subtracted from the first fitting weight to obtain the second fitting weight; the concentrated value of the hair amount is weighted according to the first fitting weight, and the predicted hair amount is weighted according to the second fitting weight to obtain the corrected hair amount, which can improve the reliability of the mean calculation result.

[0040] It should be noted that the mean fitting rule is an exemplary description proposed in the embodiments of the present application. In actual application, it can be set according to actual needs.

[0041] Further, the same type and same location produced carbon fibers in a preset time zone that meet the crack distribution scale and the hairiness distribution scale are retrieved to perform confidence analysis to obtain a confidence interval of the hairiness amount, including: Retrieving a primary historical sample set of carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale from the test historical samples; Extracting the primary crack distribution scale and the primary hairiness distribution scale of each primary historical sample of the primary historical sample set, and retrieving the secondary historical sample set that satisfies the primary crack distribution scale and the primary hairiness distribution scale; A central tendency analysis is performed on the hair quantity detection values ​​of the secondary historical sample set and the primary historical sample set to obtain the hair quantity confidence interval.

[0042] Specifically, in order to avoid insufficient analysis data, the embodiment of the present application adopts a two-level sampling strategy for data collection, that is, the tester configures the crack distribution scale deviation threshold and the hairiness distribution scale deviation threshold according to the needs. When the crack distribution scale deviation of the sample crack distribution scale and the crack distribution scale is less than the crack distribution scale deviation threshold, and the hairiness distribution scale deviation of the sample hairiness distribution scale and the hairiness distribution scale is less than the hairiness distribution scale deviation threshold, it is deemed to meet the crack distribution scale and the hairiness distribution scale. First, retrieve the test history samples that meet the preset time zone, the same model, and the same number, and then extract the samples that meet the preset time zone, the same model, and the same number. A primary historical sample set of carbon fibers of the same type and location produced in a preset time zone with the crack distribution scale and the hairiness distribution scale, and then based on the primary crack distribution scale and the primary hairiness distribution scale of each sample in the primary historical sample set, a secondary historical sample set satisfying the primary crack distribution scale and the primary hairiness distribution scale is retrieved. The secondary sampling will not deviate too much from the benchmark conditions, while increasing the amount of data and improving the objectivity of the analysis results. A central trend analysis is performed on the hairiness detection values ​​of the secondary historical sample set and the primary historical sample set to obtain the hairiness confidence interval.

[0043] An efficient method for testing the amount of carbon fiber filaments provided by an embodiment of the present invention has at least the following technical effects: By back-testing the preparation data of the test samples, the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values ​​related to the amount of hair are determined. Then, based on the stage characteristics of the amount of hair, the first stage of crack and feather generation simulation is performed, and then the second stage of hair simulation is performed to obtain the predicted amount of hair. Furthermore, the confidence interval is constructed using recent test data to perform a first-level verification of the predicted amount of hair. When it meets the confidence interval, the predicted amount of hair is used to verify the test result. If the verification passes, a reliable mark is generated, and the test result of the mark is directly available without the need for multiple tests. In addition, since the predicted amount of hair meets the long-term and short-term characteristic values, the probability of accidental risks in the test amount of hair with a reliable mark is reduced, thereby achieving the technical effect of improving efficiency and taking into account the realization of costs.

[0044] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the efficient testing method for the amount of carbon fiber hair provided in Example 1, the embodiment of the present invention further provides an efficient testing device for the amount of carbon fiber hair, comprising: Preparation data module, used to trace back the carbon fiber preparation data of the test sample, extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; A crack and hairiness generation simulation module, used to perform several crack simulations and hairiness simulations according to the raw material defects, the process mismatch parameter timing values ​​and the equipment misalignment parameter timing values, to obtain crack distribution scales and hairiness distribution scales; A hair quantity simulation generation module is used to simulate and generate the hair quantity according to the crack distribution scale and the hair distribution scale to obtain a predicted hair quantity; A confidence interval configuration module is used to retrieve the same type and same location produced carbon fiber in a preset time zone that meets the crack distribution scale and the hairiness distribution scale to perform confidence analysis and obtain a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; The trusted identification module is used to receive the tested hair amount from the hair amount indirect testing end when the predicted hair amount belongs to the hair amount confidence interval, and if the deviation from the predicted hair amount is less than the deviation threshold, perform a trusted identification and feedback to the hair amount indirect testing end.

[0045] Furthermore, it also includes a predicted hair amount correction module, and the execution steps include: When the predicted hair amount does not belong to the hair amount confidence interval, obtaining a hair amount concentration value of the hair amount confidence interval; Calculating a first deviation distance between the predicted amount of hair and the confidence interval of the amount of hair; When the first deviation distance is less than the deviation threshold, average calculation is performed on the predicted hair amount and the concentrated value of the hair amount to obtain a corrected hair amount, and the predicted hair amount is updated; When the first deviation distance is greater than or equal to the deviation threshold, the process returns to the step of simulating and generating the amount of hair and executes a loop.

[0046] Furthermore, the crack hairiness generation simulation module execution steps include: According to the impurity scale, bubble scale, and skin-to-core shrinkage ratio of the raw material defects, several crack simulations and hairiness simulations are performed to obtain several first crack distribution scales and several first hairiness distribution scales; According to the draft ratio mismatch timing value and the heat setting temperature mismatch timing value of the process mismatch parameter timing value, a plurality of crack simulation generation and hairiness simulation generation are performed to obtain a plurality of second crack distribution scales and a plurality of second hairiness distribution scales; According to the carbonization furnace gas velocity distribution misalignment timing value and the wire drawing tension misalignment timing value of the equipment misalignment parameter timing value, several crack simulation generation and hairiness simulation generation are performed to obtain several third crack distribution scales and several third hairiness distribution scales; The average values ​​of the first crack distribution scales, the second crack distribution scales and the third crack distribution scales are calculated respectively, set as the crack distribution scale, and the average values ​​of the first hairiness distribution scales, the second hairiness distribution scales and the third hairiness distribution scales are calculated respectively to obtain the hairiness distribution scale.

[0047] Furthermore, the crack hairiness generation simulation module execution steps include: Limited to the production process, production equipment model and carbon fiber model, collect carbon fiber preparation record data with impurity scale, bubble scale and skin layer to core layer shrinkage ratio as unique variables, extract multiple groups of data, any one of the multiple groups of data includes impurity scale record parameters, bubble scale record parameters, skin layer to core layer shrinkage ratio record parameters, crack distribution scale detection value and hairiness distribution scale detection value; According to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and crack distribution scale detection values ​​of the multiple sets of data, supervise the training of the crack simulation generator; According to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and hairiness distribution scale detection values ​​of the multiple groups of data, supervised training of the hairiness simulation generator.

[0048] Furthermore, the steps of executing the hair quantity simulation generation module include: The carbon fiber preparation record data is collected based on the production process, production equipment model and carbon fiber model, wherein multiple groups of data are extracted, and any group of data of the multiple groups of data includes a crack distribution scale identification value, a hairiness distribution scale identification value and a hairiness amount detection true value; According to the crack distribution scale identification values, hairiness distribution scale identification values ​​and hairiness amount detection true values ​​of the plurality of groups of data, supervised training of a hairiness amount generation simulator; The crack distribution scale and the hairiness distribution scale are trained according to the hairiness amount generation simulator to obtain the predicted hairiness amount.

[0049] Furthermore, the confidence interval configuration module execution steps include: Retrieving a primary historical sample set of carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale from the test historical samples; Extracting the primary crack distribution scale and the primary hairiness distribution scale of each primary historical sample of the primary historical sample set, and retrieving the secondary historical sample set that satisfies the primary crack distribution scale and the primary hairiness distribution scale; A central tendency analysis is performed on the hair quantity detection values ​​of the secondary historical sample set and the primary historical sample set to obtain the hair quantity confidence interval.

[0050] Furthermore, the execution steps of the predicted hair amount correction module include: Calculating a ratio of the first deviation distance to the deviation threshold, and setting the ratio as a first fitting weight; Subtracting the first fitting weight from 1 to obtain a second fitting weight; The concentrated value of the hair amount is weighted according to the first fitting weight, and the predicted hair amount is weighted according to the second fitting weight to obtain the corrected hair amount.

[0051] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0052] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0054] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0056] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0057] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. An efficient method for testing the amount of carbon fiber filaments, characterized in that: include: Back-test the carbon fiber preparation data of the sample to extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; Performing crack simulation generation and hairiness simulation generation several times according to the raw material defects, the process mismatch parameter timing values, and the equipment misalignment parameter timing values ​​to obtain a crack distribution scale and a hairiness distribution scale; Simulating and generating the amount of hairiness according to the crack distribution scale and the hairiness distribution scale to obtain a predicted amount of hairiness; Retrieving carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale, performing confidence analysis, and obtaining a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; When the predicted hair amount belongs to the hair amount confidence interval, the tested hair amount is received from the hair amount indirect testing end. If the deviation from the predicted hair amount is less than the deviation threshold, a credible mark is performed and fed back to the hair amount indirect testing end.

2. The method according to claim 1, characterized in that Also includes: When the predicted hair amount does not belong to the hair amount confidence interval, obtaining a hair amount concentration value of the hair amount confidence interval; Calculating a first deviation distance between the predicted amount of hair and the confidence interval of the amount of hair; When the first deviation distance is less than the deviation threshold, average calculation is performed on the predicted hair amount and the concentrated value of the hair amount to obtain a corrected hair amount, and the predicted hair amount is updated; When the first deviation distance is greater than or equal to the deviation threshold, the process returns to the step of simulating and generating the amount of hair and executes a loop.

3. The method according to claim 1, characterized in that According to the raw material defects, the process mismatch parameter timing values ​​and the equipment misalignment parameter timing values, several crack simulations and hairiness simulations are performed to obtain the crack distribution scale and the hairiness distribution scale, including: According to the impurity scale, bubble scale, and skin-to-core shrinkage ratio of the raw material defects, several crack simulations and hairiness simulations are performed to obtain several first crack distribution scales and several first hairiness distribution scales; According to the draft ratio mismatch timing value and the heat setting temperature mismatch timing value of the process mismatch parameter timing value, a plurality of crack simulation generation and hairiness simulation generation are performed to obtain a plurality of second crack distribution scales and a plurality of second hairiness distribution scales; According to the carbonization furnace gas velocity distribution misalignment timing value and the wire drawing tension misalignment timing value of the equipment misalignment parameter timing value, several crack simulation generation and hairiness simulation generation are performed to obtain several third crack distribution scales and several third hairiness distribution scales; The average values ​​of the first crack distribution scales, the second crack distribution scales and the third crack distribution scales are calculated respectively, set as the crack distribution scale, and the average values ​​of the first hairiness distribution scales, the second hairiness distribution scales and the third hairiness distribution scales are calculated respectively to obtain the hairiness distribution scale.

4. The method according to claim 3, characterized in that According to the impurity scale, bubble scale, and skin-to-core shrinkage ratio of the raw material defects, several crack simulations and hairiness simulations are performed to obtain several first crack distribution scales and several first hairiness distribution scales, including: Limited to the production process, production equipment model and carbon fiber model, collect carbon fiber preparation record data with impurity scale, bubble scale and skin layer to core layer shrinkage ratio as unique variables, extract multiple groups of data, any one of the multiple groups of data includes impurity scale record parameters, bubble scale record parameters, skin layer to core layer shrinkage ratio record parameters, crack distribution scale detection value and hairiness distribution scale detection value; According to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and crack distribution scale detection values ​​of the multiple sets of data, supervise the training of the crack simulation generator; According to the impurity scale recording parameters, bubble scale recording parameters, skin layer and core layer shrinkage ratio recording parameters, and hairiness distribution scale detection values ​​of the multiple groups of data, supervised training of the hairiness simulation generator.

5. The method according to claim 1, characterized in that The method of simulating and generating the amount of hairiness according to the crack distribution scale and the hairiness distribution scale to obtain the predicted amount of hairiness includes: The carbon fiber preparation record data is collected based on the production process, production equipment model and carbon fiber model, wherein multiple groups of data are extracted, and any group of data of the multiple groups of data includes a crack distribution scale identification value, a hairiness distribution scale identification value and a hairiness amount detection true value; According to the crack distribution scale identification values, hairiness distribution scale identification values ​​and hairiness amount detection true values ​​of the plurality of groups of data, supervised training of a hairiness amount generation simulator; The crack distribution scale and the hairiness distribution scale are trained according to the hairiness amount generation simulator to obtain the predicted hairiness amount.

6. The method according to claim 1, characterized in that Retrieving carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale and performing confidence analysis to obtain a confidence interval of the hairiness amount, including: Retrieving a primary historical sample set of carbon fibers of the same type and position produced in a preset time zone that meet the crack distribution scale and the hairiness distribution scale from the test historical samples; Extracting the primary crack distribution scale and the primary hairiness distribution scale of each primary historical sample of the primary historical sample set, and retrieving the secondary historical sample set that satisfies the primary crack distribution scale and the primary hairiness distribution scale; A central tendency analysis is performed on the hair quantity detection values ​​of the secondary historical sample set and the primary historical sample set to obtain the hair quantity confidence interval.

7. The method according to claim 2, characterized in that When the first deviation distance is less than the deviation threshold, the predicted hair amount and the hair amount concentration value are averaged to obtain a corrected hair amount, including: Calculating a ratio of the first deviation distance to the deviation threshold, and setting the ratio as a first fitting weight; Subtracting the first fitting weight from 1 to obtain a second fitting weight; The concentrated value of the hair amount is weighted according to the first fitting weight, and the predicted hair amount is weighted according to the second fitting weight to obtain the corrected hair amount.

8. An efficient testing device for the amount of carbon fiber filaments, characterized in that: include: Preparation data module, used to trace back the carbon fiber preparation data of the test sample, extract the raw material defects, process mismatch parameter timing values ​​and equipment misalignment parameter timing values; A crack and hairiness generation simulation module, used to perform several crack simulations and hairiness simulations according to the raw material defects, the process mismatch parameter timing values ​​and the equipment misalignment parameter timing values, to obtain crack distribution scales and hairiness distribution scales; A hair quantity simulation generation module is used to simulate and generate the hair quantity according to the crack distribution scale and the hair distribution scale to obtain a predicted hair quantity; A confidence interval configuration module is used to retrieve the same type and same location produced carbon fiber in a preset time zone that meets the crack distribution scale and the hairiness distribution scale to perform confidence analysis and obtain a confidence interval of the hairiness amount, wherein the preset time zone is a time zone obtained by pushing a preset time length forward from the current moment; The trusted identification module is used to receive the tested hair amount from the hair amount indirect testing end when the predicted hair amount belongs to the hair amount confidence interval, and if the deviation from the predicted hair amount is less than the deviation threshold, perform a trusted identification and feedback to the hair amount indirect testing end.

Images