Method and device for evaluating the fire-retardant properties of a fire-retardant network cable

Abstract

This application relates to the field of flame retardant performance evaluation technology, specifically to a method and device for evaluating the flame retardant performance of fire-resistant and flame-retardant network cables. The method includes: determining correlation characteristics based on the similarity between the flame retardant index and thermal conductivity obtained from various flame retardant tests for each group of network cables, combined with a flame retardant penalty factor constructed based on droplet markings; comparing the correlation characteristics obtained from different flame retardant tests to determine a first deviation characteristic; building a model based on historical data to predict the flame retardant index for each flame retardant test, analyzing the similarity between the predicted and actual values, and combining the first deviation characteristic to determine a second deviation characteristic, thereby obtaining a total deviation characteristic and evaluating the flame retardant performance of each group of network cables. This application aims to improve the reliability of flame retardant performance evaluation of network cables.

Description

Technical Field

[0001] This application relates to the field of flame retardant performance evaluation technology, specifically to a method and equipment for evaluating the flame retardant performance of fire-resistant and flame-retardant network cables. Background Technology

[0002] Network cables are crucial carriers of data transmission and are widely used in intelligent buildings, data centers, and other similar environments. The concentrated laying of large numbers of cables poses a potential fire hazard. Therefore, fire-resistant and flame-retardant network cables have emerged, making the evaluation of their flame-retardant properties particularly important.

[0003] Current methods for evaluating flame retardant performance primarily utilize vertical burning tests and oxygen index tests on individual cables. However, during the manufacturing process of network cables, various performance parameters exist within a acceptable range. Fluctuations in microscopic parameters within this range (such as uneven dispersion of flame retardants) are difficult to detect using a single conventional flame retardant test indicator. By utilizing the bivariate mapping relationship between thermal conductivity and flame retardant indicators, implicit drift in the process baseline can be monitored. Existing evaluation methods lack in-depth analysis of batch-to-batch process stability, thus affecting the accurate assessment of product quality stability. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method and equipment for evaluating the flame retardant performance of fire-resistant and flame-retardant network cables to solve the above problems.

[0005] The first aspect of this application provides a method for evaluating the flame-retardant performance of fire-resistant and flame-retardant network cables, the method comprising: Obtain the thermal conductivity of the network cable, as well as the flame retardant index and drip mark corresponding to various flame retardant tests; The historical batches were divided into multiple groups. Based on the similarity between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests, and combined with the flame retardant penalty factor constructed based on droplet markings, the correlation characteristics between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests in the historical batches were determined. The correlation characteristics obtained from different flame retardant tests were compared to determine the first deviation characteristic of each group of network cables. Based on the thermal conductivity of historical network cables, the flame retardant indicators of each group of network cables are predicted. The similarity between the predicted and actual values ​​is analyzed to obtain the fluctuation characteristics. Combined with the first deviation characteristics, the second deviation characteristics of each group of network cables are determined. The total deviation characteristic is obtained based on the first and second deviation characteristics of each group of network cables, and the flame retardant performance of each group of network cables is evaluated.

[0006] Preferably, the flame retardant penalty factor is specifically the negative correlation mapping result of the mean droplet markings of all network cables in each group in each flame retardant test.

[0007] Preferably, the determination of the correlation between the flame retardant index and thermal conductivity of each group of network cables in the historical batches during various flame retardant tests specifically includes: Based on the flame retardant indexes obtained from various flame retardant tests for each group of network cables in historical batches, the similarity between thermal conductivity and flame retardant indexes is analyzed to determine the first relevant feature. The second relevant feature is determined based on the fitting accuracy of the linear fit between thermal conductivity and flame retardancy index. By combining the first correlation feature, the second correlation feature, and the flame retardant penalty factor, the correlation features between the flame retardant index and thermal conductivity obtained by each group of network cables in various flame retardant tests are determined; the correlation features are positively correlated with the first correlation feature, the second correlation feature, and the flame retardant penalty factor.

[0008] Preferably, the first relevant feature is obtained through the Spearman rank correlation between the thermal conductivity and flame retardancy index of each group of network cables.

[0009] Preferably, the second relevant feature is specifically: The thermal conductivity and flame retardancy index of each group of network cables were fitted, and the coefficient of determination of the fitting results was used as the corresponding second correlation feature.

[0010] Preferably, the difference between the first deviation feature and the correlation feature obtained from different flame retardant tests is positively correlated.

[0011] Preferably, the fluctuation characteristic is specifically the correlation coefficient between the actual value and the predicted value of the flame retardant index of each group of network cables in various flame retardant tests.

[0012] Preferably, the specific process for determining the second deviation characteristic of each group of network cables is as follows: The mean value of the fluctuation characteristics of all flame retardant tests for each group of network cables after normalization is obtained. The negative correlation mapping result of the mean value is positively fused with the first deviation characteristic to obtain the second deviation characteristic of each group of network cables.

[0013] Preferably, the process of evaluating the flame-retardant performance of each group of network cables by obtaining the total deviation characteristic based on the first deviation characteristic and the second deviation characteristic obtained for each group of network cables specifically involves: The average of the normalized first deviation feature and the normalized second deviation feature of each group of network cables is taken as the total deviation feature of each group of network cables. The tolerance threshold is obtained based on the total deviation characteristics of all previous network cables using the 3σ principle. If the total deviation characteristics of each network cable group are greater than or equal to the tolerance threshold, the corresponding network cable group has a risk of flame retardant performance fluctuation; otherwise, there is no risk of flame retardant performance fluctuation.

[0014] Secondly, embodiments of this application also provide an evaluation device for the flame-retardant performance of fire-resistant and flame-retardant network cables, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0015] This application has at least the following beneficial effects: This application constructs a correlation feature model for historical batches by combining multi-dimensional data such as thermal conductivity, flame retardancy index, and drip mark. This model not only considers the intrinsic relationship between the thermal conductivity and flame retardancy of materials, but also introduces a flame retardancy penalty factor through drip mark, effectively quantifying the performance differences between different flame retardancy tests, thereby accurately identifying the first deviation characteristic of each group of cables.

[0016] Secondly, this application utilizes similarity analysis between the predicted and actual measurement sequences of various flame retardant indicators to obtain a second deviation characteristic, revealing the fluctuation patterns and consistency of flame retardant performance between different batches. This method can quantify the changing trends of flame retardant performance between batches, promptly identify potential process fluctuations, and effectively characterize the stability of the production processes of different batches of cables. This solves the problem that traditional evaluation methods struggle to identify potential performance differences between batches, thus improving the reliability of cable flame retardant performance evaluation.

[0017] Finally, by employing a dual-bias verification mechanism, combining the first and second deviation characteristics, potential risks arising from batch-to-batch material variations or process fluctuations can be effectively identified, avoiding the limitations of single-index evaluation. This method achieves a comprehensive and objective assessment of the flame-retardant performance of each cable group. The data-driven and feature-correlation-based evaluation approach not only enhances the scientific rigor of the evaluation results but also provides strong data support for optimizing cable material formulations and production processes, ensuring the safety and reliability of fire-resistant and flame-retardant network cables in practical applications. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the steps of an evaluation method for the flame-retardant performance of a fire-resistant and flame-retardant network cable, provided in one embodiment of this application; Figure 2 This is a schematic diagram illustrating the relationship between flame retardancy index and thermal conductivity, provided in one embodiment of this application. Detailed Implementation

[0019] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0021] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0022] The following, in conjunction with the accompanying drawings, details the specific scheme of the evaluation method and equipment for the flame-retardant performance of a fire-resistant and flame-retardant network cable provided in this application.

[0023] Please see Figure 1 The diagram illustrates a flowchart of a method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable according to an embodiment of this application. The method includes the following steps: The first step: Obtain the thermal conductivity of the network cable, as well as the flame retardant index and drip mark corresponding to various flame retardant tests.

[0024] To analyze the correlation between the thermal conductivity and flame retardant performance of network cables, this application requires collecting the thermal conductivity and flame retardant performance indicators of network cables. Specifically: after slicing the network cable, a thermal conductivity tester (Netzsch LFA457 in this embodiment) is used to test the sliced ​​network cable to obtain the thermal conductivity of the network cable; a single-cable vertical burning test is conducted on the network cable connected to the sliced ​​location using existing combustion testing equipment (UL94 flame retardant testing machine in this embodiment), denoted as test a, to obtain the flame retardant performance indicator of the network cable, namely the flame self-extinguishing time. Additionally, the dripping markings from test a are obtained, including a dripping presence marking and a dripping ignition marking. If dripping is present or ignites the cotton material below, the marking value is set to 1; otherwise, the marking value is set to 0. An oxygen index tester (ENVITEC of Germany in this embodiment) is used to test the oxygen index of the network cable connected to the sliced ​​location, denoted as test b, to obtain the minimum oxygen concentration required for the network cable to sustain combustion, i.e., the oxygen index. In each batch, both test a and test b require 15 network cables for testing. This application does not impose any special restrictions on the number of network cables to be sampled, and implementers may adjust the number according to the actual situation.

[0025] For each batch of test data, the thermal conductivity of all cables was normalized using the min-max algorithm. Similarly, the self-extinguishing time of the cable undergoing the vertical combustion test and the oxygen index of the cable undergoing the oxygen index test were normalized.

[0026] The second step is to divide the historical batches into multiple groups. Based on the similarity between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests, and combined with the flame retardant penalty factor constructed based on droplet markings, the correlation characteristics between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests in the historical batches are determined. The correlation characteristics obtained from different flame retardant tests are compared to determine the first deviation characteristic of each group of network cables.

[0027] Thermal conductivity is a physical quantity that measures a material's ability to conduct heat. The higher the thermal conductivity of a cable, the stronger its heat conduction ability. Therefore, there is a certain correlation between the thermal conductivity of a cable and its flame retardancy index (e.g., higher thermal conductivity corresponds to longer self-extinguishing time or lower oxygen index, i.e., lower flame retardancy). If there are differences in the thermal conductivity between different cables, this correlation will change. Therefore, the stability of the correlation between thermal conductivity and flame retardancy index will be affected between different flame retardancy indexes or different batches, resulting in a non-linear relationship between the two.

[0028] In this application, by analyzing the historical stability levels between the thermal conductivity and flame retardancy indicators of N batches of network cables, the flame retardancy performance of the network cables is evaluated based on the deviation between the actual stability level and the historical stability level during actual flame retardancy performance assessment. This application does not impose any special restrictions on the value of N, which can be adjusted according to actual conditions; in this embodiment, N is taken as 20.

[0029] The correlation between thermal conductivity and flame retardancy may not be directly apparent between two adjacent batches. Therefore, historical batches are grouped into groups of 5, with a step size of 1. That is, Group 1 consists of [batches 1, 2, 3, 4, and 5], and Group 2 consists of [batches 2, 3, 4, 5, and 6]. The thermal conductivity sequence of each group in each test is concatenated end-to-end according to the batch order to obtain the thermal conductivity sequence of each group. Similarly, the self-extinguishing time sequence and oxygen index sequence are processed in the same way. This application does not impose any special restrictions on the number of batches within each group; implementers can adjust this according to actual circumstances.

[0030] This embodiment takes the a-th test L(i,a) in the i-th group as an example. L(i,a) includes a thermal conductivity sequence and a self-extinguishing time sequence. Each thermal conductivity corresponds to a self-extinguishing time, and each self-extinguishing time corresponds to a droplet presence marker. A dripping ignition mark .

[0031] To analyze the correlation between the thermal conductivity of cables and their flame retardancy index, this embodiment uses the normalized thermal conductivity sequence and self-extinguishing time sequence as inputs to the Spearman rank correlation algorithm. A significance level threshold of 0.05 is set to determine significant correlation, and a confidence interval of 95% is set to construct the correlation coefficient confidence interval. Correlation coefficient analysis is performed on the input data, and the obtained correlation coefficient is used as the first correlation feature of L(i,a) to characterize the monotonic nonlinear mapping relationship between thermal conductivity and flame retardancy index, improving the accuracy of capturing nonlinear quality fluctuations. The larger the first correlation feature, the stronger the consistency of the changing trend between the thermal conductivity and self-extinguishing time of cables in the same group, i.e., the stronger the synergy of increased self-extinguishing time as thermal conductivity increases. The Spearman rank correlation algorithm is a well-known existing technology and will not be described in detail here.

[0032] To further analyze the correlation between the thermal conductivity of the cable and its flame retardancy index, this embodiment uses the normalized thermal conductivity sequence and the self-extinguishing time sequence as inputs to the least squares method, setting the initial values ​​of the intercept and slope to 0, and setting the iteration convergence threshold to 10. -6As a control parameter for judging the fitting accuracy, linear regression is performed on the input data to obtain the fitting curve. The coefficient of determination between the fitting curves is used as the second correlation feature of L(i,a). The second correlation feature reflects the degree of correlation between the linear fit of the input data. The larger the second correlation feature, the higher the correlation between thermal conductivity and self-extinguishing time, indicating that the trend of change of thermal conductivity and flame retardant performance of the cable is more consistent, and the flame retardant stability is higher. This embodiment does not impose special restrictions on the selection of the linear regression algorithm, parameter values, or the calculation method of the second correlation feature, which can be adjusted according to the actual situation. There are no restrictions on the calculation method of the second correlation feature, as long as the logic that the larger the second correlation feature, the stronger the consistency of the trend of change of thermal conductivity and flame retardant performance, or the smaller the second correlation feature, the weaker the consistency of the trend of change of thermal conductivity and flame retardant performance, is met.

[0033] Furthermore, the dripping of debris from a burning cable constitutes a nonlinear thermal runaway event, and the debris carrying away localized heat disrupts the correlation between thermal conductivity and self-extinguishing time. Therefore, in this embodiment, and As a penalty term in the correlation calculation between the self-extinguishing time and thermal conductivity of L(i,a), a flame retardant penalty factor for L(i,a) is constructed to reduce the weight of distorted samples in the correlation analysis. The specific formula is as follows: in, Denotes the flame retardant penalty factor of L(i,a). This represents the total number of cables in test a. Indicates the first A cable, , Represent the i-th term in L(i,a) respectively The cable has markings for dripping material and markings for dripping material ignition; both the markings for dripping material presence and the markings for dripping material ignition are dripping material markings; This is denoted as the mean of the droplet markings.

[0034] When a large number of cables in L(i,a) produce dripping material or the dripping material ignites cotton fibers, it indicates that the flame-retardant performance of the self-extinguishing time is affected by factors other than thermal conductivity (e.g., the flammability of the cable), which leads to a weakening of the true correlation between thermal conductivity and self-extinguishing time. This can reflect the degree of influence of interfering factors on the correlation between thermal conductivity and flame retardancy in the experiment. The larger the size, the lower the impact.

[0035] In this application, the presence and ignition markers of dripping material are used as quantitative indicators to mitigate the interference of the correlation between thermal conductivity and flame retardancy. A scaling factor is introduced for adjustment, constructing a flame retardancy penalty factor to correct the correlation between thermal conductivity and self-extinguishing time. This reduces the interference of non-thermal conductivity factors on the correlation analysis and improves the accuracy of assessing the impact of thermal conductivity on flame retardancy performance. This penalty factor serves as an engineering experience weight; when dripping damages the physical structure, it reduces the confidence weight of the current sample in the bivariate correlation analysis, while reserving a non-zero base weight (e.g., 0.1) to prevent the feature from being completely zeroed out.

[0036] Furthermore, the association features of L(i,a) are constructed, with the specific formula as follows: In the formula, Let L(i,a) represent the association features. Denotes the flame retardant penalty factor of L(i,a). This represents the first relevant feature of L(i,a). Denotes the second relevant feature of L(i,a); where, The Pearson similarity calculation result has a value range of -1 to 1, so a fraction is used. right Normalization is performed.

[0037] The diagram illustrating the correlation between flame retardancy and thermal conductivity is shown below. Figure 2 As shown.

[0038] It should be understood that, This can reflect the correlation between the flame retardant properties and thermal conductivity of cables. The larger the value, the stronger the correlation between the thermal conductivity and the flame retardancy index, and the closer the linear relationship between the two, which means that the flame retardancy performance of the cable is more stable.

[0039] In this application, the flame retardant penalty factor is used as a constraint on the flame retardant performance of the cable, the normalized first correlation feature is used as a measure of the correlation direction between thermal conductivity and flame retardant index, and the second correlation feature is used as a measure of the goodness of linear fit between the two. By combining these features, a correlation feature that can reflect the correlation strength between thermal conductivity and flame retardant performance of the cable is obtained, providing a basis for judgment when conducting stability assessment of the flame retardant performance of the cable.

[0040] Similarly, calculate the association characteristics of the b-th experiment in the i-th group. In this example, the flame retardant penalty factor for test b is set to 1. The min-max algorithm is used to normalize the correlation characteristics of all groups of cables in each flame retardant test. To analyze the consistency of the correlation between the thermal conductivity and flame retardant index of all cables in group i, in this embodiment, the normalized characteristics are... and The absolute difference is used as the first deviation characteristic between the thermal conductivity and flame retardancy index of the i-th group of cables. Normalize across all historical trial sets of item a. Normalization was performed on all historical test sets (b); the first deviation feature reflects the degree of deviation of the correlation features between different test groups. The larger the first deviation feature, the greater the difference in the correlation features between the thermal conductivity and flame retardancy index of the cable within that group.

[0041] The third step: Based on the thermal conductivity of the network cables in the historical groups, predict the flame retardant indicators of each group of network cables in various flame retardant tests, analyze the similarity between the predicted values ​​and the actual values ​​to obtain the fluctuation characteristics, and combine the first deviation characteristics to determine the second deviation characteristics of each group of network cables.

[0042] During cable production, all process parameters fluctuate within preset standard ranges. These fine-tunings can cause variations in the thermal conductivity of different batches of cables, affecting the relationship between thermal conductivity and flame retardant properties. This variation leads to fluctuations in the performance stability of each batch, further increasing the differences in flame retardant performance between batches. Therefore, relying solely on test results from a single batch is insufficient to accurately reflect the consistency of overall product quality, thus reducing the reliability of flame retardant performance evaluation.

[0043] The stability characteristics of each group of cables are derived from the correlation between the cable's thermal conductivity and flame retardancy index. Between different groups, the consistency of the trend between the cable's thermal conductivity and flame retardancy fluctuates due to changes in various performance parameters of the network cables. To analyze the fluctuations in flame retardancy performance between groups, in this embodiment, the single-point normalized thermal conductivity of individual cables in groups i-2 and i-1 is used as independent input features, and the corresponding single-point normalized self-extinguishing time is used as the corresponding target label. An SVR model is trained, with the kernel function set as a radial basis function, a penalty coefficient of 1, and an insensitive loss function parameter of 0.1. After determining the optimal hyperparameters through grid search, a regression equation is obtained. Using this regression equation, the thermal conductivity of each cable in group i is input into the regression equation to obtain the predicted self-extinguishing time sequence for group i. It should be noted that the purpose of calculating the fluctuation characteristics using the actual and predicted values ​​is not to replace actual flame retardancy testing, but to compare the bivariate mapping relationship of the current batch data with the historical joint distribution benchmark, and to quantify the degree of implicit drift in the micro-process formulation through the predicted residuals.

[0044] The min-max algorithm is used to normalize the predicted and actual self-extinguishing time sequences of the i-th group of cables. These normalized sequences are then used as inputs to the Pearson correlation algorithm. A significance level threshold of 0.05 and a confidence interval of 95% are set. Correlation coefficient analysis is performed on the input data, and the obtained correlation coefficient is used as the first fluctuation characteristic of the i-th group of cables. The first fluctuation characteristic reflects the consistency of the self-extinguishing time fluctuations of the i-th group of cables. The larger the first deviation characteristic, the stronger the correlation between the predicted and actual sequences, indicating that the fluctuation pattern of the self-extinguishing time of the i-th group of cables is more stable and predictable.

[0045] Similarly, the predicted oxygen index sequence of the i-th group of cables is obtained. The Pearson correlation coefficient between the actual oxygen index sequence and the predicted oxygen index sequence of the i-th group of cables is taken as the second fluctuation feature of the i-th group of cables, reflecting the fluctuation pattern of the oxygen index of the i-th group of cables. It should be noted that both the first and second fluctuation features are fluctuation features.

[0046] The first wave characteristic and the second wave characteristic are classified according to The normalization method is used for processing; the min-max algorithm is used to normalize the first deviation feature of all groups of cables, and then the second deviation feature of the i-th group of cables is constructed, with the specific formula as follows: In the formula, This represents the second deviation characteristic of the i-th group of cables. , Let represent the first and second normalized fluctuation characteristics of the i-th group of cables, respectively. This represents the normalized result of the first deviation characteristic of the i-th group of cables. This indicates that the mean is being calculated, because , , The values ​​of all values ​​are between 0 and 1, so the mean can be calculated without... , Direct addition leads to an over-dominance of the denominator. To represent extremely small positive numbers, preventing issues in extremely stable cases. , The case where the value is zero does not occur; this embodiment does not apply. The value of is subject to special restrictions and can be adjusted according to the actual situation. In this embodiment, The value is 0.001.

[0047] It should be understood that, It can reflect the relative deviation of the flame retardant performance of the i-th group of cables; The larger the value, the more prominent the deviation characteristics of this group of cables are when the mean of the normalized fluctuation characteristics is small. In other words, the flame retardant performance of this group of cables deviates more and the stability of the flame retardant performance is lower.

[0048] In this application, based on the mean processing method in existing statistical calculations, the normalized first deviation characteristic of the i-th group of cables is combined with the mean of the normalized first fluctuation characteristic and the second fluctuation characteristic. The second deviation characteristic is obtained through the ratio form, which reflects the fluctuation of the flame retardant index and thermal conductivity of the group of cables, as well as the relative deviation of the flame retardant performance.

[0049] The fourth step: Based on the first and second deviation characteristics obtained for each group of network cables, the total deviation characteristics are obtained, and the flame retardant performance of each group of network cables is evaluated.

[0050] In the actual evaluation of the flame retardant performance of cables, the thermal conductivity, self-extinguishing time, drip presence mark and drip ignition mark, and oxygen index of the cables in the current batch undergoing flame retardant performance evaluation (batch j in this embodiment) are obtained according to the method of this application. The current batch undergoing flame retardant performance evaluation is grouped with the previous four batches in history (group z in this embodiment). The first deviation characteristic and the second deviation characteristic of the cables in this group are calculated, and after processing by the maximum-minimum value normalization method, the mean of the two normalized deviation characteristics of the cables in this group is calculated as the total deviation characteristic of the cables in this group.

[0051] A tolerance threshold for the total deviation characteristic is set. In this embodiment, no special restrictions are placed on the value of the tolerance threshold for the total deviation characteristic. It can be adjusted according to the actual situation. In this embodiment, the upper limit threshold rule in the 3σ principle is referenced. The sum of the mean of the total deviation characteristics of the first z-1 groups of cables and three times the variance is used as the threshold for evaluating whether the total deviation characteristics of the z-th group of cables have a deviation tolerance threshold.

[0052] This application uses the flame-retardant performance evaluation of the first three groups of network cables as an example: For the flame retardant performance evaluation of the first two groups of cables, the self-extinguishing time, drip presence marking and drip ignition marking, and oxygen index of each cable were evaluated.

[0053] For the third group of cables, the flame retardant performance of each cable was first evaluated individually. After the evaluation, it was determined whether the total deviation characteristic exceeded the tolerance threshold. If the total deviation characteristic exceeded the tolerance threshold, it indicated that the flame retardant performance of the third group of cables deviated from that of the historical groups, and the consistency of its flame retardant performance was poor, posing a risk of flame retardant performance fluctuation. Otherwise, there was no risk of flame retardant performance fluctuation. This process was repeated for each subsequent group of cables, performing the same flame retardant performance evaluation as for the third group.

[0054] In this application, when the number of historical network cables is less than the preset cold start threshold, a manually preset value of 0.75 is used as the tolerance threshold, and the preset cold start threshold is set to 5.

[0055] Based on the same inventive concept as the above method, this application embodiment also provides an evaluation device for the flame retardant performance of fire-resistant and flame-retardant network cables, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described methods for evaluating the flame retardant performance of fire-resistant and flame-retardant network cables.

[0056] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0057] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some technical features, without causing the essence of the corresponding technical solutions to deviate from the scope of the technical solutions in the embodiments of this application, should all be included within the protection scope of this application.

Claims

1. A method for evaluating the flame-retardant performance of fire-resistant and flame-retardant network cables, characterized in that, The method includes the following steps: Obtain the thermal conductivity of the network cable, as well as the flame retardant index and drip mark corresponding to various flame retardant tests; Historical batches were divided into multiple groups. Based on the similarity between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests, and combined with the flame retardant penalty factor constructed based on droplet markers, the correlation characteristics between the flame retardant index and thermal conductivity of each group of network cables in various flame retardant tests in the historical batches were determined. The correlation characteristics obtained from different flame retardant tests were compared to determine the first deviation characteristic of each group of network cables. The absolute difference between the correlation characteristics of two flame retardant tests after normalization was taken as the first deviation characteristic between the thermal conductivity and flame retardant index of each group of network cables. Based on the thermal conductivity of historical network cables, the flame retardant indicators of each group of network cables are predicted. The similarity between the predicted and actual values ​​is analyzed to obtain the fluctuation characteristics. Combined with the first deviation characteristics, the second deviation characteristics of each group of network cables are determined. The total deviation characteristic is obtained based on the first and second deviation characteristics of each group of network cables, and the flame retardant performance of each group of network cables is evaluated. The specific characteristics of the correlation between the flame retardant index and thermal conductivity obtained from various flame retardant tests for each group of network cables in the historical batches are as follows: Based on the flame retardant indexes obtained from various flame retardant tests for each group of network cables in historical batches, the similarity between thermal conductivity and flame retardant indexes is analyzed to determine the first relevant feature. The second relevant feature is determined based on the fitting accuracy of the linear fit between thermal conductivity and flame retardancy index. By combining the first correlation feature, the second correlation feature, and the flame retardant penalty factor, the correlation characteristics between the flame retardant index and thermal conductivity obtained by each group of network cables in various flame retardant tests are determined; the correlation characteristics are positively correlated with the first correlation feature, the second correlation feature, and the flame retardant penalty factor. The specific process for determining the second deviation characteristic of each group of network cables is as follows: The mean value between the fluctuation characteristics of all flame retardant tests of each group of network cables after normalization is obtained. The negative correlation mapping result of the mean value is positively fused with the first deviation characteristic to obtain the second deviation characteristic of each group of network cables. The process of evaluating the flame-retardant performance of each group of network cables by obtaining the total deviation characteristic based on the first and second deviation characteristics obtained for each group of network cables is as follows: The average of the normalized first deviation feature and the normalized second deviation feature of each group of network cables is taken as the total deviation feature of each group of network cables. The tolerance threshold is obtained based on the total deviation characteristics of all previous network cables using the 3σ principle. If the total deviation characteristics of each network cable group are greater than or equal to the tolerance threshold, the corresponding network cable group has a risk of flame retardant performance fluctuation; otherwise, there is no risk of flame retardant performance fluctuation.

2. The method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable as described in claim 1, characterized in that, The flame retardant penalty factor is specifically the negative correlation mapping result of the mean droplet markings of all network cables in each group during various flame retardant tests.

3. The method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable as described in claim 1, characterized in that, The first relevant feature was obtained through the Spearman rank correlation between the thermal conductivity and flame retardancy index of each group of network cables.

4. The method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable as described in claim 1, characterized in that, The second relevant feature is specifically: The thermal conductivity and flame retardancy index of each group of network cables were fitted, and the coefficient of determination of the fitting results was used as the corresponding second correlation feature.

5. The method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable as described in claim 1, characterized in that, The first deviation characteristic is positively correlated with the difference between the correlation characteristics obtained from different flame retardant tests.

6. The method for evaluating the flame-retardant performance of a fire-resistant and flame-retardant network cable as described in claim 1, characterized in that, The fluctuation characteristic is specifically the correlation coefficient between the actual value and the predicted value of the flame retardant index of each group of network cables in various flame retardant tests.

7. An evaluation device for the flame-retardant performance of fire-resistant and flame-retardant network cables, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-6.

Images