A flame retardant performance intelligent monitoring method and system for flame retardants

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for intelligently monitoring the flame retardant performance of a flame retardant. The method comprises the following steps: taking the product of the heat release rate and the mass loss rate of a data point in a flame retardant data set as a first feature, and obtaining the flame retardant feature by the ratio of the limiting oxygen index to the first feature; obtaining the reliability of the subset by the degree of deviation between the flame retardant feature of the data point and the mean value of the flame retardant feature of the corresponding subset; obtaining the mode of the flame retardant feature within a preset local range of each data point in the subset, and determining the discreteness of the data point by the degree of deviation between the flame retardant feature of the data point and the mode of the flame retardant feature; eliminating the subset with less than a preset number of data points in the subset, and the remaining subsets constitute the target data set, and calculating the flame retardancy of the flame retardant; obtaining the flame retardant performance monitoring result by comparing the flame retardancy of the flame retardant with a preset threshold, and effectively improving the accuracy of the flame retardant performance monitoring of the flame retardant.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for intelligently monitoring the flame retardant performance of a flame retardant. Background Art

[0002] Flame retardant is a functional additive that can increase the flame resistance of polymer materials. After adding flame retardant to combustible materials, the flame retardant can form a glassy or stable foam covering layer at high temperature, isolating oxygen, absorbing part of the heat released by combustion, and reducing the temperature of the surface of the combustible material, thereby effectively inhibiting the generation of combustible gas and achieving the purpose of flame retardancy.

[0003] There are many applications of flame retardants in the prior art. For example, a patent application document with publication number CN114112782A discloses a method for evaluating the influence of different flame retardants on the flame retardant and smoke suppression effects of asphalt. This method is based on the theory of thermal reaction kinetics and uses thermogravimetric-mass spectrometry to analyze asphalt mixed with flame retardants. By comparing and analyzing the change rate of the reaction activation energy of asphalt during combustion and the content of toxic and harmful gases in its gas products caused by different flame retardants, the type or dosage of flame retardant with the best flame retardant effect can be screened out.

[0004] The research direction of the existing technology mostly tends to the application of flame retardants. However, the main function of flame retardants is to slow down the spread of fire and protect the safety of materials in fire. If the performance of flame retardants is insufficient, it may cause the product to easily catch fire during use, and may cause the material to produce harmful gases or substances during use, causing environmental pollution. Therefore, it is necessary to monitor the flame retardant performance of flame retardants, and how to accurately obtain the flame retardant performance monitoring results of flame retardants is a problem that technicians in this field need to solve urgently. Summary of the invention

[0005] In order to solve the technical problem of how to accurately obtain the flame retardant performance monitoring result of a flame retardant, the present invention provides a flame retardant performance intelligent monitoring method and system for a flame retardant.

[0006] In a first aspect, the present invention provides a method for intelligently monitoring the flame retardant performance of a flame retardant, which adopts the following technical solution:

[0007] A method for intelligently monitoring the flame retardant performance of a flame retardant, comprising the steps of:

[0008] Obtain the limited oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set;

[0009] The product of the heat release rate and mass loss rate of the data point is used as the first feature, and the flame retardant feature is obtained by the ratio of the limited oxygen index to the first feature; the flame retardant data set is divided into multiple subsets, and the reliability of the subset is obtained by the degree of deviation between the flame retardant feature of the data point and the mean value of the flame retardant feature of the corresponding subset; the flame retardant feature mode within a preset local range of each data point in the subset is obtained, and the discreteness of the data point is determined by the degree of deviation between the flame retardant feature of the data point and the flame retardant feature mode; the subset with less than the preset number of data points in the subset is eliminated, and the remaining subsets constitute the target data set, and the flame retardancy of the flame retardant is calculated:

[0010] ;

[0011] In the formula, Indicates the flame retardancy of the flame retardant. Represents the total number of data points in the target data set, Indicates the target data set The reliability of the subset corresponding to the data point, Indicates The dispersion of the data points, Indicates The flame retardant characteristics of the data points, represents a linear normalized function; and the flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with a preset threshold.

[0012] The present invention obtains the flame retardancy of each data point by analyzing the heat release rate, mass loss rate and limited oxygen index of each data point, and can accurately obtain the flame retardancy of the flame retardant. In this process, the present invention takes into account that the difference in combustion performance between flame retardants of different grades may affect the analysis results of the data, so by calculating the reliability of subsets of different grades, the accuracy of obtaining the flame retardancy of the flame retardant is effectively improved; in addition, the present invention also takes into account that when the monitoring results of the flame retardant are obtained by a common anomaly detection algorithm, there may be misjudgment of abnormal data with high aggregation, so by calculating the aggregation degree of each data point as a weight for determining the flame retardancy of the flame retardant, the accuracy of the obtained flame retardancy can be effectively improved, thereby effectively improving the accuracy of monitoring the flame retardancy of the flame retardant.

[0013] According to a method for intelligently monitoring the flame retardant properties of a flame retardant provided by the present invention, the method of obtaining the limiting oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set includes: obtaining the limiting oxygen index of the data point by a fully automatic limiting oxygen index instrument; and obtaining the heat release rate and mass loss rate of the data point by a heat release rate tester.

[0014] According to a method for intelligently monitoring flame retardant properties of a flame retardant provided by the present invention, the flame retardant data set is divided into a plurality of subsets according to the UL94 grade of the flame retardant.

[0015] The present invention takes into account that the difference in combustion performance between flame retardants of different grades may affect the analysis results of the data, and therefore divides the data set by UL94 grade, so that accurate analysis can be performed on the subsets corresponding to each grade.

[0016] According to a method for intelligently monitoring the flame retardant properties of a flame retardant provided by the present invention, the reliability of the subset is obtained by measuring the degree of deviation between the flame retardant characteristics of the data points and the mean value of the flame retardant characteristics of the corresponding subset, including: recording the absolute value of the difference between the flame retardant characteristics of each data point in the subset and the mean value of the flame retardant characteristics of the subset as the second feature, and taking the negative of the sum of the second features of all the data points in the subset as the exponent of an exponential function with e as the base, to obtain the reliability of the subset.

[0017] According to a method for intelligently monitoring the flame retardant performance of a flame retardant provided by the present invention, the method of obtaining the flame retardant characteristic mode within a preset local range of each data point in the subset includes:

[0018] Obtain the flame retardant feature difference between a data point and other data points in the subset, take other data points corresponding to the flame retardant feature difference less than or equal to 0.1 as data points within a preset local range of the data point, and determine the flame retardant feature mode within the preset local range of the data point.

[0019] The present invention takes into account that when the flame retardant monitoring data is unevenly distributed, the global statistical analysis method may not accurately reflect the true characteristics of the data. Therefore, analysis is performed in a local range to better adapt to the non-uniformity of the data, thereby providing a more accurate flame retardant characteristic mode.

[0020] According to a method for intelligently monitoring the flame retardant properties of a flame retardant provided by the present invention, the discreteness of the data point is determined by the degree of deviation between the flame retardant characteristics of the data point and the flame retardant characteristic mode, including: obtaining the absolute value of the difference between the flame retardant characteristics of each data point in the subset and the flame retardant characteristic mode within a preset local range, recording it as the third feature of the data point; and recording the ratio of the third feature to the normalized value of the number of data points in the preset local range as the discreteness of the data point.

[0021] According to a method for intelligently monitoring the flame retardant performance of a flame retardant provided by the present invention, the flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with a preset threshold value, including: if the flame retardancy of the flame retardant is greater than the preset threshold value, the monitoring result of the flame retardant is qualified; if the flame retardancy of the flame retardant is not greater than the preset threshold value, the monitoring result of the flame retardant is unqualified.

[0022] The present invention compares the preset threshold with the flame retardancy, so that the threshold can be flexibly adjusted according to actual conditions, and the monitoring result of the flame retardant can be accurately obtained.

[0023] According to a method for intelligently monitoring flame retardant properties of flame retardants provided by the present invention, when the monitoring result of the flame retardant is unqualified, the method further includes: marking the batch of flame retardant corresponding to the unqualified monitoring result and issuing an unqualified prompt.

[0024] The present invention takes into account that the flame retardant with abnormal monitoring results has poor quality, and therefore effectively improves the accuracy of obtaining samples with poor quality by marking and reminding staff of the flame retardant sample batches corresponding to the abnormal monitoring results.

[0025] In a second aspect, the present invention provides a flame retardant performance intelligent monitoring system for flame retardants, which adopts the following technical solutions:

[0026] A flame retardant performance intelligent monitoring system of a flame retardant comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the flame retardant performance intelligent monitoring method of the flame retardant is implemented.

[0027] By adopting the above technical solution, the above-mentioned flame retardant performance intelligent monitoring method of a flame retardant is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0028] The present invention has the following technical effects:

[0029] Based on the above technical solution, when determining the flame retardant performance monitoring result of the flame retardant, the present invention obtains the flame retardancy of each data point by analyzing the heat release rate, mass loss rate and limited oxygen index of each data point, and the flame retardant performance of the flame retardant can be obtained. In this process, the present invention takes into account that the difference in combustion performance between flame retardants of different grades may affect the analysis results of the data, so by calculating the reliability of subsets of different grades, the accuracy of obtaining the flame retardant performance of the flame retardant is effectively improved; in addition, the present invention also takes into account that when the monitoring results of the flame retardant are obtained by a common anomaly detection algorithm, there may be misjudgment of abnormal data with high aggregation, so by calculating the aggregation degree of each data point as the weight for determining the flame retardant performance of the flame retardant, the accuracy of the obtained flame retardancy can be effectively improved, thereby effectively improving the accuracy of the flame retardant performance monitoring of the flame retardant. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0031] Figure 1 A schematic flow chart of a method for intelligently monitoring the flame retardant properties of a flame retardant provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] 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 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.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0034] It should be noted that the main function of flame retardants is to slow down the spread of fire and protect the safety of materials in fire. If the flame retardant performance is insufficient, it may cause the product to easily catch fire during use, and may cause the material to produce harmful gases or substances during use, causing environmental pollution. Therefore, it is necessary to monitor the flame retardant performance of flame retardants.

[0035] The Local Outlier Factor (LOF) anomaly detection algorithm is a density-based algorithm that identifies outliers by comparing the local density difference between a data point and other data points in its neighborhood. Flame retardants generate a large amount of monitoring data during the monitoring process, so the LOF anomaly detection algorithm can be used to process the monitoring data to obtain performance monitoring results. However, when the conventional LOF anomaly detection algorithm is used to process the monitoring data to obtain monitoring results, a large amount of concentrated abnormal data may be filtered as normal, resulting in the inability to accurately determine the target object with better flame retardant performance from each batch of flame retardants.

[0036] Based on this, the embodiment of the present invention discloses an intelligent monitoring method for the flame retardant performance of a flame retardant. By analyzing the flame retardant characteristics of each data point, the data reliability and discreteness of the data set are obtained, and the flame retardancy of the data point is determined by combining the two. This can effectively avoid misclassifying abnormal data with a small discreteness as normal data, thereby accurately obtaining the flame retardant performance monitoring results of the flame retardant. Please refer to Figure 1 As shown, Figure 1 A schematic flow chart of a method for intelligently monitoring the flame retardant properties of a flame retardant provided in an embodiment of the present invention specifically includes the following steps S1 to S4.

[0037] S1: Obtain the limited oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set, take the product of the heat release rate and mass loss rate of the data point as the first feature, and obtain the flame retardant feature by the ratio of the limited oxygen index to the first feature.

[0038] It should be noted that flame retardants will generate a large number of monitoring parameters during use. By analyzing the data characteristics of the monitoring parameters, the flame retardancy of the flame retardant at each data point can be obtained.

[0039] For example, in an embodiment of the present invention, the limiting oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set are obtained, including: obtaining the limiting oxygen index of the data point through a fully automatic limiting oxygen index instrument; obtaining the heat release rate and mass loss rate of the data point through a heat release rate testing machine.

[0040] The data collection frequency can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this. Each sampling moment corresponds to a data point, and each data point corresponds to a unique heat release rate, mass loss rate and limited oxygen index. All the collected data points are arranged in time sequence to form a flame retardant data set.

[0041] Specifically, the fully automatic limiting oxygen index instrument can accurately measure and record the minimum oxygen concentration required for the combustion of flame retardant samples, namely the limiting oxygen index. The heat release rate tester uses core components such as a cone calorimeter to measure the heat released during the combustion of the sample. The cone calorimeter can accurately measure parameters such as the radiant heat flow on the sample surface and the smoke generated by the combustion, and obtain the heat release rate by calculation. The mass measurement system in the heat release rate tester can monitor the mass change of the sample in real time during the combustion process. By calculating the mass difference of the sample before and after combustion, the mass loss rate can be obtained.

[0042] Among them, when the heat release rate is lower, it means that the sample releases less energy during combustion, resulting in a higher limited oxygen index, and the corresponding sample has better flame retardancy, and the heat release rate and limited oxygen index are negatively correlated; when the mass loss rate is higher, it means that the sample loses mass faster during the heating process, the heat release rate is higher, and the corresponding sample has worse flame retardancy, and the mass loss rate and heat release rate are positively correlated.

[0043] Based on this, the flame retardancy of each data point can be obtained by analyzing the heat release rate, mass loss rate and limited oxygen index of each data point.

[0044] For example, in the embodiment of the present invention, the flame retardant characteristics of the data points are determined, and the specific relationship can be referred to as follows:

[0045] ;

[0046] In the formula, represents the flame retardant characteristics of the i-th data point, represents the oxygen limiting index of the ith data point, represents the mass loss rate of the ith data point, represents the heat release rate of the ith data point.

[0047] In the above formula, Represents the first feature of the i-th data point. The higher the flame retardant feature of the data point, the better the flame retardancy of the sample; conversely, the lower the flame retardant feature of the data point, the worse the flame retardancy of the sample.

[0048] Based on the above steps, the flame retardant characteristics of each data point in the flame retardant data set can be obtained. By analyzing the flame retardant characteristics of each data point, the reliability of the data set and the discreteness of each data point can be accurately obtained, that is, continue to perform the following steps.

[0049] S2: Divide the flame retardant data set into multiple subsets, and obtain the reliability of the subsets through the degree of deviation between the flame retardant characteristics of the data points and the mean value of the flame retardant characteristics of the corresponding subsets.

[0050] It should be noted that the flame retardant characteristics of the flame retardant can be obtained through the monitoring parameters of each data point of the flame retardant, and the amount of monitoring data of the flame retardant samples is large and the flame retardant grades may be different, and their combustion performance is different. If the monitoring results are obtained directly based on the flame retardant characteristics of each data point in the flame retardant data set, the difference in combustion performance between flame retardants of different grades may affect the data analysis results. Based on this, the reliability of the data set can be obtained first, and then the flame retardant characteristics of the data points can be corrected according to the reliability.

[0051] For example, in an embodiment of the present invention, the flame retardant data set can be divided into multiple subsets according to the UL94 grade of the flame retardant, and the flame retardant characteristics of materials of different grades are analyzed in each subset, so as to more accurately reflect the combustion performance of the material and improve the accuracy of data analysis.

[0052] Specifically, the UL94 grade is a classification standard for the flame retardant properties of plastic materials. This standard can be used to classify flame retardant data sets into different flame retardant grades, which may include subsets V-1, V-2, etc. After the data set is divided into multiple subsets, a more accurate analysis can be performed on materials of different grades.

[0053] For example, in an embodiment of the present invention, the reliability of the subset is obtained by the degree of deviation between the flame retardant characteristics of the data points and the mean flame retardant characteristics of the corresponding subset, including: recording the absolute value of the difference between the flame retardant characteristics of each data point in the subset and the mean flame retardant characteristics of the subset as the second feature, and taking the negative of the sum of the second features of all data points in the subset as the exponent of an exponential function with base e to obtain the reliability of the subset.

[0054] Specifically, determine the i-th data point to which The reliability of a subset can be seen from the following relationship:

[0055] ;

[0056] In the formula, Indicates The reliability of the subset, Indicates The number of data points in the subset, Indicates The flame retardant characteristics of the i-th data point in the subset, Indicates The flame retardant characteristics of the jth data point in the subset, represents the exponential function with base e, represents the mean function, Represents the absolute value symbol.

[0057] In the above formula, The second feature represents the i-th data point. The larger the second feature is, the greater the deviation between the flame retardant feature of the i-th data point and the mean value of the flame retardant feature is, and the lower the reliability of the data point is.

[0058] After obtaining the reliability of each subset based on the above steps, continue to perform the following steps.

[0059] S3: Obtain the flame retardant feature mode within a preset local range of each data point in the subset, and determine the dispersion of the data point by the degree of deviation between the flame retardant feature of the data point and the flame retardant feature mode.

[0060] It should be noted that the abnormal monitoring results of the data points can be obtained through the flame retardant characteristics of each data point in the data set, but abnormal data with a high degree of aggregation may be classified as normal data, thereby affecting the accuracy of flame retardant performance monitoring.

[0061] Based on this, the embodiment of the present invention obtains the dispersion of the data point by obtaining the degree of deviation between each data point and the mode of the flame retardant characteristics in the preset local range. The mode is the data value with the highest frequency in the preset local range, representing the average performance of the flame retardant performance in the set. The greater the degree of deviation between the flame retardant characteristics of the data point and the mode of the flame retardant characteristics, the greater the difference between the flame retardant performance of the data point and the typical performance in the local range of the set.

[0062] Based on this, the discreteness of the data point can be accurately obtained by the degree of deviation between the flame retardant characteristics of the data point and the flame retardant characteristic mode.

[0063] It should be further explained that when the flame retardant monitoring data is unevenly distributed, the global statistical analysis method may not accurately reflect the true characteristics of the data. However, local analysis can better adapt to the non-uniformity of the data and provide a more accurate flame retardant feature mode.

[0064] For example, in an embodiment of the present invention, obtaining the mode of flame retardant characteristics within a preset local range of each data point in a subset includes: obtaining the flame retardant characteristic difference between a data point and other data points in the subset, taking other data points corresponding to the flame retardant characteristic difference less than or equal to 0.1 as data points within the preset local range of the data point, and determining the flame retardant characteristic mode within the preset local range of the data point.

[0065] It can be understood that since the difference in flame retardant characteristics between a data point and data points within its preset local range is no more than 0.1, when the number of modes within the preset local range is greater than one, one of the modes can be selected as the flame retardant characteristic mode within the preset local range of the data point.

[0066] For example, in an embodiment of the present invention, the discreteness of a data point is determined by the degree of deviation between the flame retardant characteristics of the data point and the mode of the flame retardant characteristics, including: obtaining the absolute value of the difference between the flame retardant characteristics of each data point in the subset and the mode of the flame retardant characteristics within its preset local range, and recording it as the third feature of the data point; recording the ratio of the third feature to the normalized value of the number of data points in the preset local range as the discreteness of the data point.

[0067] The larger the normalized value of the number of data points in the preset local range, the more concentrated the density at the data points, that is, the smaller the discrete amplitude. The larger the deviation between the data point and the flame retardant characteristic mode and the smaller the normalized value of the number of data points in the preset local range, the greater the discreteness of the corresponding data point.

[0068] After obtaining the reliability of the subset and the discreteness of each data point based on the above steps, the flame retardant characteristics of the data point can be corrected based on the reliability of the subset and the discreteness of each data point, so as to accurately obtain the flame retardant performance of the flame retardant, that is, continue to perform the following steps.

[0069] S4: The subsets with less than a preset number of data points are eliminated, and the remaining subsets constitute the target data set, and the flame retardancy of the flame retardant is calculated. The flame retardancy of the flame retardant is compared with the preset threshold value to obtain the flame retardant performance monitoring result.

[0070] It should be noted that based on the above steps, the discreteness of the data points and the reliability of the data subset can be obtained respectively. By correcting the flame retardant characteristics of the data points through the discreteness of the data points and the reliability of the subset, the misjudgment of abnormal data with high aggregation can be effectively avoided. In this process, the embodiment of the present invention takes into account the huge amount of flame retardant monitoring data. In order to effectively improve the efficiency of data processing, the subset with fewer data points in the subset can also be eliminated as invalid data to improve the overall data quality and accurately obtain the flame retardancy of the flame retardant.

[0071] Among them, when presetting the number, the subset with the largest amount of data among all subsets can be obtained, and 60% of the number of data points in the largest subset can be used as the preset number of subsets to be eliminated; the preset number can be set specifically according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0072] For example, in the embodiment of the present invention, the flame retardancy of the flame retardant is determined by referring to the following relationship:

[0073] ;

[0074] In the formula, Indicates the flame retardancy of the flame retardant. Represents the total number of data points in the target data set, Indicates the target data set The reliability of the subset corresponding to the data point, Indicates The dispersion of the data points, Indicates The flame retardant characteristics of the data points, represents the linear normalization function.

[0075] In the above formula, the higher the reliability of the subset and the lower the discreteness of the data point, the higher the weight of the data point for determining the flame retardancy of the flame retardant. The flame retardancy of the flame retardant can be accurately obtained by correcting the weight of the flame retardancy of each data point in the flame retardant target data set. The higher the flame retardancy, the better the flame retardant performance of the flame retardant.

[0076] Based on the above steps, the flame retardancy of each batch of flame retardant samples can be obtained, and the performance monitoring result of the flame retardant can be accurately obtained by comparing the flame retardancy with the preset threshold value.

[0077] For example, in an embodiment of the present invention, a flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with a preset threshold value, including: if the flame retardancy of the flame retardant is greater than the preset threshold value, the monitoring result of the flame retardant is qualified; if the flame retardancy of the flame retardant is not greater than the preset threshold value, the monitoring result of the flame retardant is unqualified.

[0078] The preset threshold may be 0.8; the preset threshold may be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0079] It can be understood that if the flame retardancy of the flame retardant is greater than the preset threshold, it means that the performance of the flame retardant is good and the quality of the product is qualified; if the flame retardancy of the flame retardant is not greater than the preset threshold, it means that the performance of the flame retardant is poor and the product quality is unqualified. For such unqualified flame retardants, the staff can be reminded through marking.

[0080] For example, in the embodiment of the present invention, the monitoring result of the flame retardant is unqualified, and then the method further includes: marking the batch of the flame retardant corresponding to the unqualified monitoring result and issuing an unqualified prompt.

[0081] The marking method can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0082] Among them, the method of providing the unqualified prompt can be a sound prompt or a color prompt, etc. The prompt method can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0083] It can be seen that in the embodiment of the present invention, when determining the flame retardant performance monitoring result of the flame retardant, the limited oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set can be obtained; the product of the heat release rate and the mass loss rate of the data point is used as the first feature, and the flame retardant feature is obtained by the ratio of the limited oxygen index to the first feature; the flame retardant data set is divided into multiple subsets, and the reliability of the subset is obtained by the degree of deviation between the flame retardant feature of the data point and the mean value of the flame retardant feature of the corresponding subset; the flame retardant feature mode within a preset local range of each data point in the subset is obtained, and the discreteness of the data point is determined by the degree of deviation between the flame retardant feature of the data point and the flame retardant feature mode; the subset with less than the preset number of data points in the subset is eliminated, and the remaining subsets constitute the target data set, and the flame retardancy of the flame retardant is calculated; the flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with the preset threshold.

[0084] In this way, the embodiment of the present invention accurately obtains the flame retardancy of each data point by analyzing the heat release rate, mass loss rate and limited oxygen index of each data point, and can accurately obtain the flame retardant performance of the flame retardant. In this process, the embodiment of the present invention takes into account that the difference in combustion performance between flame retardants of different grades may affect the analysis results of the data, so by calculating the reliability of subsets of different grades, the accuracy of the flame retardant performance of the flame retardant is effectively improved; in addition, the embodiment of the present invention also takes into account that when the monitoring results of the flame retardant are obtained by using a common anomaly detection algorithm, there may be misjudgment of abnormal data with high aggregation, so by calculating the aggregation degree of each data point as a weight for determining the flame retardant performance of the flame retardant, the accuracy of the flame retardancy obtained can be effectively improved, thereby effectively improving the accuracy of the flame retardant performance monitoring of the flame retardant.

[0085] An embodiment of the present invention further discloses a flame retardant performance intelligent monitoring system of a flame retardant, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a flame retardant performance intelligent monitoring method of a flame retardant according to the present invention is implemented.

[0086] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0087] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0088] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0089] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A flame retardant performance intelligent monitoring method for a flame retardant, characterized in that: include: Obtain the limited oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set; The product of the heat release rate and the mass loss rate of the data point is taken as the first characteristic, and the flame retardant characteristic is obtained by the ratio of the limiting oxygen index to the first characteristic; Dividing the flame retardant data set into a plurality of subsets, and obtaining the reliability of the subsets according to the degree of deviation between the flame retardant characteristics of the data points and the mean value of the flame retardant characteristics of the corresponding subsets comprises: recording the absolute value of the difference between the flame retardant characteristics of each data point in the subset and the mean value of the flame retardant characteristics of the subset as the second feature, and taking the negative of the sum of the second features of all the data points in the subset as the exponent of an exponential function with e as the base, to obtain the reliability of the subset; Obtaining the flame retardant feature mode within a preset local range of each data point in the subset includes: obtaining the flame retardant feature difference between a data point and other data points in the subset, taking other data points corresponding to the flame retardant feature difference being less than or equal to 0.1 as data points within the preset local range of the data point, determining the flame retardant feature mode within the preset local range of the data point, and determining the discreteness of the data point by the degree of deviation between the flame retardant feature of the data point and the flame retardant feature mode includes: obtaining the absolute value of the difference between the flame retardant feature of each data point in the subset and the flame retardant feature mode within the preset local range, recording it as the third feature of the data point; recording the ratio of the third feature to the normalized value of the number of data points in the preset local range as the discreteness of the data point; The subsets with less than the preset number of data points in the subsets are removed, and the remaining subsets form the target data set to calculate the flame retardancy of the flame retardant: ; In the formula, Indicates the flame retardancy of the flame retardant. Represents the total number of data points in the target data set, Indicates the target data set The reliability of the subset corresponding to the data point, Indicates The dispersion of the data points, Indicates The flame retardant characteristics of the data points, represents a linear normalized function; and the flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with a preset threshold.

2. The method for intelligently monitoring the flame retardant performance of a flame retardant according to claim 1, characterized in that: The step of obtaining the limited oxygen index, heat release rate and mass loss rate of each data point in the flame retardant data set includes: The limiting oxygen index of the data point is obtained by a fully automatic limiting oxygen index instrument; the heat release rate and mass loss rate of the data point are obtained by a heat release rate testing machine.

3. The flame retardant performance intelligent monitoring method of a flame retardant according to claim 1, characterized in that: The flame retardant data set is divided into subsets by the UL94 rating of the flame retardant.

4. The method for intelligently monitoring the flame retardant performance of a flame retardant according to claim 1, characterized in that: The flame retardant performance monitoring result is obtained by comparing the flame retardancy of the flame retardant with a preset threshold value, including: If the flame retardancy of the flame retardant is greater than the preset threshold, the monitoring result of the flame retardant is qualified; If the flame retardancy of the flame retardant is not greater than the preset threshold, the monitoring result of the flame retardant is unqualified.

5. The method for intelligently monitoring the flame retardant performance of a flame retardant according to claim 4, characterized in that: The monitoring result of the flame retardant is unqualified, and then further includes: The batches of flame retardants corresponding to the unqualified monitoring results are marked and an unqualified prompt is issued externally.

6. An intelligent monitoring system for flame retardant performance of flame retardants, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for intelligently monitoring the flame retardant performance of a flame retardant according to any one of claims 1 to 5 is implemented.

Images